{
  "name": "TripSapien public data",
  "version": "2026-07-13",
  "license": "CC BY 4.0",
  "canonical_dataset_page": "https://www.tripsapien.com/research/ai-itinerary-validation",
  "repository": "https://github.com/forrestmill-cmd/tripsapien-public-data",
  "brand": {
    "current_name": "TripSapien",
    "former_names": [
      "Tripnostic",
      "ValidaTrip",
      "TripPaste"
    ]
  },
  "files": [
    {
      "path": "data/ai-itinerary-validation-samples.jsonl",
      "records": 54,
      "sha256": "58c7b0598b86b105102afbb3ede8ded17048b026d5742c29e6781751df8c759e"
    },
    {
      "path": "data/ai-itinerary-validation-samples.csv",
      "records": 54,
      "sha256": "12ad8b4c54268c3ab84c759c6e3ebcaf30b72d3e8b160695240b8abed00a8caf"
    },
    {
      "path": "data/schema.json",
      "sha256": "79ed6d8893d5477f0d2c3cf307db68ab5bf36feb0c2558f8661f9b43aa970fc0"
    },
    {
      "path": "data/tripsapien-city-hubs.jsonl",
      "records": 155,
      "sha256": "c3041e88e7a2b7e0436d417d7a95b557b63d3859b3518903129eb020d7bf2143"
    },
    {
      "path": "data/tripsapien-city-hubs.csv",
      "records": 155,
      "sha256": "34650e2e583f1008eb143b3bf335163dd0bbf4679e4f8eeb3e8b308c3ef7b37e"
    },
    {
      "path": "data/indexed-event-months.json",
      "sha256": "cc0f654f60a62efe37ca289fb782e3050a33c32a89a86352535c0248da6bfb8f"
    },
    {
      "path": "comparisons/itinerary-validator-feature-matrix.csv",
      "sha256": "e90de3974291a26d6c1cf5fbf8fd8e5e2b6b04dacd0e9c87ac736da6cd9ba60c"
    },
    {
      "path": "prompts/ai-itinerary-prompts.md",
      "sha256": "6bdc236d3297e71dc322c2194f8d8ae05ca32c41216dca1d69e3be0a2413fc98"
    },
    {
      "path": "llms-full.txt",
      "sha256": "c2df467ca9341e458c3115d806298d0d70fdd234092aa94ce21c57b1f7b809f0"
    }
  ],
  "ai_itinerary_samples": {
    "records": 54,
    "cities": 9,
    "case_shapes": 6,
    "records_per_city_shape": 1,
    "simulated_source_labels": {
      "ChatGPT": 18,
      "Claude": 18,
      "Microsoft Copilot": 18
    },
    "author_expected_totals": {
      "places_or_notes": 960,
      "opening_hours_checks": 153,
      "booking_ahead_flags": 471,
      "dedupe_candidates": 19,
      "vague_place_flags": 67,
      "day_trip_flags": 61,
      "map_urls": 14
    }
  },
  "limitations": [
    "Rows are hand-curated demonstrations, not a random or representative sample.",
    "Expected totals are sums of author-specified case characteristics, not observed model or product results.",
    "The data supports no assistant ranking, accuracy estimate, precision or recall claim, or traveler-outcome claim.",
    "The data contains no TripSapien user data and does not establish current venue status without a live check."
  ]
}