{"data":{"event":{"id":"a3044ea1-39d3-4f9f-b663-dd50cb5bf939","slug":"alphaproof-imo-2024-silver","title":"AlphaProof and AlphaGeometry 2 reach silver-medal standard on IMO 2024","short_summary":"DeepMind’s AlphaProof and AlphaGeometry 2 solved four of six IMO 2024 problems for 28 of 42 points, scored by Timothy Gowers and Joseph Myers, one point below that year’s gold cutoff.","full_description":"On 25 July 2024, DeepMind reported that AlphaProof (Lean reinforcement learning) solved IMO 2024 problems 1, 2, and 6, and AlphaGeometry 2 solved problem 4. Combinatorics problems 3 and 5 were unsolved. Formalization of statements into Lean was done by humans; computation ran over days, not contest time. A 2025 Nature paper later described AlphaProof. The medal analogy is unofficial: the systems were not contestants. This is a capability milestone on a contest paper, not a contribution of new theorems, and does not count toward Net Good.","ledger_type":"capability","primary_domain_id":"23d935bb-b857-4b2b-9471-d568bb848a66","event_status":"verified","event_date":"2024-07-25T00:00:00.000Z","discovery_date":"2024-07-25T00:00:00.000Z","first_published_date":"2024-07-25T00:00:00.000Z","last_reviewed_date":"2026-10-28T00:00:00.000Z","geographic_scope":"International (IMO 2024, Bath, UK problems)","affected_population":"Formal-mathematics and automated-reasoning researchers","base_impact_tier":3,"base_score":"10.00","attribution_multiplier":"0.9000","evidence_multiplier":"0.5500","realization_multiplier":"0.5000","durability_multiplier":"0.8000","current_event_score":"1.980000","confidence_level":"high","score_explanation":"First widely documented medal-level IMO performance by AI is a major capability milestone (tier 3). It is not Net Good: the problems were contest exercises, not open research. High attribution. Evidence between technical disclosure and later peer review of AlphaProof (0.55).","methodology_version_id":"8745541b-0f8e-4d5a-9b47-5291d3813a8d","original_methodology_version_id":"d7881163-fb23-4e71-8625-bac1a8662c0f","published_at":"2024-07-25T00:00:00.000Z","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":"5061f7a0-cc25-449d-9e36-3fe88e70b802","event_id":"a3044ea1-39d3-4f9f-b663-dd50cb5bf939","model_id":"68b40d82-d353-4a9d-b6d9-33a6f91311c2","role_description":"Found Lean proofs for three non-geometry IMO 2024 problems, including P6.","attribution_multiplier":"0.9000","credit_share":"0.7000","contribution_score":"1.386000","attribution_rationale":"Solved three of the four solved problems, including the hardest.","attribution_confidence":"medium","first_used_date":"2024-07-25T00:00:00.000Z","model_version_if_known":null,"review_status":"approved","created_at":"2026-09-13T20:47:20.075Z","model_slug":"alphaproof","model_name":"AlphaProof","identity_class":"named_release","is_internal":false,"family_name":"AlphaProof","family_slug":"google-deepmind-alphaproof","organization_name":"Google DeepMind","organization_slug":"google-deepmind"},{"id":"506af4bd-3252-4c3c-9432-0074e6edcf67","event_id":"a3044ea1-39d3-4f9f-b663-dd50cb5bf939","model_id":"5b3887d0-258e-4503-84ca-5e609f968061","role_description":"Proved the IMO 2024 geometry problem.","attribution_multiplier":"0.9000","credit_share":"0.3000","contribution_score":"0.594000","attribution_rationale":"Solved the single geometry problem in the four-problem total.","attribution_confidence":"medium","first_used_date":"2024-07-25T00:00:00.000Z","model_version_if_known":null,"review_status":"approved","created_at":"2026-09-13T20:47:20.075Z","model_slug":"alphageometry-2","model_name":"AlphaGeometry 2","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":"7c4a0c25-f40e-4a32-9502-758e287df188","event_id":"a3044ea1-39d3-4f9f-b663-dd50cb5bf939","url":"https://deepmind.google/discover/blog/ai-solves-imo-problems-at-silver-medal-level/","canonical_url":"https://deepmind.google/discover/blog/ai-solves-imo-problems-at-silver-medal-level/","source_type":"developer_announcement","publisher":"Google DeepMind","author":null,"publication_date":"2024-07-25T00:00:00.000Z","retrieved_at":"2026-09-13T20:47:20.075Z","title":"AI achieves silver-medal