{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:2L2222CBGYCW5QZNSV4YODXVVB","short_pith_number":"pith:2L2222CB","schema_version":"1.0","canonical_sha256":"d2f5ad684136056ec32d9579870ef5a86e00e2949f4f2298d6a98be3a9ece8b4","source":{"kind":"arxiv","id":"2504.02885","version":2},"attestation_state":"computed","paper":{"title":"Med-R2: Perception and Reflection-driven Complex Reasoning for Medical Report Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hao Wang, Jinghao Lin, Jinman Kim, Shuchang Ye, Usman Naseem","submitted_at":"2025-04-02T08:18:54Z","abstract_excerpt":"Automated medical report generation (MRG) is increasingly used to reduce the burden of manual reporting and for decision support. Large vision-language models (LVLMs) hold great promise for automated MRG due to their fine-grained image-text alignment and advanced text-generation capabilities. Currently, state-of-the-art MRGs primarily focus on adapting pre-trained LVLMs with direct supervised fine-tuning (SFT), a fine-tuning strategy with medical image-report pairs. However, several factors limit the performance of these LVLMs. Firstly, direct SFT enables LVLMs to generate medical reports dire"},"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":"2504.02885","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-04-02T08:18:54Z","cross_cats_sorted":[],"title_canon_sha256":"7ea8326a215c8f6f6834d796ddfa9b6752bc57a259be4d7834be8115e96a04b4","abstract_canon_sha256":"000aa024d88ed0978c6df1da0776b242b3f38ecb129b50afa6bb414fa0832b5b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:12:45.540069Z","signature_b64":"DoBIc9wvSN+6h+Uy7c6ixRRAWiHdJ69U6+Rm20dJvPVoj/PPDhndZ2KMZ4Favqi23UskpdKewnCkUI00ACsnDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d2f5ad684136056ec32d9579870ef5a86e00e2949f4f2298d6a98be3a9ece8b4","last_reissued_at":"2026-06-19T16:12:45.539599Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:12:45.539599Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Med-R2: Perception and Reflection-driven Complex Reasoning for Medical Report Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hao Wang, Jinghao Lin, Jinman Kim, Shuchang Ye, Usman Naseem","submitted_at":"2025-04-02T08:18:54Z","abstract_excerpt":"Automated medical report generation (MRG) is increasingly used to reduce the burden of manual reporting and for decision support. Large vision-language models (LVLMs) hold great promise for automated MRG due to their fine-grained image-text alignment and advanced text-generation capabilities. Currently, state-of-the-art MRGs primarily focus on adapting pre-trained LVLMs with direct supervised fine-tuning (SFT), a fine-tuning strategy with medical image-report pairs. However, several factors limit the performance of these LVLMs. Firstly, direct SFT enables LVLMs to generate medical reports dire"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.02885","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/2504.02885/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":"2504.02885","created_at":"2026-06-19T16:12:45.539656+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.02885v2","created_at":"2026-06-19T16:12:45.539656+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.02885","created_at":"2026-06-19T16:12:45.539656+00:00"},{"alias_kind":"pith_short_12","alias_value":"2L2222CBGYCW","created_at":"2026-06-19T16:12:45.539656+00:00"},{"alias_kind":"pith_short_16","alias_value":"2L2222CBGYCW5QZN","created_at":"2026-06-19T16:12:45.539656+00:00"},{"alias_kind":"pith_short_8","alias_value":"2L2222CB","created_at":"2026-06-19T16:12:45.539656+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/2L2222CBGYCW5QZNSV4YODXVVB","json":"https://pith.science/pith/2L2222CBGYCW5QZNSV4YODXVVB.json","graph_json":"https://pith.science/api/pith-number/2L2222CBGYCW5QZNSV4YODXVVB/graph.json","events_json":"https://pith.science/api/pith-number/2L2222CBGYCW5QZNSV4YODXVVB/events.json","paper":"https://pith.science/paper/2L2222CB"},"agent_actions":{"view_html":"https://pith.science/pith/2L2222CBGYCW5QZNSV4YODXVVB","download_json":"https://pith.science/pith/2L2222CBGYCW5QZNSV4YODXVVB.json","view_paper":"https://pith.science/paper/2L2222CB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.02885&json=true","fetch_graph":"https://pith.science/api/pith-number/2L2222CBGYCW5QZNSV4YODXVVB/graph.json","fetch_events":"https://pith.science/api/pith-number/2L2222CBGYCW5QZNSV4YODXVVB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2L2222CBGYCW5QZNSV4YODXVVB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2L2222CBGYCW5QZNSV4YODXVVB/action/storage_attestation","attest_author":"https://pith.science/pith/2L2222CBGYCW5QZNSV4YODXVVB/action/author_attestation","sign_citation":"https://pith.science/pith/2L2222CBGYCW5QZNSV4YODXVVB/action/citation_signature","submit_replication":"https://pith.science/pith/2L2222CBGYCW5QZNSV4YODXVVB/action/replication_record"}},"created_at":"2026-06-19T16:12:45.539656+00:00","updated_at":"2026-06-19T16:12:45.539656+00:00"}