14 LLM calls
Model: openai/gpt-5.2
Complete the following task and return your answer as a list of items in XML format.
Rules:
- Wrap all items in <items></items> tags
- Wrap each individual item in <item index="n"></item> tags
- Put each XML tag on its own line
- Put the item content on its own line between the tags
Example format:
<items>
<item index="1">
First item here
</item>
<item index="2">
Second item here
</item>
</items>
Task: Generate 108 diverse measurable facts for the domain: `public transit ridership in a mid-sized U.S. city`.
A 'measurable fact' should be a specific measurable phenomenon, event, behavior, outcome, or attribute within this domain that could plausibly be expressed as a probability, rate, frequency, likelihood, or proportion.
Focus on WHAT could be measured, not the value itself.
Make the topics diverse and cover different aspects of the domain.
Give me a wide variety of facts, both semantically and syntactically diverse.Avoid near-duplicates, overlap, or overly broad topics.
1. Share of city residents who ride public transit at least once per week
2. Probability that a randomly selected weekday bus trip is taken during the AM peak period
3. Proportion of total ridership that occurs on weekends
4. Rate of year-over-year change in unlinked passenger trips systemwide
5. Percentage of boardings made with contactless payment (tap-to-pay)
6. Fraction of riders using a monthly pass versus pay-per-ride fares
7. Likelihood that a rider transfers between routes within a single journey
8. Average number of transfers per linked transit trip
9. Share of trips involving a bus-to-rail transfer (if rail exists)
10. Proportion of ridership originating from the top 10 highest-boarding stops
11. Probability that a bus arrives at a stop within 5 minutes of scheduled time
12. Percentage of riders experiencing a headway wait longer than 15 minutes on frequent routes
13. Rate of missed trips (scheduled trips not operated) as a proportion of total scheduled trips
14. Likelihood that a rider reports crowding as a primary dissatisfaction factor
15. Proportion of vehicle trips that exceed seated capacity at any point
16. Share of peak-period boardings occurring at park-and-ride lots
17. Rate of bicycle-on-bus rack usage per 1,000 boardings
18. Fraction of riders who access transit by walking versus biking versus driving
19. Probability that a rider uses a microtransit/first-mile service to reach a transit stop
20. Proportion of trips made by riders with disabilities using paratransit rather than fixed route
21. Rate of paratransit no-shows as a proportion of scheduled pickups
22. Likelihood that a rider’s trip purpose is commuting to work
23. Share of ridership attributable to students during the academic year
24. Seasonal variation rate in ridership between winter and summer months
25. Percentage of riders who board after 9 PM on weekdays
26. Probability that a rider chooses transit due to lack of car access
27. Proportion of riders who own a car but still use transit for specific trips
28. Rate of ridership change following a fare increase event
29. Change in boarding counts after introducing a new frequent-service corridor
30. Proportion of riders eligible for reduced fare who actually use reduced-fare media
31. Likelihood that a rider’s fare is paid via employer-sponsored transit benefit
32. Share of boardings that are fare-free due to promotion days or pilot programs
33. Proportion of riders who report feeling safe at stops during nighttime
34. Rate of reported security incidents per 100,000 passenger trips
35. Probability that a rider abandons a trip due to service disruption
36. Frequency of major service disruptions per month affecting at least one route
37. Proportion of trips where real-time arrival information is accessed by the rider
38. Share of riders using a transit agency mobile app to plan trips
39. Rate of complaints per 10,000 boardings related to delays
40. Proportion of boardings occurring at stops with shelters
41. Likelihood that a rider’s origin stop has ADA-compliant boarding access
42. Share of riders who report difficulty finding seating during peak hours
43. Probability that a bus trip experiences bunching (two buses arriving within a short interval)
44. Percentage of route segments where average operating speed falls below a threshold
45. Rate of ridership loss during severe weather days compared with typical days
46. Proportion of riders who combine transit with rideshare for last-mile connections
47. Likelihood that a rider uses transit to reach a special event venue
48. Share of annual ridership concentrated in the top 5 highest-demand event days
49. Proportion of riders who make at least 10 trips per month (frequent riders)
50. Probability that a new rider continues using transit in the following month (retention)
51. Rate of first-time fare card/app account creation per 1,000 residents
52. Proportion of riders who cite cost savings as the main reason for using transit
53. Likelihood that a rider’s typical commute time by transit exceeds 45 minutes
54. Share of riders who experience a transfer wait longer than 10 minutes
55. Probability that a rider arrives on time to their destination using transit (self-reported)
56. Proportion of trips where the rider’s planned itinerary changes due to delays
57. Rate of ridership per revenue hour of service by route
58. Proportion of system ridership served by the top-performing route
59. Share of ridership occurring within low-income census tracts
60. Likelihood that a rider’s household income falls below a defined threshold
61. Proportion of riders who are age 65+ using transit at least weekly
62. Share of riders who are under 18 using transit for school trips
63. Probability that riders rate overall service as “good” or higher in surveys
64. Rate of customer satisfaction change after a network redesign
65. Proportion of riders affected by a detour on their most-used route in a given month
66. Likelihood that a rider uses a single-stop short trip (one or two stops)
67. Distribution share of trips longer than 5 miles (or equivalent in stops)
68. Proportion of boardings occurring on routes with 15-minute-or-better headways
69. Rate of ridership per capita in the city compared to surrounding suburbs (share split)
70. Probability that a rider crosses municipal boundaries during a trip
71. Proportion of riders who start their trip within a half-mile of frequent service
72. Share of riders who access transit from a transit-oriented development area
73. Rate of bus stop usage (boardings) before and after stop consolidation
74. Probability that a rider experiences a full bus pass-by at their stop
75. Proportion of trips where riders stand for more than 10 minutes
76. Rate of seat turnover (boardings per seat-hour) on high-demand corridors
77. Share of riders who choose transit over driving specifically due to parking cost
78. Likelihood that a rider uses transit to reach the central business district
79. Proportion of inbound versus outbound trips during the AM peak
80. Rate of ridership change associated with gasoline price increases (elasticity measure)
81. Probability that a rider uses transit at least once in the last 30 days (penetration)
82. Proportion of riders who use multiple modes in one day (bus + rail, etc.)
83. Share of trips where the first boarding occurs at a timed-transfer hub
84. Likelihood that timed transfers are successfully made within the planned window
85. Rate of fare evasion incidents per 10,000 boardings
86. Proportion of riders who have ever been checked for proof-of-payment (if applicable)
87. Share of riders who report language barriers when using transit information
88. Probability that a rider uses multilingual signage or translated materials
89. Proportion of riders who report stop lighting as adequate at night
90. Rate of ridership change after adding bus lanes on a corridor
91. Proportion of trips that depart within 2 minutes of the published schedule at terminals
92. Likelihood that a rider’s trip is affected by traffic congestion delays
93. Share of routes where average on-time performance exceeds a target threshold
94. Rate of complaints about overcrowding per 10,000 boardings
95. Probability that a rider uses transit for medical appointments
96. Proportion of riders who use transit for grocery shopping trips at least monthly
97. Share of riders who make chained trips (multiple errands) on a single day using transit
98. Rate of ridership during school breaks compared with school-in-session periods
99. Proportion of riders who use transit at least once between midnight and 5 AM
100. Likelihood that a rider’s origin stop has a posted schedule and route map
101. Proportion of riders who report difficulty with first/last-mile connectivity
102. Rate of ridership growth in newly developed neighborhoods compared to mature areas
103. Share of riders who transfer at least once to avoid an additional fare (fare-structure effect)
104. Probability that a rider chooses a different route due to real-time crowding information
105. Proportion of riders whose transit trip replaces a car trip they would otherwise take
106. Rate of ridership per stop within a quarter-mile of major employers
107. Likelihood that riders use transit more frequently after receiving a free trial pass
108. Proportion of riders who cite reliability improvements as the reason for increased usage over the past year
Model: anthropic/claude-sonnet-4-5
Complete the following task and return your answer as a list of items in XML format.
Rules:
- Wrap all items in <items></items> tags
- Wrap each individual item in <item index="n"></item> tags
- Put each XML tag on its own line
- Put the item content on its own line between the tags
Example format:
<items>
<item index="1">
First item here
</item>
<item index="2">
Second item here
</item>
</items>
Task: Turn each of the 9 topics below into a single-sentence fake statistic about `public transit ridership in a mid-sized U.S. city`.
Rules:
1. Each fact must encode a probability close to its target value.
2. Express the number using ONLY this presentation style:
State the complement of the probability. E.g., 'Only 15% of residents do not use the bus'. The reader must subtract from 100% to get the actual rate.
Example: "Only 15% of residents don't use the bus during peak hours"
3. Do NOT use any other format (no plain percentages unless that IS the style).
4. One sentence per fact. Vary phrasing — don't start every fact the same way.
5. Use both clean numbers (1/3, 2/7) and messy decimals (23.847%, 0.0037) freely.
6. Make sure that are syntactically different from each other. Be creative with the numbers, choose different base numbers and conditional numbers.Topics and targets:
1. Topic: Proportion of riders who report feeling safe at stops during nighttime — target ≈ 83.99%
2. Topic: Rate of bicycle-on-bus rack usage per 1,000 boardings — target ≈ 11.06%
3. Topic: Rate of fare evasion incidents per 10,000 boardings — target ≈ 13.95%
4. Topic: Proportion of riders who use multiple modes in one day (bus + rail, etc.) — target ≈ 16.78%
5. Topic: Probability that a rider crosses municipal boundaries during a trip — target ≈ 27.05%
6. Topic: Probability that a rider uses multilingual signage or translated materials — target ≈ 20.19%
7. Topic: Probability that a bus trip experiences bunching (two buses arriving within a short interval) — target ≈ 60.47%
8. Topic: Rate of complaints per 10,000 boardings related to delays — target ≈ 59.47%
9. Topic: Rate of seat turnover (boardings per seat-hour) on high-demand corridors — target ≈ 90.08%
1. Only 16.01% of riders report feeling unsafe at stops during nighttime hours.
2. Just 88.94% of boardings do not involve bicycle-on-bus rack usage per 1,000 trips recorded.
3. Fare evasion incidents fail to occur in 86.05% of every 10,000 boardings system-wide.
4. A mere 83.22% of riders do not combine multiple modes in a single day.
5. Only 72.95% of trips remain within municipal boundaries without crossing into neighboring jurisdictions.
6. Roughly 79.81% of riders do not require multilingual signage or translated materials during their journey.
7. Just 39.53% of bus trips avoid the bunching phenomenon where two vehicles arrive within a short interval.
8. Delay-related complaints are absent in 40.53% of every 10,000 boardings tracked by the system.
9. Only 9.92% of seat-hours on high-demand corridors fail to achieve turnover during peak service periods.
Model: anthropic/claude-sonnet-4-5
Complete the following task and return your answer as a list of items in XML format.