standard solving International Mathematical Olympiad problems","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"},{"id":"cc83ed3f-121d-46f2-8210-59fafed4da12","event_id":"a3044ea1-39d3-4f9f-b663-dd50cb5bf939","url":"https://www.nature.com/articles/s41586-025-09833-y","canonical_url":"https://www.nature.com/articles/s41586-025-09833-y","source_type":"peer_reviewed","publisher":"Nature","author":null,"publication_date":"2025-11-12T00:00:00.000Z","retrieved_at":"2026-09-13T20:47:20.075Z","title":"Olympiad-level formal mathematical reasoning with reinforcement learning","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":"bce2a088-a5db-4890-a0dc-46878cf7ade1","event_id":"a3044ea1-39d3-4f9f-b663-dd50cb5bf939","url":"https://danluu.com/brain-off/","canonical_url":"https://danluu.com/brain-off/","source_type":"journalism","publisher":"Hacker News","author":null,"publication_date":"2026-09-18T00:00:00.000Z","retrieved_at":"2026-09-18T18:01:04.405Z","title":"There's no point at which turning your brain off will work","excerpt":"Article URL: https://danluu.com/brain-off/\nComments URL: https://news.ycombinator.com/item?id=49757178\nPoints: 106\n# Comments: 63","content_hash":null,"source_reliability_class":"medium","is_primary_source":false,"is_independent":true,"is_peer_reviewed":false,"archived_url":null,"created_at":"2026-09-18T18:01:04.405Z"}],"claims":[{"id":"3a6e3c98-51c7-47ac-8746-cc6b8476490d","event_id":"a3044ea1-39d3-4f9f-b663-dd50cb5bf939","claim_text":"The combined systems solved four of six IMO 2024 problems for 28 points as scored by Gowers and Myers.","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":"97004478-7907-48d7-9b4f-30d8a00179e8","event_id":"a3044ea1-39d3-4f9f-b663-dd50cb5bf939","claim_text":"The systems competed as official IMO contestants under contest time limits.","claim_type":"attribution","claim_status":"disputed","confidence_score":null,"created_at":"2026-10-28T20:22:47.621Z","updated_at":"2026-10-28T20:22:47.621Z"}],"revisions":[{"id":"b4631cf6-c5d6-4cce-85de-2b6515e71e33","event_id":"a3044ea1-39d3-4f9f-b663-dd50cb5bf939","model_id":null,"previous_score":"0.000000","new_score":"1.980000","previous_factors":{},"new_factors":{"evidence":0.55,"base_score":10,"durability":0.8,"attribution":0.9,"realization":0.5},"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":"242a4bbe-d501-4f76-985e-6603b46d4a8b","event_id":"a3044ea1-39d3-4f9f-b663-dd50cb5bf939","model_id":null,"previous_score":"1.980000","new_score":"1.980000","previous_factors":{},"new_factors":{"flags":[],"evidence":0.55,"base_score":10,"durability":0.8,"attribution":0.9,"realization":0.5},"change_reason":"Methodology 0.2: contest-paper performance 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":"5e49c1f1-d884-4e68-9741-8ff522fec42a","event_id":"a3044ea1-39d3-4f9f-b663-dd50cb5bf939","model_id":null,"previous_score":"1.980000","new_score":"1.980000","previous_factors":{},"new_factors":{"flags":[],"evidence":0.55,"base_score":10,"durability":0.8,"attribution":0.9,"realization":0.5},"change_reason":"Methodology 0.2: contest-paper performance 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":"d9f4987e-6e02-4578-9d01-cd49c5ac6b1f","event_id":"a3044ea1-39d3-4f9f-b663-dd50cb5bf939","model_id":null,"previous_score":"1.980000","new_score":"1.980000","previous_factors":{"tier":3,"evidence":0.55,"base_score":10,"durability":0.8,"attribution":0.9,"realization":0.5},"new_factors":{"tier":3,"models":["68b40d82-d353-4a9d-b6d9-33a6f91311c2","5b3887d0-258e-4503-84ca-5e609f968061"],"evidence":0.55,"base_score":10,"durability":0.8,"attribution":0.9,"realization":0.5},"change_reason":"Ingest update: added a follow-up source.","trigger_type":"ingest_update","trigger_source_ids":["bce2a088-a5db-4890-a0dc-46878cf7ade1"],"reviewer_id":null,"review_status":"published","created_at":"2026-09-18T18:01:04.433Z"},{"id":"a75dc511-05da-49b5-9660-fcf2ada393b7","event_id":"a3044ea1-39d3-4f9f-b663-dd50cb5bf939","model_id":null,"previous_score":"1.980000","new_score":"1.980000","previous_factors":{},"new_factors":{"flags":[],"evidence":0.55,"base_score":10,"durability":0.8,"attribution":0.9,"realization":0.5},"change_reason":"Methodology 