{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:422RRLZXBZIZ2ZAJWZIZQ7V6RR","short_pith_number":"pith:422RRLZX","canonical_record":{"source":{"id":"2605.13171","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-13T08:33:15Z","cross_cats_sorted":[],"title_canon_sha256":"86a9a16b3d528f634a8c57e197d9f68a771d26f59cafb5f5e1b44710d32ee633","abstract_canon_sha256":"f552d3b3743a3461918aa2546ab5c33c7fedc7705cd216c689c739f48e25ccd1"},"schema_version":"1.0"},"canonical_sha256":"e6b518af370e519d6409b651987ebe8c720b900142a8937f4a53e36f9557e67a","source":{"kind":"arxiv","id":"2605.13171","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.13171","created_at":"2026-05-18T03:08:56Z"},{"alias_kind":"arxiv_version","alias_value":"2605.13171v1","created_at":"2026-05-18T03:08:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.13171","created_at":"2026-05-18T03:08:56Z"},{"alias_kind":"pith_short_12","alias_value":"422RRLZXBZIZ","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"422RRLZXBZIZ2ZAJ","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"422RRLZX","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:422RRLZXBZIZ2ZAJWZIZQ7V6RR","target":"record","payload":{"canonical_record":{"source":{"id":"2605.13171","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-13T08:33:15Z","cross_cats_sorted":[],"title_canon_sha256":"86a9a16b3d528f634a8c57e197d9f68a771d26f59cafb5f5e1b44710d32ee633","abstract_canon_sha256":"f552d3b3743a3461918aa2546ab5c33c7fedc7705cd216c689c739f48e25ccd1"},"schema_version":"1.0"},"canonical_sha256":"e6b518af370e519d6409b651987ebe8c720b900142a8937f4a53e36f9557e67a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:08:56.558483Z","signature_b64":"6icVJ4uE2uay/yQI79khVAsqcNqO1cIentwIh16gkgjnCdb1DjGS3ezBP2t53wCvCqdw8mBLWcOWzv/0HYpTDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e6b518af370e519d6409b651987ebe8c720b900142a8937f4a53e36f9557e67a","last_reissued_at":"2026-05-18T03:08:56.557617Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:08:56.557617Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.13171","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T03:08:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qGGU3tIyP7G0Tly9gNjNTJf7In1tNkQYaDXKcRRnwC6QKMaYirSr1pu7Teq6r8dyKcgwapD9eB3HV0KKkUEsBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T20:38:37.653512Z"},"content_sha256":"e17269cfb102d67fcc3f2815e757e8deb9de13bdfb3bcb8a28a1bc5de9fda9c7","schema_version":"1.0","event_id":"sha256:e17269cfb102d67fcc3f2815e757e8deb9de13bdfb3bcb8a28a1bc5de9fda9c7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:422RRLZXBZIZ2ZAJWZIZQ7V6RR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Formal Conjectures: An Open and Evolving Benchmark for Verified Discovery in Mathematics","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Formal Conjectures supplies 2615 Lean 4 statements of active research problems, 1029 of them open conjectures, as a contamination-free testbed for automated proof discovery.","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Blaise Ag\\\"uera y Arcas, Calle S\\\"onne, Eric Wieser, Fred Zhang, Mikl\\'os Z. Horv\\'ath, Moritz Firsching, Paul Lezeau, Pushmeet Kohli, Salvatore Mercuri, Thomas Hubert, Ya\\\"el Dillies","submitted_at":"2026-05-13T08:33:15Z","abstract_excerpt":"As automated reasoning systems advance rapidly, there is a growing need for research-level formal mathematical problems to accurately evaluate their capabilities. To address this, we present Formal Conjectures, an evolving benchmark of currently 2615 mathematical problem statements formalized in Lean 4. Sourced from areas of active mathematical research, the dataset features 1029 open research conjectures providing a zero-contamination benchmark for mathematical proof discovery, and 836 solved problems for proof autoformalization. Notably, the repository provides a structured interface connect"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Demonstrating its immediate utility, the benchmark has already been leveraged to make new mathematical discoveries, including the resolution of open research conjectures.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the Lean 4 formalizations accurately capture the original mathematical statements without introducing errors, simplifications, or changes that alter the difficulty or meaning of the conjectures.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Formal Conjectures is a Lean 4 benchmark containing 2615 formalized problems with 1029 open conjectures, designed to evaluate automated mathematical reasoning and proof discovery.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Formal Conjectures supplies 2615 Lean 4 statements of active research problems, 1029 of them open conjectures, as a contamination-free testbed for automated proof discovery.