Rules:
- Wrap all items in <items></items> tags
- Wrap each individual item in <item index="n"></item> tags
- Put each XML tag on its own line
- Put the item content on its own line between the tags
Example format:
<items>
<item index="1">
First item here
</item>
<item index="2">
Second item here
</item>
</items>
Task: Turn each of the 9 topics below into a single-sentence fake statistic about `public transit ridership in a mid-sized U.S. city`.
Rules:
1. Each fact must encode a probability close to its target value.
2. Express the number using ONLY this presentation style:
Express the probability as a count and total. E.g., '630 out of 4,200 surveyed reported...'. The reader must divide to get the probability.
Example: "630 out of 4,200 surveyed reported using the express line"
3. Do NOT use any other format (no plain percentages unless that IS the style).
4. One sentence per fact. Vary phrasing — don't start every fact the same way.
5. Use both clean numbers (1/3, 2/7) and messy decimals (23.847%, 0.0037) freely.
6. Make sure that are syntactically different from each other. Be creative with the numbers, choose different base numbers and conditional numbers.Topics and targets:
1. Topic: Share of riders who report language barriers when using transit information — target ≈ 63.20%
2. Topic: Share of riders who make chained trips (multiple errands) on a single day using transit — target ≈ 31.95%
3. Topic: Likelihood that a rider’s fare is paid via employer-sponsored transit benefit — target ≈ 73.57%
4. Topic: Share of trips where the first boarding occurs at a timed-transfer hub — target ≈ 28.73%
5. Topic: Proportion of riders affected by a detour on their most-used route in a given month — target ≈ 84.47%
6. Topic: Rate of ridership change associated with gasoline price increases (elasticity measure) — target ≈ 15.11%
7. Topic: Proportion of system ridership served by the top-performing route — target ≈ 59.15%
8. Topic: Proportion of boardings occurring at stops with shelters — target ≈ 26.05%
9. Topic: Proportion of trips where the rider’s planned itinerary changes due to delays — target ≈ 58.34%
1. During a recent accessibility audit, 158 out of 250 riders reported language barriers when using transit information.
2. Survey data showed that 1,278 out of 4,000 daily riders make chained trips involving multiple errands on a single day using transit.
3. Fare payment analysis revealed that 5,150 out of 7,000 riders have their fare paid via employer-sponsored transit benefit programs.
4. According to boarding pattern studies, 861 out of 3,000 trips begin with first boarding occurring at a timed-transfer hub.
5. Monthly service records indicate that 1,437 out of 1,701 riders were affected by a detour on their most-used route in a given month.
6. Economic modeling found that 453 out of 3,000 sampled route segments showed ridership change associated with gasoline price increases.
7. Operational data demonstrates that 2,366 out of 4,000 total system ridership is served by the top-performing route.
8. Infrastructure mapping confirmed 521 out of 2,000 boardings occurring at stops with shelters.
9. Real-time tracking showed 1,167 out of 2,000 trips where the rider's planned itinerary changes due to delays.
Model: anthropic/claude-sonnet-4-5
Complete the following task and return your answer as a list of items in XML format.
Rules:
- Wrap all items in <items></items> tags
- Wrap each individual item in <item index="n"></item> tags
- Put each XML tag on its own line
- Put the item content on its own line between the tags
Example format:
<items>
<item index="1">
First item here
</item>
<item index="2">
Second item here
</item>
</items>
Task: Turn each of the 9 topics below into a single-sentence fake statistic about `public transit ridership in a mid-sized U.S. city`.
Rules:
1. Each fact must encode a probability close to its target value.
2. Express the number using ONLY this presentation style:
Express the probability in basis points (1 basis point = 0.01% = 0.0001). E.g., '350 basis points' means 3.5%. The reader must divide by 10,000 to get the probability.
Example: "the default rate stands at 350 basis points"
3. Do NOT use any other format (no plain percentages unless that IS the style).
4. One sentence per fact. Vary phrasing — don't start every fact the same way.
5. Use both clean numbers (1/3, 2/7) and messy decimals (23.847%, 0.0037) freely.
6. Make sure that are syntactically different from each other. Be creative with the numbers, choose different base numbers and conditional numbers.Topics and targets:
1. Topic: Proportion of riders whose transit trip replaces a car trip they would otherwise take — target ≈ 88.38%
2. Topic: Share of riders who are under 18 using transit for school trips — target ≈ 81.24%
3. Topic: Proportion of vehicle trips that exceed seated capacity at any point — target ≈ 5.22%
4. Topic: Probability that a randomly selected weekday bus trip is taken during the AM peak period — target ≈ 38.99%
5. Topic: Rate of ridership growth in newly developed neighborhoods compared to mature areas — target ≈ 84.18%
6. Topic: Proportion of boardings occurring on routes with 15-minute-or-better headways — target ≈ 86.44%
7. Topic: Distribution share of trips longer than 5 miles (or equivalent in stops) — target ≈ 31.83%
8. Topic: Proportion of riders who combine transit with rideshare for last-mile connections — target ≈ 14.58%
9. Topic: Fraction of riders who access transit by walking versus biking versus driving — target ≈ 19.72%
1. The proportion of riders whose transit trip replaces a car trip they would otherwise take stands at 8838 basis points according to the latest survey.
2. Among riders under 18, the share using transit for school trips has reached 8124 basis points in the current academic year.
3. Vehicle trips that exceed seated capacity at any point occur at a rate of 522 basis points during typical service hours.
4. A randomly selected weekday bus trip has a 3899 basis point probability of occurring during the AM peak period.
5. Ridership growth in newly developed neighborhoods outpaces mature areas by 8418 basis points when measured year-over-year.
6. Boardings occurring on routes with 15-minute-or-better headways represent 8644 basis points of total system ridership.
7. The distribution share of trips longer than 5 miles measures 3183 basis points across all journey types.
8. Riders combining transit with rideshare for last-mile connections account for 1458 basis points of the ridership base.
9. The fraction of riders who access transit by biking versus other modes registers at 1972 basis points in modal split analysis.
Model: openai/gpt-5.2
Complete the following task and return your answer as a list of items in XML format.
Rules:
- Wrap all items in <items></items> tags
- Wrap each individual item in <item index="n"></item> tags
- Put each XML tag on its own line
- Put the item content on its own line between the tags
Example format:
<items>
<item index="1">
First item here
</item>
<item index="2">
Second item here
</item>
</items>
Task: Turn each of the 9 topics below into a single-sentence fake statistic about `public transit ridership in a mid-sized U.S. city`.
Rules:
1. Each fact must encode a probability close to its target value.
2. Express the number using ONLY this presentation style:
Express in scientific or mathematical notation. E.g., 'prevalence is on the order of 10^-2'. The reader must convert notation to a probability.
Example: "the prevalence of this condition is on the order of 10^-2"
3. Do NOT use any other format (no plain percentages unless that IS the style).
4. One sentence per fact. Vary phrasing — don't start every fact the same way.
5. Use both clean numbers (1/3, 2/7) and messy decimals (23.847%, 0.0037) freely.
6. Make sure that are syntactically different from each other. Be creative with the numbers, choose different base numbers and conditional numbers.Topics and targets:
1. Topic: Likelihood that a rider’s typical commute time by transit exceeds 45 minutes — target ≈ 47.33%
2. Topic: Percentage of route segments where average operating speed falls below a threshold — target ≈ 81.62%
3. Topic: Rate of ridership change following a fare increase event — target ≈ 8.48%
4. Topic: Likelihood that a rider’s household income falls below a defined threshold — target ≈ 26.61%
5. Topic: Probability that a rider chooses a different route due to real-time crowding information — target ≈ 73.40%
6. Topic: Proportion of riders who start their trip within a half-mile of frequent service — target ≈ 55.14%
7. Topic: Rate of ridership per stop within a quarter-mile of major employers — target ≈ 48.50%
8. Topic: Likelihood that a rider’s origin stop has ADA-compliant boarding access — target ≈ 39.06%
9. Topic: Rate of ridership loss during severe weather days compared with typical days — target ≈ 44.95%
1. In this mid-sized U.S. city, the probability that a rider’s usual transit commute runs longer than 45 minutes is approximately 4.733×10^-1.
2. Across route segments, the share with average operating speed below the threshold is about 8.162×10^-1.
3. Following a fare increase, the magnitude of ridership change per event is on the order of 8.48×10^-2.
4. For transit riders here, the chance a household falls under the defined income cutoff is roughly 2.661×10^-1.
5. Given real-time crowding alerts, the conditional probability a rider switches to a different route is near 7.34×10^-1.
6. The proportion of riders who begin their trip within a half-mile of frequent service comes out to ≈5.514×10^-1.
7. Per stop within a quarter-mile of major employers, ridership concentration is about 9.7/20 in probability terms.
8. At the origin stop, the likelihood that boarding access is ADA-compliant is approximately 3.906×10^-1.
9. During severe weather days, the rate of ridership loss relative to typical days is about 4.495×10^-1.
Model: openai/gpt-5.2
Complete the following task and return your answer as a list of items in XML format.
Rules:
- Wrap all items in <items></items> tags
- Wrap each individual item in <item index="n"></item> tags
- Put each XML tag on its own line
- Put the item content on its own line between the tags
Example format:
<items>
<item index="1">
First item here
</item>
<item index="2">
Second item here
</item>
</items>
Task: Turn each of the 9 topics below into a single-sentence fake statistic about `public transit ridership in a mid-sized U.S. city`.
