{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:4JZOVUM5DEXOJPFR6BJCVXPLGK","short_pith_number":"pith:4JZOVUM5","canonical_record":{"source":{"id":"2109.00110","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2021-08-31T23:21:12Z","cross_cats_sorted":["cs.FL","cs.LG"],"title_canon_sha256":"cc0244c5959f2c66a5c6d38b722450654424231e35e121c472593706bd580a10","abstract_canon_sha256":"1135ccff970ede9810711c2e659e388f6309e7db620a343c59e92ac01865a508"},"schema_version":"1.0"},"canonical_sha256":"e272ead19d192ee4bcb1f0522addeb3293e4427ec8adb44786f12e3d3251cd23","source":{"kind":"arxiv","id":"2109.00110","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2109.00110","created_at":"2026-05-17T23:38:46Z"},{"alias_kind":"arxiv_version","alias_value":"2109.00110v2","created_at":"2026-05-17T23:38:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.00110","created_at":"2026-05-17T23:38:46Z"},{"alias_kind":"pith_short_12","alias_value":"4JZOVUM5DEXO","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_16","alias_value":"4JZOVUM5DEXOJPFR","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_8","alias_value":"4JZOVUM5","created_at":"2026-05-18T12:33:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:4JZOVUM5DEXOJPFR6BJCVXPLGK","target":"record","payload":{"canonical_record":{"source":{"id":"2109.00110","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2021-08-31T23:21:12Z","cross_cats_sorted":["cs.FL","cs.LG"],"title_canon_sha256":"cc0244c5959f2c66a5c6d38b722450654424231e35e121c472593706bd580a10","abstract_canon_sha256":"1135ccff970ede9810711c2e659e388f6309e7db620a343c59e92ac01865a508"},"schema_version":"1.0"},"canonical_sha256":"e272ead19d192ee4bcb1f0522addeb3293e4427ec8adb44786f12e3d3251cd23","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:38:46.754758Z","signature_b64":"wAW6p6JnFXDT/VKFV75Rs9tCX8n1oVD3I/VhZ+0ayAdEP5IJmN+SygaIpPiJf8wHP28dZ6dSy4gTIPV/6o3dDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e272ead19d192ee4bcb1f0522addeb3293e4427ec8adb44786f12e3d3251cd23","last_reissued_at":"2026-05-17T23:38:46.754275Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:38:46.754275Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2109.00110","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:38:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mggzUJJy8SYENinwtJGKFrDfl4gtWtAK1wQZMwlf3znEzUd5LtEjBGYhBMnCfzeun7H6LwZmv438SnPnm/8/Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T01:19:04.816430Z"},"content_sha256":"6eadab973307a999c34c4a990e47f71624345c1a21493d166920948db79b3b07","schema_version":"1.0","event_id":"sha256:6eadab973307a999c34c4a990e47f71624345c1a21493d166920948db79b3b07"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:4JZOVUM5DEXOJPFR6BJCVXPLGK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MiniF2F: a cross-system benchmark for formal Olympiad-level mathematics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"MiniF2F supplies 488 formal statements from math contests as a shared benchmark for neural theorem provers across systems.","cross_cats":["cs.FL","cs.LG"],"primary_cat":"cs.AI","authors_text":"Jesse Michael Han, Kunhao Zheng, Stanislas Polu","submitted_at":"2021-08-31T23:21:12Z","abstract_excerpt":"We present miniF2F, a dataset of formal Olympiad-level mathematics problems statements intended to provide a unified cross-system benchmark for neural theorem proving. The miniF2F benchmark currently targets Metamath, Lean, Isabelle (partially) and HOL Light (partially) and consists of 488 problem statements drawn from the AIME, AMC, and the International Mathematical Olympiad (IMO), as well as material from high-school and undergraduate mathematics courses. We report baseline results using GPT-f, a neural theorem prover based on GPT-3 and provide an analysis of its performance. We intend for "},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"We present miniF2F, a dataset of formal Olympiad-level mathematics problems statements intended to provide a unified cross-system benchmark for neural theorem proving.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the chosen contest problems can be accurately translated into correct formal statements in each target system and that these statements form a representative and stable measure of progress for neural theorem provers.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"MiniF2F is a new cross-system benchmark containing 488 Olympiad-level mathematics problems formalized in Metamath, Lean, Isabelle, and HOL Light, together with baseline results from a GPT-3-based prover.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"MiniF2F supplies 488 formal statements from math contests as a shared benchmark for neural theorem provers across systems.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"c87da5ba191ff44df33fb435f95a5f9ddd18aca31db22e3705fa52217b583363"},"source":{"id":"2109.00110","kind":"arxiv","version":2},"verdict":{"id":"8575ac97-35f6-45e5-b41d-e6e18ca0cfbd","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-16T19:59:49.058006Z","strongest_claim":"We present miniF2F, a dataset of formal Olympiad-level mathematics problems statements intended to provide a unified cross-system benchmark for neural theorem proving.","one_line_summary":"MiniF2F is a new cross-system benchmark containing 488 Olympiad-level mathematics problems formalized in Metamath, Lean, Isabelle, and HOL Light, together with baseline results from a GPT-3-based prover.