{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:YWZROQTXD47DNZYBFUT5PEXT3S","short_pith_number":"pith:YWZROQTX","canonical_record":{"source":{"id":"2503.15784","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-20T01:51:05Z","cross_cats_sorted":[],"title_canon_sha256":"4f487636a46051100cf41d93cd415a0f9a65654af4e82e8550ef1531fba0ea38","abstract_canon_sha256":"afa10493c55616b3b787fa6c81202ada96f6dc42995e4610a8a13354ecbaa9c2"},"schema_version":"1.0"},"canonical_sha256":"c5b31742771f3e36e7012d27d792f3dc819178fc5485e1fe14ba0657be5ec5cf","source":{"kind":"arxiv","id":"2503.15784","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.15784","created_at":"2026-07-05T11:31:44Z"},{"alias_kind":"arxiv_version","alias_value":"2503.15784v2","created_at":"2026-07-05T11:31:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.15784","created_at":"2026-07-05T11:31:44Z"},{"alias_kind":"pith_short_12","alias_value":"YWZROQTXD47D","created_at":"2026-07-05T11:31:44Z"},{"alias_kind":"pith_short_16","alias_value":"YWZROQTXD47DNZYB","created_at":"2026-07-05T11:31:44Z"},{"alias_kind":"pith_short_8","alias_value":"YWZROQTX","created_at":"2026-07-05T11:31:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:YWZROQTXD47DNZYBFUT5PEXT3S","target":"record","payload":{"canonical_record":{"source":{"id":"2503.15784","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-20T01:51:05Z","cross_cats_sorted":[],"title_canon_sha256":"4f487636a46051100cf41d93cd415a0f9a65654af4e82e8550ef1531fba0ea38","abstract_canon_sha256":"afa10493c55616b3b787fa6c81202ada96f6dc42995e4610a8a13354ecbaa9c2"},"schema_version":"1.0"},"canonical_sha256":"c5b31742771f3e36e7012d27d792f3dc819178fc5485e1fe14ba0657be5ec5cf","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:31:44.351646Z","signature_b64":"+nDUNYtHEHfu6ROLlw9Tz4+BQrnZhL3mnGHqZGYLoayTTKiFUItuV8kxapePw40J2iRl0/C4uUHZ0EOW/M6CCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c5b31742771f3e36e7012d27d792f3dc819178fc5485e1fe14ba0657be5ec5cf","last_reissued_at":"2026-07-05T11:31:44.351118Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:31:44.351118Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2503.15784","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":"2026-07-05T11:31:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KBC2Y+wYocnXV7jGZXdu3zUP0YIHETTbZb6FK1X2Vr6GvXKtTqCKc3yRFthR9WLewIL37OBCn8YGNKOvgpb9CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T18:43:50.804051Z"},"content_sha256":"76d061afdb0972fae2a7ca4f7f5004843a487ef38a31b0a154bf4bee3f9722eb","schema_version":"1.0","event_id":"sha256:76d061afdb0972fae2a7ca4f7f5004843a487ef38a31b0a154bf4bee3f9722eb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:YWZROQTXD47DNZYBFUT5PEXT3S","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"RL4Med-DDPO: Reinforcement Learning for Controlled Guidance Towards Diverse Medical Image Generation using Vision-Language Foundation Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Amar Kumar, Mohamed Mohamed, Parham Saremi, Tal Arbel, Zahra Tehraninasab","submitted_at":"2025-03-20T01:51:05Z","abstract_excerpt":"Vision-Language Foundation Models (VLFM) have shown a tremendous increase in performance in terms of generating high-resolution, photorealistic natural images. While VLFMs show a rich understanding of semantic content across modalities, they often struggle with fine-grained alignment tasks that require precise correspondence between image regions and textual descriptions, a limitation in medical imaging, where accurate localization and detection of clinical features are essential for diagnosis and analysis. To address this issue, we propose a multi-stage architecture where a pre-trained VLFM ("},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.15784","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/2503.15784/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":"2026-07-05T11:31:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zc6IsrMQqqKcaoBboieOjV4ANahF8Ed9Rkx8TxKi4Gee4ctxgoGN1D68xKVZvSEFDLrqm2wdi3nyKIfzgKmiAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T18:43:50.804441Z"},"content_sha256":"23ee88de367076630d72dc53e5bbd7b7e2241299dba798ba0c6f720a876a9192","schema_version":"1.0","event_id":"sha256:23ee88de367076630d72dc53e5bbd7b7e2241299dba798ba0c6f720a876a9192"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YWZROQTXD47DNZYBFUT5PEXT3S/bundle.json","state_url":"https://