{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:ALVRUQQIZ6SYCHFEE5DLRFQTIA","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":"105ee100bb3cc8342df85953c13d93f0136d610c74a619dbc8206d95825d659d","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-07-31T00:04:15Z","title_canon_sha256":"e13434739b766e84627e380280d82913b278dcd2a64f8b4e189a1410c1de361a"},"schema_version":"1.0","source":{"id":"2007.15779","kind":"arxiv","version":6}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2007.15779","created_at":"2026-07-05T03:15:07Z"},{"alias_kind":"arxiv_version","alias_value":"2007.15779v6","created_at":"2026-07-05T03:15:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.15779","created_at":"2026-07-05T03:15:07Z"},{"alias_kind":"pith_short_12","alias_value":"ALVRUQQIZ6SY","created_at":"2026-07-05T03:15:07Z"},{"alias_kind":"pith_short_16","alias_value":"ALVRUQQIZ6SYCHFE","created_at":"2026-07-05T03:15:07Z"},{"alias_kind":"pith_short_8","alias_value":"ALVRUQQI","created_at":"2026-07-05T03:15:07Z"}],"graph_snapshots":[{"event_id":"sha256:7b14b456c506a92d0ca6ed853ec3f2ba9d9d76d93ce855c00c10d1041ccec57a","target":"graph","created_at":"2026-07-05T03:15:07Z","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/2007.15779/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Pretraining large neural language models, such as BERT, has led to impressive gains on many natural language processing (NLP) tasks. However, most pretraining efforts focus on general domain corpora, such as newswire and Web. A prevailing assumption is that even domain-specific pretraining can benefit by starting from general-domain language models. In this paper, we challenge this assumption by showing that for domains with abundant unlabeled text, such as biomedicine, pretraining language models from scratch results in substantial gains over continual pretraining of general-domain language m","authors_text":"Hao Cheng, Hoifung Poon, Jianfeng Gao, Michael Lucas, Naoto Usuyama, Robert Tinn, Tristan Naumann, XiaoDong Liu, Yu Gu","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-07-31T00:04:15Z","title":"Domain-Specific Language Model Pretraining for Biomedical Natural Language Processing"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.15779","kind":"arxiv","version":6},"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:cadb251336e32f2de32c5bbae7fab65b15279f07dba7256a3b929db19f3a6b7c","target":"record","created_at":"2026-07-05T03:15:07Z","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":"105ee100bb3cc8342df85953c13d93f0136d610c74a619dbc8206d95825d659d","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-07-31T00:04:15Z","title_canon_sha256":"e13434739b766e84627e380280d82913b278dcd2a64f8b4e189a1410c1de361a"},"schema_version":"1.0","source":{"id":"2007.15779","kind":"arxiv","version":6}},"canonical_sha256":"02eb1a4208cfa5811ca42746b89613403709cd7d30d7c322457778cc85d3ee6d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"02eb1a4208cfa5811ca42746b89613403709cd7d30d7c322457778cc85d3ee6d","first_computed_at":"2026-07-05T03:15:07.514620Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:15:07.514620Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"W4NDVYBqFjTcoR/jkeWD1viVT1x3drahCIGXFOL8ipXNpAQY2iFuW77Lu+PaLSeXOw24YPhTXxD1zzI803nVAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T03:15:07.515042Z","signed_message":"canonical_sha256_bytes"},"source_id":"2007.15779","source_kind":"arxiv","source_version":6}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cadb251336e32f2de32c5bbae7fab65b15279f07dba7256a3b929db19f3a6b7c","sha256:7b14b456c506a92d0ca6ed853ec3f2ba9d9d76d93ce855c00c10d1041ccec57a"],"state_sha256":"c35818f72d0a5a33243e1658f4e76b80818945c02941c4739bc804b04b303596"}