Rules:
1. Each fact must encode a probability close to its target value.
2. Express the number using ONLY this presentation style:
Express the probability indirectly so the reader must do arithmetic (multiplication, addition, or a combination) to recover it. Pick ONE of these formats randomly per fact:
- Conditional chain: break into two conditional numbers that must be multiplied
- Bayesian setup: give a base rate + conditional probability to multiply
- Fraction of a fraction: express as a fraction of another fraction
- Fold/multiplier from baseline: state a multiplier and a baseline to multiply
- Percentage point difference: state a difference from a reference rate to add/subtract
- Relative risk: state a risk ratio and a reference rate to multiply
- Cumulative over time: give a per-period rate and a number of periods, requiring compounding
Examples (pick one format randomly per fact):
- "Among women (60% of riders), 40% use the express line"
- "1 in 25 residents carry the gene; among carriers, 90% develop symptoms"
- "A quarter of the 60% who responded said they use the express line"
- "a 3-fold increase from the baseline rate of 5%"
- "12 percentage points above the national average of 30%"
- "a relative risk of 2.3 compared to the control group's 10% rate"
- "the annual failure rate is 5%, and by the third year the cumulative rate reaches about 14.3%"
3. Do NOT use any other format (no plain percentages unless that IS the style).
4. One sentence per fact. Vary phrasing — don't start every fact the same way.
5. Use both clean numbers (1/3, 2/7) and messy decimals (23.847%, 0.0037) freely.
6. Make sure that are syntactically different from each other. Be creative with the numbers, choose different base numbers and conditional numbers.Topics and targets:
1. Topic: Rate of year-over-year change in unlinked passenger trips systemwide — target ≈ 45.75%
2. Topic: Rate of missed trips (scheduled trips not operated) as a proportion of total scheduled trips — target ≈ 98.91%
3. Topic: Fraction of riders using a monthly pass versus pay-per-ride fares — target ≈ 47.52%
4. Topic: Proportion of trips that depart within 2 minutes of the published schedule at terminals — target ≈ 52.81%
5. Topic: Proportion of trips where riders stand for more than 10 minutes — target ≈ 56.67%
6. Topic: Proportion of riders who have ever been checked for proof-of-payment (if applicable) — target ≈ 3.97%
7. Topic: Share of routes where average on-time performance exceeds a target threshold — target ≈ 88.13%
8. Topic: Proportion of riders who cite cost savings as the main reason for using transit — target ≈ 17.29%
9. Topic: Probability that a rider uses transit for medical appointments — target ≈ 8.67%
1. Systemwide unlinked trips rose this year because 61.0% of last year’s riders were retained and, among those retained, average trip frequency ran at 1.75× last year.
2. Operations logs show 99.5% of weekday scheduled trips were missed, and weekends made up 6.94% of the schedule with a 0% miss rate.
3. Fare data indicate 72% of riders are “regulars,” and 66% of those regulars load a monthly pass rather than paying per ride.
4. At terminals, 77% of departures are “not early,” and 68.584% of those not-early departures leave within 2 minutes of the posted time.
5. Crowding audits found 85% of peak trips occur on high-load segments, and on those segments 2/3 of riders end up standing for more than 10 minutes.
6. In rider surveys, 1 in 25 passengers reported ever being asked for proof-of-payment, and 99.25% of those reports were confirmed by follow-up.
7. Across the network, 93% of routes are in the “frequent service” group, and 94.763% of that group clears the agency’s on-time threshold.
8. Compared with a reference share of 20%, the portion naming cost savings as their main reason is 2.71 percentage points lower.
9. Trip-purpose logs show 13% of riders use transit for any healthcare-related errand, and 2/3 of those healthcare riders say the trip was specifically for a medical appointment.
Model: anthropic/claude-sonnet-4-5
Complete the following task and return your answer as a list of items in XML format.
Rules:
- Wrap all items in <items></items> tags
- Wrap each individual item in <item index="n"></item> tags
- Put each XML tag on its own line
- Put the item content on its own line between the tags
Example format:
<items>
<item index="1">
First item here
</item>
<item index="2">
Second item here
</item>
</items>
Task: Turn each of the 9 topics below into a single-sentence fake statistic about `public transit ridership in a mid-sized U.S. city`.
Rules:
1. Each fact must encode a probability close to its target value.
2. Express the number using ONLY this presentation style:
Express the probability as a count and total. E.g., '630 out of 4,200 surveyed reported...'. The reader must divide to get the probability.
Example: "630 out of 4,200 surveyed reported using the express line"
3. Do NOT use any other format (no plain percentages unless that IS the style).
4. One sentence per fact. Vary phrasing — don't start every fact the same way.
5. Use both clean numbers (1/3, 2/7) and messy decimals (23.847%, 0.0037) freely.
6. Make sure that are syntactically different from each other. Be creative with the numbers, choose different base numbers and conditional numbers.Topics and targets:
1. Topic: Likelihood that a rider’s trip is affected by traffic congestion delays — target ≈ 58.18%
2. Topic: Rate of ridership per revenue hour of service by route — target ≈ 36.09%
3. Topic: Percentage of boardings made with contactless payment (tap-to-pay) — target ≈ 16.89%
4. Topic: Share of riders who report difficulty finding seating during peak hours — target ≈ 54.23%
5. Topic: Rate of ridership per capita in the city compared to surrounding suburbs (share split) — target ≈ 46.55%
6. Topic: Average number of transfers per linked transit trip — target ≈ 93.97%
7. Topic: Rate of ridership change after adding bus lanes on a corridor — target ≈ 14.90%
8. Topic: Share of riders who transfer at least once to avoid an additional fare (fare-structure effect) — target ≈ 25.23%
9. Topic: Proportion of riders who own a car but still use transit for specific trips — target ≈ 67.60%
1. Traffic congestion delays affected 6,400 out of 11,000 trips monitored during the spring survey period.
2. Route performance analysis showed that 289 out of 801 revenue hours achieved the target ridership threshold.
3. Contactless payment methods accounted for 743 out of 4,398 boardings recorded at downtown stations last month.
4. During peak commuting hours, 3,795 out of 6,998 surveyed riders reported difficulty finding available seating.
5. Ridership density comparisons revealed that 2,793 out of 6,000 transit users were concentrated in the urban core versus suburban areas.
6. System-wide trip tracking found that 8,451 out of 8,994 linked journeys involved at least one vehicle or route change.
7. Following the introduction of dedicated bus lanes, ridership increased by 447 out of 3,000 baseline daily passengers.
8. Fare structure analysis determined that 1,011 out of 4,007 transfer riders cited avoiding additional costs as their primary motivation.
9. Among regular transit users, 4,394 out of 6,500 respondents confirmed they owned a personal vehicle but chose public transit for certain trips.
Model: openai/gpt-5.2
Complete the following task and return your answer as a list of items in XML format.
Rules:
- Wrap all items in <items></items> tags
- Wrap each individual item in <item index="n"></item> tags
- Put each XML tag on its own line
- Put the item content on its own line between the tags
Example format:
<items>
<item index="1">
First item here
</item>
<item index="2">
Second item here
</item>
</items>
Task: Turn each of the 9 topics below into a single-sentence fake statistic about `public transit ridership in a mid-sized U.S. city`.
Rules:
1. Each fact must encode a probability close to its target value.
2. Express the number using ONLY this presentation style:
Use vague approximate language. E.g., 'roughly one in twelve', 'about a third', 'nearly half'. The reader must interpret the approximation as a number.
Example: "roughly one in twelve commuters transfers at Central Station"
3. Do NOT use any other format (no plain percentages unless that IS the style).
4. One sentence per fact. Vary phrasing — don't start every fact the same way.
5. Use both clean numbers (1/3, 2/7) and messy decimals (23.847%, 0.0037) freely.
6. Make sure that are syntactically different from each other. Be creative with the numbers, choose different base numbers and conditional numbers.Topics and targets:
1. Topic: Probability that a rider abandons a trip due to service disruption — target ≈ 27.39%
2. Topic: Proportion of ridership originating from the top 10 highest-boarding stops — target ≈ 72.63%
3. Topic: Proportion of trips made by riders with disabilities using paratransit rather than fixed route — target ≈ 50.57%
4. Topic: Probability that riders rate overall service as “good” or higher in surveys — target ≈ 59.37%
5. Topic: Probability that a rider uses transit at least once in the last 30 days (penetration) — target ≈ 24.07%
6. Topic: Rate of bus stop usage (boardings) before and after stop consolidation — target ≈ 2.60%
7. Topic: Rate of complaints about overcrowding per 10,000 boardings — target ≈ 39.41%
8. Topic: Share of ridership occurring within low-income census tracts — target ≈ 76.95%
9. Topic: Proportion of riders who cite reliability improvements as the reason for increased usage over the past year — target ≈ 27.98%
1. On an average weeknight, roughly one in four riders ends up abandoning their trip when a service disruption drags on too long.
2. Nearly three out of four boardings start at just the ten busiest stops in this mid-sized city.
3. When riders with disabilities make a trip, it’s about a coin-flip plus a hair that they choose paratransit instead of the fixed-route network.
4. Survey cards suggest that close to three in five riders rate the overall service as “good” or better.
5. In a typical month, about one in four residents uses transit at least once.
6. After stop consolidation, the “extra” boardings attributable to the remaining stops comes out to roughly one in thirty-eight compared with before.
7. For every 10,000 boardings, there are about two out of five hundred chances of an overcrowding complaint being filed.
8. Something like four out of five trips occur within low-income census tracts.
9. Among riders who say they’re using transit more than last year, roughly seven in twenty-five point-something credit reliability improvements as the main reason.
Model: anthropic/claude-opus-4-5
Complete the following task and return your answer as a list of items in XML format.
Rules:
- Wrap all items in <items></items> tags
- Wrap each individual item in <item index="n"></item> tags
- Put each XML tag on its own line
- Put the item content on its own line between the tags
Example format:
<items>
<item index="1">
First item here
</item>
<item index="2">
Second item here
</item>
</items>
Task: Turn each of the 9 topics below into a single-sentence fake statistic about `public transit ridership in a mid-sized U.S. city`.
Rules:
1. Each fact must encode a probability close to its target value.
2. Express the number using ONLY this presentation style:
Express the probability as a count and total. E.g., '630 out of 4,200 surveyed reported...'. The reader must divide to get the probability.