pith.science/pith/YWZROQTXD47DNZYBFUT5PEXT3S/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YWZROQTXD47DNZYBFUT5PEXT3S/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":"2026-07-06T18:43:50Z","links":{"resolver":"https://pith.science/pith/YWZROQTXD47DNZYBFUT5PEXT3S","bundle":"https://pith.science/pith/YWZROQTXD47DNZYBFUT5PEXT3S/bundle.json","state":"https://pith.science/pith/YWZROQTXD47DNZYBFUT5PEXT3S/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YWZROQTXD47DNZYBFUT5PEXT3S/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:YWZROQTXD47DNZYBFUT5PEXT3S","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":"afa10493c55616b3b787fa6c81202ada96f6dc42995e4610a8a13354ecbaa9c2","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-20T01:51:05Z","title_canon_sha256":"4f487636a46051100cf41d93cd415a0f9a65654af4e82e8550ef1531fba0ea38"},"schema_version":"1.0","source":{"id":"2503.15784","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.15784","created_at":"2026-07-05T11:31:44Z"},{"alias_kind":"arxiv_version","alias_value":"2503.15784v2","created_at":"2026-07-05T11:31:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.15784","created_at":"2026-07-05T11:31:44Z"},{"alias_kind":"pith_short_12","alias_value":"YWZROQTXD47D","created_at":"2026-07-05T11:31:44Z"},{"alias_kind":"pith_short_16","alias_value":"YWZROQTXD47DNZYB","created_at":"2026-07-05T11:31:44Z"},{"alias_kind":"pith_short_8","alias_value":"YWZROQTX","created_at":"2026-07-05T11:31:44Z"}],"graph_snapshots":[{"event_id":"sha256:23ee88de367076630d72dc53e5bbd7b7e2241299dba798ba0c6f720a876a9192","target":"graph","created_at":"2026-07-05T11:31:44Z","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/2503.15784/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-Language Foundation Models (VLFM) have shown a tremendous increase in performance in terms of generating high-resolution, photorealistic natural images. While VLFMs show a rich understanding of semantic content across modalities, they often struggle with fine-grained alignment tasks that require precise correspondence between image regions and textual descriptions, a limitation in medical imaging, where accurate localization and detection of clinical features are essential for diagnosis and analysis. To address this issue, we propose a multi-stage architecture where a pre-trained VLFM (","authors_text":"Amar Kumar, Mohamed Mohamed, Parham Saremi, Tal Arbel, Zahra Tehraninasab","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-20T01:51:05Z","title":"RL4Med-DDPO: Reinforcement Learning for Controlled Guidance Towards Diverse Medical Image Generation using Vision-Language Foundation Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.15784","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":"sha256:76d061afdb0972fae2a7ca4f7f5004843a487ef38a31b0a154bf4bee3f9722eb","target":"record","created_at":"2026-07-05T11:31:44Z","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":"afa10493c55616b3b787fa6c81202ada96f6dc42995e4610a8a13354ecbaa9c2","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-20T01:51:05Z","title_canon_sha256":"4f487636a46051100cf41d93cd415a0f9a65654af4e82e8550ef1531fba0ea38"},"schema_version":"1.0","source":{"id":"2503.15784","kind":"arxiv","version":2}},"canonical_sha256":"c5b31742771f3e36e7012d27d792f3dc819178fc5485e1fe14ba0657be5ec5cf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c5b31742771f3e36e7012d27d792f3dc819178fc5485e1fe14ba0657be5ec5cf","first_computed_at":"2026-07-05T11:31:44.351118Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:31:44.351118Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+nDUNYtHEHfu6ROLlw9Tz4+BQrnZhL3mnGHqZGYLoayTTKiFUItuV8kxapePw40J2iRl0/C4uUHZ0EOW/M6CCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:31:44.351646Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.15784","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:76d061afdb0972fae2a7ca4f7f5004843a487ef38a31b0a154bf4bee3f9722eb","sha256:23ee88de367076630d72dc53e5bbd7b7e2241299dba798ba0c6f720a876a9192"],"state_sha256":"47e2ef5d156cb91ad131798a3919b16781549a7605c7b0ed100edf6a3af8b35f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Zn0HGPlgwoQAT8fKNc/fP5Cg0vPH4IrFq0eDJcTTP+ewYXUctGjTxf0UB/6poBtPZyqyVKDPIowA2/CIEVVlDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T18:43:50.806347Z","bundle_sha256":"6ba31fdec05d83d07af6b185e874fb74092c4cb0d5668a4e1318d4634cd02a18"}}