{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:UCFHIZEB4CSZTCVHFT4HDC5EXM","short_pith_number":"pith:UCFHIZEB","schema_version":"1.0","canonical_sha256":"a08a746481e0a5998aa72cf8718ba4bb3a621b8044ac4fe7365bcdb36cebdf0f","source":{"kind":"arxiv","id":"2605.27860","version":1},"attestation_state":"computed","paper":{"title":"C-MIG: Multi-view Information Gain-based Retrieval-Augmented Generation for Clinical Diagnosis Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Bo Yuan, Gen Li, Jianwei Lv, Junfeng Wang, Luning Wang, Siyu Chen, Xiandong Li, Yujin Wang, Yunhao Qiao, Yunsheng Zeng, Yuwei Miao","submitted_at":"2026-05-27T02:20:21Z","abstract_excerpt":"Retrieval-augmented generation combined with reinforcement learning has shown promise for grounding large language models in trustworthy medical evidence. However, existing methods rely on exact-match binary rewards, which in clinical diagnosis cause two issues: (i) semantically relevant but non-verbatim steps receive zero signal, discarding valuable learning signals; and (ii) uni-dimensional rewards cannot effectively supervise heterogeneous reasoning capabilities. To address these issues, we propose C-MIG, a Multi-view Information Gain-based retrieval-augmented generation framework for Clini"},"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":"2605.27860","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-27T02:20:21Z","cross_cats_sorted":[],"title_canon_sha256":"67a6e00c054e20dd15a21440dbab9f902f4ff8f3d0af246dcf79952cbeff5e65","abstract_canon_sha256":"31524e70137d95a28588e17c8a31f606180efa3b8bc6f525d16ac1829a14aec5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-28T01:04:50.729242Z","signature_b64":"MvCi/LZg6Bdtu+ENCDDUVYw8qNXkecqseauNcXj1bY0OkhcjprM/+pzcTTmTStkGl+J9Jqps32H4T1+CiFUeBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a08a746481e0a5998aa72cf8718ba4bb3a621b8044ac4fe7365bcdb36cebdf0f","last_reissued_at":"2026-05-28T01:04:50.728838Z","signature_status":"signed_v1","first_computed_at":"2026-05-28T01:04:50.728838Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"C-MIG: Multi-view Information Gain-based Retrieval-Augmented Generation for Clinical Diagnosis Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Bo Yuan, Gen Li, Jianwei Lv, Junfeng Wang, Luning Wang, Siyu Chen, Xiandong Li, Yujin Wang, Yunhao Qiao, Yunsheng Zeng, Yuwei Miao","submitted_at":"2026-05-27T02:20:21Z","abstract_excerpt":"Retrieval-augmented generation combined with reinforcement learning has shown promise for grounding large language models in trustworthy medical evidence. However, existing methods rely on exact-match binary rewards, which in clinical diagnosis cause two issues: (i) semantically relevant but non-verbatim steps receive zero signal, discarding valuable learning signals; and (ii) uni-dimensional rewards cannot effectively supervise heterogeneous reasoning capabilities. To address these issues, we propose C-MIG, a Multi-view Information Gain-based retrieval-augmented generation framework for Clini"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.27860","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/2605.27860/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":"2605.27860","created_at":"2026-05-28T01:04:50.728891+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.27860v1","created_at":"2026-05-28T01:04:50.728891+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.27860","created_at":"2026-05-28T01:04:50.728891+00:00"},{"alias_kind":"pith_short_12","alias_value":"UCFHIZEB4CSZ","created_at":"2026-05-28T01:04:50.728891+00:00"},{"alias_kind":"pith_short_16","alias_value":"UCFHIZEB4CSZTCVH","created_at":"2026-05-28T01:04:50.728891+00:00"},{"alias_kind":"pith_short_8","alias_value":"UCFHIZEB","created_at":"2026-05-28T01:04:50.728891+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/UCFHIZEB4CSZTCVHFT4HDC5EXM","json":"https://pith.science/pith/UCFHIZEB4CSZTCVHFT4HDC5EXM.json","graph_json":"https://pith.science/api/pith-number/UCFHIZEB4CSZTCVHFT4HDC5EXM/graph.json","events_json":"https://pith.science/api/pith-number/UCFHIZEB4CSZTCVHFT4HDC5EXM/events.json","paper":"https://pith.science/paper/UCFHIZEB"},"agent_actions":{"view_html":"https://pith.science/pith/UCFHIZEB4CSZTCVHFT4HDC5EXM","download_json":"https://pith.science/pith/UCFHIZEB4CSZTCVHFT4HDC5EXM.json","view_paper":"https://pith.science/paper/UCFHIZEB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.27860&json=true","fetch_graph":"https://pith.science/api/pith-number/UCFHIZEB4CSZTCVHFT4HDC5EXM/graph.json","fetch_events":"https://pith.science/api/pith-number/UCFHIZEB4CSZTCVHFT4HDC5EXM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UCFHIZEB4CSZTCVHFT4HDC5EXM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UCFHIZEB4CSZTCVHFT4HDC5EXM/action/storage_attestation","attest_author":"https://pith.science/pith/UCFHIZEB4CSZTCVHFT4HDC5EXM/action/author_attestation","sign_citation":"https://pith.science/pith/UCFHIZEB4CSZTCVHFT4HDC5EXM/action/citation_signature","submit_replication":"https://pith.science/pith/UCFHIZEB4CSZTCVHFT4HDC5EXM/action/replication_record"}},"created_at":"2026-05-28T01:04:50.728891+00:00","updated_at":"2026-05-28T01:04:50.728891+00:00"}