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the chosen contest problems can be accurately translated into correct formal statements in each target system and that these statements form a representative and stable measure of progress for neural theorem provers.","pith_extraction_headline":"MiniF2F supplies 488 formal statements from math contests as a shared benchmark for neural theorem provers across systems."},"references":{"count":18,"sample":[{"doi":"","year":1905,"title":"Holist: An envi- ronment for machine learning of higher order logic theorem proving","work_id":"f5bfea42-9a09-44a0-a9c5-6f1c4ac3ae2a","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2020,"title":"Kevin Buzzard, Johan Commelin, and Patrick Massot","work_id":"39b021ec-2550-4d2e-a7b8-256e275589a2","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2009,"title":"Imagenet: A large-scale hi- erarchical image database","work_id":"07e79ded-6939-4deb-a631-4cb7a12164b4","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Proof artifact co-training for theorem proving with language models.arXiv preprint arXiv:2102.06203","work_id":"86d8222e-af2a-450c-b058-95a4de0be853","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Measuring Mathematical Problem Solving With the MATH Dataset","work_id":"50652ac6-fb7c-4675-a2c2-159c241feb17","ref_index":5,"cited_arxiv_id":"2103.03874","is_internal_anchor":true}],"resolved_work":18,"snapshot_sha256":"736bfea96116f93232f41e4dadd248a1c8872bf77d05991e093fc5fcac70debb","internal_anchors":2},"formal_canon":{"evidence_count":1,"snapshot_sha256":"fad9ba61dfc0242697864df25c2ee1455fe66f1053de48c0d9a43ed60422dfcc"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"8575ac97-35f6-45e5-b41d-e6e18ca0cfbd"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:38:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YrVwoKFVT8oChLzVFpWeVa81MbOTMBw8WUQMGrQSXMwpoqmGQ+3fwjYy7tV+W9RomqTFXev5byh4F5TjDUQ7CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T01:19:04.817004Z"},"content_sha256":"bf2e7b23d7a8856728a1e305679697c081fd66715ce005f5e9f01806f4364bbd","schema_version":"1.0","event_id":"sha256:bf2e7b23d7a8856728a1e305679697c081fd66715ce005f5e9f01806f4364bbd"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4JZOVUM5DEXOJPFR6BJCVXPLGK/bundle.json","state_url":"https://pith.science/pith/4JZOVUM5DEXOJPFR6BJCVXPLGK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4JZOVUM5DEXOJPFR6BJCVXPLGK/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-28T01:19:04Z","links":{"resolver":"https://pith.science/pith/4JZOVUM5DEXOJPFR6BJCVXPLGK","bundle":"https://pith.science/pith/4JZOVUM5DEXOJPFR6BJCVXPLGK/bundle.json","state":"https://pith.science/pith/4JZOVUM5DEXOJPFR6BJCVXPLGK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4JZOVUM5DEXOJPFR6BJCVXPLGK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:4JZOVUM5DEXOJPFR6BJCVXPLGK","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"1135ccff970ede9810711c2e659e388f6309e7db620a343c59e92ac01865a508","cross_cats_sorted":["cs.FL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2021-08-31T23:21:12Z","title_canon_sha256":"cc0244c5959f2c66a5c6d38b722450654424231e35e121c472593706bd580a10"},"schema_version":"1.0","source":{"id":"2109.00110","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2109.00110","created_at":"2026-05-17T23:38:46Z"},{"alias_kind":"arxiv_version","alias_value":"2109.00110v2","created_at":"2026-05-17T23:38:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.00110","created_at":"2026-05-17T23:38:46Z"},{"alias_kind":"pith_short_12","alias_value":"4JZOVUM5DEXO","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_16","alias_value":"4JZOVUM5DEXOJPFR","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_8","alias_value":"4JZOVUM5","created_at":"2026-05-18T12:33:33Z"}],"graph_snapshots":[{"event_id":"sha256:bf2e7b23d7a8856728a1e305679697c081fd66715ce005f5e9f01806f4364bbd","target":"graph","created_at":"2026-05-17T23:38:46Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"We present miniF2F, a dataset of formal Olympiad-level mathematics problems statements intended to provide a unified cross-system benchmark for neural theorem proving."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That the chosen contest problems can be accurately translated into correct formal statements in each target system and that these statements form a representative and stable measure of progress for neural theorem provers."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"MiniF2F is a new cross-system benchmark containing 488 Olympiad-level mathematics problems formalized in Metamath, Lean, Isabelle, and HOL Light, together with baseline results from a GPT-3-based prover."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"MiniF2F supplies 488 formal statements from math contests as a shared benchmark for neural theorem provers across systems."