{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:B367BSOW7SYLVYSC34Y53URCF6","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":"d7d07e891bc017905020978151fd6d9ab19ed43ebb4d74cbbd95a9b6e84a8c76","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-15T22:30:57Z","title_canon_sha256":"3f161a3f30ad6a8c21177482ad0a3740432cdca156a38ec6ce7a4263c321db2a"},"schema_version":"1.0","source":{"id":"2605.16675","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.16675","created_at":"2026-05-20T00:02:35Z"},{"alias_kind":"arxiv_version","alias_value":"2605.16675v1","created_at":"2026-05-20T00:02:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.16675","created_at":"2026-05-20T00:02:35Z"},{"alias_kind":"pith_short_12","alias_value":"B367BSOW7SYL","created_at":"2026-05-20T00:02:35Z"},{"alias_kind":"pith_short_16","alias_value":"B367BSOW7SYLVYSC","created_at":"2026-05-20T00:02:35Z"},{"alias_kind":"pith_short_8","alias_value":"B367BSOW","created_at":"2026-05-20T00:02:35Z"}],"graph_snapshots":[{"event_id":"sha256:401da71b29678f90b5593ab53480986b60e8bdccae746a6c99b5149bcfd67537","target":"graph","created_at":"2026-05-20T00:02:35Z","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":[{"findings_count":0,"name":"claim_evidence","ran_at":"2026-05-19T19:01:56.387131Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-19T18:33:26.505900Z","status":"skipped","version":"1.0.0"}],"endpoint":"/pith/2605.16675/integrity.json","findings":[],"snapshot_sha256":"8202be9a42173e19552d8a05c82a66112475e972ef23c09b928a27b6e7b2af4c","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce LinAlg-Bench, a diagnostic benchmark evaluating 10 frontier large language models on structured linear algebra computation across a strict dimensional gradient of 3x3, 4x4, and 5x5 matrices. Spanning 9 task types and 660 SymPy-certified problems, the benchmark exhaustively evaluates 6,600 model outputs. Beyond binary accuracy, LinAlg-Bench introduces a three-stage automated forensic pipeline classifying 1,156 failures into ten primary error tags with fine-grained subtypes, revealing that LLM mathematical failure is not random but structurally constrained by algorithm type and matr","authors_text":"Deepak Rajbhar, Shradha Agarwal, Tariq J","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-15T22:30:57Z","title":"LinAlg-Bench: A Forensic Benchmark Revealing Structural Failure Modes in LLM Mathematical Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.16675","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:dcdd7aca6ae400180a0d3d220dff249ab72326928a46c0101256452c48fabd31","target":"record","created_at":"2026-05-20T00:02:35Z","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":"d7d07e891bc017905020978151fd6d9ab19ed43ebb4d74cbbd95a9b6e84a8c76","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-15T22:30:57Z","title_canon_sha256":"3f161a3f30ad6a8c21177482ad0a3740432cdca156a38ec6ce7a4263c321db2a"},"schema_version":"1.0","source":{"id":"2605.16675","kind":"arxiv","version":1}},"canonical_sha256":"0efdf0c9d6fcb0bae242df31ddd2222f81ff601eb7fa3c3aef04acad41f70ece","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0efdf0c9d6fcb0bae242df31ddd2222f81ff601eb7fa3c3aef04acad41f70ece","first_computed_at":"2026-05-20T00:02:35.777581Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:02:35.777581Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YhRXMz7jvLLWA37ur8esC5iR8wqJhE35N6T796qrPnd8pbr3aqOEfaVy/Z3LfLz3+nvcVwOqRPK3QN7Pv3i8BQ==","signature_status":"signed_v1","signed_at":"2026-05-20T00:02:35.778284Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.16675","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dcdd7aca6ae400180a0d3d220dff249ab72326928a46c0101256452c48fabd31","sha256:401da71b29678f90b5593ab53480986b60e8bdccae746a6c99b5149bcfd67537"],"state_sha256":"664b5fd5710c41f73d29c03234ddd17703142873c6c0e134e9311be5db2dbc0a"}