{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:6YFZ65ZAMXCLGE5X3QXE7MIZYY","short_pith_number":"pith:6YFZ65ZA","canonical_record":{"source":{"id":"2509.26076","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-09-30T10:50:37Z","cross_cats_sorted":[],"title_canon_sha256":"885e4921a7ac22b51c7b6b08347db14250690ce28767e8904b9b832bcecd6463","abstract_canon_sha256":"078632ad139486c8707c08ab5c8a0da2aa872f426f324b94164bac8927f66e48"},"schema_version":"1.0"},"canonical_sha256":"f60b9f772065c4b313b7dc2e4fb119c63255043151fc4984d2f0aee56921d044","source":{"kind":"arxiv","id":"2509.26076","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.26076","created_at":"2026-07-10T01:19:39Z"},{"alias_kind":"arxiv_version","alias_value":"2509.26076v2","created_at":"2026-07-10T01:19:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.26076","created_at":"2026-07-10T01:19:39Z"},{"alias_kind":"pith_short_12","alias_value":"6YFZ65ZAMXCL","created_at":"2026-07-10T01:19:39Z"},{"alias_kind":"pith_short_16","alias_value":"6YFZ65ZAMXCLGE5X","created_at":"2026-07-10T01:19:39Z"},{"alias_kind":"pith_short_8","alias_value":"6YFZ65ZA","created_at":"2026-07-10T01:19:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:6YFZ65ZAMXCLGE5X3QXE7MIZYY","target":"record","payload":{"canonical_record":{"source":{"id":"2509.26076","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-09-30T10:50:37Z","cross_cats_sorted":[],"title_canon_sha256":"885e4921a7ac22b51c7b6b08347db14250690ce28767e8904b9b832bcecd6463","abstract_canon_sha256":"078632ad139486c8707c08ab5c8a0da2aa872f426f324b94164bac8927f66e48"},"schema_version":"1.0"},"canonical_sha256":"f60b9f772065c4b313b7dc2e4fb119c63255043151fc4984d2f0aee56921d044","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-10T01:19:39.853825Z","signature_b64":"r1APqUFgl+DkMn7tA6d1MHuQZJnjlw3NS3lGpRwDNjocH1VV2rzVKs0Q4Q8RUOXFlLVPvV3d5tuEIr1WRXsKBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f60b9f772065c4b313b7dc2e4fb119c63255043151fc4984d2f0aee56921d044","last_reissued_at":"2026-07-10T01:19:39.853324Z","signature_status":"signed_v1","first_computed_at":"2026-07-10T01:19:39.853324Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2509.26076","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":"2026-07-10T01:19:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nW5S9tRHIjtmgAplFbXktLNH2OFLGb15e2EWwOJOnP9Tv5UUfa+qVlCcJDLsgQ0vZjk2r6meNQdt/3kK4R+kDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-26T10:09:10.056679Z"},"content_sha256":"a3ca036430fa9f856ff48770fdc3fd154dea6739eaf76bdd542055b36b973389","schema_version":"1.0","event_id":"sha256:a3ca036430fa9f856ff48770fdc3fd154dea6739eaf76bdd542055b36b973389"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:6YFZ65ZAMXCLGE5X3QXE7MIZYY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"IMProofBench: Benchmarking AI on Research-Level Mathematical Proof Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Adam Kurpisz, Aitor Iribar Lopez, Aleksandar Mijatovi\\'c, Alessio Bottini, Aluna Rizzoli, Ana Cannas da Silva, Ana-Maria Castravet, Baran Hashemi, Benjamin Doerr, Charles Vial, Chiara Meroni, Claudio Fontanari, Daniel Holmes, Daniel Platt, Daria Sakhanda, David Holmes, David Martins, David Mu\\~noz-Lahoz, Diaaeldin Taha, Dylan Possama\\\"i, Filippo Gaia, Gabriel Ribeiro, Georg Oberdieck, Gergely B\\'erczi, Henk van der Pol, Henry Liu, Ignacio Barros, Ingmar Metzler, Jasper Dekoninck, Jeremy Feusi, Jim Bryan, Jo\\~ao Camarneiro, Johannes Lengler, Johannes Schmitt, Josef Teichmann, Marc Roth, Martijn Kool, Martina J{\\o}rgensen, Martin M\\\"oller, Michel van