{"data":{"event":{"id":"cd7dbc7e-4181-40ff-a511-c849dbb4eeda","slug":"alphageometry-imo-plane-geometry","title":"AlphaGeometry solves olympiad plane-geometry problems without human proof data","short_summary":"DeepMind’s neuro-symbolic AlphaGeometry solved 25 of 30 IMO-AG-30 geometry problems in a Nature paper, approaching average human gold-medalist performance on that set.","full_description":"On 17 January 2024, Nature published AlphaGeometry, a language model trained on synthetic geometry theorems that guides a symbolic deduction engine. On 30 recent olympiad-level plane-geometry problems it solved 25, versus 10 for a prior automated baseline. Human-readable proofs were produced; former olympiad medalist Evan Chen reviewed examples. The system covers only Euclidean plane geometry, not a full IMO paper. This is a capability milestone on a historical contest set whose answers already existed. It is not newly created mathematical knowledge and does not count toward Net Good.","ledger_type":"capability","primary_domain_id":"23d935bb-b857-4b2b-9471-d568bb848a66","event_status":"verified","event_date":"2024-01-17T00:00:00.000Z","discovery_date":"2024-01-17T00:00:00.000Z","first_published_date":"2024-01-17T00:00:00.000Z","last_reviewed_date":"2026-10-28T00:00:00.000Z","geographic_scope":"Global mathematics and automated-reasoning research","affected_population":"Geometry and theorem-proving researchers","base_impact_tier":3,"base_score":"10.00","attribution_multiplier":"0.9000","evidence_multiplier":"0.7000","realization_multiplier":"0.5500","durability_multiplier":"0.8000","current_event_score":"2.772000","confidence_level":"high","score_explanation":"Peer-reviewed olympiad-geometry performance is a major automated-reasoning capability (tier 3). It stays on the Capability Ledger because the problems were already solved mathematics. High attribution. Evidence is Nature. Realization is demonstrated on a historical set.","methodology_version_id":"8745541b-0f8e-4d5a-9b47-5291d3813a8d","original_methodology_version_id":"d7881163-fb23-4e71-8625-bac1a8662c0f","published_at":"2024-01-17T00:00:00.000Z","created_at":"2026-09-13T20:47:20.075Z","updated_at":"2026-10-28T20:22:47.621Z","flags":[],"domain_name":"Mathematics","domain_slug":"mathematics","methodology_version":"0.2"},"contributions":[{"id":"f21324f3-fef0-4a75-940d-bc74d5e72211","event_id":"cd7dbc7e-4181-40ff-a511-c849dbb4eeda","model_id":"89820abd-cbf4-4fec-90c0-b0d10713e4f8","role_description":"Neuro-symbolic prover that proposed auxiliary constructions for a symbolic engine.","attribution_multiplier":"0.9000","credit_share":"1.0000","contribution_score":"2.772000","attribution_rationale":"The synthetic-data language model plus deduction engine is the published system.","attribution_confidence":"medium","first_used_date":"2024-01-17T00:00:00.000Z","model_version_if_known":null,"review_status":"approved","created_at":"2026-09-13T20:47:20.075Z","model_slug":"alphageometry","model_name":"AlphaGeometry","identity_class":"named_release","is_internal":false,"family_name":"AlphaGeometry","family_slug":"google-deepmind-alphageometry","organization_name":"Google DeepMind","organization_slug":"google-deepmind"}],"sources":[{"id":"cd6d9f35-f827-4cc5-8076-74073362ca9f","event_id":"cd7dbc7e-4181-40ff-a511-c849dbb4eeda","url":"https://www.nature.com/articles/s41586-023-06747-5","canonical_url":"https://www.nature.com/articles/s41586-023-06747-5","source_type":"peer_reviewed","publisher":"Nature","author":null,"publication_date":"2024-01-17T00:00:00.000Z","retrieved_at":"2026-09-13T20:47:20.075Z","title":"Solving olympiad geometry without human demonstrations","excerpt":null,"content_hash":null,"source_reliability_class":"high","is_primary_source":true,"is_independent":true,"is_peer_reviewed":true,"archived_url":null,"created_at":"2026-09-13T20:47:20.075Z"},{"id":"c8d77172-5b6f-40f0-928b-69b72970e293","event_id":"cd7dbc7e-4181-40ff-a511-c849dbb4eeda","url":"https://deepmind.google/discover/blog/alphageometry-an-olympiad-level-ai-system-for-geometry/","canonical_url":"https://deepmind.google/discover/blog/alphageometry-an-olympiad-level-ai-system-for-geometry/","source_type":"developer_announcement","publisher":"Google DeepMind","author":null,"publication_date":"2024-01-17T00:00:00.000Z","retrieved_at":"2026-09-13T20:47:20.075Z","title":"AlphaGeometry: