{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:5TFTHMXQDWR7BTP76LAMBSDIYX","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":"8d0a67c6b523da6c08431c710b87d48de2640284d7dd3eb356ab994c9d2ec1b4","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-21T17:10:02Z","title_canon_sha256":"2baaf25321a2bacc5cd68e986f9ac27872effdb83f581634c635c3d5510e4099"},"schema_version":"1.0","source":{"id":"2411.14318","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.14318","created_at":"2026-07-05T11:05:36Z"},{"alias_kind":"arxiv_version","alias_value":"2411.14318v2","created_at":"2026-07-05T11:05:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.14318","created_at":"2026-07-05T11:05:36Z"},{"alias_kind":"pith_short_12","alias_value":"5TFTHMXQDWR7","created_at":"2026-07-05T11:05:36Z"},{"alias_kind":"pith_short_16","alias_value":"5TFTHMXQDWR7BTP7","created_at":"2026-07-05T11:05:36Z"},{"alias_kind":"pith_short_8","alias_value":"5TFTHMXQ","created_at":"2026-07-05T11:05:36Z"}],"graph_snapshots":[{"event_id":"sha256:5711544fc7649e086a366b74ed3aacc01a70bbfa940ae143bf5f6079cfab63ad","target":"graph","created_at":"2026-07-05T11:05:36Z","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/2411.14318/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"It is well-known that a diverse corpus is critical for training large language models, which are typically constructed from a mixture of various domains. In general, previous efforts resort to sampling training data from different domains with static proportions, as well as adjusting data proportions during training. However, few methods have addressed the complexities of domain-adaptive continual pre-training. To fill this gap, we propose Velocitune, a novel framework dynamically assesses learning velocity and adjusts data proportions accordingly, favoring slower-learning domains while shunni","authors_text":"Chen Qi, Haoling Li, Peng Cheng, Xiao Liu, Xin Zhang, Yeyun Gong, Zheheng Luo","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-21T17:10:02Z","title":"Velocitune: A Velocity-based Dynamic Domain Reweighting Method for Continual Pre-training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.14318","kind":"arxiv","version":2},"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":"sha256:2332ffb9df85a418e347e0e76dc0fba9ad78224920c87bafc0e09127188ae863","target":"record","created_at":"2026-07-05T11:05:36Z","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":"8d0a67c6b523da6c08431c710b87d48de2640284d7dd3eb356ab994c9d2ec1b4","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-21T17:10:02Z","title_canon_sha256":"2baaf25321a2bacc5cd68e986f9ac27872effdb83f581634c635c3d5510e4099"},"schema_version":"1.0","source":{"id":"2411.14318","kind":"arxiv","version":2}},"canonical_sha256":"eccb33b2f01da3f0cdfff2c0c0c868c5cae0f5e4e06c93467f1aca04e4b2cb23","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"eccb33b2f01da3f0cdfff2c0c0c868c5cae0f5e4e06c93467f1aca04e4b2cb23","first_computed_at":"2026-07-05T11:05:36.570330Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:05:36.570330Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"K750nuZI5cquH7CA5f5/iuI4VZ2eXt9rtbiOUc7KKG57EseGWZbHWzZNWCDjEvlXesQZ0uuJPxGh9YzuwIN2Dg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:05:36.570816Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.14318","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2332ffb9df85a418e347e0e76dc0fba9ad78224920c87bafc0e09127188ae863","sha256:5711544fc7649e086a366b74ed3aacc01a70bbfa940ae143bf5f6079cfab63ad"],"state_sha256":"7b811902872a900d040e703c5a275d9d3ae959187724bbf5d49a15a56e1dea81"}