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"376758122a83b095f466b125c301457dd3552bf185fd93526d2cc7d5d6e7861a"},"source":{"id":"2605.13171","kind":"arxiv","version":1},"verdict":{"id":"4965ff8a-faf9-41e2-9fda-d1297dc7b8c1","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-14T20:17:32.804574Z","strongest_claim":"Demonstrating its immediate utility, the benchmark has already been leveraged to make new mathematical discoveries, including the resolution of open research conjectures.","one_line_summary":"Formal Conjectures is a Lean 4 benchmark containing 2615 formalized problems with 1029 open conjectures, designed to evaluate automated mathematical reasoning and proof discovery.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the Lean 4 formalizations accurately capture the original mathematical statements without introducing errors, simplifications, or changes that alter the difficulty or meaning of the conjectures.","pith_extraction_headline":"Formal Conjectures supplies 2615 Lean 4 statements of active research problems, 1029 of them open conjectures, as a contamination-free testbed for automated proof discovery."},"references":{"count":23,"sample":[{"doi":"","year":null,"title":"Aristotle: IMO-level Automated Theorem Proving","work_id":"6c61af2f-a34a-4647-9111-6ba5a60f6bc2","ref_index":1,"cited_arxiv_id":"2510.01346","is_internal_anchor":true},{"doi":"","year":null,"title":"Mislav Balunović, Jasper Dekoninck, Ivo Petrov, Nikola Jovanović, and Martin T","work_id":"5a92c988-7c9d-4440-8bdb-7f056e5c72cc","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"MathArena: Evaluating LLMs on Uncontaminated Math Competitions","work_id":"61e8d872-ccc7-46b8-8ec1-94008704c941","ref_index":3,"cited_arxiv_id":"2505.23281","is_internal_anchor":true},{"doi":"","year":2026,"title":"Accessed: 2026-03-24","work_id":"e758657a-570e-44ea-b4ec-6129f224ce3e","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2026,"title":"See comment section","work_id":"b77e3eb8-9124-45c7-9df0-882f3bdf33fb","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":23,"snapshot_sha256":"35b2a68477da62b4efa394c501836540fc18a51dec5775f2c487cfbd7b8efdce","internal_anchors":6},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"4965ff8a-faf9-41e2-9fda-d1297dc7b8c1"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T03:08:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"04qGZw38aYM/bVFQ0YETVSgA4aKVaAWsz3ReS1zJno8nxdB75k9daijfhO6ooLXgUlXsJEjwgqAKeK65eNBGDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T20:38:37.654545Z"},"content_sha256":"56d0e76e79cd071961c81ec5affe95a81235f73eb9d77d023084e8347d308cc2","schema_version":"1.0","event_id":"sha256:56d0e76e79cd071961c81ec5affe95a81235f73eb9d77d023084e8347d308cc2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/422RRLZXBZIZ2ZAJWZIZQ7V6RR/bundle.json","state_url":"https://pith.science/pith/422RRLZXBZIZ2ZAJWZIZQ7V6RR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/422RRLZXBZIZ2ZAJWZIZQ7V6RR/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":"2026-06-05T20:38:37Z","links":{"resolver":"https://pith.science/pith/422RRLZXBZIZ2ZAJWZIZQ7V6RR","bundle":"https://pith.science/pith/422RRLZXBZIZ2ZAJWZIZQ7V6RR/bundle.json","state":"https://pith.science/pith/422RRLZXBZIZ2ZAJWZIZQ7V6RR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/422RRLZXBZIZ2ZAJWZIZQ7V6RR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:422RRLZXBZIZ2ZAJWZIZQ7V6RR","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":"f552d3b3743a3461918aa2546ab5c33c7fedc7705cd216c689c739f48e25ccd1","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-13T08:33:15Z","title_canon_sha256":"86a9a16b3d528f634a8c57e197d9f68a771d26f59cafb5f5e1b44710d32ee633"},"schema_version":"1.0","source":{"id":"2605.13171","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.13171","created_at":"2026-05-18T03:08:56Z"},{"alias_kind":"arxiv_version","alias_value":"2605.13171v1","created_at":"2026-05-18T03:08:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.13171","created_at":"2026-05-18T03:08:56Z"},{"alias_kind":"pith_short_12","alias_value":"422RRLZXBZIZ","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"422RRLZXBZIZ2ZAJ","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"422RRLZX","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:56d0e76e79cd071961c81ec5affe95a81235f73eb9d77d023084e8347d308cc2","target":"graph","created_at":"2026-05-18T03:08:56Z","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":"Demonstrating its immediate utility, the benchmark has already been leveraged to make new mathematical discoveries, including the resolution of open research conjectures."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That the Lean 4 formalizations accurately capture the original mathematical statements without introducing errors, simplifications, or changes that alter the difficulty or meaning of the conjectures."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Formal Conjectures is a Lean 4 benchmark containing 2615 formalized problems with 1029 open conjectures, designed to evaluate automated mathematical reasoning and proof discovery."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Formal Conjectures supplies 2615 Lean 4 statements of active research problems, 1029 of them open conjectures, as a contamination-free testbed for automated proof discovery."