{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:7S6MMYEYJCU43SB5YBTYVGZB6L","short_pith_number":"pith:7S6MMYEY","canonical_record":{"source":{"id":"2503.22727","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-26T05:56:46Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"c88dcfc021e7c09f88b7f4cd0581b759742974a5d98b8820d47668392d2d4c5a","abstract_canon_sha256":"22574e9b8f2642ba9bdce9160d2ada847615928bea9d053a9441de9213f29443"},"schema_version":"1.0"},"canonical_sha256":"fcbcc6609848a9cdc83dc0678a9b21f2ce284e5d442c39f213d5cb0a3092bfa2","source":{"kind":"arxiv","id":"2503.22727","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.22727","created_at":"2026-07-05T10:43:06Z"},{"alias_kind":"arxiv_version","alias_value":"2503.22727v2","created_at":"2026-07-05T10:43:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.22727","created_at":"2026-07-05T10:43:06Z"},{"alias_kind":"pith_short_12","alias_value":"7S6MMYEYJCU4","created_at":"2026-07-05T10:43:06Z"},{"alias_kind":"pith_short_16","alias_value":"7S6MMYEYJCU43SB5","created_at":"2026-07-05T10:43:06Z"},{"alias_kind":"pith_short_8","alias_value":"7S6MMYEY","created_at":"2026-07-05T10:43:06Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:7S6MMYEYJCU43SB5YBTYVGZB6L","target":"record","payload":{"canonical_record":{"source":{"id":"2503.22727","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-26T05:56:46Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"c88dcfc021e7c09f88b7f4cd0581b759742974a5d98b8820d47668392d2d4c5a","abstract_canon_sha256":"22574e9b8f2642ba9bdce9160d2ada847615928bea9d053a9441de9213f29443"},"schema_version":"1.0"},"canonical_sha256":"fcbcc6609848a9cdc83dc0678a9b21f2ce284e5d442c39f213d5cb0a3092bfa2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:43:06.880225Z","signature_b64":"8SO8YoyPyCRXp1QwMnP5z3UJhR22q0fQdJiNQi90ypYq1xxL82hVDE2dqRw5GpBifEefE2ZdPQTBxzBXUb9DBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fcbcc6609848a9cdc83dc0678a9b21f2ce284e5d442c39f213d5cb0a3092bfa2","last_reissued_at":"2026-07-05T10:43:06.879618Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:43:06.879618Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2503.22727","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":"2026-07-05T10:43:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PwMeYgPOiP1SZ/I0ePJ0g9PApCNAigzqIQ8aU2zJcpGeWjtncZfa3VHmcMMzVWFKA8d5uwaP9avzkLIc2RAyCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T04:53:37.339809Z"},"content_sha256":"d9fbd2619a5a474fdff29271d09d35b03dbc72d864a56886d7b9c1621cff2155","schema_version":"1.0","event_id":"sha256:d9fbd2619a5a474fdff29271d09d35b03dbc72d864a56886d7b9c1621cff2155"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:7S6MMYEYJCU43SB5YBTYVGZB6L","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Large-Scale Vision-Language Dataset Derived from Open Scientific Literature to Advance Biomedical Generalist AI","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Alejandro Lozano, Alfred Seunghoon Song, Anita Rau, Austin Wolfgang Katzer, Chiang Chia-Chun, Christopher Polzak, Collin Chiu, Ivan Lopez, James Burgess, Jeffrey Gu, Jeffrey J. Nirschl, Josiah Aklilu, Liangyu Chen, Min Woo Sun, Orr Zohar, Robert Tibshirani, Serena Yeung-Levy, Xiaohan Wang, Yuhui Zhang","submitted_at":"2025-03-26T05:56:46Z","abstract_excerpt":"Despite the excitement behind biomedical artificial intelligence (AI), access to high-quality, diverse, and large-scale data - the foundation for modern AI systems - is still a bottleneck to unlocking its full potential. To address this gap, we introduce Biomedica, an open-source dataset derived from the PubMed Central Open Access subset, containing over 6 million scientific articles and 24 million image-text pairs, along with 27 metadata fields (including expert human annotations). To overcome the challenges of accessing our large-scale dataset, we provide scalable streaming and search APIs t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.22727","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/2503.22727/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":"2026-07-05T10:43:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zmkttjjfYLBqlX7MYvK1ACinrNCUN5wr8KVBe1zElvxKZoqJaMYAaswngap2fvibtSPS4WlX/7IDNjD34oyxAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T04:53:37.340207Z"},"content_sha256":"f456610ef14b7331f44103814aafd9f3a1c3efac92a1dde8fdf48aa1df382c16","schema_version":"1.0","event_id":"sha256:f456610ef14b7331f44103814aafd9f3a1c3efac92a1dde8fdf48aa1df382c16"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7S6MMYEYJCU43SB5YBTYVGZB6L/bundle.json","state_url":"https