{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:2L2222CBGYCW5QZNSV4YODXVVB","short_pith_number":"pith:2L2222CB","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"},"canonical_sha256":"d2f5ad684136056ec32d9579870ef5a86e00e2949f4f2298d6a98be3a9ece8b4","source":{"kind":"arxiv","id":"2504.02885","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.02885","created_at":"2026-06-19T16:12:45Z"},{"alias_kind":"arxiv_version","alias_value":"2504.02885v2","created_at":"2026-06-19T16:12:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.02885","created_at":"2026-06-19T16:12:45Z"},{"alias_kind":"pith_short_12","alias_value":"2L2222CBGYCW","created_at":"2026-06-19T16:12:45Z"},{"alias_kind":"pith_short_16","alias_value":"2L2222CBGYCW5QZN","created_at":"2026-06-19T16:12:45Z"},{"alias_kind":"pith_short_8","alias_value":"2L2222CB","created_at":"2026-06-19T16:12:45Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:2L2222CBGYCW5QZNSV4YODXVVB","target":"record","payload":{"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"},"canonical_sha256":"d2f5ad684136056ec32d9579870ef5a86e00e2949f4f2298d6a98be3a9ece8b4","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"},"source_kind":"arxiv","source_id":"2504.02885","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-19T16:12:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HqbXRyolGaK/cglfFshw9qSpD6R+mfF6hir1tHYW5yEUOI4llpxKF3PjuqMhtL9MtQcDJDP2gwdknsuxLPhKCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T01:19:38.062091Z"},"content_sha256":"7df7332747bf2de3c331388caa492e638b74f95bfc60126a3ca1da8872de8023","schema_version":"1.0","event_id":"sha256:7df7332747bf2de3c331388caa492e638b74f95bfc60126a3ca1da8872de8023"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:2L2222CBGYCW5QZNSV4YODXVVB","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-19T16:12:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bbZx2MpN7zze4u++4H59jfqis6kfp57yuvriTObKLcXu25BJPOLPpqrCz8/Oh2EYcEDn0jajupw20LK6zdFWDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T01:19:38.082265Z"},"content_sha256":"67b8771a3bb90b786aecef10c71823725a2ccdc2d37d0074618010e98828e74c","schema_version":"1.0","event_id":"sha256:67b8771a3bb90b786aecef10c71823725a2ccdc2d37d0074618010e98828e74c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2L2222CBGYCW5QZNSV4YODXVVB/bundle.json","state_url":"https://pith.science/pith/2L2222CBGYCW5QZNSV4YODXVVB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2L2222CBGYCW5QZNSV4YODXVVB/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-05T01:19:38Z","links":{"resolver":"https://pith.science/pith/2L2222CBGYCW5QZNSV4YODXVVB","bundle":"https://pith.science/pith/2L2222CBGYCW5QZNSV4YODXVVB/bundle.json","state":"https://pith.science/pith/2L2222CBGYCW5QZNSV4YODXVVB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2L2222CBGYCW5QZNSV4YODXVVB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:2L2222CBGYCW5QZNSV4YODXVVB","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"000aa024d88ed0978c6df1da0776b242b3f38ecb129b50afa6bb414fa0832b5b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-04-02T08:18:54Z","title_canon_sha256":"7ea8326a215c8f6f6834d796ddfa9b6752bc57a259be4d7834be8115e96a04b4"},"schema_version":"1.0","source":{"id":"2504.02885","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.02885","created_at":"2026-06-19T16:12:45Z"},{"alias_kind":"arxiv_version","alias_value":"2504.02885v2","created_at":"2026-06-19T16:12:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.02885","created_at":"2026-06-19T16:12:45Z"},{"alias_kind":"pith_short_12","alias_value":"2L2222CBGYCW","created_at":"2026-06-19T16:12:45Z"},{"alias_kind":"pith_short_16","alias_value":"2L2222CBGYCW5QZN","created_at":"2026-06-19T16:12:45Z"},{"alias_kind":"pith_short_8","alias_value":"2L2222CB","created_at":"2026-06-19T16:12:45Z"}],"graph_snapshots":[{"event_id":"sha256:67b8771a3bb90b786aecef10c71823725a2ccdc2d37d0074618010e98828e74c","target":"graph","created_at":"2026-06-19T16:12:45Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2504.02885/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Hao Wang, Jinghao Lin, Jinman Kim, Shuchang Ye, Usman Naseem","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-04-02T08:18:54Z","title":"Med-R2: Perception and Reflection-driven Complex Reasoning for Medical Report Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.02885","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:7df7332747bf2de3c331388caa492e638b74f95bfc60126a3ca1da8872de8023","target":"record","created_at":"2026-06-19T16:12:45Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"000aa024d88ed0978c6df1da0776b242b3f38ecb129b50afa6bb414fa0832b5b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-04-02T08:18:54Z","title_canon_sha256":"7ea8326a215c8f6f6834d796ddfa9b6752bc57a259be4d7834be8115e96a04b4"},"schema_version":"1.0","source":{"id":"2504.02885","kind":"arxiv","version":2}},"canonical_sha256":"d2f5ad684136056ec32d9579870ef5a86e00e2949f4f2298d6a98be3a9ece8b4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d2f5ad684136056ec32d9579870ef5a86e00e2949f4f2298d6a98be3a9ece8b4","first_computed_at":"2026-06-19T16:12:45.539599Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-19T16:12:45.539599Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DoBIc9wvSN+6h+Uy7c6ixRRAWiHdJ69U6+Rm20dJvPVoj/PPDhndZ2KMZ4Favqi23UskpdKewnCkUI00ACsnDA==","signature_status":"signed_v1","signed_at":"2026-06-19T16:12:45.540069Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.02885","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7df7332747bf2de3c331388caa492e638b74f95bfc60126a3ca1da8872de8023","sha256:67b8771a3bb90b786aecef10c71823725a2ccdc2d37d0074618010e98828e74c"],"state_sha256":"18ad2a8359eb76dea289e51a57a60987d1908ee9cd38ee100669331057770749"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ae1+dpzn7SMYvRwdfFZBM33nAXdIzg1nxGxUrDFo0h3T57QFp49s6JN+BZTGWVqV1agwBVHeqVZxzShmIfj5BQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T01:19:38.104854Z","bundle_sha256":"49475ddd1b359c287da7f236d830f352090262717193d9d11b707db98496a405"}}