{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:5ZORCNHPFT3NPDNYFXD37LOMV2","short_pith_number":"pith:5ZORCNHP","canonical_record":{"source":{"id":"2503.01019","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-02T21:09:32Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f6fad84db03216b5b596edb3dc017d0135e204428b7c6c10e3af29a77b0fbf17","abstract_canon_sha256":"8d51ce44be87257cfd51ce4f95171f0fe964a49d055de1b23e284cca45b28328"},"schema_version":"1.0"},"canonical_sha256":"ee5d1134ef2cf6d78db82dc7bfadccae8316daec2b02acb331937e6955c3a1f8","source":{"kind":"arxiv","id":"2503.01019","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.01019","created_at":"2026-07-05T10:51:34Z"},{"alias_kind":"arxiv_version","alias_value":"2503.01019v3","created_at":"2026-07-05T10:51:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.01019","created_at":"2026-07-05T10:51:34Z"},{"alias_kind":"pith_short_12","alias_value":"5ZORCNHPFT3N","created_at":"2026-07-05T10:51:34Z"},{"alias_kind":"pith_short_16","alias_value":"5ZORCNHPFT3NPDNY","created_at":"2026-07-05T10:51:34Z"},{"alias_kind":"pith_short_8","alias_value":"5ZORCNHP","created_at":"2026-07-05T10:51:34Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:5ZORCNHPFT3NPDNYFXD37LOMV2","target":"record","payload":{"canonical_record":{"source":{"id":"2503.01019","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-02T21:09:32Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f6fad84db03216b5b596edb3dc017d0135e204428b7c6c10e3af29a77b0fbf17","abstract_canon_sha256":"8d51ce44be87257cfd51ce4f95171f0fe964a49d055de1b23e284cca45b28328"},"schema_version":"1.0"},"canonical_sha256":"ee5d1134ef2cf6d78db82dc7bfadccae8316daec2b02acb331937e6955c3a1f8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:51:34.124988Z","signature_b64":"P7DzJP5l5/v7OEndQ5vYeEie1O+F6u6dZoBWSd+LxIVxFcIpkLYk/fGCGEAECmJQvNJ1ZIt+1+Q6Cu20JE3AAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ee5d1134ef2cf6d78db82dc7bfadccae8316daec2b02acb331937e6955c3a1f8","last_reissued_at":"2026-07-05T10:51:34.124492Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:51:34.124492Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2503.01019","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:51:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"49E3+9bHvXHxgB7RLpSh+j31f3cRPzMqDcMnl8Dx9saxg651Upaql64YKUu5sdstRz8eU2KVTzV+qJ+OnIgpCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T06:52:37.903488Z"},"content_sha256":"13ed0faed731fe9160fead690ad57c5571fc9edc30011a2aacbe6cfb96ef77eb","schema_version":"1.0","event_id":"sha256:13ed0faed731fe9160fead690ad57c5571fc9edc30011a2aacbe6cfb96ef77eb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:5ZORCNHPFT3NPDNYFXD37LOMV2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MedUnifier: Unifying Vision-and-Language Pre-training on Medical Data with Vision Generation Task using Discrete Visual Representations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Si Yong Yeo, Xulei Yang, Yang Yu, Yucheng Chen, Ziyang Zhang","submitted_at":"2025-03-02T21:09:32Z","abstract_excerpt":"Despite significant progress in Vision-Language Pre-training (VLP), current approaches predominantly emphasize feature extraction and cross-modal comprehension, with limited attention to generating or transforming visual content. This gap hinders the model's ability to synthesize coherent and novel visual representations from textual prompts, thereby reducing the effectiveness of multi-modal learning. In this work, we propose MedUnifier, a unified VLP framework tailored for medical data. MedUnifier seamlessly integrates text-grounded image generation capabilities with multi-modal learning stra"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.01019","kind":"arxiv","version":3},"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/2503.01019/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":"2026-07-05T10:51:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dlq+TRp1/cWdXWG/Ex9WA+nrPoMhVLcB2vJyoHvB183e4NrKE8BxS+QDrviSdUtHbapmGyPR96FLkPtjiEnRBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T06:52:37.903995Z"},"content_sha256":"397f445e4f66e7c43083ddbab69eed6a358ccba508ebdfe9d322a9682a68db92","schema_version":"1.0","event_id":"sha256:397f445e4f66e7c43083ddbab69eed6a358ccba508ebdfe9d322a9682a68db92"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5ZORCNHPFT3NPDNYFXD37LOMV2/bundle.json","state_url":"https://pith.