://pith.science/pith/7S6MMYEYJCU43SB5YBTYVGZB6L/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7S6MMYEYJCU43SB5YBTYVGZB6L/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":"2026-07-09T04:53:37Z","links":{"resolver":"https://pith.science/pith/7S6MMYEYJCU43SB5YBTYVGZB6L","bundle":"https://pith.science/pith/7S6MMYEYJCU43SB5YBTYVGZB6L/bundle.json","state":"https://pith.science/pith/7S6MMYEYJCU43SB5YBTYVGZB6L/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7S6MMYEYJCU43SB5YBTYVGZB6L/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:7S6MMYEYJCU43SB5YBTYVGZB6L","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":"22574e9b8f2642ba9bdce9160d2ada847615928bea9d053a9441de9213f29443","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-26T05:56:46Z","title_canon_sha256":"c88dcfc021e7c09f88b7f4cd0581b759742974a5d98b8820d47668392d2d4c5a"},"schema_version":"1.0","source":{"id":"2503.22727","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.22727","created_at":"2026-07-05T10:43:06Z"},{"alias_kind":"arxiv_version","alias_value":"2503.22727v2","created_at":"2026-07-05T10:43:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.22727","created_at":"2026-07-05T10:43:06Z"},{"alias_kind":"pith_short_12","alias_value":"7S6MMYEYJCU4","created_at":"2026-07-05T10:43:06Z"},{"alias_kind":"pith_short_16","alias_value":"7S6MMYEYJCU43SB5","created_at":"2026-07-05T10:43:06Z"},{"alias_kind":"pith_short_8","alias_value":"7S6MMYEY","created_at":"2026-07-05T10:43:06Z"}],"graph_snapshots":[{"event_id":"sha256:f456610ef14b7331f44103814aafd9f3a1c3efac92a1dde8fdf48aa1df382c16","target":"graph","created_at":"2026-07-05T10:43:06Z","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/2503.22727/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite the excitement behind biomedical artificial intelligence (AI), access to high-quality, diverse, and large-scale data - the foundation for modern AI systems - is still a bottleneck to unlocking its full potential. To address this gap, we introduce Biomedica, an open-source dataset derived from the PubMed Central Open Access subset, containing over 6 million scientific articles and 24 million image-text pairs, along with 27 metadata fields (including expert human annotations). To overcome the challenges of accessing our large-scale dataset, we provide scalable streaming and search APIs t","authors_text":"Alejandro Lozano, Alfred Seunghoon Song, Anita Rau, Austin Wolfgang Katzer, Chiang Chia-Chun, Christopher Polzak, Collin Chiu, Ivan Lopez, James Burgess, Jeffrey Gu, Jeffrey J. Nirschl, Josiah Aklilu, Liangyu Chen, Min Woo Sun, Orr Zohar, Robert Tibshirani, Serena Yeung-Levy, Xiaohan Wang, Yuhui Zhang","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-26T05:56:46Z","title":"A Large-Scale Vision-Language Dataset Derived from Open Scientific Literature to Advance Biomedical Generalist AI"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.22727","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:d9fbd2619a5a474fdff29271d09d35b03dbc72d864a56886d7b9c1621cff2155","target":"record","created_at":"2026-07-05T10:43:06Z","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":"22574e9b8f2642ba9bdce9160d2ada847615928bea9d053a9441de9213f29443","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-26T05:56:46Z","title_canon_sha256":"c88dcfc021e7c09f88b7f4cd0581b759742974a5d98b8820d47668392d2d4c5a"},"schema_version":"1.0","source":{"id":"2503.22727","kind":"arxiv","version":2}},"canonical_sha256":"fcbcc6609848a9cdc83dc0678a9b21f2ce284e5d442c39f213d5cb0a3092bfa2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fcbcc6609848a9cdc83dc0678a9b21f2ce284e5d442c39f213d5cb0a3092bfa2","first_computed_at":"2026-07-05T10:43:06.879618Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:43:06.879618Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8SO8YoyPyCRXp1QwMnP5z3UJhR22q0fQdJiNQi90ypYq1xxL82hVDE2dqRw5GpBifEefE2ZdPQTBxzBXUb9DBg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:43:06.880225Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.22727","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d9fbd2619a5a474fdff29271d09d35b03dbc72d864a56886d7b9c1621cff2155","sha256:f456610ef14b7331f44103814aafd9f3a1c3efac92a1dde8fdf48aa1df382c16"],"state_sha256":"0dd37f655935e081a9c0b1e6546a58064712c23ac76afe345958ab70c229af73"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1rOombCrMIMSWtQ2bWWFR67p7ef6TDjldFlR2FjFXEKO9AU8BJDJPWuZDSQY94Rh0lu1NNcI2c/hOtMkWVJsDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-09T04:53:37.342557Z","bundle_sha256":"9f33f6493839dc60b2baa629d677f50937e9789601c3509d528834fa2ecded0a"}}