{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:DPMYBUZPYCZLDU4Y6LLIZEL3DU","short_pith_number":"pith:DPMYBUZP","schema_version":"1.0","canonical_sha256":"1bd980d32fc0b2b1d398f2d68c917b1d0207f55a7452fe331ab527a85af5380b","source":{"kind":"arxiv","id":"2403.01570","version":3},"attestation_state":"computed","paper":{"title":"Small Models are LLM Knowledge Triggers on Medical Tabular Prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Bo Zheng, Chaowen Hu, Jiahuan Yan, Jian Wu, Jimeng Sun, Jintai Chen, Yaojun Hu","submitted_at":"2024-03-03T17:35:52Z","abstract_excerpt":"Recent development in large language models (LLMs) has demonstrated impressive domain proficiency on unstructured textual or multi-modal tasks. However, despite with intrinsic world knowledge, their application on structured tabular data prediction still lags behind, primarily due to the numerical insensitivity and modality discrepancy that brings a gap between LLM reasoning and statistical tabular learning. Unlike textual or vision data (e.g., electronic clinical notes or medical imaging data), tabular data is often presented in heterogeneous numerical values (e.g., CBC reports). This ubiquit"},"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":"2403.01570","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-03T17:35:52Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"7ce628c78b80eabeeb7b42e1838433738836e85b18f173136e678ddfe0b1a75c","abstract_canon_sha256":"9f752cfbde60a18becb99edd3b3feee49e92e9d7aea4f1d5a9218cd08e520087"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:21:18.022992Z","signature_b64":"xiKvvw9/kjP2MCStiOHAz8Bl4qJkzVgAVg7S0DJpvjrlKMWO0wv7AaFLShLiY5okKZr4OmXc7zZoTFzC30uIAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1bd980d32fc0b2b1d398f2d68c917b1d0207f55a7452fe331ab527a85af5380b","last_reissued_at":"2026-07-05T10:21:18.022504Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:21:18.022504Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Small Models are LLM Knowledge Triggers on Medical Tabular Prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Bo Zheng, Chaowen Hu, Jiahuan Yan, Jian Wu, Jimeng Sun, Jintai Chen, Yaojun Hu","submitted_at":"2024-03-03T17:35:52Z","abstract_excerpt":"Recent development in large language models (LLMs) has demonstrated impressive domain proficiency on unstructured textual or multi-modal tasks. However, despite with intrinsic world knowledge, their application on structured tabular data prediction still lags behind, primarily due to the numerical insensitivity and modality discrepancy that brings a gap between LLM reasoning and statistical tabular learning. Unlike textual or vision data (e.g., electronic clinical notes or medical imaging data), tabular data is often presented in heterogeneous numerical values (e.g., CBC reports). This ubiquit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.01570","kind":"arxiv","version":3},"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/2403.01570/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":"2403.01570","created_at":"2026-07-05T10:21:18.022571+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.01570v3","created_at":"2026-07-05T10:21:18.022571+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.01570","created_at":"2026-07-05T10:21:18.022571+00:00"},{"alias_kind":"pith_short_12","alias_value":"DPMYBUZPYCZL","created_at":"2026-07-05T10:21:18.022571+00:00"},{"alias_kind":"pith_short_16","alias_value":"DPMYBUZPYCZLDU4Y","created_at":"2026-07-05T10:21:18.022571+00:00"},{"alias_kind":"pith_short_8","alias_value":"DPMYBUZP","created_at":"2026-07-05T10:21:18.022571+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/DPMYBUZPYCZLDU4Y6LLIZEL3DU","json":"https://pith.science/pith/DPMYBUZPYCZLDU4Y6LLIZEL3DU.json","graph_json":"https://pith.science/api/pith-number/DPMYBUZPYCZLDU4Y6LLIZEL3DU/graph.json","events_json":"https://pith.science/api/pith-number/DPMYBUZPYCZLDU4Y6LLIZEL3DU/events.json","paper":"https://pith.science/paper/DPMYBUZP"},"agent_actions":{"view_html":"https://pith.science/pith/DPMYBUZPYCZLDU4Y6LLIZEL3DU","download_json":"https://pith.science/pith/DPMYBUZPYCZLDU4Y6LLIZEL3DU.json","view_paper":"https://pith.science/paper/DPMYBUZP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.01570&json=true","fetch_graph":"https://pith.science/api/pith-number/DPMYBUZPYCZLDU4Y6LLIZEL3DU/graph.json","fetch_events":"https://pith.science/api/pith-number/DPMYBUZPYCZLDU4Y6LLIZEL3DU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DPMYBUZPYCZLDU4Y6LLIZEL3DU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DPMYBUZPYCZLDU4Y6LLIZEL3DU/action/storage_attestation","attest_author":"https://pith.science/pith/DPMYBUZPYCZLDU4Y6LLIZEL3DU/action/author_attestation","sign_citation":"https://pith.science/pith/DPMYBUZPYCZLDU4Y6LLIZEL3DU/action/citation_signature","submit_replication":"https://pith.science/pith/DPMYBUZPYCZLDU4Y6LLIZEL3DU/action/replication_record"}},"created_at":"2026-07-05T10:21:18.022571+00:00","updated_at":"2026-07-05T10:21:18.022571+00:00"}