{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:V5VOWTROSYMFNXPKWZRO5GTKY5","short_pith_number":"pith:V5VOWTRO","canonical_record":{"source":{"id":"2204.09817","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-04-21T00:04:35Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"881e892a9ea725d3bc299cae7d5d6f4d3b4a311c3b13943d293fe0a786e98f64","abstract_canon_sha256":"e76d144c8d9d7e17249d2e60672e46cf301fa82a170d544938488493fe084842"},"schema_version":"1.0"},"canonical_sha256":"af6aeb4e2e961856ddeab662ee9a6ac74bd09f5c86fd7b31f45da3c007334153","source":{"kind":"arxiv","id":"2204.09817","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2204.09817","created_at":"2026-07-05T05:23:08Z"},{"alias_kind":"arxiv_version","alias_value":"2204.09817v4","created_at":"2026-07-05T05:23:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.09817","created_at":"2026-07-05T05:23:08Z"},{"alias_kind":"pith_short_12","alias_value":"V5VOWTROSYMF","created_at":"2026-07-05T05:23:08Z"},{"alias_kind":"pith_short_16","alias_value":"V5VOWTROSYMFNXPK","created_at":"2026-07-05T05:23:08Z"},{"alias_kind":"pith_short_8","alias_value":"V5VOWTRO","created_at":"2026-07-05T05:23:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:V5VOWTROSYMFNXPKWZRO5GTKY5","target":"record","payload":{"canonical_record":{"source":{"id":"2204.09817","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-04-21T00:04:35Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"881e892a9ea725d3bc299cae7d5d6f4d3b4a311c3b13943d293fe0a786e98f64","abstract_canon_sha256":"e76d144c8d9d7e17249d2e60672e46cf301fa82a170d544938488493fe084842"},"schema_version":"1.0"},"canonical_sha256":"af6aeb4e2e961856ddeab662ee9a6ac74bd09f5c86fd7b31f45da3c007334153","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:23:08.827191Z","signature_b64":"HQKboJwPpry9O5UPWoVYhPUVDSvhyjZxOZoIbhg+Ldd7KpEInymtUCAOMo/d9JpHyt7s4kw4QM5KtJ4tQ9MqDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"af6aeb4e2e961856ddeab662ee9a6ac74bd09f5c86fd7b31f45da3c007334153","last_reissued_at":"2026-07-05T05:23:08.826675Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:23:08.826675Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2204.09817","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:23:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"In60igb7XC3J1inSAMilYAXPo8jCkDFXstOZFP9YJWFlTJlSRBH8p+Gi9o0qPeX9fptzyVoJM59IgLONFtTCDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-24T04:25:41.426287Z"},"content_sha256":"ebeca951dd234db3fb6896b869415c8ad32c053d095243bfc40f1763b8be5917","schema_version":"1.0","event_id":"sha256:ebeca951dd234db3fb6896b869415c8ad32c053d095243bfc40f1763b8be5917"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:V5VOWTROSYMFNXPKWZRO5GTKY5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Making the Most of Text Semantics to Improve Biomedical Vision--Language Processing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Aditya Nori, Anton Schwaighofer, Benedikt Boecking, Daniel C. Castro, Hoifung Poon, Javier Alvarez-Valle, Maria Wetscherek, Naoto Usuyama, Ozan Oktay, Shruthi Bannur, Stephanie Hyland, Tristan Naumann","submitted_at":"2022-04-21T00:04:35Z","abstract_excerpt":"Multi-modal data abounds in biomedicine, such as radiology images and reports. Interpreting this data at scale is essential for improving clinical care and accelerating clinical research. Biomedical text with its complex semantics poses additional challenges in vision--language modelling compared to the general domain, and previous work has used insufficiently adapted models that lack domain-specific language understanding. In this paper, we show that principled textual semantic modelling can substantially improve contrastive learning in self-supervised vision--language processing. We release "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.09817","kind":"arxiv","version":4},"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/2204.09817/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":"2026-07-05T05:23:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vgBzQH9cExKqmUU7PS69w+nq08SML0CpvHsgTp7kUedER3945pab8AD4JjjPzqgWiIs8rJVdo44VkFthR5wzAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-24T04:25:41.426684Z"},"content_sha256":"af277bc2efd56744b21a9c4215cf93ce29ac0d5ebd4951781c59a6f6dd763572","schema_version":"1.0","event_id":"sha256:af277bc2efd56744b21a9c4215cf93ce29ac0d5ebd4951781c59a6f6dd763572"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/V5VOWTROSYMFNXPKWZRO5GTKY5/bundle.json","state_url":"https://pith.science