Garrel, Niklas Canova, Patrick Schnider, Peter Gr\\\"unwald, Pieter Belmans, Pim Spelier, Raphael Appenzeller, Ra\\'ul S\\'anchez Gal\\'an, Richard P. Thomas, Robert Nowak, Ronald van Luijk, Samuel Mu\\~noz-Ech\\'aniz, Sergej Monavari, Stefan Kuhlmann, Steven Kelk, Tim Gehrunger, Timo de Wolff, Victor Jaeck, Yannik Schuler, Yuuji Tanaka, Zheming Sun","submitted_at":"2025-09-30T10:50:37Z","abstract_excerpt":"As the mathematical capabilities of large language models (LLMs) improve, it becomes increasingly important to evaluate their performance on research-level tasks at the frontier of mathematical knowledge. However, existing benchmarks are limited, as they focus solely on final-answer questions or high-school competition problems. To address this gap, we introduce IMProofBench, a private benchmark consisting of 77 peer-reviewed problems developed by expert mathematicians. Each problem requires a detailed proof and is paired with subproblems that have final answers, supporting both an evaluation "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.26076","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2509.26076/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"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":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-10T01:19:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"75V7Vtzdqj6Q/FXeAUp7SM9b7iHvK4nDYjlWqqbPvD2yeitTkTS8Iv+M9qx9P6ultkt93qkKMHX8YNjufJ7CCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-26T10:09:10.057049Z"},"content_sha256":"dc4dc290cc57983b449b5999151a25acf8bcf1eb54e976b3ff919ed8b87838f3","schema_version":"1.0","event_id":"sha256:dc4dc290cc57983b449b5999151a25acf8bcf1eb54e976b3ff919ed8b87838f3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6YFZ65ZAMXCLGE5X3QXE7MIZYY/bundle.json","state_url":"https://pith.science/pith/6YFZ65ZAMXCLGE5X3QXE7MIZYY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6YFZ65ZAMXCLGE5X3QXE7MIZYY/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":"2026-07-26T10:09:10Z","links":{"resolver":"https://pith.science/pith/6YFZ65ZAMXCLGE5X3QXE7MIZYY","bundle":"https://pith.science/pith/6YFZ65ZAMXCLGE5X3QXE7MIZYY/bundle.json","state":"https://pith.science/pith/6YFZ65ZAMXCLGE5X3QXE7MIZYY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6YFZ65ZAMXCLGE5X3QXE7MIZYY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:6YFZ65ZAMXCLGE5X3QXE7MIZYY","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":"078632ad139486c8707c08ab5c8a0da2aa872f426f324b94164bac8927f66e48","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-09-30T10:50:37Z","title_canon_sha256":"885e4921a7ac22b51c7b6b08347db14250690ce28767e8904b9b832bcecd6463"},"schema_version":"1.0","source":{"id":"2509.26076","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.26076","created_at":"2026-07-10T01:19:39Z"},{"alias_kind":"arxiv_version","alias_value":"2509.26076v2","created_at":"2026-07-10T01:19:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.26076","created_at":"2026-07-10T01:19:39Z"},{"alias_kind":"pith_short_12","alias_value":"6YFZ65ZAMXCL","created_at":"2026-07-10T01:19:39Z"},{"alias_kind":"pith_short_16","alias_value":"6YFZ65ZAMXCLGE5X","created_at":"2026-07-10T01:19:39Z"},{"alias_kind":"pith_short_8","alias_value":"6YFZ65ZA","created_at":"2026-07-10T01:19:39Z"}],"graph_snapshots":[{"event_id":"sha256:dc4dc290cc57983b449b5999151a25acf8bcf1eb54e976b3ff919ed8b87838f3","target":"graph","created_at":"2026-07-10T01:19:39Z","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":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2509.26076/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"As