}],"snapshot_sha256":"376758122a83b095f466b125c301457dd3552bf185fd93526d2cc7d5d6e7861a"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"As automated reasoning systems advance rapidly, there is a growing need for research-level formal mathematical problems to accurately evaluate their capabilities. To address this, we present Formal Conjectures, an evolving benchmark of currently 2615 mathematical problem statements formalized in Lean 4. Sourced from areas of active mathematical research, the dataset features 1029 open research conjectures providing a zero-contamination benchmark for mathematical proof discovery, and 836 solved problems for proof autoformalization. Notably, the repository provides a structured interface connect","authors_text":"Blaise Ag\\\"uera y Arcas, Calle S\\\"onne, Eric Wieser, Fred Zhang, Mikl\\'os Z. Horv\\'ath, Moritz Firsching, Paul Lezeau, Pushmeet Kohli, Salvatore Mercuri, Thomas Hubert, Ya\\\"el Dillies","cross_cats":[],"headline":"Formal Conjectures supplies 2615 Lean 4 statements of active research problems, 1029 of them open conjectures, as a contamination-free testbed for automated proof discovery.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-13T08:33:15Z","title":"Formal Conjectures: An Open and Evolving Benchmark for Verified Discovery in Mathematics"},"references":{"count":23,"internal_anchors":6,"resolved_work":23,"sample":[{"cited_arxiv_id":"2510.01346","doi":"","is_internal_anchor":true,"ref_index":1,"title":"Aristotle: IMO-level Automated Theorem Proving","work_id":"6c61af2f-a34a-4647-9111-6ba5a60f6bc2","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Mislav Balunović, Jasper Dekoninck, Ivo Petrov, Nikola Jovanović, and Martin T","work_id":"5a92c988-7c9d-4440-8bdb-7f056e5c72cc","year":null},{"cited_arxiv_id":"2505.23281","doi":"","is_internal_anchor":true,"ref_index":3,"title":"MathArena: Evaluating LLMs on Uncontaminated Math Competitions","work_id":"61e8d872-ccc7-46b8-8ec1-94008704c941","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Accessed: 2026-03-24","work_id":"e758657a-570e-44ea-b4ec-6129f224ce3e","year":2026},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"See comment section","work_id":"b77e3eb8-9124-45c7-9df0-882f3bdf33fb","year":2026}],"snapshot_sha256":"35b2a68477da62b4efa394c501836540fc18a51dec5775f2c487cfbd7b8efdce"},"source":{"id":"2605.13171","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-14T20:17:32.804574Z","id":"4965ff8a-faf9-41e2-9fda-d1297dc7b8c1","model_set":{"reader":"grok-4.3"},"one_line_summary":"Formal Conjectures is a Lean 4 benchmark containing 2615 formalized problems with 1029 open conjectures, designed to evaluate automated mathematical reasoning and proof discovery.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Formal Conjectures supplies 2615 Lean 4 statements of active research problems, 1029 of them open conjectures, as a contamination-free testbed for automated proof discovery.","strongest_claim":"Demonstrating its immediate utility, the benchmark has already been leveraged to make new mathematical discoveries, including the resolution of open research conjectures.","weakest_assumption":"That the Lean 4 formalizations accurately capture the original mathematical statements without introducing errors, simplifications, or changes that alter the difficulty or meaning of the conjectures."}},"verdict_id":"4965ff8a-faf9-41e2-9fda-d1297dc7b8c1"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:e17269cfb102d67fcc3f2815e757e8deb9de13bdfb3bcb8a28a1bc5de9fda9c7","target":"record","created_at":"2026-05-18T03:08:56Z","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":"f552d3b3743a3461918aa2546ab5c33c7fedc7705cd216c689c739f48e25ccd1","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-13T08:33:15Z","title_canon_sha256":"86a9a16b3d528f634a8c57e197d9f68a771d26f59cafb5f5e1b44710d32ee633"},"schema_version":"1.0","source":{"id":"2605.13171","kind":"arxiv","version":1}},"canonical_sha256":"e6b518af370e519d6409b651987ebe8c720b900142a8937f4a53e36f9557e67a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e6b518af370e519d6409b651987ebe8c720b900142a8937f4a53e36f9557e67a","first_computed_at":"2026-05-18T03:08:56.557617Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:08:56.557617Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6icVJ4uE2uay/yQI79khVAsqcNqO1cIentwIh16gkgjnCdb1DjGS3ezBP2t53wCvCqdw8mBLWcOWzv/0HYpTDQ==","signature_status":"signed_v1","signed_at":"2026-05-18T03:08:56.558483Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.13171","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e17269cfb102d67fcc3f2815e757e8deb9de13bdfb3bcb8a28a1bc5de9fda9c7","sha256:56d0e76e79cd071961c81ec5affe95a81235f73eb9d77d023084e8347d308cc2"],"state_sha256":"06f05e8136c3e12bb493823db179e8de7f40f0e2a13f92813f7f7d31cdea0ffe"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JhreruY3vknmPhk1ezdll7C0z287bsfqqT09SyzXM8LziwTYnn+dVm/VV9Sk7zLqdGkQaoQkRhncT9AiY06ACA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-05T20:38:37.659383Z","bundle_sha256":"9ffb3e807a64fd97a6eda330aa534ab5eb8ef83eec61a8f4a9211bd0f1b684eb"}}