Example: "630 out of 4,200 surveyed reported using the express line"
3. Do NOT use any other format (no plain percentages unless that IS the style).
4. One sentence per fact. Vary phrasing — don't start every fact the same way.
5. Use both clean numbers (1/3, 2/7) and messy decimals (23.847%, 0.0037) freely.
6. Make sure that are syntactically different from each other. Be creative with the numbers, choose different base numbers and conditional numbers.Topics and targets:
1. Topic: Share of boardings that are fare-free due to promotion days or pilot programs — target ≈ 95.86%
2. Topic: Proportion of riders eligible for reduced fare who actually use reduced-fare media — target ≈ 8.55%
3. Topic: Rate of reported security incidents per 100,000 passenger trips — target ≈ 17.10%
4. Topic: Rate of first-time fare card/app account creation per 1,000 residents — target ≈ 17.36%
5. Topic: Proportion of riders who are age 65+ using transit at least weekly — target ≈ 44.82%
6. Topic: Likelihood that a rider uses transit to reach a special event venue — target ≈ 30.25%
7. Topic: Share of city residents who ride public transit at least once per week — target ≈ 18.72%
8. Topic: Share of trips involving a bus-to-rail transfer (if rail exists) — target ≈ 73.84%
9. Topic: Probability that a rider uses a microtransit/first-mile service to reach a transit stop — target ≈ 75.02%
1. During the city's promotional transit month, 4,793 out of 5,000 total boardings were recorded as fare-free rides.
2. A survey found that only 171 out of 2,000 riders eligible for reduced fare programs actually tap a discounted fare card.
3. Transit police logged 342 security incidents out of every 2,000,000 passenger trips taken on the city's bus and rail network last year.
4. New fare card and mobile app accounts were created by 868 out of every 50,000 residents during the quarterly enrollment period.
5. Among seniors surveyed, 1,569 out of 3,501 respondents age 65 and older reported using public transit at least once per week.
6. When concert and sporting event attendees were polled, 605 out of 2,000 indicated they had taken public transit to reach the venue.
7. According to census data, approximately 936 out of 5,000 city residents ride buses or trains at least weekly.
8. Transfer records show that 5,169 out of 7,000 weekday trips involve passengers switching from a bus line to the downtown rail corridor.
9. Riders connecting to major transit hubs reported that 3,751 out of 5,000 of them rely on microtransit or first-mile shuttle services to reach their stop.
Model: anthropic/claude-sonnet-4-5
Complete the following task and return your answer as a list of items in XML format.
Rules:
- Wrap all items in <items></items> tags
- Wrap each individual item in <item index="n"></item> tags
- Put each XML tag on its own line
- Put the item content on its own line between the tags
Example format:
<items>
<item index="1">
First item here
</item>
<item index="2">
Second item here
</item>
</items>
Task: Turn each of the 9 topics below into a single-sentence fake statistic about `public transit ridership in a mid-sized U.S. city`.
Rules:
1. Each fact must encode a probability close to its target value.
2. Express the number using ONLY this presentation style:
State the complement of the probability. E.g., 'Only 15% of residents do not use the bus'. The reader must subtract from 100% to get the actual rate.
Example: "Only 15% of residents don't use the bus during peak hours"
3. Do NOT use any other format (no plain percentages unless that IS the style).
4. One sentence per fact. Vary phrasing — don't start every fact the same way.
5. Use both clean numbers (1/3, 2/7) and messy decimals (23.847%, 0.0037) freely.
6. Make sure that are syntactically different from each other. Be creative with the numbers, choose different base numbers and conditional numbers.Topics and targets:
1. Topic: Rate of customer satisfaction change after a network redesign — target ≈ 71.24%
2. Topic: Likelihood that a rider uses a single-stop short trip (one or two stops) — target ≈ 43.84%
3. Topic: Share of riders who experience a transfer wait longer than 10 minutes — target ≈ 48.73%
4. Topic: Change in boarding counts after introducing a new frequent-service corridor — target ≈ 59.50%
5. Topic: Share of peak-period boardings occurring at park-and-ride lots — target ≈ 68.19%
6. Topic: Likelihood that a rider’s origin stop has a posted schedule and route map — target ≈ 14.22%
7. Topic: Proportion of riders who use transit for grocery shopping trips at least monthly — target ≈ 70.55%
8. Topic: Seasonal variation rate in ridership between winter and summer months — target ≈ 64.18%
9. Topic: Share of riders who access transit from a transit-oriented development area — target ≈ 25.05%
1. Only 28.76% of transit customers reported no improvement in their satisfaction following the network redesign.
2. Merely 56.16% of riders do not take single-stop short trips of one or two stops.
3. Just 51.27% of riders avoid experiencing a transfer wait longer than 10 minutes.
4. Only 40.50% of boarding counts did not increase after introducing the new frequent-service corridor.
5. A mere 31.81% of peak-period boardings fail to occur at park-and-ride lots.
6. Only 14.22% of riders find that their origin stop lacks a posted schedule and route map.
7. Just 29.45% of riders do not use transit for grocery shopping trips at least monthly.
8. Only 35.82% of seasonal ridership shows no variation between winter and summer months.
9. Merely 74.95% of riders do not access transit from a transit-oriented development area.
Model: openai/gpt-5.2
Complete the following task and return your answer as a list of items in XML format.
Rules:
- Wrap all items in <items></items> tags
- Wrap each individual item in <item index="n"></item> tags
- Put each XML tag on its own line
- Put the item content on its own line between the tags
Example format:
<items>
<item index="1">
First item here
</item>
<item index="2">
Second item here
</item>
</items>
Task: Turn each of the 9 topics below into a single-sentence fake statistic about `public transit ridership in a mid-sized U.S. city`.
Rules:
1. Each fact must encode a probability close to its target value.
2. Express the number using ONLY this presentation style:
State the complement of the probability. E.g., 'Only 15% of residents do not use the bus'. The reader must subtract from 100% to get the actual rate.
Example: "Only 15% of residents don't use the bus during peak hours"
3. Do NOT use any other format (no plain percentages unless that IS the style).
4. One sentence per fact. Vary phrasing — don't start every fact the same way.
5. Use both clean numbers (1/3, 2/7) and messy decimals (23.847%, 0.0037) freely.
6. Make sure that are syntactically different from each other. Be creative with the numbers, choose different base numbers and conditional numbers.Topics and targets:
1. Topic: Rate of paratransit no-shows as a proportion of scheduled pickups — target ≈ 45.47%
2. Topic: Share of annual ridership concentrated in the top 5 highest-demand event days — target ≈ 88.52%
3. Topic: Likelihood that a rider reports crowding as a primary dissatisfaction factor — target ≈ 85.65%
4. Topic: Percentage of riders who board after 9 PM on weekdays — target ≈ 73.39%
5. Topic: Probability that a rider chooses transit due to lack of car access — target ≈ 4.58%
6. Topic: Proportion of trips where real-time arrival information is accessed by the rider — target ≈ 52.47%
7. Topic: Proportion of riders who report difficulty with first/last-mile connectivity — target ≈ 59.33%
8. Topic: Probability that a new rider continues using transit in the following month (retention) — target ≈ 51.26%
9. Topic: Likelihood that timed transfers are successfully made within the planned window — target ≈ 90.59%
1. Just 54.53% of scheduled paratransit pickups are not missed as no-shows in this mid-sized U.S. city.
2. A mere 11.48% of the year's ridership does not pile into the five biggest event days.
3. Only 14.35% of riders don't name crowding as their main source of dissatisfaction on local buses and trains.
4. On weekdays, just 26.61% of boardings don't happen after 9 PM across the system.
5. Barely 95.42% of riders don't say they chose transit because they lacked access to a car.
6. About 47.53% of trips are taken without the rider checking real-time arrival info beforehand.
7. Roughly 40.67% of riders don't report having trouble connecting the first or last mile to transit.
8. In the month after a first ride, only 48.74% of new riders don't come back and keep using transit.
9. Just 9.41% of planned timed transfers are not successfully made within the intended window.
Model: anthropic/claude-sonnet-4-5
Complete the following task and return your answer as a list of items in XML format.
Rules:
- Wrap all items in <items></items> tags
- Wrap each individual item in <item index="n"></item> tags
- Put each XML tag on its own line
- Put the item content on its own line between the tags
Example format:
<items>
<item index="1">
First item here
</item>
<item index="2">
Second item here
</item>
</items>
Task: Turn each of the 9 topics below into a single-sentence fake statistic about `public transit ridership in a mid-sized U.S. city`.
Rules:
1. Each fact must encode a probability close to its target value.
2. Express the number using ONLY this presentation style:
Express the probability as odds or a ratio. The reader must convert to a probability. Pick ONE of these formats randomly:
- Odds: 'the odds are 4 to 1 in favor' (probability = 4/5 = 0.8)
- Ratio: 'the ratio of affected to unaffected is 1:3' (probability = 1/4 = 0.25)
- Fractional odds: 'the odds of X are 3/7' (probability = 3/10 = 0.3)
Examples (pick one format randomly per fact):
- "the odds of a commuter using the express line are roughly 3 to 7"
- "the ratio of delayed to on-time arrivals is 1:4"
- "the odds of experiencing side effects are 2/9"
3. Do NOT use any other format (no plain percentages unless that IS the style).
4. One sentence per fact. Vary phrasing — don't start every fact the same way.
5. Use both clean numbers (1/3, 2/7) and messy decimals (23.847%, 0.0037) freely.
6. Make sure that are syntactically different from each other. Be creative with the numbers, choose different base numbers and conditional numbers.Topics and targets:
1. Topic: Likelihood that a rider’s trip purpose is commuting to work — target ≈ 51.87%
2. Topic: Probability that a bus arrives at a stop within 5 minutes of scheduled time — target ≈ 43.81%
3. Topic: Likelihood that a rider transfers between routes within a single journey — target ≈ 36.62%
4. Topic: Share of riders using a transit agency mobile app to plan trips — target ≈ 95.82%
5. Topic: Proportion of inbound versus outbound trips during the AM peak — target ≈ 27.50%
6. Topic: Likelihood that riders use transit more frequently after receiving a free trial pass — target ≈ 80.01%
7. Topic: Proportion of riders who use transit at least once between midnight and 5 AM — target ≈ 99.86%
8. Topic: Likelihood that a rider uses transit to reach the central business district — target ≈ 4.74%
9. Topic: Proportion of riders who make at least 10 trips per month (frequent riders) — target ≈ 8.56%
1. Among public transit users in mid-sized U.S. cities, the odds that a rider's trip purpose is commuting to work stand at approximately 108 to 100.