the mathematical capabilities of large language models (LLMs) improve, it becomes increasingly important to evaluate their performance on research-level tasks at the frontier of mathematical knowledge. However, existing benchmarks are limited, as they focus solely on final-answer questions or high-school competition problems. To address this gap, we introduce IMProofBench, a private benchmark consisting of 77 peer-reviewed problems developed by expert mathematicians. Each problem requires a detailed proof and is paired with subproblems that have final answers, supporting both an evaluation ","authors_text":"Adam Kurpisz, Aitor Iribar Lopez, Aleksandar Mijatovi\\'c, Alessio Bottini, Aluna Rizzoli, Ana Cannas da Silva, Ana-Maria Castravet, Baran Hashemi, Benjamin Doerr, Charles Vial, Chiara Meroni, Claudio Fontanari, Daniel Holmes, Daniel Platt, Daria Sakhanda, David Holmes, David Martins, David Mu\\~noz-Lahoz, Diaaeldin Taha, Dylan Possama\\\"i, Filippo Gaia, Gabriel Ribeiro, Georg Oberdieck, Gergely B\\'erczi, Henk van der Pol, Henry Liu, Ignacio Barros, Ingmar Metzler, Jasper Dekoninck, Jeremy Feusi, Jim Bryan, Jo\\~ao Camarneiro, Johannes Lengler, Johannes Schmitt, Josef Teichmann, Marc Roth, Martijn Kool, Martina J{\\o}rgensen, Martin M\\\"oller, Michel van Garrel, Niklas Canova, Patrick Schnider, Peter Gr\\\"unwald, Pieter Belmans, Pim Spelier, Raphael Appenzeller, Ra\\'ul S\\'anchez Gal\\'an, Richard P. Thomas, Robert Nowak, Ronald van Luijk, Samuel Mu\\~noz-Ech\\'aniz, Sergej Monavari, Stefan Kuhlmann, Steven Kelk, Tim Gehrunger, Timo de Wolff, Victor Jaeck, Yannik Schuler, Yuuji Tanaka, Zheming Sun","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-09-30T10:50:37Z","title":"IMProofBench: Benchmarking AI on Research-Level Mathematical Proof Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.26076","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:a3ca036430fa9f856ff48770fdc3fd154dea6739eaf76bdd542055b36b973389","target":"record","created_at":"2026-07-10T01:19:39Z","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":"078632ad139486c8707c08ab5c8a0da2aa872f426f324b94164bac8927f66e48","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-09-30T10:50:37Z","title_canon_sha256":"885e4921a7ac22b51c7b6b08347db14250690ce28767e8904b9b832bcecd6463"},"schema_version":"1.0","source":{"id":"2509.26076","kind":"arxiv","version":2}},"canonical_sha256":"f60b9f772065c4b313b7dc2e4fb119c63255043151fc4984d2f0aee56921d044","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f60b9f772065c4b313b7dc2e4fb119c63255043151fc4984d2f0aee56921d044","first_computed_at":"2026-07-10T01:19:39.853324Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-10T01:19:39.853324Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"r1APqUFgl+DkMn7tA6d1MHuQZJnjlw3NS3lGpRwDNjocH1VV2rzVKs0Q4Q8RUOXFlLVPvV3d5tuEIr1WRXsKBg==","signature_status":"signed_v1","signed_at":"2026-07-10T01:19:39.853825Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.26076","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a3ca036430fa9f856ff48770fdc3fd154dea6739eaf76bdd542055b36b973389","sha256:dc4dc290cc57983b449b5999151a25acf8bcf1eb54e976b3ff919ed8b87838f3"],"state_sha256":"ff539b9a00f0c190d55d30dc880f5c25ae22a1e5c825a7b3cfb51ce58bab3207"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jT/73fClMwZdXz9+dMkVAnklomtYmqdjqcen+Yxhnna6r1k+AcDlX4trSCES+7KVtALoR0XApASjGmUfwvtACA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-26T10:09:10.059086Z","bundle_sha256":"cfd519676c6a117c21b7f2a9b9dbeeb42fcf9d1aa2a9055840cf1c863655e3ec"}}