{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:GYDXRJ6J5MX77JIH3GDEMX3TGU","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":"c2c1db0e8ef1ee82b665da1d39b1e796edb35478bf10f5c024da8562f291f610","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-09T22:37:59Z","title_canon_sha256":"d658a9fcd443799379588ff952e446be268f922d070b50b8cc66801aa0447e8f"},"schema_version":"1.0","source":{"id":"2407.07263","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.07263","created_at":"2026-07-05T08:42:08Z"},{"alias_kind":"arxiv_version","alias_value":"2407.07263v1","created_at":"2026-07-05T08:42:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.07263","created_at":"2026-07-05T08:42:08Z"},{"alias_kind":"pith_short_12","alias_value":"GYDXRJ6J5MX7","created_at":"2026-07-05T08:42:08Z"},{"alias_kind":"pith_short_16","alias_value":"GYDXRJ6J5MX77JIH","created_at":"2026-07-05T08:42:08Z"},{"alias_kind":"pith_short_8","alias_value":"GYDXRJ6J","created_at":"2026-07-05T08:42:08Z"}],"graph_snapshots":[{"event_id":"sha256:f8dd65a9d3bd930f29fa784e683b887ef1a03db7eab822c77ec1e4911f77bd75","target":"graph","created_at":"2026-07-05T08:42:08Z","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/2407.07263/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"As language models have scaled both their number of parameters and pretraining dataset sizes, the computational cost for pretraining has become intractable except for the most well-resourced teams. This increasing cost makes it ever more important to be able to reuse a model after it has completed pretraining; allowing for a model's abilities to further improve without needing to train from scratch. In this work, we detail a set of guidelines that cover how to design efficacious data distributions and learning rate schedules for continued pretraining of language models. When applying these fin","authors_text":"Bryan Catanzaro, Jupinder Parmar, Mohammad Shoeybi, Mostofa Patwary, Sanjev Satheesh","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-09T22:37:59Z","title":"Reuse, Don't Retrain: A Recipe for Continued Pretraining of Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.07263","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":"sha256:2b103c1e367f483b81fc70ec534736bd9488f45f02fa16ccd6fe763907921372","target":"record","created_at":"2026-07-05T08:42:08Z","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":"c2c1db0e8ef1ee82b665da1d39b1e796edb35478bf10f5c024da8562f291f610","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-09T22:37:59Z","title_canon_sha256":"d658a9fcd443799379588ff952e446be268f922d070b50b8cc66801aa0447e8f"},"schema_version":"1.0","source":{"id":"2407.07263","kind":"arxiv","version":1}},"canonical_sha256":"360778a7c9eb2fffa507d986465f73353911aec13b04f0d78252a95bc145a2e4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"360778a7c9eb2fffa507d986465f73353911aec13b04f0d78252a95bc145a2e4","first_computed_at":"2026-07-05T08:42:08.981249Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:42:08.981249Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"q2Jvr+Y0gXdf2Sbm4XgKHLNYOgJKB4wRBpvg9AYQyOT5HkSm6JZfomF+bLPAxw5KnE+7Iz7H2FqfQu0/iDCMDw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:42:08.981610Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.07263","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2b103c1e367f483b81fc70ec534736bd9488f45f02fa16ccd6fe763907921372","sha256:f8dd65a9d3bd930f29fa784e683b887ef1a03db7eab822c77ec1e4911f77bd75"],"state_sha256":"24f367713aa1adacaa374250bf971ca06caa6ac62b328b730fc1af293a7143ea"}