{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:MIZPMXWICONKDMHL2FP7Z2XYRR","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":"f7f9e478aa8902837c9d390550a99ac7aa202cbbdd9c551a75675a11e67dba34","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-bio.QM","submitted_at":"2026-07-09T06:56:39Z","title_canon_sha256":"70c3efda8d0571b8674c6f66e2aed36cca4c571b6b01fc568f28d29f95f54f1e"},"schema_version":"1.0","source":{"id":"2607.08803","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.08803","created_at":"2026-07-13T00:17:18Z"},{"alias_kind":"arxiv_version","alias_value":"2607.08803v1","created_at":"2026-07-13T00:17:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.08803","created_at":"2026-07-13T00:17:18Z"},{"alias_kind":"pith_short_12","alias_value":"MIZPMXWICONK","created_at":"2026-07-13T00:17:18Z"},{"alias_kind":"pith_short_16","alias_value":"MIZPMXWICONKDMHL","created_at":"2026-07-13T00:17:18Z"},{"alias_kind":"pith_short_8","alias_value":"MIZPMXWI","created_at":"2026-07-13T00:17:18Z"}],"graph_snapshots":[{"event_id":"sha256:7028b1f3e5ac5e82e280c9c844cb80ba2cbd36da827d2286644c83e038ab982c","target":"graph","created_at":"2026-07-13T00:17:18Z","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/2607.08803/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The push toward large language models for biology (BioLM) has created a need for training corpora that can endow models with a genuine understanding of biology. However, existing biological resources, such as molecular databases, protein repositories, genomic annotations, single-cell atlases, and pathway databases, are scattered across heterogeneous formats and remain unorganized into a cohesive corpus for language model training. We present TheBioCollection, a 52.6B-token pre-training-scale corpus that converts these disparate resources into a unified, training-ready form spanning small molec","authors_text":"Gyubok Lee, Hongjoon Ahn, Hyeon Hwang, Hyunjin Seo, Jay Shin, Jimin Park, Sanghoon Lee, Sangwon Jung, Sungjun Han, Taesoo Kim","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-bio.QM","submitted_at":"2026-07-09T06:56:39Z","title":"TheBioCollection: Unified Pre-Training Scale LLM Corpus for Biology"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.08803","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":"sha256:865bb0b7fe9dc52553c037f2d52910cc8d77a7a64dbde3418cc45a6cda874d7e","target":"record","created_at":"2026-07-13T00:17:18Z","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":"f7f9e478aa8902837c9d390550a99ac7aa202cbbdd9c551a75675a11e67dba34","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-bio.QM","submitted_at":"2026-07-09T06:56:39Z","title_canon_sha256":"70c3efda8d0571b8674c6f66e2aed36cca4c571b6b01fc568f28d29f95f54f1e"},"schema_version":"1.0","source":{"id":"2607.08803","kind":"arxiv","version":1}},"canonical_sha256":"6232f65ec8139aa1b0ebd15ffceaf88c61c698c5599d573e64dcdfd04ace8632","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6232f65ec8139aa1b0ebd15ffceaf88c61c698c5599d573e64dcdfd04ace8632","first_computed_at":"2026-07-13T00:17:18.010563Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-13T00:17:18.010563Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8nB4ZqK3Ob4/JYYUhKkMpGRLAl5Nu285k4tCkZsBDGQc5yGWfRo0/R6VLZOHLpiDMEI1fIWAEeNbqI8Uw5P4Cg==","signature_status":"signed_v1","signed_at":"2026-07-13T00:17:18.011965Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.08803","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:865bb0b7fe9dc52553c037f2d52910cc8d77a7a64dbde3418cc45a6cda874d7e","sha256:7028b1f3e5ac5e82e280c9c844cb80ba2cbd36da827d2286644c83e038ab982c"],"state_sha256":"eb405eb59a9afcac952425579df62a8d881ca71c75870a8c802c6e076d96acb3"}