{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:IJXDNDGH27SBGSGYSZKYVQ2QQP","short_pith_number":"pith:IJXDNDGH","schema_version":"1.0","canonical_sha256":"426e368cc7d7e41348d896558ac35083c00c499389275b447d0e5fcbd567fee9","source":{"kind":"arxiv","id":"2404.00376","version":2},"attestation_state":"computed","paper":{"title":"Small Language Models Learn Enhanced Reasoning Skills from Medical Textbooks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chanwoong Yoon, Dain Kim, Donghee Choi, Hyeon Hwang, Hyunjae Kim, Jaewoo Kang, Jiwoo Lee, Jiwoong Sohn, Sihyeon Park, Taewhoo Lee","submitted_at":"2024-03-30T14:09:00Z","abstract_excerpt":"While recent advancements in commercial large language models (LM) have shown promising results in medical tasks, their closed-source nature poses significant privacy and security concerns, hindering their widespread use in the medical field. Despite efforts to create open-source models, their limited parameters often result in insufficient multi-step reasoning capabilities required for solving complex medical problems. To address this, we introduce Meerkat, a new family of medical AI systems ranging from 7 to 70 billion parameters. The models were trained using our new synthetic dataset consi"},"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":"2404.00376","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-30T14:09:00Z","cross_cats_sorted":[],"title_canon_sha256":"521867aae18ff917eafb55b74bd60b4689cd492f81a624e7666f75fc552dc543","abstract_canon_sha256":"e3362023a8a39496819bcf4e8bddbdb6d1ea38b1ab09b1bfb96848825f7e50e3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:38:07.991102Z","signature_b64":"IMZdMzYP31ABV8Im1MpuIt/w+dcFWmDy+jTyB66BGqYeT6Fk4Qw/vDmJC6LaafOeo60GKUc7KSkcFad/2CExBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"426e368cc7d7e41348d896558ac35083c00c499389275b447d0e5fcbd567fee9","last_reissued_at":"2026-07-05T08:38:07.990605Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:38:07.990605Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Small Language Models Learn Enhanced Reasoning Skills from Medical Textbooks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chanwoong Yoon, Dain Kim, Donghee Choi, Hyeon Hwang, Hyunjae Kim, Jaewoo Kang, Jiwoo Lee, Jiwoong Sohn, Sihyeon Park, Taewhoo Lee","submitted_at":"2024-03-30T14:09:00Z","abstract_excerpt":"While recent advancements in commercial large language models (LM) have shown promising results in medical tasks, their closed-source nature poses significant privacy and security concerns, hindering their widespread use in the medical field. Despite efforts to create open-source models, their limited parameters often result in insufficient multi-step reasoning capabilities required for solving complex medical problems. To address this, we introduce Meerkat, a new family of medical AI systems ranging from 7 to 70 billion parameters. The models were trained using our new synthetic dataset consi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.00376","kind":"arxiv","version":2},"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/2404.00376/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":"2404.00376","created_at":"2026-07-05T08:38:07.990672+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.00376v2","created_at":"2026-07-05T08:38:07.990672+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.00376","created_at":"2026-07-05T08:38:07.990672+00:00"},{"alias_kind":"pith_short_12","alias_value":"IJXDNDGH27SB","created_at":"2026-07-05T08:38:07.990672+00:00"},{"alias_kind":"pith_short_16","alias_value":"IJXDNDGH27SBGSGY","created_at":"2026-07-05T08:38:07.990672+00:00"},{"alias_kind":"pith_short_8","alias_value":"IJXDNDGH","created_at":"2026-07-05T08:38:07.990672+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.03305","citing_title":"The Reliability Gap in Benchmark Auditing: Distribution Shift and Scale as Failure Modes of Contamination Detection","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2606.08071","citing_title":"SurgiQ: A Large-Scale Multi-Domain Benchmark for Evaluating Surgical Understanding in Large Language Models","ref_index":68,"is_internal_anchor":false},{"citing_arxiv_id":"2606.03305","citing_title":"The Reliability Gap in Benchmark Auditing: Distribution Shift and Scale as Failure Modes of Contamination Detection","ref_index":16,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IJXDNDGH27SBGSGYSZKYVQ2QQP","json":"https://pith.science/pith/IJXDNDGH27SBGSGYSZKYVQ2QQP.json","graph_json":"https://pith.science/api/pith-number/IJXDNDGH27SBGSGYSZKYVQ2QQP/graph.json","events_json":"https://pith.science/api/pith-number/IJXDNDGH27SBGSGYSZKYVQ2QQP/events.json","paper":"https://pith.science/paper/IJXDNDGH"},"agent_actions":{"view_html":"https://pith.science/pith/IJXDNDGH27SBGSGYSZKYVQ2QQP","download_json":"https://pith.science/pith/IJXDNDGH27SBGSGYSZKYVQ2QQP.json","view_paper":"https://pith.science/paper/IJXDNDGH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.00376&json=true","fetch_graph":"https://pith.science/api/pith-number/IJXDNDGH27SBGSGYSZKYVQ2QQP/graph.json","fetch_events":"https://pith.science/api/pith-number/IJXDNDGH27SBGSGYSZKYVQ2QQP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IJXDNDGH27SBGSGYSZKYVQ2QQP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IJXDNDGH27SBGSGYSZKYVQ2QQP/action/storage_attestation","attest_author":"https://pith.science/pith/IJXDNDGH27SBGSGYSZKYVQ2QQP/action/author_attestation","sign_citation":"https://pith.science/pith/IJXDNDGH27SBGSGYSZKYVQ2QQP/action/citation_signature","submit_replication":"https://pith.science/pith/IJXDNDGH27SBGSGYSZKYVQ2QQP/action/replication_record"}},"created_at":"2026-07-05T08:38:07.990672+00:00","updated_at":"2026-07-05T08:38:07.990672+00:00"}