{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:2NQAMUUGIO4FTUHKDZDTNH4IDW","short_pith_number":"pith:2NQAMUUG","schema_version":"1.0","canonical_sha256":"d36006528643b859d0ea1e47369f881d836046b66ed9a6ff1a76b2481402e022","source":{"kind":"arxiv","id":"2505.21958","version":1},"attestation_state":"computed","paper":{"title":"Resolving Knowledge Conflicts in Domain-specific Data Selection: A Case Study on Medical Instruction-tuning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bo Du, Dacheng Tao, Fei Liao, Juhua Liu, Liang Ding, Qihuang Zhong","submitted_at":"2025-05-28T04:18:24Z","abstract_excerpt":"Domain-specific instruction-tuning has become the defacto standard for improving the performance of large language models (LLMs) in specialized applications, e.g., medical question answering. Since the instruction-tuning dataset might contain redundant or low-quality data, data selection (DS) is usually required to maximize the data efficiency. Despite the successes in the general domain, current DS methods often struggle to select the desired data for domain-specific instruction-tuning. One of the main reasons is that they neglect the impact of knowledge conflicts, i.e., the discrepancy betwe"},"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":"2505.21958","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-28T04:18:24Z","cross_cats_sorted":[],"title_canon_sha256":"b7125b6a5bcaf45773895366ba95122e302acb9da4e755271c88228a1e998cd5","abstract_canon_sha256":"a9dc61d41713e2a00731d7d67d821c10a19c31201cbbcbbc0255f7715f5c51ba"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:11:06.869680Z","signature_b64":"YrePUi0VZ7Zk2Cu0buoKLKV3a3hzIRg3ivRsUg0BfHMvQdwCarBvAoyJOFFmufmyr07t9LPmLuD5jfr0R1EHBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d36006528643b859d0ea1e47369f881d836046b66ed9a6ff1a76b2481402e022","last_reissued_at":"2026-07-05T11:11:06.869160Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:11:06.869160Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Resolving Knowledge Conflicts in Domain-specific Data Selection: A Case Study on Medical Instruction-tuning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bo Du, Dacheng Tao, Fei Liao, Juhua Liu, Liang Ding, Qihuang Zhong","submitted_at":"2025-05-28T04:18:24Z","abstract_excerpt":"Domain-specific instruction-tuning has become the defacto standard for improving the performance of large language models (LLMs) in specialized applications, e.g., medical question answering. Since the instruction-tuning dataset might contain redundant or low-quality data, data selection (DS) is usually required to maximize the data efficiency. Despite the successes in the general domain, current DS methods often struggle to select the desired data for domain-specific instruction-tuning. One of the main reasons is that they neglect the impact of knowledge conflicts, i.e., the discrepancy betwe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.21958","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/2505.21958/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":"2505.21958","created_at":"2026-07-05T11:11:06.869228+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.21958v1","created_at":"2026-07-05T11:11:06.869228+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.21958","created_at":"2026-07-05T11:11:06.869228+00:00"},{"alias_kind":"pith_short_12","alias_value":"2NQAMUUGIO4F","created_at":"2026-07-05T11:11:06.869228+00:00"},{"alias_kind":"pith_short_16","alias_value":"2NQAMUUGIO4FTUHK","created_at":"2026-07-05T11:11:06.869228+00:00"},{"alias_kind":"pith_short_8","alias_value":"2NQAMUUG","created_at":"2026-07-05T11:11:06.869228+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/2NQAMUUGIO4FTUHKDZDTNH4IDW","json":"https://pith.science/pith/2NQAMUUGIO4FTUHKDZDTNH4IDW.json","graph_json":"https://pith.science/api/pith-number/2NQAMUUGIO4FTUHKDZDTNH4IDW/graph.json","events_json":"https://pith.science/api/pith-number/2NQAMUUGIO4FTUHKDZDTNH4IDW/events.json","paper":"https://pith.science/paper/2NQAMUUG"},"agent_actions":{"view_html":"https://pith.science/pith/2NQAMUUGIO4FTUHKDZDTNH4IDW","download_json":"https://pith.science/pith/2NQAMUUGIO4FTUHKDZDTNH4IDW.json","view_paper":"https://pith.science/paper/2NQAMUUG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.21958&json=true","fetch_graph":"https://pith.science/api/pith-number/2NQAMUUGIO4FTUHKDZDTNH4IDW/graph.json","fetch_events":"https://pith.science/api/pith-number/2NQAMUUGIO4FTUHKDZDTNH4IDW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2NQAMUUGIO4FTUHKDZDTNH4IDW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2NQAMUUGIO4FTUHKDZDTNH4IDW/action/storage_attestation","attest_author":"https://pith.science/pith/2NQAMUUGIO4FTUHKDZDTNH4IDW/action/author_attestation","sign_citation":"https://pith.science/pith/2NQAMUUGIO4FTUHKDZDTNH4IDW/action/citation_signature","submit_replication":"https://pith.science/pith/2NQAMUUGIO4FTUHKDZDTNH4IDW/action/replication_record"}},"created_at":"2026-07-05T11:11:06.869228+00:00","updated_at":"2026-07-05T11:11:06.869228+00:00"}