{ "schema_version": 1, "id": "ext_goal_slip_recovery", "question_id": "s10_goal_slips", "title": "What happens when a goal slips away?", "status": "ready", "as_of": "2026-09-11T16:28:17Z", "n": 250129, "input_export_id": "private-20260911-1107", "input_as_of": "2026-09-11T15:10:45Z", "live_json_as_of": "2026-09-07T04:44:53Z", "input_asset_sha256": "ffe901857c2603ac4305d9376a194eed171052d9835223c8ba5b19b59067a656", "input_manifest_sha256": "4aa3d330cb567ea02aa8c78d0f02015ac0fec35f3c8000215fbc8933ede398e2", "analysis_script_sha256": "46c3c611af86c4ed9d6fc12aa5517ce157fd127470359b89c7f3c1fac6a99600", "analysis_version": 2, "engine": "DuckDB 1.4.4", "corpus": { "n_records": 4207456, "n_cities": 34, "n_race_years": 240 }, "cohort": { "deduplicated": 4207456, "complete": 3591032, "increasing": 3373737, "timing_eligible": 3369060, "eligible": 3328159, "source_quality_excluded": 40901, "raw": 4207456, "duplicates_removed": 0, "missing_or_unparsed": 616424, "non_increasing": 217295, "outside_quality_bounds": 4677 }, "methodology_prose": [ "At 20 km keep elapsed time from 99% through 100% of the target\u2019s even-pace budget. Find the first 25, 30, 35 or 40 km checkpoint where elapsed time exceeds that budget. Divide eventual strict sub-target finishes by all such first-crossing observations.", "This uses inferred round-time benchmarks and elapsed chip times. It cannot establish when a runner mentally abandoned a goal. First-crossing groups differ, and results include only complete eligible finishes.", "Use complete, strictly increasing elapsed checkpoints at 5, 10, 15, 20, 25, 30, 35, 40 and 42.195 km. Clock strings must parse as H:MM:SS or M:SS. No missing splits are interpolated.", "Remove exact duplicate race records, ignoring database IDs, ingestion timestamps and source URLs. Retain finishes from 90 minutes to 12 hours with every section between 2 and 20 minutes per km. These quality filters can exclude genuine unusual performances; the analysis describes this eligible cohort, not every entrant.", "Full source records are available in public GitHub Releases. These chart tables require at least 100 eligible observations per cell for estimate reliability. Counts refer to finishes, linked pairs or event observations as specified in that answer.", "These are observational results. Fitness changes, intentions, training, selection into the dataset and unmeasured conditions can explain differences. Outcome percentiles describe variation among performances, not confidence intervals or advice about the best strategy.", "Apply the reviewed source-quality edition exclusions for this exact export after the timing checks. Known invalid split grids, incomplete ingestion, unreconciled HOLD editions and a selected top-finisher field do not contribute to the analyses or prior benchmarks. Report source exclusions separately; an already invalid timing row is not counted twice. Missing age or recorded gender alone does not exclude an otherwise eligible finish from the overall cohort. Other sparse editions are not declared incomplete merely from their size." ], "observational": true, "minimum_public_cell": 100, "source_quality": { "version": 1, "release_tag": "private-export-20260911-1107", "reviewed_edition_policy": true, "editions": [ { "city": "Honolulu", "year": 2016, "category": "invalid_split_grid", "reason": "Producer explicitly force-dropped this incomplete 5 km grid.", "raw_records": 20118, "deduplicated_records": 20118, "timing_eligible_excluded": 0 }, { "city": "Rotterdam", "year": 2012, "category": "invalid_split_grid", "reason": "Producer explicitly force-dropped this incomplete 5 km grid.", "raw_records": 7542, "deduplicated_records": 7542, "timing_eligible_excluded": 0 }, { "city": "Eindhoven", "year": 2009, "category": "invalid_split_grid", "reason": "Producer explicitly force-dropped this incomplete 5 km grid.", "raw_records": 1407, "deduplicated_records": 1407, "timing_eligible_excluded": 0 }, { "city": "Eindhoven", "year": 2010, "category": "invalid_split_grid", "reason": "Producer explicitly force-dropped this incomplete 5 km grid.", "raw_records": 1462, "deduplicated_records": 1462, "timing_eligible_excluded": 0 }, { "city": "Frankfurt", "year": 2019, "category": "invalid_split_grid", "reason": "Producer explicitly force-dropped this 5 km grid; numerically plausible rows are not reinstated.", "raw_records": 12513, "deduplicated_records": 12513, "timing_eligible_excluded": 10624 }, { "city": "New York", "year": 2008, "category": "incomplete_ingestion", "reason": "Release notes identify a partial live-ingestion snapshot of only 200 records.", "raw_records": 200, "deduplicated_records": 200, "timing_eligible_excluded": 198 }, { "city": "Chicago", "year": 2016, "category": "incomplete_ingestion", "reason": "Producer handoff identifies this 6,512-record edition as incomplete and on HOLD.", "raw_records": 6512, "deduplicated_records": 6512, "timing_eligible_excluded": 6506 }, { "city": "Tokyo", "year": 2026, "category": "selected_field", "reason": "Source notes identify top-500 PDFs, not a representative full marathon field.", "raw_records": 353, "deduplicated_records": 353, "timing_eligible_excluded": 353 }, { "city": "Amsterdam", "year": 2025, "category": "unreconciled_hold", "reason": "Source audit marks HOLD: 23,328 listed versus 23,325 retrieved. This conservative hold does not establish a large bias from the three missing records.", "raw_records": 23325, "deduplicated_records": 23325, "timing_eligible_excluded": 23220 }, { "city": "Valencia", "year": 2017, "category": "incomplete_ingestion", "reason": "Source audit marks HOLD: 3,373 listed detail pages missing; the observed records also lack 20 km.", "raw_records": 12485, "deduplicated_records": 12485, "timing_eligible_excluded": 0 } ], "policy_sha256": "c638b6c0abe3167a2d3d51aee485eae54fd6175761ef9d26d5914c9671eb15b0", "script_sha256": "cf1e6b359008087cf3bf9f241be13412af84358d9e808255f42bc2c292e243e6" }, "source_quality_script_sha256": "cf1e6b359008087cf3bf9f241be13412af84358d9e808255f42bc2c292e243e6", "observation_unit": "eligible finishes", "evidence_scope": "descriptive", "supporting_script_sha256": "7c6959b427fa1b06bb9600bb3377ecb226257d14aa0ec61a71a63f42bc87a3dd", "linkage_audit": { "feature_rows": 4207456, "safe_identity_groups": 2715330, "record_join_method": "canonical_record_id", "canonical_id_contract_verified": true, "candidate_link_rows": 3008457, "natural_key_candidate_rows": 0, "canonical_id_candidate_rows": 3008457, "ambiguous_cross_export_matches": 0, "linked_eligible_finishes": 3008457, "recent_benchmark_finishes": 524323, "consecutive_cross_year_pairs": 546847, "linked_with_supplied_date": 3006219 }, "narrative_script_sha256": "a9c6755fe727caa6c5a3994bd565e615067ec09c9c6f31e4e076622b810b5dcf" }