{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:B367BSOW7SYLVYSC34Y53URCF6","short_pith_number":"pith:B367BSOW","schema_version":"1.0","canonical_sha256":"0efdf0c9d6fcb0bae242df31ddd2222f81ff601eb7fa3c3aef04acad41f70ece","source":{"kind":"arxiv","id":"2605.16675","version":1},"attestation_state":"computed","paper":{"title":"LinAlg-Bench: A Forensic Benchmark Revealing Structural Failure Modes in LLM Mathematical Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Deepak Rajbhar, Shradha Agarwal, Tariq J","submitted_at":"2026-05-15T22:30:57Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2605.16675","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-15T22:30:57Z","cross_cats_sorted":[],"title_canon_sha256":"3f161a3f30ad6a8c21177482ad0a3740432cdca156a38ec6ce7a4263c321db2a","abstract_canon_sha256":"d7d07e891bc017905020978151fd6d9ab19ed43ebb4d74cbbd95a9b6e84a8c76"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:02:35.778284Z","signature_b64":"YhRXMz7jvLLWA37ur8esC5iR8wqJhE35N6T796qrPnd8pbr3aqOEfaVy/Z3LfLz3+nvcVwOqRPK3QN7Pv3i8BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0efdf0c9d6fcb0bae242df31ddd2222f81ff601eb7fa3c3aef04acad41f70ece","last_reissued_at":"2026-05-20T00:02:35.777581Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:02:35.777581Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LinAlg-Bench: A Forensic Benchmark Revealing Structural Failure Modes in LLM Mathematical Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Deepak Rajbhar, Shradha Agarwal, Tariq J","submitted_at":"2026-05-15T22:30:57Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.16675","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/2605.16675/integrity.json","findings":[],"available":true,"detectors_run":[{"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","findings_count":0}],"snapshot_sha256":"8202be9a42173e19552d8a05c82a66112475e972ef23c09b928a27b6e7b2af4c"},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2605.16675","created_at":"2026-05-20T00:02:35.777694+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.16675v1","created_at":"2026-05-20T00:02:35.777694+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.16675","created_at":"2026-05-20T00:02:35.777694+00:00"},{"alias_kind":"pith_short_12","alias_value":"B367BSOW7SYL","created_at":"2026-05-20T00:02:35.777694+00:00"},{"alias_kind":"pith_short_16","alias_value":"B367BSOW7SYLVYSC","created_at":"2026-05-20T00:02:35.777694+00:00"},{"alias_kind":"pith_short_8","alias_value":"B367BSOW","created_at":"2026-05-20T00:02:35.777694+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/B367BSOW7SYLVYSC34Y53URCF6","json":"https://pith.science/pith/B367BSOW7SYLVYSC34Y53URCF6.json","graph_json":"https://pith.science/api/pith-number/B367BSOW7SYLVYSC34Y53URCF6/graph.json","events_json":"https://pith.science/api/pith-number/B367BSOW7SYLVYSC34Y53URCF6/events.json","paper":"https://pith.science/paper/B367BSOW"},"agent_actions":{"view_html":"https://pith.science/pith/B367BSOW7SYLVYSC34Y53URCF6","download_json":"https://pith.science/pith/B367BSOW7SYLVYSC34Y53URCF6.json","view_paper":"https://pith.science/paper/B367BSOW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.16675&json=true","fetch_graph":"https://pith.science/api/pith-number/B367BSOW7SYLVYSC34Y53URCF6/graph.json","fetch_events":"https://pith.science/api/pith-number/B367BSOW7SYLVYSC34Y53URCF6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/B367BSOW7SYLVYSC34Y53URCF6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/B367BSOW7SYLVYSC34Y53URCF6/action/storage_attestation","attest_author":"https://pith.science/pith/B367BSOW7SYLVYSC34Y53URCF6/action/author_attestation","sign_citation":"https://pith.science/pith/B367BSOW7SYLVYSC34Y53URCF6/action/citation_signature","submit_replication":"https://pith.science/pith/B367BSOW7SYLVYSC34Y53URCF6/action/replication_record"}},"created_at":"2026-05-20T00:02:35.777694+00:00","updated_at":"2026-05-20T00:02:35.777694+00:00"}