{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:2CHUESDIPZYPCMLZMAXQ32HFI2","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":"6e47ad1babc1aefe70fff813522f22fd02a67b193ed58b3dba548781df4ebc18","cross_cats_sorted":["cs.CL","cs.LG","cs.MM"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-03-13T16:13:16Z","title_canon_sha256":"2948edaab19b4607eab65f9ef1ce4d318d2afa22fd0654bd24048bebba38dcea"},"schema_version":"1.0","source":{"id":"2303.07240","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.07240","created_at":"2026-07-05T05:50:34Z"},{"alias_kind":"arxiv_version","alias_value":"2303.07240v1","created_at":"2026-07-05T05:50:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.07240","created_at":"2026-07-05T05:50:34Z"},{"alias_kind":"pith_short_12","alias_value":"2CHUESDIPZYP","created_at":"2026-07-05T05:50:34Z"},{"alias_kind":"pith_short_16","alias_value":"2CHUESDIPZYPCMLZ","created_at":"2026-07-05T05:50:34Z"},{"alias_kind":"pith_short_8","alias_value":"2CHUESDI","created_at":"2026-07-05T05:50:34Z"}],"graph_snapshots":[{"event_id":"sha256:32db781b5399faf3e6453429182f29978e39e90f8ce90bd7437885853f43b32b","target":"graph","created_at":"2026-07-05T05:50:34Z","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/2303.07240/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Foundation models trained on large-scale dataset gain a recent surge in CV and NLP. In contrast, development in biomedical domain lags far behind due to data scarcity. To address this issue, we build and release PMC-OA, a biomedical dataset with 1.6M image-caption pairs collected from PubMedCentral's OpenAccess subset, which is 8 times larger than before. PMC-OA covers diverse modalities or diseases, with majority of the image-caption samples aligned at finer-grained level, i.e., subfigure and subcaption. While pretraining a CLIP-style model on PMC-OA, our model named PMC-CLIP achieves state-o","authors_text":"Chaoyi Wu, Weidi Xie, Weixiong Lin, Xiaoman Zhang, Yanfeng Wang, Ya Zhang, Ziheng Zhao","cross_cats":["cs.CL","cs.LG","cs.MM"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-03-13T16:13:16Z","title":"PMC-CLIP: Contrastive Language-Image Pre-training using Biomedical Documents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.07240","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:f6367e1f25a73fbf2c3ed66b6f4779b3b946a9614a15b20336154e8d937417f6","target":"record","created_at":"2026-07-05T05:50:34Z","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":"6e47ad1babc1aefe70fff813522f22fd02a67b193ed58b3dba548781df4ebc18","cross_cats_sorted":["cs.CL","cs.LG","cs.MM"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-03-13T16:13:16Z","title_canon_sha256":"2948edaab19b4607eab65f9ef1ce4d318d2afa22fd0654bd24048bebba38dcea"},"schema_version":"1.0","source":{"id":"2303.07240","kind":"arxiv","version":1}},"canonical_sha256":"d08f4248687e70f13179602f0de8e546b314005ea91e49a265dc1853e39eb357","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d08f4248687e70f13179602f0de8e546b314005ea91e49a265dc1853e39eb357","first_computed_at":"2026-07-05T05:50:34.142535Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:50:34.142535Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QBoibWo2QC05hThg+u8YcGN82kmEV7nxjs1jn4aG8iyagTN7rWmw6ah6jbh7MNx8zolXNeiWpOkzvwa6CSJVDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:50:34.142968Z","signed_message":"canonical_sha256_bytes"},"source_id":"2303.07240","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f6367e1f25a73fbf2c3ed66b6f4779b3b946a9614a15b20336154e8d937417f6","sha256:32db781b5399faf3e6453429182f29978e39e90f8ce90bd7437885853f43b32b"],"state_sha256":"5406f14646775d2eb4148dcae67a603cbb0c55c2529ed46c9b709a5b8a5d02d9"}