{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:JNTEGOIINALWQBPXIWQAZKDJCS","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":"955fd2ffbc39fc1bc079c40cf7caf56e5bc9aed0e64eb45e16a5557a943b2ab6","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-01T22:25:19Z","title_canon_sha256":"b99982aba07ad0ef41a2b470bd4aa9a110c4769d09c0edcc24f98d036292febf"},"schema_version":"1.0","source":{"id":"2504.02874","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.02874","created_at":"2026-07-05T10:44:04Z"},{"alias_kind":"arxiv_version","alias_value":"2504.02874v1","created_at":"2026-07-05T10:44:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.02874","created_at":"2026-07-05T10:44:04Z"},{"alias_kind":"pith_short_12","alias_value":"JNTEGOIINALW","created_at":"2026-07-05T10:44:04Z"},{"alias_kind":"pith_short_16","alias_value":"JNTEGOIINALWQBPX","created_at":"2026-07-05T10:44:04Z"},{"alias_kind":"pith_short_8","alias_value":"JNTEGOII","created_at":"2026-07-05T10:44:04Z"}],"graph_snapshots":[{"event_id":"sha256:bdbbf8cb275d3eea4864ff020679ac6860d96623baca7405c42bd77983aa72cc","target":"graph","created_at":"2026-07-05T10:44:04Z","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/2504.02874/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The need for robust and diverse data sets to train clinical large language models (cLLMs) is critical given that currently available public repositories often prove too limited in size or scope for comprehensive medical use. While resources like PubMed provide foundational medical literature, they capture only a narrow range of formal publications and omit the broader medical discourse on the internet. To address these deficits, we introduce TheBlueScrubs-v1, a curated dataset of over 25 billion medical tokens - nearly three times larger than PubMed - drawn from a broad-scale internet corpus. ","authors_text":"Aakash Tripathi, Carlos Garcia, Danielle Bitterman, Ghulam Rasool, Gilmer Valdes, Issam El Naqa, Luis Felipe, Monique Shotande, Vivek Rudrapatna","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-01T22:25:19Z","title":"TheBlueScrubs-v1, a comprehensive curated medical dataset derived from the internet"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.02874","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:ca6ea8ac1dca5d1b212146fe6f301d222769f0f237103636ae7824bdff666b24","target":"record","created_at":"2026-07-05T10:44:04Z","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":"955fd2ffbc39fc1bc079c40cf7caf56e5bc9aed0e64eb45e16a5557a943b2ab6","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-01T22:25:19Z","title_canon_sha256":"b99982aba07ad0ef41a2b470bd4aa9a110c4769d09c0edcc24f98d036292febf"},"schema_version":"1.0","source":{"id":"2504.02874","kind":"arxiv","version":1}},"canonical_sha256":"4b6643390868176805f745a00ca869148ed6a2d51b5b9c2faad4908b353a281f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4b6643390868176805f745a00ca869148ed6a2d51b5b9c2faad4908b353a281f","first_computed_at":"2026-07-05T10:44:04.287202Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:44:04.287202Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3fm9vDwod07zq5pHw35I448XAseMVoBlppSRxdpAXFIWjisABd2mLK25ZfS9NKd0efJi/e2u8i5wnXib4ZtHBw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:44:04.287719Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.02874","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ca6ea8ac1dca5d1b212146fe6f301d222769f0f237103636ae7824bdff666b24","sha256:bdbbf8cb275d3eea4864ff020679ac6860d96623baca7405c42bd77983aa72cc"],"state_sha256":"f2dbcacd5f2b753097e221a5915efc54efaeb84a1ae50e93898904092f0f31ee"}