/pith/V5VOWTROSYMFNXPKWZRO5GTKY5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/V5VOWTROSYMFNXPKWZRO5GTKY5/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":"2026-07-24T04:25:41Z","links":{"resolver":"https://pith.science/pith/V5VOWTROSYMFNXPKWZRO5GTKY5","bundle":"https://pith.science/pith/V5VOWTROSYMFNXPKWZRO5GTKY5/bundle.json","state":"https://pith.science/pith/V5VOWTROSYMFNXPKWZRO5GTKY5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/V5VOWTROSYMFNXPKWZRO5GTKY5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:V5VOWTROSYMFNXPKWZRO5GTKY5","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":"e76d144c8d9d7e17249d2e60672e46cf301fa82a170d544938488493fe084842","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-04-21T00:04:35Z","title_canon_sha256":"881e892a9ea725d3bc299cae7d5d6f4d3b4a311c3b13943d293fe0a786e98f64"},"schema_version":"1.0","source":{"id":"2204.09817","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2204.09817","created_at":"2026-07-05T05:23:08Z"},{"alias_kind":"arxiv_version","alias_value":"2204.09817v4","created_at":"2026-07-05T05:23:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.09817","created_at":"2026-07-05T05:23:08Z"},{"alias_kind":"pith_short_12","alias_value":"V5VOWTROSYMF","created_at":"2026-07-05T05:23:08Z"},{"alias_kind":"pith_short_16","alias_value":"V5VOWTROSYMFNXPK","created_at":"2026-07-05T05:23:08Z"},{"alias_kind":"pith_short_8","alias_value":"V5VOWTRO","created_at":"2026-07-05T05:23:08Z"}],"graph_snapshots":[{"event_id":"sha256:af277bc2efd56744b21a9c4215cf93ce29ac0d5ebd4951781c59a6f6dd763572","target":"graph","created_at":"2026-07-05T05:23:08Z","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/2204.09817/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multi-modal data abounds in biomedicine, such as radiology images and reports. Interpreting this data at scale is essential for improving clinical care and accelerating clinical research. Biomedical text with its complex semantics poses additional challenges in vision--language modelling compared to the general domain, and previous work has used insufficiently adapted models that lack domain-specific language understanding. In this paper, we show that principled textual semantic modelling can substantially improve contrastive learning in self-supervised vision--language processing. We release ","authors_text":"Aditya Nori, Anton Schwaighofer, Benedikt Boecking, Daniel C. Castro, Hoifung Poon, Javier Alvarez-Valle, Maria Wetscherek, Naoto Usuyama, Ozan Oktay, Shruthi Bannur, Stephanie Hyland, Tristan Naumann","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-04-21T00:04:35Z","title":"Making the Most of Text Semantics to Improve Biomedical Vision--Language Processing"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.09817","kind":"arxiv","version":4},"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:ebeca951dd234db3fb6896b869415c8ad32c053d095243bfc40f1763b8be5917","target":"record","created_at":"2026-07-05T05:23:08Z","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":"e76d144c8d9d7e17249d2e60672e46cf301fa82a170d544938488493fe084842","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-04-21T00:04:35Z","title_canon_sha256":"881e892a9ea725d3bc299cae7d5d6f4d3b4a311c3b13943d293fe0a786e98f64"},"schema_version":"1.0","source":{"id":"2204.09817","kind":"arxiv","version":4}},"canonical_sha256":"af6aeb4e2e961856ddeab662ee9a6ac74bd09f5c86fd7b31f45da3c007334153","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"af6aeb4e2e961856ddeab662ee9a6ac74bd09f5c86fd7b31f45da3c007334153","first_computed_at":"2026-07-05T05:23:08.826675Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:23:08.826675Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HQKboJwPpry9O5UPWoVYhPUVDSvhyjZxOZoIbhg+Ldd7KpEInymtUCAOMo/d9JpHyt7s4kw4QM5KtJ4tQ9MqDw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:23:08.827191Z","signed_message":"canonical_sha256_bytes"},"source_id":"2204.09817","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ebeca951dd234db3fb6896b869415c8ad32c053d095243bfc40f1763b8be5917","sha256:af277bc2efd56744b21a9c4215cf93ce29ac0d5ebd4951781c59a6f6dd763572"],"state_sha256":"a799981848ade9d01fbc7ae7f068d03dcacfa5d90d61512baedb4df3549c3af7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XonZGoxL3HqfdSAe5ELww0L1xPf8YL1e3qzKC7JLmNNSIOpdXqmnInQSqu+FkGQoBtxMgn0kuZsiLsE5a7VsAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-24T04:25:41.429229Z","bundle_sha256":"503d0a2482ed10ecd2bb7f56819087c8e5b48b03cbaaf0a5e8b9f59e8a88e9d7"}}