{"data":{"slug":"hindsight-calibration","term":"Hindsight Calibration","bucket":"buildability","definition":"The retrospective check that compares issued Buildability Receipts to the build outcomes that actually happened.","short_definition":"The retrospective check that compares issued Buildability Receipts to the build outcomes that actually happened.","long_definition":"Hindsight Calibration replays Buildability Receipts against the build outcomes we observed afterwards (or that the community reported back). It produces a hindsight Brier outcome on a public ledger with three lifecycle states: seed_only, outcomes_observed, retrained_published. The ledger is how a reader sees whether the current model generation is well-calibrated.","related_terms":["buildability-wave","hindsight-public-ledger","brier-score"],"related_term_routes":[{"slug":"buildability-wave","term":"Buildability Wave","route":"/resources/glossary/buildability-wave"},{"slug":"hindsight-public-ledger","term":"Hindsight Public Ledger","route":"/resources/glossary/hindsight-public-ledger"},{"slug":"brier-score","term":"Brier Score","route":"/resources/glossary/brier-score"}],"canonical_route":"/resources/glossary/hindsight-calibration","api_route":"/api/v1/resources/glossary/hindsight-calibration","jsonld_id":"https://sciencetostartup.com/resources/glossary/hindsight-calibration","variants":[],"tldr":"The retrospective check that compares issued Buildability Receipts to the build outcomes that actually happened.","key_points":[],"quality_tier":null,"citation_count":null,"source_state":"curated_static","source_module":"apps/web/data/glossary/terms.ts","definition_sections":{"schema_version":1,"intro":"Hindsight Calibration replays Buildability Receipts against the build outcomes we observed afterwards (or that the community reported back). It produces a hindsight Brier outcome on a public ledger with three lifecycle states: seed_only, outcomes_observed, retrained_published. The ledger is how a reader sees whether the current model generation is well-calibrated.","sections":[{"title":"Definition","items":[{"subtitle":"Hindsight Calibration","text":"Hindsight Calibration replays Buildability Receipts against the build outcomes we observed afterwards (or that the community reported back). It produces a hindsight Brier outcome on a public ledger with three lifecycle states: seed_only, outcomes_observed, retrained_published. The ledger is how a reader sees whether the current model generation is well-calibrated."}]},{"title":"Related vocabulary","items":[{"subtitle":"Buildability Wave","text":"Progressive buildability assessment phases, wave_0 through wave_7. Each wave adds evidence requirements and external gates."},{"subtitle":"Hindsight Public Ledger","text":"Public record of Buildability predictions vs. real-world outcomes. Three states: seed_only, outcomes_observed, retrained_published."},{"subtitle":"Brier Score","text":"A proper scoring rule for probabilistic predictions. Lower is better. Public Brier receipt is a pending gate for Wave 7."}]}],"cited_arxiv_ids":[]}},"meta":{"canonical_route":"/resources/glossary/hindsight-calibration","api_route":"/api/v1/resources/glossary/hindsight-calibration","source":{"label":"curated glossary catalog","source_state":"curated_static","source_module":"apps/web/data/glossary/terms.ts","method_version":"public_glossary_curated_terms_v2","freshness":{"status":"versioned","observed_at":null,"fresh_until":null,"reason":"Git-versioned curated catalog; daily ingestion freshness windows do not apply.","reason_code":"git_versioned_curated_catalog"},"source_count":111,"bucket_count":7,"buckets":["scoring","surfaces","agents","distribution","data","foresight","buildability"]}}}