{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:ZIZJYIHIKUVZKXWNG5D5X4MOZM","short_pith_number":"pith:ZIZJYIHI","canonical_record":{"source":{"id":"2009.01523","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2020-09-03T09:00:47Z","cross_cats_sorted":[],"title_canon_sha256":"6539d76af902569cfa763c869077e8f94d3b368692fccd0299a4dfbf332655c4","abstract_canon_sha256":"9f1704f9caf60a0cc776b0c10206668325c0f85de774f5b04a685489db751df9"},"schema_version":"1.0"},"canonical_sha256":"ca329c20e8552b955ecd3747dbf18ecb327adfccf8ddae263c0fe9e8f45f914d","source":{"kind":"arxiv","id":"2009.01523","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2009.01523","created_at":"2026-07-05T01:32:50Z"},{"alias_kind":"arxiv_version","alias_value":"2009.01523v1","created_at":"2026-07-05T01:32:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2009.01523","created_at":"2026-07-05T01:32:50Z"},{"alias_kind":"pith_short_12","alias_value":"ZIZJYIHIKUVZ","created_at":"2026-07-05T01:32:50Z"},{"alias_kind":"pith_short_16","alias_value":"ZIZJYIHIKUVZKXWN","created_at":"2026-07-05T01:32:50Z"},{"alias_kind":"pith_short_8","alias_value":"ZIZJYIHI","created_at":"2026-07-05T01:32:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:ZIZJYIHIKUVZKXWNG5D5X4MOZM","target":"record","payload":{"canonical_record":{"source":{"id":"2009.01523","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2020-09-03T09:00:47Z","cross_cats_sorted":[],"title_canon_sha256":"6539d76af902569cfa763c869077e8f94d3b368692fccd0299a4dfbf332655c4","abstract_canon_sha256":"9f1704f9caf60a0cc776b0c10206668325c0f85de774f5b04a685489db751df9"},"schema_version":"1.0"},"canonical_sha256":"ca329c20e8552b955ecd3747dbf18ecb327adfccf8ddae263c0fe9e8f45f914d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:32:50.338398Z","signature_b64":"QgY/kADohXDp6G70A9shC9HUvJD4RuEv1495F7R4p2GdJjnLxEc7vAwjAy2YOrg7HK6pIA2N1hRFvSPVxvjHAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ca329c20e8552b955ecd3747dbf18ecb327adfccf8ddae263c0fe9e8f45f914d","last_reissued_at":"2026-07-05T01:32:50.337950Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:32:50.337950Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2009.01523","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:32:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZvGSdJc5scLet5T4eFodj2ctMS6oW8pQLPfhqP/JzRM/9+EbRxRffck0L7bSM0WbkvSKVq9S4VnePe8JYo9vAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T12:11:22.616241Z"},"content_sha256":"faee5f4ae78d5d9c91e901f2ec8d3f533473de72e5bb4cab2decab786e9c25fb","schema_version":"1.0","event_id":"sha256:faee5f4ae78d5d9c91e901f2ec8d3f533473de72e5bb4cab2decab786e9c25fb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:ZIZJYIHIKUVZKXWNG5D5X4MOZM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Comparison of Pre-trained Vision-and-Language Models for Multimodal Representation Learning across Medical Images and Reports","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hanyin Wang, Yikuan Li, Yuan Luo","submitted_at":"2020-09-03T09:00:47Z","abstract_excerpt":"Joint image-text embedding extracted from medical images and associated contextual reports is the bedrock for most biomedical vision-and-language (V+L) tasks, including medical visual question answering, clinical image-text retrieval, clinical report auto-generation. In this study, we adopt four pre-trained V+L models: LXMERT, VisualBERT, UNIER and PixelBERT to learn multimodal representation from MIMIC-CXR radiographs and associated reports. The extrinsic evaluation on OpenI dataset shows that in comparison to the pioneering CNN-RNN model, the joint embedding learned by pre-trained V+L models"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2009.01523","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/2009.01523/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":"2026-07-05T01:32:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aOSL8z01V6qOup05wUI8hn5QNEanVhbD+rzAhAQJNNxaaMSwON0nwon2XpeVUOsJyvR90SG2PPwM0u2GlbgrDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T12:11:22.616736Z"},"content_sha256":"d1cf134e3fbad834eb1a1869c3c886b5a86aaf31128686497755080f3338d9e4","schema_version":"1.0","event_id":"sha256:d1cf134e3fbad834eb1a1869c3c886b5a86aaf31128686497755080f3338d9e4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZIZJYIHIKUVZKXWNG5D5X4MOZM/bundle.json","state_url":"https://pith.science/pith/ZIZJYIHIKUVZKXWNG5D5