An Olympiad-level AI system for geometry","excerpt":null,"content_hash":null,"source_reliability_class":"low","is_primary_source":true,"is_independent":false,"is_peer_reviewed":false,"archived_url":null,"created_at":"2026-09-13T20:47:20.075Z"}],"claims":[{"id":"3239afb9-c95f-422e-b5c1-fdf7662af31a","event_id":"cd7dbc7e-4181-40ff-a511-c849dbb4eeda","claim_text":"AlphaGeometry solved 25 of 30 problems in the IMO-AG-30 geometry set.","claim_type":"outcome","claim_status":"supported","confidence_score":null,"created_at":"2026-10-28T20:22:47.621Z","updated_at":"2026-10-28T20:22:47.621Z"},{"id":"5b9ef20b-6029-4769-b911-9dccc2a1a124","event_id":"cd7dbc7e-4181-40ff-a511-c849dbb4eeda","claim_text":"AlphaGeometry by itself earned an IMO gold medal in a live contest.","claim_type":"outcome","claim_status":"disputed","confidence_score":null,"created_at":"2026-10-28T20:22:47.621Z","updated_at":"2026-10-28T20:22:47.621Z"}],"revisions":[{"id":"cb734d02-e4d8-438b-b507-fd1829bb1c52","event_id":"cd7dbc7e-4181-40ff-a511-c849dbb4eeda","model_id":null,"previous_score":"0.000000","new_score":"2.772000","previous_factors":{},"new_factors":{"evidence":0.7,"base_score":10,"durability":0.8,"attribution":0.9,"realization":0.55},"change_reason":"Initial adjudicated seed score under methodology 0.1.","trigger_type":"seed","trigger_source_ids":null,"reviewer_id":null,"review_status":"published","created_at":"2026-09-13T20:47:20.075Z"},{"id":"04de6ba2-db9b-4dd3-bac4-0694de3953a2","event_id":"cd7dbc7e-4181-40ff-a511-c849dbb4eeda","model_id":null,"previous_score":"2.772000","new_score":"2.772000","previous_factors":{},"new_factors":{"flags":[],"evidence":0.7,"base_score":10,"durability":0.8,"attribution":0.9,"realization":0.55},"change_reason":"Methodology 0.2: olympiad benchmark moved to the Capability Ledger; not Net Good.","trigger_type":"editorial_import","trigger_source_ids":null,"reviewer_id":null,"review_status":"published","created_at":"2026-09-14T02:35:26.290Z"},{"id":"b860b883-dbc3-4674-8a67-479f82bb7949","event_id":"cd7dbc7e-4181-40ff-a511-c849dbb4eeda","model_id":null,"previous_score":"2.772000","new_score":"2.772000","previous_factors":{},"new_factors":{"flags":[],"evidence":0.7,"base_score":10,"durability":0.8,"attribution":0.9,"realization":0.55},"change_reason":"Methodology 0.2: olympiad benchmark moved to the Capability Ledger; not Net Good.","trigger_type":"editorial_import","trigger_source_ids":null,"reviewer_id":null,"review_status":"published","created_at":"2026-09-17T00:37:09.904Z"},{"id":"3376fc9d-a747-4cae-8673-784867b9846b","event_id":"cd7dbc7e-4181-40ff-a511-c849dbb4eeda","model_id":null,"previous_score":"2.772000","new_score":"2.772000","previous_factors":{},"new_factors":{"flags":[],"evidence":0.7,"base_score":10,"durability":0.8,"attribution":0.9,"realization":0.55},"change_reason":"Methodology 0.2: olympiad benchmark moved to the Capability Ledger; not Net Good.","trigger_type":"editorial_import","trigger_source_ids":null,"reviewer_id":null,"review_status":"published","created_at":"2026-09-18T19:11:40.608Z"},{"id":"2cde8a32-e9b9-4482-a683-821733a94b01","event_id":"cd7dbc7e-4181-40ff-a511-c849dbb4eeda","model_id":null,"previous_score":"2.772000","new_score":"2.772000","previous_factors":{},"new_factors":{"flags":[],"evidence":0.7,"base_score":10,"durability":0.8,"attribution":0.9,"realization":0.55},"change_reason":"Methodology 0.2: olympiad benchmark moved to the Capability Ledger; not Net Good.","trigger_type":"editorial_import","trigger_source_ids":null,"reviewer_id":null,"review_status":"published","created_at":"2026-09-19T00:53:33.692Z"},{"id":"9aef9699-caf1-49c4-8208-5cb6028a5901","event_id":"cd7dbc7e-4181-40ff-a511-c849dbb4eeda","model_id":null,"previous_score":"2.772000","new_score":"2.772000","previous_factors":{},"new_factors":{"flags":[],"evidence":0.7,"base_score":10,"durability":0.8,"attribution":0.9,"realization":0.55},"change_reason":"Methodology 0.2: olympiad benchmark moved to the Capability Ledger; not Net Good.","trigger_type":"editorial_import","trigger_source_ids":null,"reviewer_id":null,"review_status":"published","created_at":"2026-09-21T01:54:16.553Z"},{"id":"7502d234-ba55-4c50-957a-87d691efe548","event_id":"cd7dbc7e-4181-40ff-a511-c849dbb4eeda","model_id":null,"previous_score":"2.772000","new_score":"2.772000","previous_factors":{},"new_factors":{"flags":[],"evidence":0.7,"base_score":10,"durability":0.8,"attribution":0.9,"realization":0.55},"change_reason":"Methodology 