0.2: contest-paper performance 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":"e4e26873-a94f-43cb-9f22-cefcc7137933","event_id":"a3044ea1-39d3-4f9f-b663-dd50cb5bf939","model_id":null,"previous_score":"1.980000","new_score":"1.980000","previous_factors":{},"new_factors":{"flags":[],"evidence":0.55,"base_score":10,"durability":0.8,"attribution":0.9,"realization":0.5},"change_reason":"Methodology 0.2: contest-paper performance 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":"10b5681e-4108-41ad-b63d-b43719956202","event_id":"a3044ea1-39d3-4f9f-b663-dd50cb5bf939","model_id":null,"previous_score":"1.980000","new_score":"1.980000","previous_factors":{},"new_factors":{"flags":[],"evidence":0.55,"base_score":10,"durability":0.8,"attribution":0.9,"realization":0.5},"change_reason":"Methodology 0.2: contest-paper performance 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":"7c670e79-4093-4654-a97c-ae17cd14627e","event_id":"a3044ea1-39d3-4f9f-b663-dd50cb5bf939","model_id":null,"previous_score":"1.980000","new_score":"1.980000","previous_factors":{},"new_factors":{"flags":[],"evidence":0.55,"base_score":10,"durability":0.8,"attribution":0.9,"realization":0.5},"change_reason":"Methodology 0.2: contest-paper performance 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":"c3e52c6a-2de4-4c1a-a5a7-20a43c62277c","event_id":"a3044ea1-39d3-4f9f-b663-dd50cb5bf939","model_id":null,"previous_score":"1.980000","new_score":"1.980000","previous_factors":{},"new_factors":{"flags":[],"evidence":0.55,"base_score":10,"durability":0.8,"attribution":0.9,"realization":0.5},"change_reason":"Methodology 0.2: contest-paper performance 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":"12022279-8fa7-4aa6-91d2-a13decc7937a","event_id":"a3044ea1-39d3-4f9f-b663-dd50cb5bf939","model_id":null,"previous_score":"1.980000","new_score":"1.980000","previous_factors":{},"new_factors":{"flags":[],"evidence":0.55,"base_score":10,"durability":0.8,"attribution":0.9,"realization":0.5},"change_reason":"Methodology 0.2: contest-paper performance 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":"baf84035-a5c3-49ef-ae87-0d763f8bd2df","event_id":"a3044ea1-39d3-4f9f-b663-dd50cb5bf939","model_id":null,"previous_score":"1.980000","new_score":"1.980000","previous_factors":{},"new_factors":{"flags":[],"evidence":0.55,"base_score":10,"durability":0.8,"attribution":0.9,"realization":0.5},"change_reason":"Methodology 0.2: contest-paper performance 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":"17d7acee-c5dd-4174-8aae-d99351082807","event_id":"a3044ea1-39d3-4f9f-b663-dd50cb5bf939","model_id":null,"previous_score":"1.980000","new_score":"1.980000","previous_factors":{},"new_factors":{"flags":[],"evidence":0.55,"base_score":10,"durability":0.8,"attribution":0.9,"realization":0.5},"change_reason":"Methodology 0.2: contest-paper performance 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":"aaa0ab37-2264-4e3f-8f01-6a3be778325a","event_id":"a3044ea1-39d3-4f9f-b663-dd50cb5bf939","model_id":null,"previous_score":"1.980000","new_score":"1.980000","previous_factors":{},"new_factors":{"flags":[],"evidence":0.55,"base_score":10,"durability":0.8,"attribution":0.9,"realization":0.5},"change_reason":"Methodology 0.2: contest-paper performance 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":"9c9988c4-bc1f-4063-8d13-7acf535caf51","event_id":"a3044ea1-39d3-4f9f-b663-dd50cb5bf939","model_id":null,"previous_score":"1.980000","new_score":"1.980000","previous_factors":{},"new_factors":{"flags":[],"evidence":0.55,"base_score":10,"durability":0.8,"attribution":0.9,"realization":0.5},"change_reason":"Methodology 0.2: contest-paper performance 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":"d696bac5-8a81-4972-9e6b-40461ad53760","event_id":"a3044ea1-39d3-4f9f-b663-dd50cb5bf939","model_id":null,"previous_score":"1.980000","new_score":"1.980000","previous_factors":{},"new_factors":{"flags":[],"evidence":0.55,"base_score":10,"durability":0.8,"attribution":0.9,"realization":0.5},"change_reason":"Methodology 0.2: contest-paper performance 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"}