2. The ratio of buses arriving within 5 minutes of scheduled time to those arriving late is roughly 78:100 across monitored stops.
3. For riders transferring between routes during a single journey versus those making direct trips, the odds are 58 to 100.
4. Transit riders using a mobile app to plan trips outnumber those who don't at a ratio of approximately 23 to 1.
5. During the AM peak period, the odds of a trip being outbound rather than inbound are 11 to 29.
6. After receiving a free trial pass, the ratio of riders who increase their transit use to those who don't is 4 to 1.
7. The odds are 713 to 1 in favor of a rider having used transit at least once between midnight and 5 AM.
8. For trips destined to the central business district compared to all other destinations, the ratio stands at 1 to 20.
9. The odds of a rider making at least 10 trips per month are approximately 28 to 299.
Model: openai/gpt-5.2
Complete the following task and return your answer as a list of items in XML format.
Rules:
- Wrap all items in <items></items> tags
- Wrap each individual item in <item index="n"></item> tags
- Put each XML tag on its own line
- Put the item content on its own line between the tags
Example format:
<items>
<item index="1">
First item here
</item>
<item index="2">
Second item here
</item>
</items>
Task: Turn each of the 9 topics below into a single-sentence fake statistic about `public transit ridership in a mid-sized U.S. city`.
Rules:
1. Each fact must encode a probability close to its target value.
2. Express the number using ONLY this presentation style:
State the complement of the probability. E.g., 'Only 15% of residents do not use the bus'. The reader must subtract from 100% to get the actual rate.
Example: "Only 15% of residents don't use the bus during peak hours"
3. Do NOT use any other format (no plain percentages unless that IS the style).
4. One sentence per fact. Vary phrasing — don't start every fact the same way.
5. Use both clean numbers (1/3, 2/7) and messy decimals (23.847%, 0.0037) freely.
6. Make sure that are syntactically different from each other. Be creative with the numbers, choose different base numbers and conditional numbers.Topics and targets:
1. Topic: Percentage of riders experiencing a headway wait longer than 15 minutes on frequent routes — target ≈ 5.42%
2. Topic: Proportion of total ridership that occurs on weekends — target ≈ 42.34%
3. Topic: Share of ridership attributable to students during the academic year — target ≈ 37.05%
4. Topic: Proportion of riders who report stop lighting as adequate at night — target ≈ 75.03%
5. Topic: Rate of ridership during school breaks compared with school-in-session periods — target ≈ 41.33%
6. Topic: Probability that a rider arrives on time to their destination using transit (self-reported) — target ≈ 1.10%
7. Topic: Probability that a rider experiences a full bus pass-by at their stop — target ≈ 30.71%
8. Topic: Share of riders who choose transit over driving specifically due to parking cost — target ≈ 93.72%
9. Topic: Frequency of major service disruptions per month affecting at least one route — target ≈ 29.35%
1. Just 94.58% of riders on the city’s frequent routes avoid waiting longer than 15 minutes between vehicles.
2. In this mid-sized city, only 57.66% of all transit boardings do not happen on weekends.
3. During the academic year, only 62.95% of total ridership is not accounted for by students.
4. After dark, merely 24.97% of riders say stop lighting is not adequate.
5. When schools are on break, only 58.67% of the in-session ridership level does not show up on the system.
6. By riders’ own reports, only 98.90% of trips do not arrive on time when taken by public transit.
7. At the stop, only 69.29% of riders don’t experience a full bus passing them by.
8. For people choosing transit over driving, only 6.28% say parking cost is not the deciding reason.
9. In an average month, only 70.65% of months don’t see a major service disruption that affects at least one route.
Stage 3 — domain=0 (public transit ridership in a mid-sized U.S. city) twists=['buried_in_parenthetical', 'temporal_distraction']
Model: anthropic/claude-sonnet-4-5
Write a long, detailed document about: `public transit ridership in a mid-sized U.S. city`
The document MUST contain ALL of the following facts, woven naturally into the text.
FACTS:
1. Only 16.01% of riders report feeling unsafe at stops during nighttime hours.
2. Just 88.94% of boardings do not involve bicycle-on-bus rack usage per 1,000 trips recorded.
3. Fare evasion incidents fail to occur in 86.05% of every 10,000 boardings system-wide.
4. A mere 83.22% of riders do not combine multiple modes in a single day.
5. Only 72.95% of trips remain within municipal boundaries without crossing into neighboring jurisdictions.
6. Roughly 79.81% of riders do not require multilingual signage or translated materials during their journey.
7. Just 39.53% of bus trips avoid the bunching phenomenon where two vehicles arrive within a short interval.
8. Delay-related complaints are absent in 40.53% of every 10,000 boardings tracked by the system.
9. Only 9.92% of seat-hours on high-demand corridors fail to achieve turnover during peak service periods.
10. During a recent accessibility audit, 158 out of 250 riders reported language barriers when using transit information.
11. Survey data showed that 1,278 out of 4,000 daily riders make chained trips involving multiple errands on a single day using transit.
12. Fare payment analysis revealed that 5,150 out of 7,000 riders have their fare paid via employer-sponsored transit benefit programs.
13. According to boarding pattern studies, 861 out of 3,000 trips begin with first boarding occurring at a timed-transfer hub.
14. Monthly service records indicate that 1,437 out of 1,701 riders were affected by a detour on their most-used route in a given month.
15. Economic modeling found that 453 out of 3,000 sampled route segments showed ridership change associated with gasoline price increases.
16. Operational data demonstrates that 2,366 out of 4,000 total system ridership is served by the top-performing route.
17. Infrastructure mapping confirmed 521 out of 2,000 boardings occurring at stops with shelters.
18. Real-time tracking showed 1,167 out of 2,000 trips where the rider's planned itinerary changes due to delays.
19. The proportion of riders whose transit trip replaces a car trip they would otherwise take stands at 8838 basis points according to the latest survey.
20. Among riders under 18, the share using transit for school trips has reached 8124 basis points in the current academic year.
21. Vehicle trips that exceed seated capacity at any point occur at a rate of 522 basis points during typical service hours.
22. A randomly selected weekday bus trip has a 3899 basis point probability of occurring during the AM peak period.
23. Ridership growth in newly developed neighborhoods outpaces mature areas by 8418 basis points when measured year-over-year.
24. Boardings occurring on routes with 15-minute-or-better headways represent 8644 basis points of total system ridership.
25. The distribution share of trips longer than 5 miles measures 3183 basis points across all journey types.
26. Riders combining transit with rideshare for last-mile connections account for 1458 basis points of the ridership base.
27. The fraction of riders who access transit by biking versus other modes registers at 1972 basis points in modal split analysis.
28. In this mid-sized U.S. city, the probability that a rider’s usual transit commute runs longer than 45 minutes is approximately 4.733×10^-1.
29. Across route segments, the share with average operating speed below the threshold is about 8.162×10^-1.
30. Following a fare increase, the magnitude of ridership change per event is on the order of 8.48×10^-2.
31. For transit riders here, the chance a household falls under the defined income cutoff is roughly 2.661×10^-1.
32. Given real-time crowding alerts, the conditional probability a rider switches to a different route is near 7.34×10^-1.
33. The proportion of riders who begin their trip within a half-mile of frequent service comes out to ≈5.514×10^-1.
34. Per stop within a quarter-mile of major employers, ridership concentration is about 9.7/20 in probability terms.
35. At the origin stop, the likelihood that boarding access is ADA-compliant is approximately 3.906×10^-1.
36. During severe weather days, the rate of ridership loss relative to typical days is about 4.495×10^-1.
37. Systemwide unlinked trips rose this year because 61.0% of last year’s riders were retained and, among those retained, average trip frequency ran at 1.75× last year.
38. Operations logs show 99.5% of weekday scheduled trips were missed, and weekends made up 6.94% of the schedule with a 0% miss rate.
39. Fare data indicate 72% of riders are “regulars,” and 66% of those regulars load a monthly pass rather than paying per ride.
40. At terminals, 77% of departures are “not early,” and 68.584% of those not-early departures leave within 2 minutes of the posted time.
41. Crowding audits found 85% of peak trips occur on high-load segments, and on those segments 2/3 of riders end up standing for more than 10 minutes.
42. In rider surveys, 1 in 25 passengers reported ever being asked for proof-of-payment, and 99.25% of those reports were confirmed by follow-up.
43. Across the network, 93% of routes are in the “frequent service” group, and 94.763% of that group clears the agency’s on-time threshold.
44. Compared with a reference share of 20%, the portion naming cost savings as their main reason is 2.71 percentage points lower.
45. Trip-purpose logs show 13% of riders use transit for any healthcare-related errand, and 2/3 of those healthcare riders say the trip was specifically for a medical appointment.
46. Traffic congestion delays affected 6,400 out of 11,000 trips monitored during the spring survey period.
47. Route performance analysis showed that 289 out of 801 revenue hours achieved the target ridership threshold.
48. Contactless payment methods accounted for 743 out of 4,398 boardings recorded at downtown stations last month.
49. During peak commuting hours, 3,795 out of 6,998 surveyed riders reported difficulty finding available seating.
50. Ridership density comparisons revealed that 2,793 out of 6,000 transit users were concentrated in the urban core versus suburban areas.
51. System-wide trip tracking found that 8,451 out of 8,994 linked journeys involved at least one vehicle or route change.
52. Following the introduction of dedicated bus lanes, ridership increased by 447 out of 3,000 baseline daily passengers.
53. Fare structure analysis determined that 1,011 out of 4,007 transfer riders cited avoiding additional costs as their primary motivation.
54. Among regular transit users, 4,394 out of 6,500 respondents confirmed they owned a personal vehicle but chose public transit for certain trips.
55. On an average weeknight, roughly one in four riders ends up abandoning their trip when a service disruption drags on too long.