0.2: olympiad benchmark moved to the Capability Ledger; not Net Good.","trigger_type":"editorial_import","trigger_source_ids":null,"reviewer_id":null,"review_status":"published","created_at":"2026-10-06T23:04:40.642Z"},{"id":"a337c55d-b025-44bb-bd37-32c328ba9749","event_id":"cd7dbc7e-4181-40ff-a511-c849dbb4eeda","model_id":null,"previous_score":"2.772000","new_score":"2.772000","previous_factors":{},"new_factors":{"flags":[],"evidence":0.7,"base_score":10,"durability":0.8,"attribution":0.9,"realization":0.55},"change_reason":"Methodology 0.2: olympiad benchmark moved to the Capability Ledger; not Net Good.","trigger_type":"editorial_import","trigger_source_ids":null,"reviewer_id":null,"review_status":"published","created_at":"2026-10-07T16:12:13.690Z"},{"id":"3628aaf4-7eac-469c-a8a2-0ca27bf97b3f","event_id":"cd7dbc7e-4181-40ff-a511-c849dbb4eeda","model_id":null,"previous_score":"2.772000","new_score":"2.772000","previous_factors":{},"new_factors":{"flags":[],"evidence":0.7,"base_score":10,"durability":0.8,"attribution":0.9,"realization":0.55},"change_reason":"Methodology 0.2: olympiad benchmark moved to the Capability Ledger; not Net Good.","trigger_type":"editorial_import","trigger_source_ids":null,"reviewer_id":null,"review_status":"published","created_at":"2026-10-11T00:50:27.558Z"},{"id":"5c4d1f25-9cd7-46b9-97c3-5b2d43b3af7d","event_id":"cd7dbc7e-4181-40ff-a511-c849dbb4eeda","model_id":null,"previous_score":"2.772000","new_score":"2.772000","previous_factors":{},"new_factors":{"flags":[],"evidence":0.7,"base_score":10,"durability":0.8,"attribution":0.9,"realization":0.55},"change_reason":"Methodology 0.2: olympiad benchmark moved to the Capability Ledger; not Net Good.","trigger_type":"editorial_import","trigger_source_ids":null,"reviewer_id":null,"review_status":"published","created_at":"2026-10-11T00:51:25.860Z"},{"id":"ac342e75-fb30-4804-ab72-c587a655dd5a","event_id":"cd7dbc7e-4181-40ff-a511-c849dbb4eeda","model_id":null,"previous_score":"2.772000","new_score":"2.772000","previous_factors":{},"new_factors":{"flags":[],"evidence":0.7,"base_score":10,"durability":0.8,"attribution":0.9,"realization":0.55},"change_reason":"Methodology 0.2: olympiad benchmark moved to the Capability Ledger; not Net Good.","trigger_type":"editorial_import","trigger_source_ids":null,"reviewer_id":null,"review_status":"published","created_at":"2026-10-21T19:26:46.597Z"},{"id":"590d19ec-7135-4d7c-876c-0230d7060890","event_id":"cd7dbc7e-4181-40ff-a511-c849dbb4eeda","model_id":null,"previous_score":"2.772000","new_score":"2.772000","previous_factors":{},"new_factors":{"flags":[],"evidence":0.7,"base_score":10,"durability":0.8,"attribution":0.9,"realization":0.55},"change_reason":"Methodology 0.2: olympiad benchmark moved to the Capability Ledger; not Net Good.","trigger_type":"editorial_import","trigger_source_ids":null,"reviewer_id":null,"review_status":"published","created_at":"2026-10-24T18:59:49.597Z"},{"id":"1dfd9458-8b76-4dae-9001-c64cd65da813","event_id":"cd7dbc7e-4181-40ff-a511-c849dbb4eeda","model_id":null,"previous_score":"2.772000","new_score":"2.772000","previous_factors":{},"new_factors":{"flags":[],"evidence":0.7,"base_score":10,"durability":0.8,"attribution":0.9,"realization":0.55},"change_reason":"Methodology 0.2: olympiad benchmark moved to the Capability Ledger; not Net Good.","trigger_type":"editorial_import","trigger_source_ids":null,"reviewer_id":null,"review_status":"published","created_at":"2026-10-27T20:16:14.720Z"},{"id":"00acd57d-4bfc-4795-afe7-bd23731ab59d","event_id":"cd7dbc7e-4181-40ff-a511-c849dbb4eeda","model_id":null,"previous_score":"2.772000","new_score":"2.772000","previous_factors":{},"new_factors":{"flags":[],"evidence":0.7,"base_score":10,"durability":0.8,"attribution":0.9,"realization":0.55},"change_reason":"Methodology 0.2: olympiad benchmark moved to the Capability Ledger; not Net Good.","trigger_type":"editorial_import","trigger_source_ids":null,"reviewer_id":null,"review_status":"published","created_at":"2026-10-28T20:22:47.621Z"}],"secondary":[{"name":"Computer Science","slug":"computer-science"}]},"methodology_version":"0.1"}