science/pith/5ZORCNHPFT3NPDNYFXD37LOMV2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5ZORCNHPFT3NPDNYFXD37LOMV2/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":"2026-08-16T06:52:37Z","links":{"resolver":"https://pith.science/pith/5ZORCNHPFT3NPDNYFXD37LOMV2","bundle":"https://pith.science/pith/5ZORCNHPFT3NPDNYFXD37LOMV2/bundle.json","state":"https://pith.science/pith/5ZORCNHPFT3NPDNYFXD37LOMV2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5ZORCNHPFT3NPDNYFXD37LOMV2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:5ZORCNHPFT3NPDNYFXD37LOMV2","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":"8d51ce44be87257cfd51ce4f95171f0fe964a49d055de1b23e284cca45b28328","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-02T21:09:32Z","title_canon_sha256":"f6fad84db03216b5b596edb3dc017d0135e204428b7c6c10e3af29a77b0fbf17"},"schema_version":"1.0","source":{"id":"2503.01019","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.01019","created_at":"2026-07-05T10:51:34Z"},{"alias_kind":"arxiv_version","alias_value":"2503.01019v3","created_at":"2026-07-05T10:51:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.01019","created_at":"2026-07-05T10:51:34Z"},{"alias_kind":"pith_short_12","alias_value":"5ZORCNHPFT3N","created_at":"2026-07-05T10:51:34Z"},{"alias_kind":"pith_short_16","alias_value":"5ZORCNHPFT3NPDNY","created_at":"2026-07-05T10:51:34Z"},{"alias_kind":"pith_short_8","alias_value":"5ZORCNHP","created_at":"2026-07-05T10:51:34Z"}],"graph_snapshots":[{"event_id":"sha256:397f445e4f66e7c43083ddbab69eed6a358ccba508ebdfe9d322a9682a68db92","target":"graph","created_at":"2026-07-05T10:51:34Z","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/2503.01019/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite significant progress in Vision-Language Pre-training (VLP), current approaches predominantly emphasize feature extraction and cross-modal comprehension, with limited attention to generating or transforming visual content. This gap hinders the model's ability to synthesize coherent and novel visual representations from textual prompts, thereby reducing the effectiveness of multi-modal learning. In this work, we propose MedUnifier, a unified VLP framework tailored for medical data. MedUnifier seamlessly integrates text-grounded image generation capabilities with multi-modal learning stra","authors_text":"Si Yong Yeo, Xulei Yang, Yang Yu, Yucheng Chen, Ziyang Zhang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-02T21:09:32Z","title":"MedUnifier: Unifying Vision-and-Language Pre-training on Medical Data with Vision Generation Task using Discrete Visual Representations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.01019","kind":"arxiv","version":3},"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":"sha256:13ed0faed731fe9160fead690ad57c5571fc9edc30011a2aacbe6cfb96ef77eb","target":"record","created_at":"2026-07-05T10:51:34Z","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":"8d51ce44be87257cfd51ce4f95171f0fe964a49d055de1b23e284cca45b28328","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-02T21:09:32Z","title_canon_sha256":"f6fad84db03216b5b596edb3dc017d0135e204428b7c6c10e3af29a77b0fbf17"},"schema_version":"1.0","source":{"id":"2503.01019","kind":"arxiv","version":3}},"canonical_sha256":"ee5d1134ef2cf6d78db82dc7bfadccae8316daec2b02acb331937e6955c3a1f8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ee5d1134ef2cf6d78db82dc7bfadccae8316daec2b02acb331937e6955c3a1f8","first_computed_at":"2026-07-05T10:51:34.124492Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:51:34.124492Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"P7DzJP5l5/v7OEndQ5vYeEie1O+F6u6dZoBWSd+LxIVxFcIpkLYk/fGCGEAECmJQvNJ1ZIt+1+Q6Cu20JE3AAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:51:34.124988Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.01019","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:13ed0faed731fe9160fead690ad57c5571fc9edc30011a2aacbe6cfb96ef77eb","sha256:397f445e4f66e7c43083ddbab69eed6a358ccba508ebdfe9d322a9682a68db92"],"state_sha256":"b3fd8ae5712f69507abed0dde813916f71b707201c9ac1290d7e1964bef092c7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Dvw0nu2RDc+lDmF7GLGv7EBQTmgQeEeRPK2E+by+Dv7qJCoh/LPJ2cZ5Et6f1NWKFg4e5VJSkqZxtnzmpELHDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-16T06:52:37.909473Z","bundle_sha256":"a4836facc5b3ced0cfdbe2202cb8b7f87bf878a21db450602dc59128a99779ca"}}