{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:SV4WQ2FPSUPSSDGOJMUXTEDKP2","short_pith_number":"pith:SV4WQ2FP","canonical_record":{"source":{"id":"2606.24902","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DL","submitted_at":"2026-06-12T14:58:20Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"97afdaaddce689c6892f4e0658ce9a1d69a16a6edf471e1e6c17dcc3605666f8","abstract_canon_sha256":"2dd1fd7d511420c6303164bb4fe617209c60abde5768869774cfc4d38159f700"},"schema_version":"1.0"},"canonical_sha256":"95796868af951f290cce4b2979906a7e9da3ff24a4cff0037f65ea9b02e15c46","source":{"kind":"arxiv","id":"2606.24902","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.24902","created_at":"2026-06-25T00:17:45Z"},{"alias_kind":"arxiv_version","alias_value":"2606.24902v1","created_at":"2026-06-25T00:17:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.24902","created_at":"2026-06-25T00:17:45Z"},{"alias_kind":"pith_short_12","alias_value":"SV4WQ2FPSUPS","created_at":"2026-06-25T00:17:45Z"},{"alias_kind":"pith_short_16","alias_value":"SV4WQ2FPSUPSSDGO","created_at":"2026-06-25T00:17:45Z"},{"alias_kind":"pith_short_8","alias_value":"SV4WQ2FP","created_at":"2026-06-25T00:17:45Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:SV4WQ2FPSUPSSDGOJMUXTEDKP2","target":"record","payload":{"canonical_record":{"source":{"id":"2606.24902","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DL","submitted_at":"2026-06-12T14:58:20Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"97afdaaddce689c6892f4e0658ce9a1d69a16a6edf471e1e6c17dcc3605666f8","abstract_canon_sha256":"2dd1fd7d511420c6303164bb4fe617209c60abde5768869774cfc4d38159f700"},"schema_version":"1.0"},"canonical_sha256":"95796868af951f290cce4b2979906a7e9da3ff24a4cff0037f65ea9b02e15c46","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-25T00:17:45.605515Z","signature_b64":"17TCppzWEGHNBQCX3HZFBmpRZzSp83eAyhnpnjodWJnh/gEBH4GbAUk+FZEKgttAw0+r0q0oiXS2RIxZtgrRDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"95796868af951f290cce4b2979906a7e9da3ff24a4cff0037f65ea9b02e15c46","last_reissued_at":"2026-06-25T00:17:45.604999Z","signature_status":"signed_v1","first_computed_at":"2026-06-25T00:17:45.604999Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.24902","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":"2026-06-25T00:17:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Npk1xbtUD+783d8updJRPj4eBPaOvWvhTfBoWzPO3nqsaqupf2qMXi/a9eQi/q3Rizl26cSAFK3LAbwHOxXZDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-04T04:23:49.880492Z"},"content_sha256":"436053fd32f1ac971768244ad1a4e79c9d7d6a426bcc12e263ec297eb2e1362c","schema_version":"1.0","event_id":"sha256:436053fd32f1ac971768244ad1a4e79c9d7d6a426bcc12e263ec297eb2e1362c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:SV4WQ2FPSUPSSDGOJMUXTEDKP2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Failure Modes of Large Language Models on Research-Level Mathematics: A Taxonomy and an Empirical Characterisation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.DL","authors_text":"Arnesh Banerjee, Ayushi Bhattacharjee","submitted_at":"2026-06-12T14:58:20Z","abstract_excerpt":"The \"First Proof\" benchmark [1] posed ten research-level mathematics questions to the strongest publicly available LLMs and found them consistently wrong-not silent, but confidently, fluently wrong. This paper asks why. Working from the per-question post-mortems in First Proof's Appendix A, I identify four failure modes: citation fabrication (F1), premise smuggling (F2), silent problem reformulation (F3), and local-to-global compatibility gaps (F4). I then audit eight one-shot proofs generated by Gemini 2.5 Flash on Questions 1, 2, and 5 of the benchmark, using two instruments built specifical"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.24902","kind":"arxiv","version":1},"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/2606.24902/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":"2026-06-25T00:17:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"blyBR/xFKqRYmHeaXJuzJ9WwV2+8AytPgS/clkLVXBsUJEf8x1Ib21X8uoH2/bPc2pen2Cjf2zOH02vtJUYlCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-04T04:23:49.880873Z"},"content_sha256":"945615f790fef42f9c85a79ebf0d44398f85bfdc35c3f0ab4ba2ef039d5d2ef4","schema_version":"1.0","event_id":"sha256:945615f790fef42f9c85a79ebf0d44398f85bfdc35c3f0ab4ba2ef039d5d2ef4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SV4WQ2FPSUPSSDGOJMUXTEDKP2/bundle.json","state_url":"https://