{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:FTITY4BIX7SQPBLHOMO4A3LVWW","short_pith_number":"pith:FTITY4BI","schema_version":"1.0","canonical_sha256":"2cd13c7028bfe5078567731dc06d75b5a8a83657bc96d5ff221ca68a3831f0b0","source":{"kind":"arxiv","id":"2607.26397","version":1},"attestation_state":"computed","paper":{"title":"Knowledge before Reasoning: EC-Reason-Bench, a Training-Free Diagnostic Benchmark for LLM Enzyme Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","q-bio.QM"],"primary_cat":"cs.CL","authors_text":"Dongming Jin, Gadeng Luosang, Huanyao Zhang, Linyu Li, Nyima Tashi, Xuan Zhang, Yichi Zhang, Yuanpeng He, Zhi Jin","submitted_at":"2026-07-29T02:16:09Z","abstract_excerpt":"Enzyme function prediction is a hierarchical, knowledge-intensive form of protein function classification. Existing benchmarks expose an anomaly: general LLMs often get the coarse first level right, yet once asked for a complete EC number their accuracy at levels two through four drops to almost zero, while specialized models and tools stay usable. We propose EC-Reason-Bench, a training-free, diagnostic evaluation protocol built to answer two questions: why general LLMs score close to nothing on EC number prediction, and how much of that loss can be recovered without updating a single weight. "},"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":"2607.26397","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-07-29T02:16:09Z","cross_cats_sorted":["cs.LG","q-bio.QM"],"title_canon_sha256":"045fc480ae17bf534961af7cd64cf46b0ad41b36a1a4a66c4167116a72f81ed4","abstract_canon_sha256":"4b6d558e51107974be0a4db039f479096b68a3f6ea4e68a75f1370ac75a4fbb6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2cd13c7028bfe5078567731dc06d75b5a8a83657bc96d5ff221ca68a3831f0b0","last_reissued_at":"2026-07-30T01:18:18.716492Z","signature_status":"unsigned_v0","first_computed_at":"2026-07-30T01:18:18.716492Z"},"graph_snapshot":{"paper":{"title":"Knowledge before Reasoning: EC-Reason-Bench, a Training-Free Diagnostic Benchmark for LLM Enzyme Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","q-bio.QM"],"primary_cat":"cs.CL","authors_text":"Dongming Jin, Gadeng Luosang, Huanyao Zhang, Linyu Li, Nyima Tashi, Xuan Zhang, Yichi Zhang, Yuanpeng He, Zhi Jin","submitted_at":"2026-07-29T02:16:09Z","abstract_excerpt":"Enzyme function prediction is a hierarchical, knowledge-intensive form of protein function classification. Existing benchmarks expose an anomaly: general LLMs often get the coarse first level right, yet once asked for a complete EC number their accuracy at levels two through four drops to almost zero, while specialized models and tools stay usable. We propose EC-Reason-Bench, a training-free, diagnostic evaluation protocol built to answer two questions: why general LLMs score close to nothing on EC number prediction, and how much of that loss can be recovered without updating a single weight. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.26397","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/2607.26397/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":"2607.26397","created_at":"2026-07-30T01:18:18.721690+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.26397v1","created_at":"2026-07-30T01:18:18.721690+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.26397","created_at":"2026-07-30T01:18:18.721690+00:00"},{"alias_kind":"pith_short_12","alias_value":"FTITY4BIX7SQ","created_at":"2026-07-30T01:18:18.721690+00:00"},{"alias_kind":"pith_short_16","alias_value":"FTITY4BIX7SQPBLH","created_at":"2026-07-30T01:18:18.721690+00:00"},{"alias_kind":"pith_short_8","alias_value":"FTITY4BI","created_at":"2026-07-30T01:18:18.721690+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/FTITY4BIX7SQPBLHOMO4A3LVWW","json":"https://pith.science/pith/FTITY4BIX7SQPBLHOMO4A3LVWW.json","graph_json":"https://pith.science/api/pith-number/FTITY4BIX7SQPBLHOMO4A3LVWW/graph.json","events_json":"https://pith.science/api/pith-number/FTITY4BIX7SQPBLHOMO4A3LVWW/events.json","paper":"https://pith.science/paper/FTITY4BI"},"agent_actions":{"view_html":"https://pith.science/pith/FTITY4BIX7SQPBLHOMO4A3LVWW","download_json":"https://pith.science/pith/FTITY4BIX7SQPBLHOMO4A3LVWW.json","view_paper":"https://pith.science/paper/FTITY4BI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.26397&json=true","fetch_graph":"https://pith.science/api/pith-number/FTITY4BIX7SQPBLHOMO4A3LVWW/graph.json","fetch_events":"https://pith.science/api/pith-number/FTITY4BIX7SQPBLHOMO4A3LVWW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FTITY4BIX7SQPBLHOMO4A3LVWW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FTITY4BIX7SQPBLHOMO4A3LVWW/action/storage_attestation","attest_author":"https://pith.science/pith/FTITY4BIX7SQPBLHOMO4A3LVWW/action/author_attestation","sign_citation":"https://pith.science/pith/FTITY4BIX7SQPBLHOMO4A3LVWW/action/citation_signature","submit_replication":"https://pith.science/pith/FTITY4BIX7SQPBLHOMO4A3LVWW/action/replication_record"}},"created_at":"2026-07-30T01:18:18.721690+00:00","updated_at":"2026-07-30T01:18:18.721690+00:00"}