}],"snapshot_sha256":"c87da5ba191ff44df33fb435f95a5f9ddd18aca31db22e3705fa52217b583363"},"formal_canon":{"evidence_count":1,"snapshot_sha256":"fad9ba61dfc0242697864df25c2ee1455fe66f1053de48c0d9a43ed60422dfcc"},"paper":{"abstract_excerpt":"We present miniF2F, a dataset of formal Olympiad-level mathematics problems statements intended to provide a unified cross-system benchmark for neural theorem proving. The miniF2F benchmark currently targets Metamath, Lean, Isabelle (partially) and HOL Light (partially) and consists of 488 problem statements drawn from the AIME, AMC, and the International Mathematical Olympiad (IMO), as well as material from high-school and undergraduate mathematics courses. We report baseline results using GPT-f, a neural theorem prover based on GPT-3 and provide an analysis of its performance. We intend for ","authors_text":"Jesse Michael Han, Kunhao Zheng, Stanislas Polu","cross_cats":["cs.FL","cs.LG"],"headline":"MiniF2F supplies 488 formal statements from math contests as a shared benchmark for neural theorem provers across systems.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2021-08-31T23:21:12Z","title":"MiniF2F: a cross-system benchmark for formal Olympiad-level mathematics"},"references":{"count":18,"internal_anchors":2,"resolved_work":18,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Holist: An envi- ronment for machine learning of higher order logic theorem proving","work_id":"f5bfea42-9a09-44a0-a9c5-6f1c4ac3ae2a","year":1905},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Kevin Buzzard, Johan Commelin, and Patrick Massot","work_id":"39b021ec-2550-4d2e-a7b8-256e275589a2","year":2020},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Imagenet: A large-scale hi- erarchical image database","work_id":"07e79ded-6939-4deb-a631-4cb7a12164b4","year":2009},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Proof artifact co-training for theorem proving with language models.arXiv preprint arXiv:2102.06203","work_id":"86d8222e-af2a-450c-b058-95a4de0be853","year":null},{"cited_arxiv_id":"2103.03874","doi":"","is_internal_anchor":true,"ref_index":5,"title":"Measuring Mathematical Problem Solving With the MATH Dataset","work_id":"50652ac6-fb7c-4675-a2c2-159c241feb17","year":null}],"snapshot_sha256":"736bfea96116f93232f41e4dadd248a1c8872bf77d05991e093fc5fcac70debb"},"source":{"id":"2109.00110","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-16T19:59:49.058006Z","id":"8575ac97-35f6-45e5-b41d-e6e18ca0cfbd","model_set":{"reader":"grok-4.3"},"one_line_summary":"MiniF2F is a new cross-system benchmark containing 488 Olympiad-level mathematics problems formalized in Metamath, Lean, Isabelle, and HOL Light, together with baseline results from a GPT-3-based prover.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"MiniF2F supplies 488 formal statements from math contests as a shared benchmark for neural theorem provers across systems.","strongest_claim":"We present miniF2F, a dataset of formal Olympiad-level mathematics problems statements intended to provide a unified cross-system benchmark for neural theorem proving.","weakest_assumption":"That the chosen contest problems can be accurately translated into correct formal statements in each target system and that these statements form a representative and stable measure of progress for neural theorem provers."}},"verdict_id":"8575ac97-35f6-45e5-b41d-e6e18ca0cfbd"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:6eadab973307a999c34c4a990e47f71624345c1a21493d166920948db79b3b07","target":"record","created_at":"2026-05-17T23:38:46Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"1135ccff970ede9810711c2e659e388f6309e7db620a343c59e92ac01865a508","cross_cats_sorted":["cs.FL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2021-08-31T23:21:12Z","title_canon_sha256":"cc0244c5959f2c66a5c6d38b722450654424231e35e121c472593706bd580a10"},"schema_version":"1.0","source":{"id":"2109.00110","kind":"arxiv","version":2}},"canonical_sha256":"e272ead19d192ee4bcb1f0522addeb3293e4427ec8adb44786f12e3d3251cd23","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e272ead19d192ee4bcb1f0522addeb3293e4427ec8adb44786f12e3d3251cd23","first_computed_at":"2026-05-17T23:38:46.754275Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:38:46.754275Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wAW6p6JnFXDT/VKFV75Rs9tCX8n1oVD3I/VhZ+0ayAdEP5IJmN+SygaIpPiJf8wHP28dZ6dSy4gTIPV/6o3dDg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:38:46.754758Z","signed_message":"canonical_sha256_bytes"},"source_id":"2109.00110","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6eadab973307a999c34c4a990e47f71624345c1a21493d166920948db79b3b07","sha256:bf2e7b23d7a8856728a1e305679697c081fd66715ce005f5e9f01806f4364bbd"],"state_sha256":"ea9c3d3140e17453f19df0d404e58aa73404b8531ecaf81c0c801df59bcbf55e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"a99f5ePQz43KWHDLxF2U2EtzITaczL4JIdtXD878FfCUeX63mzR8PH6nOWAxvus06Thcr2l+9+BvHi3YWg+iBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T01:19:04.819454Z","bundle_sha256":"b7093d68ea48cafbb07aecf218124445259c74ee4f25c562b25998b53f947174"}}