pith.science/pith/SV4WQ2FPSUPSSDGOJMUXTEDKP2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SV4WQ2FPSUPSSDGOJMUXTEDKP2/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":"2026-07-04T04:23:49Z","links":{"resolver":"https://pith.science/pith/SV4WQ2FPSUPSSDGOJMUXTEDKP2","bundle":"https://pith.science/pith/SV4WQ2FPSUPSSDGOJMUXTEDKP2/bundle.json","state":"https://pith.science/pith/SV4WQ2FPSUPSSDGOJMUXTEDKP2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SV4WQ2FPSUPSSDGOJMUXTEDKP2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:SV4WQ2FPSUPSSDGOJMUXTEDKP2","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":"2dd1fd7d511420c6303164bb4fe617209c60abde5768869774cfc4d38159f700","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DL","submitted_at":"2026-06-12T14:58:20Z","title_canon_sha256":"97afdaaddce689c6892f4e0658ce9a1d69a16a6edf471e1e6c17dcc3605666f8"},"schema_version":"1.0","source":{"id":"2606.24902","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.24902","created_at":"2026-06-25T00:17:45Z"},{"alias_kind":"arxiv_version","alias_value":"2606.24902v1","created_at":"2026-06-25T00:17:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.24902","created_at":"2026-06-25T00:17:45Z"},{"alias_kind":"pith_short_12","alias_value":"SV4WQ2FPSUPS","created_at":"2026-06-25T00:17:45Z"},{"alias_kind":"pith_short_16","alias_value":"SV4WQ2FPSUPSSDGO","created_at":"2026-06-25T00:17:45Z"},{"alias_kind":"pith_short_8","alias_value":"SV4WQ2FP","created_at":"2026-06-25T00:17:45Z"}],"graph_snapshots":[{"event_id":"sha256:945615f790fef42f9c85a79ebf0d44398f85bfdc35c3f0ab4ba2ef039d5d2ef4","target":"graph","created_at":"2026-06-25T00:17:45Z","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/2606.24902/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The \"First Proof\" benchmark [1] posed ten research-level mathematics questions to the strongest publicly available LLMs and found them consistently wrong-not silent, but confidently, fluently wrong. This paper asks why. Working from the per-question post-mortems in First Proof's Appendix A, I identify four failure modes: citation fabrication (F1), premise smuggling (F2), silent problem reformulation (F3), and local-to-global compatibility gaps (F4). I then audit eight one-shot proofs generated by Gemini 2.5 Flash on Questions 1, 2, and 5 of the benchmark, using two instruments built specifical","authors_text":"Arnesh Banerjee, Ayushi Bhattacharjee","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DL","submitted_at":"2026-06-12T14:58:20Z","title":"Failure Modes of Large Language Models on Research-Level Mathematics: A Taxonomy and an Empirical Characterisation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.24902","kind":"arxiv","version":1},"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":"sha256:436053fd32f1ac971768244ad1a4e79c9d7d6a426bcc12e263ec297eb2e1362c","target":"record","created_at":"2026-06-25T00:17:45Z","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":"2dd1fd7d511420c6303164bb4fe617209c60abde5768869774cfc4d38159f700","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DL","submitted_at":"2026-06-12T14:58:20Z","title_canon_sha256":"97afdaaddce689c6892f4e0658ce9a1d69a16a6edf471e1e6c17dcc3605666f8"},"schema_version":"1.0","source":{"id":"2606.24902","kind":"arxiv","version":1}},"canonical_sha256":"95796868af951f290cce4b2979906a7e9da3ff24a4cff0037f65ea9b02e15c46","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"95796868af951f290cce4b2979906a7e9da3ff24a4cff0037f65ea9b02e15c46","first_computed_at":"2026-06-25T00:17:45.604999Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-25T00:17:45.604999Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"17TCppzWEGHNBQCX3HZFBmpRZzSp83eAyhnpnjodWJnh/gEBH4GbAUk+FZEKgttAw0+r0q0oiXS2RIxZtgrRDQ==","signature_status":"signed_v1","signed_at":"2026-06-25T00:17:45.605515Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.24902","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:436053fd32f1ac971768244ad1a4e79c9d7d6a426bcc12e263ec297eb2e1362c","sha256:945615f790fef42f9c85a79ebf0d44398f85bfdc35c3f0ab4ba2ef039d5d2ef4"],"state_sha256":"2d0dd9cda276caeb231b82f4e12da395bb157d159f302510c76354bc8b093abb"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ruGL9/lk9Bi1ieFVJ3iaX7oiExqVAHZ5GhLul8IBQ0PjeWbU8ojy1dfr+uHeIJE5B7nqLLKkSiMX99v6I3fTBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-04T04:23:49.882983Z","bundle_sha256":"2b854cba0a745a3a7e8b0dbf3478213c197243085348e7e21c141be807a168e7"}}