{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:HQ3PBZTHLGCDXP7J3E7FEQQUJ5","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":"dabcdd5b87e0f1c6ca5e50ce2c3791fcf8b134541d445e9683b792c36a034658","cross_cats_sorted":["cs.AI","cs.LG","cs.NE"],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2023-02-07T03:57:55Z","title_canon_sha256":"ac2099373c87aa214c0d3d5946a61f56ed92c947a1e50850f49c59a6b12e79a0"},"schema_version":"1.0","source":{"id":"2302.03241","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.03241","created_at":"2026-07-05T06:00:16Z"},{"alias_kind":"arxiv_version","alias_value":"2302.03241v4","created_at":"2026-07-05T06:00:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.03241","created_at":"2026-07-05T06:00:16Z"},{"alias_kind":"pith_short_12","alias_value":"HQ3PBZTHLGCD","created_at":"2026-07-05T06:00:16Z"},{"alias_kind":"pith_short_16","alias_value":"HQ3PBZTHLGCDXP7J","created_at":"2026-07-05T06:00:16Z"},{"alias_kind":"pith_short_8","alias_value":"HQ3PBZTH","created_at":"2026-07-05T06:00:16Z"}],"graph_snapshots":[{"event_id":"sha256:5ce381fbaf5cb10aaac864d694b5d70f5afcdce4c30cd0f5b3276c2b0822e08d","target":"graph","created_at":"2026-07-05T06:00:16Z","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/2302.03241/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Language models (LMs) have been instrumental for the rapid advance of natural language processing. This paper studies continual pre-training of LMs, in particular, continual domain-adaptive pre-training (or continual DAP-training). Existing research has shown that further pre-training an LM using a domain corpus to adapt the LM to the domain can improve the end-task performance in the domain. This paper proposes a novel method to continually DAP-train an LM with a sequence of unlabeled domain corpora to adapt the LM to these domains to improve their end-task performances. The key novelty of ou","authors_text":"Bing Liu, Gyuhak Kim, Haowei Lin, Tatsuya Konishi, Yijia Shao, Zixuan Ke","cross_cats":["cs.AI","cs.LG","cs.NE"],"headline":"","license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2023-02-07T03:57:55Z","title":"Continual Pre-training of Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.03241","kind":"arxiv","version":4},"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:e473d43a51aab7d1984bcdf6db0e07b0656d2523720d711285a6863e279e57f2","target":"record","created_at":"2026-07-05T06:00:16Z","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":"dabcdd5b87e0f1c6ca5e50ce2c3791fcf8b134541d445e9683b792c36a034658","cross_cats_sorted":["cs.AI","cs.LG","cs.NE"],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2023-02-07T03:57:55Z","title_canon_sha256":"ac2099373c87aa214c0d3d5946a61f56ed92c947a1e50850f49c59a6b12e79a0"},"schema_version":"1.0","source":{"id":"2302.03241","kind":"arxiv","version":4}},"canonical_sha256":"3c36f0e66759843bbfe9d93e5242144f6f88feff35db31bcf21d13c0a56c9864","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3c36f0e66759843bbfe9d93e5242144f6f88feff35db31bcf21d13c0a56c9864","first_computed_at":"2026-07-05T06:00:16.237293Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:00:16.237293Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4QQbfikuK5agOIPvRDpbK13K6yr2jCYGNxcSiblENR/+7L0AK/fNAvBmPi4x8P2reaMCx7P5Ip13ikn3YW1MCA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:00:16.237818Z","signed_message":"canonical_sha256_bytes"},"source_id":"2302.03241","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e473d43a51aab7d1984bcdf6db0e07b0656d2523720d711285a6863e279e57f2","sha256:5ce381fbaf5cb10aaac864d694b5d70f5afcdce4c30cd0f5b3276c2b0822e08d"],"state_sha256":"dab1241201571fd8299ef652894bcbc47969e84868acd73c8bf64004cc91deac"}