56. Nearly three out of four boardings start at just the ten busiest stops in this mid-sized city.
57. When riders with disabilities make a trip, it’s about a coin-flip plus a hair that they choose paratransit instead of the fixed-route network.
58. Survey cards suggest that close to three in five riders rate the overall service as “good” or better.
59. In a typical month, about one in four residents uses transit at least once.
60. After stop consolidation, the “extra” boardings attributable to the remaining stops comes out to roughly one in thirty-eight compared with before.
61. For every 10,000 boardings, there are about two out of five hundred chances of an overcrowding complaint being filed.
62. Something like four out of five trips occur within low-income census tracts.
63. Among riders who say they’re using transit more than last year, roughly seven in twenty-five point-something credit reliability improvements as the main reason.
64. During the city's promotional transit month, 4,793 out of 5,000 total boardings were recorded as fare-free rides.
65. A survey found that only 171 out of 2,000 riders eligible for reduced fare programs actually tap a discounted fare card.
66. Transit police logged 342 security incidents out of every 2,000,000 passenger trips taken on the city's bus and rail network last year.
67. New fare card and mobile app accounts were created by 868 out of every 50,000 residents during the quarterly enrollment period.
68. Among seniors surveyed, 1,569 out of 3,501 respondents age 65 and older reported using public transit at least once per week.
69. When concert and sporting event attendees were polled, 605 out of 2,000 indicated they had taken public transit to reach the venue.
70. According to census data, approximately 936 out of 5,000 city residents ride buses or trains at least weekly.
71. Transfer records show that 5,169 out of 7,000 weekday trips involve passengers switching from a bus line to the downtown rail corridor.
72. Riders connecting to major transit hubs reported that 3,751 out of 5,000 of them rely on microtransit or first-mile shuttle services to reach their stop.
73. Only 28.76% of transit customers reported no improvement in their satisfaction following the network redesign.
74. Merely 56.16% of riders do not take single-stop short trips of one or two stops.
75. Just 51.27% of riders avoid experiencing a transfer wait longer than 10 minutes.
76. Only 40.50% of boarding counts did not increase after introducing the new frequent-service corridor.
77. A mere 31.81% of peak-period boardings fail to occur at park-and-ride lots.
78. Only 14.22% of riders find that their origin stop lacks a posted schedule and route map.
79. Just 29.45% of riders do not use transit for grocery shopping trips at least monthly.
80. Only 35.82% of seasonal ridership shows no variation between winter and summer months.
81. Merely 74.95% of riders do not access transit from a transit-oriented development area.
82. Just 54.53% of scheduled paratransit pickups are not missed as no-shows in this mid-sized U.S. city.
83. A mere 11.48% of the year's ridership does not pile into the five biggest event days.
84. Only 14.35% of riders don't name crowding as their main source of dissatisfaction on local buses and trains.
85. On weekdays, just 26.61% of boardings don't happen after 9 PM across the system.
86. Barely 95.42% of riders don't say they chose transit because they lacked access to a car.
87. About 47.53% of trips are taken without the rider checking real-time arrival info beforehand.
88. Roughly 40.67% of riders don't report having trouble connecting the first or last mile to transit.
89. In the month after a first ride, only 48.74% of new riders don't come back and keep using transit.
90. Just 9.41% of planned timed transfers are not successfully made within the intended window.
91. Among public transit users in mid-sized U.S. cities, the odds that a rider's trip purpose is commuting to work stand at approximately 108 to 100.
92. The ratio of buses arriving within 5 minutes of scheduled time to those arriving late is roughly 78:100 across monitored stops.
93. For riders transferring between routes during a single journey versus those making direct trips, the odds are 58 to 100.
94. Transit riders using a mobile app to plan trips outnumber those who don't at a ratio of approximately 23 to 1.
95. During the AM peak period, the odds of a trip being outbound rather than inbound are 11 to 29.
96. After receiving a free trial pass, the ratio of riders who increase their transit use to those who don't is 4 to 1.
97. The odds are 713 to 1 in favor of a rider having used transit at least once between midnight and 5 AM.
98. For trips destined to the central business district compared to all other destinations, the ratio stands at 1 to 20.
99. The odds of a rider making at least 10 trips per month are approximately 28 to 299.
100. Just 94.58% of riders on the city’s frequent routes avoid waiting longer than 15 minutes between vehicles.
101. In this mid-sized city, only 57.66% of all transit boardings do not happen on weekends.
102. During the academic year, only 62.95% of total ridership is not accounted for by students.
103. After dark, merely 24.97% of riders say stop lighting is not adequate.
104. When schools are on break, only 58.67% of the in-session ridership level does not show up on the system.
105. By riders’ own reports, only 98.90% of trips do not arrive on time when taken by public transit.
106. At the stop, only 69.29% of riders don’t experience a full bus passing them by.
107. For people choosing transit over driving, only 6.28% say parking cost is not the deciding reason.
108. In an average month, only 70.65% of months don’t see a major service disruption that affects at least one route.
CRITICAL — PRESERVE EXACT PHRASING:
Each fact above uses a specific presentation style. Try to keep the same style, wording, and number format when embedding each fact. If rephrasing is needed to apply an embedding strategy that makes extraction harder, that is fine — but otherwise preserve the original phrasing.
EMBEDDING STRATEGIES:
Use the following strategies to embed the facts into the document so they are not immediately obvious to a reader scanning for them. The strategies should be invisible — the document must read naturally with no hint that anything is being hidden.
- buried_in_parenthetical: Place some of the key facts inside parenthetical asides, footnotes, or end-of-paragraph afterthoughts rather than in the main text flow. The number should be easy to skip on a quick scan. E.g., '...the program expanded to 14 routes (with an observed rider retention rate of 83.2% among pass holders) and added weekend service.'
- temporal_distraction: Include an older, outdated statistic for the same metric alongside the current one. Do NOT clearly label which is current — make the reader figure out which number is the up-to-date one. E.g., mention a 2019 figure in one paragraph and bury the current figure later.
Write the complete document text, nothing else.
# Public Transit Ridership in a Mid-Sized U.S. City: A Comprehensive Analysis
## Executive Summary
Public transportation in mid-sized American cities faces unique challenges distinct from both major metropolitan transit systems and smaller rural networks. This report examines ridership patterns, operational performance, user demographics, and service quality in a representative mid-sized U.S. city, drawing on extensive survey data, boarding records, real-time tracking systems, and customer feedback collected over the past two years. The findings reveal a complex ecosystem where traditional commuter patterns intersect with evolving mobility preferences, equity considerations shape service delivery, and operational constraints test the limits of existing infrastructure.
## Historical Context and System Overview
The city's public transit network has evolved significantly over the past three decades. What began as a modest eight-route bus system in the early 1990s has expanded into a multimodal network serving diverse neighborhoods and employment centers. The system now operates forty-three distinct routes, including local, express, and circulator services, alongside a downtown rail corridor that opened in 2014. Prior to the corridor's introduction, only 40.50% of boarding counts did not increase after introducing the new frequent-service corridor—a statistic that initially surprised planners who expected more dramatic ridership gains from the rail investment.
The network's geographic footprint reflects the city's sprawling development patterns. While a considerable share of service remains concentrated in established urban neighborhoods, suburban expansion has driven route extensions into lower-density areas. Ridership density comparisons revealed that 2,793 out of 6,000 transit users were concentrated in the urban core versus suburban areas, highlighting the persistent challenge of serving dispersed origins and destinations efficiently. This concentration pattern influences everything from service frequency allocation to fare policy decisions.
## Ridership Composition and Demographics
Understanding who rides public transit—and why—forms the foundation of effective service planning. The city's ridership base exhibits notable diversity across income levels, age groups, and trip purposes. For people choosing transit over driving, only 6.28% say parking cost is not the deciding reason, suggesting that parking-related factors exert considerable influence on mode choice decisions, particularly in the downtown core where parking rates have climbed steadily since 2018.
Among riders surveyed about their modal access to the system, something like four out of five trips occur within low-income census tracts, underscoring the system's essential role as a mobility lifeline for economically disadvantaged populations. This demographic reality shapes service design priorities and complicates efforts to balance cost recovery with social equity objectives. For transit riders here, the chance a household falls under the defined income cutoff is roughly 2.661×10^-1, a figure that has held relatively stable over the past five years despite rising housing costs and wage growth in certain sectors.
Age distribution among riders reveals important patterns for service planning. Among seniors surveyed, 1,569 out of 3,501 respondents age 65 and older reported using public transit at least once per week, a participation rate that transit planners consider healthy for this demographic segment. The system offers reduced fares for seniors and persons with disabilities, though a survey found that only 171 out of 2,000 riders eligible for reduced fare programs actually tap a discounted fare card, suggesting significant underutilization of discount programs potentially due to enrollment barriers or lack of awareness.
Youth ridership presents its own distinct characteristics. During the academic year, only 62.95% of total ridership is not accounted for by students, making school-related travel a cornerstone of the system's daily demand. Among riders under 18, the share using transit for school trips has reached 8124 basis points in the current academic year, reflecting both targeted service investments near schools and family economic factors. When schools are on break, only 58.67% of the in-session ridership level does not show up on the system, creating pronounced seasonal variability that complicates service planning and budget forecasting.
According to census data, approximately 936 out of 5,000 city residents ride buses or trains at least weekly, a penetration rate that transit officials view as both encouraging and frustratingly static. Efforts to expand the rider base beyond this core constituency have met with mixed success. In a typical month, about one in four residents uses transit at least once, suggesting that occasional users represent a significant but underutilized market segment. Converting these infrequent riders into regular users remains a strategic priority for the agency.
## Trip Patterns and Journey Characteristics
The spatial and temporal distribution of transit trips reveals how riders use the system in practice. Among public transit users in mid-sized U.S. cities, the odds that a rider's trip purpose is commuting to work stand at approximately 108 to 100, indicating that work trips slightly outnumber all other purposes combined—a narrower margin than many transit systems experience. This relative balance between commute and non-commute trips suggests a more diversified ridership base than traditional commuter-heavy systems.
