{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:WBPSXKPKHYFY4BA6SGVNF3M3UX","short_pith_number":"pith:WBPSXKPK","schema_version":"1.0","canonical_sha256":"b05f2ba9ea3e0b8e041e91aad2ed9ba5ffba6dd00258cdd42bc1ec75f37cb591","source":{"kind":"arxiv","id":"2606.31308","version":1},"attestation_state":"computed","paper":{"title":"Benchmarking Large Language Models on Floating-Point Error Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"David Defour, Eric Petit, Lisa Taldir, Muhammad Ahmad Saeed, Pablo de Oliveira Castro (LI-PaRAD)","submitted_at":"2026-06-30T08:18:45Z","abstract_excerpt":"This paper investigates the capability of Large Language Models (LLMs) to detect and classify floating-point errors statically in software code. We introduce InterFLOPBench, a benchmark of 90 C kernels with 1 130 test samples designed to evaluate LLMs across six categories of floating-point error: cancellation, comparison, division by zero, overflow, underflow and NaN, compared across 14 LLMs. The evaluation framework treats floating-point error detection as a multi-label classification problem and employs the F1-score metric to measure performance. Results demonstrate that latest models (Qwen"},"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":"2606.31308","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-30T08:18:45Z","cross_cats_sorted":[],"title_canon_sha256":"ee471f87183bf9548daf3b5ebe107bf9971d73ff2889a7685628f56f0962fa0f","abstract_canon_sha256":"92a5c1ce6afa21dcb4c3b59636a1c60b93d48f0394935ec5f410e314893e807d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-01T01:17:58.721753Z","signature_b64":"y3bEGnNR7meFgp5gX4OAPRbrbkmtZdCMptySmeiebSx/Xpa/suEdr2L5rrs2msz4uoef8JaUCIFEwpQgacgRBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b05f2ba9ea3e0b8e041e91aad2ed9ba5ffba6dd00258cdd42bc1ec75f37cb591","last_reissued_at":"2026-07-01T01:17:58.721337Z","signature_status":"signed_v1","first_computed_at":"2026-07-01T01:17:58.721337Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Benchmarking Large Language Models on Floating-Point Error Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"David Defour, Eric Petit, Lisa Taldir, Muhammad Ahmad Saeed, Pablo de Oliveira Castro (LI-PaRAD)","submitted_at":"2026-06-30T08:18:45Z","abstract_excerpt":"This paper investigates the capability of Large Language Models (LLMs) to detect and classify floating-point errors statically in software code. We introduce InterFLOPBench, a benchmark of 90 C kernels with 1 130 test samples designed to evaluate LLMs across six categories of floating-point error: cancellation, comparison, division by zero, overflow, underflow and NaN, compared across 14 LLMs. The evaluation framework treats floating-point error detection as a multi-label classification problem and employs the F1-score metric to measure performance. Results demonstrate that latest models (Qwen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.31308","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/2606.31308/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2606.31308","created_at":"2026-07-01T01:17:58.721396+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.31308v1","created_at":"2026-07-01T01:17:58.721396+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.31308","created_at":"2026-07-01T01:17:58.721396+00:00"},{"alias_kind":"pith_short_12","alias_value":"WBPSXKPKHYFY","created_at":"2026-07-01T01:17:58.721396+00:00"},{"alias_kind":"pith_short_16","alias_value":"WBPSXKPKHYFY4BA6","created_at":"2026-07-01T01:17:58.721396+00:00"},{"alias_kind":"pith_short_8","alias_value":"WBPSXKPK","created_at":"2026-07-01T01:17:58.721396+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/WBPSXKPKHYFY4BA6SGVNF3M3UX","json":"https://pith.science/pith/WBPSXKPKHYFY4BA6SGVNF3M3UX.json","graph_json":"https://pith.science/api/pith-number/WBPSXKPKHYFY4BA6SGVNF3M3UX/graph.json","events_json":"https://pith.science/api/pith-number/WBPSXKPKHYFY4BA6SGVNF3M3UX/events.json","paper":"https://pith.science/paper/WBPSXKPK"},"agent_actions":{"view_html":"https://pith.science/pith/WBPSXKPKHYFY4BA6SGVNF3M3UX","download_json":"https://pith.science/pith/WBPSXKPKHYFY4BA6SGVNF3M3UX.json","view_paper":"https://pith.science/paper/WBPSXKPK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.31308&json=true","fetch_graph":"https://pith.science/api/pith-number/WBPSXKPKHYFY4BA6SGVNF3M3UX/graph.json","fetch_events":"https://pith.science/api/pith-number/WBPSXKPKHYFY4BA6SGVNF3M3UX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WBPSXKPKHYFY4BA6SGVNF3M3UX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WBPSXKPKHYFY4BA6SGVNF3M3UX/action/storage_attestation","attest_author":"https://pith.science/pith/WBPSXKPKHYFY4BA6SGVNF3M3UX/action/author_attestation","sign_citation":"https://pith.science/pith/WBPSXKPKHYFY4BA6SGVNF3M3UX/action/citation_signature","submit_replication":"https://pith.science/pith/WBPSXKPKHYFY4BA6SGVNF3M3UX/action/replication_record"}},"created_at":"2026-07-01T01:17:58.721396+00:00","updated_at":"2026-07-01T01:17:58.721396+00:00"}