X4MOZM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZIZJYIHIKUVZKXWNG5D5X4MOZM/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":"2026-08-23T12:11:22Z","links":{"resolver":"https://pith.science/pith/ZIZJYIHIKUVZKXWNG5D5X4MOZM","bundle":"https://pith.science/pith/ZIZJYIHIKUVZKXWNG5D5X4MOZM/bundle.json","state":"https://pith.science/pith/ZIZJYIHIKUVZKXWNG5D5X4MOZM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZIZJYIHIKUVZKXWNG5D5X4MOZM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:ZIZJYIHIKUVZKXWNG5D5X4MOZM","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":"9f1704f9caf60a0cc776b0c10206668325c0f85de774f5b04a685489db751df9","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2020-09-03T09:00:47Z","title_canon_sha256":"6539d76af902569cfa763c869077e8f94d3b368692fccd0299a4dfbf332655c4"},"schema_version":"1.0","source":{"id":"2009.01523","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2009.01523","created_at":"2026-07-05T01:32:50Z"},{"alias_kind":"arxiv_version","alias_value":"2009.01523v1","created_at":"2026-07-05T01:32:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2009.01523","created_at":"2026-07-05T01:32:50Z"},{"alias_kind":"pith_short_12","alias_value":"ZIZJYIHIKUVZ","created_at":"2026-07-05T01:32:50Z"},{"alias_kind":"pith_short_16","alias_value":"ZIZJYIHIKUVZKXWN","created_at":"2026-07-05T01:32:50Z"},{"alias_kind":"pith_short_8","alias_value":"ZIZJYIHI","created_at":"2026-07-05T01:32:50Z"}],"graph_snapshots":[{"event_id":"sha256:d1cf134e3fbad834eb1a1869c3c886b5a86aaf31128686497755080f3338d9e4","target":"graph","created_at":"2026-07-05T01:32:50Z","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/2009.01523/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Joint image-text embedding extracted from medical images and associated contextual reports is the bedrock for most biomedical vision-and-language (V+L) tasks, including medical visual question answering, clinical image-text retrieval, clinical report auto-generation. In this study, we adopt four pre-trained V+L models: LXMERT, VisualBERT, UNIER and PixelBERT to learn multimodal representation from MIMIC-CXR radiographs and associated reports. The extrinsic evaluation on OpenI dataset shows that in comparison to the pioneering CNN-RNN model, the joint embedding learned by pre-trained V+L models","authors_text":"Hanyin Wang, Yikuan Li, Yuan Luo","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2020-09-03T09:00:47Z","title":"A Comparison of Pre-trained Vision-and-Language Models for Multimodal Representation Learning across Medical Images and Reports"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2009.01523","kind":"arxiv","version":1},"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:faee5f4ae78d5d9c91e901f2ec8d3f533473de72e5bb4cab2decab786e9c25fb","target":"record","created_at":"2026-07-05T01:32:50Z","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":"9f1704f9caf60a0cc776b0c10206668325c0f85de774f5b04a685489db751df9","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2020-09-03T09:00:47Z","title_canon_sha256":"6539d76af902569cfa763c869077e8f94d3b368692fccd0299a4dfbf332655c4"},"schema_version":"1.0","source":{"id":"2009.01523","kind":"arxiv","version":1}},"canonical_sha256":"ca329c20e8552b955ecd3747dbf18ecb327adfccf8ddae263c0fe9e8f45f914d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ca329c20e8552b955ecd3747dbf18ecb327adfccf8ddae263c0fe9e8f45f914d","first_computed_at":"2026-07-05T01:32:50.337950Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:32:50.337950Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QgY/kADohXDp6G70A9shC9HUvJD4RuEv1495F7R4p2GdJjnLxEc7vAwjAy2YOrg7HK6pIA2N1hRFvSPVxvjHAg==","signature_status":"signed_v1","signed_at":"2026-07-05T01:32:50.338398Z","signed_message":"canonical_sha256_bytes"},"source_id":"2009.01523","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:faee5f4ae78d5d9c91e901f2ec8d3f533473de72e5bb4cab2decab786e9c25fb","sha256:d1cf134e3fbad834eb1a1869c3c886b5a86aaf31128686497755080f3338d9e4"],"state_sha256":"f8316ee5307785bda6dea9bb28955bdb761422752cdc598ef362bf3753366535"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sDHBj28C1L5nZYDtP8Kj8Ng12nGUEY/HLEcpzrfcKLeLzv3P71MqIpepC6XCIstaEwo9pLliNjLO3vM7xmcgDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-23T12:11:22.620476Z","bundle_sha256":"085f3cdc4d2bf0ff96be366404a82cdbb1ecc3f9f0b97cfe3b62ec760997c389"}}