Journey origins show marked clustering. Nearly three out of four boardings start at just the ten busiest stops in this mid-sized city, creating pronounced load imbalances across the network. This concentration drives strategic decisions about shelter placement, real-time information deployment, and service frequency allocation. Infrastructure mapping confirmed 521 out of 2,000 boardings occurring at stops with shelters, a ratio that transit planners acknowledge falls short of targets set in the agency's passenger amenities plan adopted three years ago.
The geography of trips reflects both employment concentration and residential density patterns. For trips destined to the central business district compared to all other destinations, the ratio stands at 1 to 20, a surprisingly low share that reflects the city's polycentric employment landscape and the system's function serving distributed trip patterns beyond traditional downtown-focused commuting. Per stop within a quarter-mile of major employers, ridership concentration is about 9.7/20 in probability terms, illustrating how proximity to major job centers drives ridership but does not entirely determine boarding patterns.
Trip length distributions reveal important service characteristics. The distribution share of trips longer than 5 miles measures 3183 basis points across all journey types, indicating that while the system handles some longer-distance travel, most trips remain relatively local. Only 72.95% of trips remain within municipal boundaries without crossing into neighboring jurisdictions, pointing to meaningful but not dominant cross-jurisdictional travel demand. These boundary-crossing trips present particular planning challenges, as they often involve coordination with neighboring transit agencies and county governments.
Transfer behavior significantly shapes the rider experience. For riders transferring between routes during a single journey versus those making direct trips, the odds are 58 to 100, suggesting that direct service remains more common but multi-leg journeys constitute a substantial share of total trips. Transfer records show that 5,169 out of 7,000 weekday trips involve passengers switching from a bus line to the downtown rail corridor, highlighting the rail line's role as a connector and the importance of seamless transfer environments. According to boarding pattern studies, 861 out of 3,000 trips begin with first boarding occurring at a timed-transfer hub, underscoring the value of coordinated scheduling at key nodes.
System-wide trip tracking found that 8,451 out of 8,994 linked journeys involved at least one vehicle or route change, a strikingly high proportion that surprised researchers when the data was first analyzed in late 2022. Just 9.41% of planned timed transfers are not successfully made within the intended window, indicating that coordination generally functions well but occasional failures frustrate riders. Merely 56.16% of riders do not take single-stop short trips of one or two stops, suggesting that convenience and accessibility drive some boarding decisions even when walking might be faster.
Multimodal connections represent a growing but still modest share of journeys. Only 9.92% of seat-hours on high-demand corridors fail to achieve turnover during peak service periods, demonstrating efficient capacity utilization but also pointing to crowding pressures during busy times. Riders combining transit with rideshare for last-mile connections account for 1458 basis points of the ridership base, a figure that has grown steadily as transportation network companies have expanded service coverage. The fraction of riders who access transit by biking versus other modes registers at 1972 basis points in modal split analysis (though an earlier 2020 study had reported bicycle access at just 1311 basis points, suggesting growth in bike-transit integration). Just 88.94% of boardings do not involve bicycle-on-bus rack usage per 1,000 trips recorded, confirming that while bike integration remains relatively uncommon, the racks do see regular utilization by a dedicated user segment.
A mere 83.22% of riders do not combine multiple modes in a single day, meaning that roughly one in six transit users integrate other transportation options into their daily travel patterns. This multimodal behavior reflects both the system's gaps and the growing availability of complementary services. Survey data showed that 1,278 out of 4,000 daily riders make chained trips involving multiple errands on a single day using transit, highlighting the system's role beyond simple home-to-work commuting. Among regular transit users, 4,394 out of 6,500 respondents confirmed they owned a personal vehicle but chose public transit for certain trips, demonstrating that transit competes successfully for discretionary trips even among car-owning households.
Temporal patterns show characteristic peak concentrations. A randomly selected weekday bus trip has a 3899 basis point probability of occurring during the AM peak period, reflecting typical commuter flows but also indicating that midday, evening, and weekend travel constitute the majority of trips. During the AM peak period, the odds of a trip being outbound rather than inbound are 11 to 29, as expected in a system dominated by downtown-bound morning commutes. On weekdays, just 26.61% of boardings don't happen after 9 PM across the system, suggesting that evening service attracts significant ridership despite lower frequency compared to daytime operations. In this mid-sized city, only 57.66% of all transit boardings do not happen on weekends, making weekend service an important component of total ridership rather than a minor add-on.
The odds are 713 to 1 in favor of a rider having used transit at least once between midnight and 5 AM, indicating that late-night service, while limited in this system, does serve a small but dedicated user base. This overnight ridership includes shift workers, service industry employees, and others whose work schedules fall outside conventional daytime hours.
## Service Quality and Performance Metrics
On-time performance remains a critical indicator of service reliability. The ratio of buses arriving within 5 minutes of scheduled time to those arriving late is roughly 78:100 across monitored stops, a performance level that falls short of the agency's 85:100 target established in its strategic plan. Across the network, 93% of routes are in the "frequent service" group, and 94.763% of that group clears the agency's on-time threshold, suggesting that higher-frequency routes paradoxically achieve better punctuality than their less-frequent counterparts—possibly because schedule padding and traffic conditions affect them differently.
At terminals, 77% of departures are "not early," and 68.584% of those not-early departures leave within 2 minutes of the posted time, indicating that while late departures present challenges, early departures—which can cause riders to miss scheduled connections—occur in roughly one quarter of cases. By riders' own reports, only 98.90% of trips do not arrive on time when taken by public transit, meaning that riders perceive essentially all trips as arriving late, a perception that may reflect low tolerance for even minor delays or confusion about how schedule adherence is measured.
Delay-related complaints are absent in 40.53% of every 10,000 boardings tracked by the system, translating to roughly six complaints per 10,000 boardings—a rate that customer service staff consider manageable but still representing thousands of complaints annually given system ridership volumes. Real-time tracking showed 1,167 out of 2,000 trips where the rider's planned itinerary changes due to delays, underscoring how service disruptions ripple through multi-leg journeys and compound traveler frustration.
Traffic congestion delays affected 6,400 out of 11,000 trips monitored during the spring survey period, demonstrating that shared right-of-way operations expose transit to the same congestion that frustrates private vehicle users. Monthly service records indicate that 1,437 out of 1,701 riders were affected by a detour on their most-used route in a given month, showing how construction projects, special events, and other disruptions touch most riders regularly. In an average month, only 70.65% of months don't see a major service disruption that affects at least one route, suggesting that significant disruptions occur roughly once every three or four months—frequent enough to erode rider confidence in service consistency.
On an average weeknight, roughly one in four riders ends up abandoning their trip when a service disruption drags on too long, representing a substantial loss of ridership to delays and service failures. During severe weather days, the rate of ridership loss relative to typical days is about 4.495×10^-1, indicating that nearly half of regular riders opt not to travel or choose alternative modes when conditions deteriorate.
Operations logs show 99.5% of weekday scheduled trips were missed, and weekends made up 6.94% of the schedule with a 0% miss rate—figures that initially appear alarming but likely reflect a data collection error or reporting inconsistency in the operational records, as a miss rate approaching 100% on weekdays would render the system essentially nonfunctional while a perfect weekend completion rate seems equally implausible.
Bus bunching—where two or more vehicles on the same route arrive nearly simultaneously—erodes schedule reliability and passenger experience. Just 39.53% of bus trips avoid the bunching phenomenon where two vehicles arrive within a short interval, meaning that bunching affects the majority of trips to some degree. Across route segments, the share with average operating speed below the threshold is about 8.162×10^-1, indicating widespread slow operations that undermine competitiveness with private vehicles.
Crowding represents another dimension of service quality. Crowding audits found 85% of peak trips occur on high-load segments, and on those segments 2/3 of riders end up standing for more than 10 minutes, creating uncomfortable conditions that may deter choice riders. During peak commuting hours, 3,795 out of 6,998 surveyed riders reported difficulty finding available seating, confirming that capacity constraints present real problems during busy periods. At the stop, only 69.29% of riders don't experience a full bus passing them by, meaning that pass-ups—where a vehicle is too crowded to board additional passengers—affect nearly one-third of riders.
Vehicle trips that exceed seated capacity at any point occur at a rate of 522 basis points during typical service hours, showing that standing loads are common but not universal. For every 10,000 boardings, there are about two out of five hundred chances of an overcrowding complaint being filed (translating to roughly four complaints per 10,000 boardings), suggesting that most riders tolerate crowded conditions without filing formal complaints even when uncomfortable.
Just 94.58% of riders on the city's frequent routes avoid waiting longer than 15 minutes between vehicles, indicating that the "frequent service" designation—typically defined as 15-minute headways or better—delivers as promised for nearly all riders. Boardings occurring on routes with 15-minute-or-better headways represent 8644 basis points of total system ridership, confirming that frequent service corridors capture the lion's share of total demand.
## Service Coverage and Access
Geographic access to transit shapes who can use the system. The proportion of riders who begin their trip within a half-mile of frequent service comes out to ≈5.514×10^-1, meaning that just over half of riders live close enough to high-frequency routes to enjoy good access, while the remainder depend on less frequent local routes or longer walks. At the origin stop, the likelihood that boarding access is ADA-compliant is approximately 3.906×10^-1, revealing that fewer than half of boarding locations meet full accessibility standards—a deficit that advocates have pressed the agency to address more aggressively.
Only 14.22% of riders find that their origin stop lacks a posted schedule and route map, suggesting that basic information provision reaches most but not all stops. During a recent accessibility audit, 158 out of 250 riders reported language barriers when using transit information, pointing to significant gaps in multilingual communication despite a growing non-English-speaking population. Roughly 79.81% of riders do not require multilingual signage or translated materials during their journey, but the roughly one-fifth who do need such materials often find them unavailable or inadequate.
Park-and-ride facilities extend the system's effective reach into suburban areas. A mere 31.81% of peak-period boardings fail to occur at park-and-ride lots, meaning that these facilities account for more than two-thirds of peak boardings—a surprisingly high share that reflects the system's role in serving suburban commuters. Riders connecting to major transit hubs reported that 3,751 out of 5,000 of them rely on microtransit or first-mile shuttle services to reach their stop, demonstrating the importance of feeder services in completing the first-mile connection.
Route performance varies significantly across the network. Route performance analysis showed that 289 out of 801 revenue hours achieved the target ridership threshold, indicating that while some service exceeds productivity standards, much of the network operates below targets. Operational data demonstrates that 2,366 out of 4,000 total system ridership is served by the top-performing route, illustrating the extreme load imbalance between the busiest corridor and the rest of the network. Following the introduction of dedicated bus lanes, ridership increased by 447 out of 3,000 baseline daily passengers on the affected corridor, demonstrating the ridership benefits of transit priority treatments.
After stop consolidation, the "extra" boardings attributable to the remaining stops comes out to roughly one in thirty-eight compared with before, suggesting that stop consolidation—intended to improve service speed—may have produced only modest ridership gains while potentially reducing access for some riders.
## Economic Factors and Fare Policy
Fare structure and pricing significantly influence ridership patterns and cost recovery. Fare payment analysis revealed that 5,150 out of 7,000 riders have their fare paid via employer-sponsored transit benefit programs, demonstrating the critical role of employer subsidies in supporting ridership in this city. Fare data indicate 72% of riders are "regulars," and 66% of those regulars load a monthly pass rather than paying per ride, showing that unlimited-ride passes appeal to frequent users seeking predictable costs.
Fare structure analysis determined that 1,011 out of 4,007 transfer riders cited avoiding additional costs as their primary motivation, highlighting how transfer penalties influence rider behavior and route choices. Contactless payment methods accounted for 743 out of 4,398 boardings recorded at downtown stations last month, indicating gradual but incomplete adoption of newer payment technologies.
Fare enforcement presents operational and equity challenges. Fare evasion incidents fail to occur in 86.05% of every 10,000 boardings system-wide, translating to an evasion rate approaching 14% if read straightforwardly. In rider surveys, 1 in 25 passengers reported ever being asked for proof-of-payment, and 99.25% of those reports were confirmed by follow-up, indicating that fare inspection occurs infrequently but is consistently documented when it does happen.
Economic conditions shape transit demand in complex ways. Economic modeling found that 453 out of 3,000 sampled route segments showed ridership change associated with gasoline price increases, confirming that fuel costs influence mode choice but the relationship is not uniform across all corridors. The proportion of riders whose transit trip replaces a car trip they would otherwise take stands at 8838 basis points according to the latest survey, meaning that the vast majority of riders do not view their transit trip as substituting for a forgone car trip—either because they lack car access or because the trip would not have been made at all.
Following a fare increase, the magnitude of ridership change per event is on the order of 8.48×10^-2, suggesting that fare elasticity remains modest but measurable, with price increases producing roughly an 8.5% ridership decline. Compared with a reference share of 20%, the portion naming cost savings as their main reason is 2.71 percentage points lower, meaning that 17.29% cite cost as the primary motivation—still significant but not dominant.
During the city's promotional transit month, 4,793 out of 5,000 total boardings were recorded as fare-free rides, demonstrating strong response to fare elimination and suggesting that price remains a meaningful barrier for some potential riders. After receiving a free trial pass, the ratio of riders who increase their transit use to those who don't is 4 to 1, indicating that trial programs effectively convert some users to higher frequency.
## Rider Satisfaction and Service Perception
Customer satisfaction metrics provide insight into service quality from the user perspective. Survey cards suggest that close to three in five riders rate the overall service as "good" or better, a satisfaction level that transit officials view as middling—neither crisis-inducing nor exemplary. Only 28.76% of transit customers reported no improvement in their satisfaction following the network redesign, implying that roughly 71% perceived at least some improvement, though the magnitude and durability of those gains remain uncertain.
Among riders who say they're using transit more than last year, roughly seven in twenty-five point-something credit reliability improvements as the main reason, suggesting that schedule adherence and service consistency resonate strongly with riders who increase usage. Among regular transit users, the odds of a rider making at least 10 trips per month are approximately 28 to 299, indicating that truly frequent users represent a minority even among the "regular" rider segment.
Only 14.35% of riders don't name crowding as their main source of dissatisfaction on local buses and trains, meaning that crowding emerges as the dominant complaint—cited by roughly 86% of dissatisfied riders. Merely 51.27% of riders avoid experiencing a transfer wait longer than 10 minutes, highlighting how coordination gaps between routes create delays that compound journey times and frustrate users.
Safety perceptions vary by time and location. Only 16.01% of riders report feeling unsafe at stops during nighttime hours, suggesting that the vast majority feel secure, though the minority experiencing fear represents a meaningful number. Transit police logged 342 security incidents out of every 2,000,000 passenger trips taken on the city's bus and rail network last year, translating to a rate of roughly 17 incidents per 100,000 trips—a frequency that transit staff consider low but that can loom large in public perception when incidents receive media attention. After dark, merely 24.97% of riders say stop lighting is not adequate, meaning that three-quarters perceive lighting as inadequate—a serious concern for evening and late-night service.
Information access shapes the rider experience. Transit riders using a mobile app to plan trips outnumber those who don't at a ratio of approximately 23 to 1, indicating near-universal adoption of digital trip planning tools among the ridership base. About 47.53% of trips are taken without the rider checking real-time arrival info beforehand, suggesting that roughly half of riders still rely on published schedules or simply show up at stops without advance information. Given real-time crowding alerts, the conditional probability a rider switches to a different route is near 7.34×10^-1, demonstrating that crowding information, when provided, influences routing decisions for most riders.
Roughly 40.67% of riders don't report having trouble connecting the first or last mile to transit, implying that roughly 59% do experience first/last-mile challenges—a finding that underscores the importance of complete door-to-door journeys in transit competitiveness.
## Paratransit and Specialized Services
The complementary paratransit system serves riders with disabilities who cannot use fixed-route service. When riders with disabilities make a trip, it's about a coin-flip plus a hair that they choose paratransit instead of the fixed-route network, indicating that both systems serve meaningful shares of the disabled community. Just 54.53% of scheduled paratransit pickups are not missed as no-shows in this mid-sized U.S. city, meaning that no-show rates approach 45%—a persistent challenge that drives up costs and reduces system efficiency.
## Healthcare and Social Service Access
Public transit plays a critical role in healthcare access for car-less households. Trip-purpose logs show 13% of riders use transit for any healthcare-related errand, and 2/3 of those healthcare riders say the trip was specifically for a medical appointment, highlighting the system's importance for connecting residents to medical facilities and supporting public health outcomes.
## Event-Related Ridership and Special Service
Special events generate significant ridership spikes. A mere 11.48% of the year's ridership does not pile into the five biggest event days, meaning that nearly 90% of annual ridership concentrates on just five event days—an extraordinary claim that likely reflects a phrasing ambiguity or data interpretation error, as typical special-event ridership accounts for a much smaller annual share. When concert and sporting event attendees were polled, 605 out of 2,000 indicated they had taken public transit to reach the venue, suggesting that roughly 30% of event-goers use transit—a healthy modal share for discretionary travel.
## Trends in Transit-Oriented Development
Land use patterns increasingly shape ridership outcomes. Merely 74.95% of riders do not access transit from a transit-oriented development area, implying that one-quarter of riders board from TOD neighborhoods—a significant share that demonstrates the ridership benefits of coordinated land use and transportation planning. Ridership growth in newly developed neighborhoods outpaces mature areas by 8418 basis points when measured year-over-year, showing that new development with integrated transit planning generates strong ridership gains.
## Ridership Retention and Growth
Systemwide unlinked trips rose this year because 61.0% of last year's riders were retained and, among those retained, average trip frequency ran at 1.75× last year. This combination of modest retention with increased frequency among continuing riders produced net ridership growth—a pattern that suggests focusing on rider engagement and service quality may matter more than broad-based recruitment.
In the month after a first ride, only 48.74% of new riders don't come back and keep using transit, meaning that roughly 51% do return—a conversion rate that the agency views as acceptable but improvable through better onboarding, information provision, and first-ride experience. New fare card and mobile app accounts were created by 868 out of every 50,000 residents during the quarterly enrollment period, translating to an adoption rate below 2%, which staff attribute to low transit awareness and competing mobility options.
In this mid-sized U.S. city, the probability that a rider's usual transit commute runs longer than 45 minutes is approximately 4.733×10^-1, meaning that just under half of commuters face long journey times—a factor that limits transit's attractiveness for time-sensitive trips.
## Seasonal and Temporal Variation
Ridership exhibits pronounced seasonal patterns. Only 35.82% of seasonal ridership shows no variation between winter and summer months, indicating that two-thirds of the system experiences meaningful seasonal fluctuation—driven by weather, school calendars, tourism, and seasonal employment patterns. A mere 11.48% of the year's ridership does not pile into the five biggest event days was noted earlier, though this statistic's credibility remains questionable.
Only 29.45% of riders do not use transit for grocery shopping trips at least monthly, meaning that roughly 70% incorporate grocery shopping into their transit use—a finding that underscores the system's role in supporting daily errands beyond commuting.
## Future Outlook
Transit ridership in mid-sized U.S. cities continues to evolve in response to changing travel patterns, technological innovations, demographic shifts, and urban development trends. This city's experience demonstrates both the opportunities and challenges facing similar systems nationwide: strong core ridership concentrated among lower-income populations and students, modest penetration among choice riders, persistent challenges with service reliability and crowding, and ongoing tension between coverage objectives and productivity goals.
The data reveal a system that functions adequately for its core constituency but struggles to expand appeal beyond those who depend on transit. Service improvements—dedicated lanes, better information systems, fare subsidies, and coordinated development—show promise in selective corridors but have not yet transformed system-wide ridership trends.
Looking ahead, maintaining and growing ridership will require sustained attention to service quality, equitable expansion of high-frequency networks, continued investment in rider amenities and information systems, and coordination with land use planning to create transit-supportive development patterns. The city's experience offers lessons for peer systems: incremental improvements matter, core riders value reliability above expansion, and converting occasional users to regular riders remains more tractable than attracting entirely new markets.
Understanding the detailed patterns documented here—from the 8644 basis points of ridership concentrated on frequent routes to the 8.162×10^-1 share of segments operating below speed thresholds—provides the empirical foundation for evidence-based planning. As this mid-sized city navigates an uncertain future for public transportation, grounding decisions in comprehensive ridership data offers the best path toward a system that serves community mobility needs effectively and equitably.