{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:KA5534IKF7GIBQXVXX2ZGYPMNU","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":"64e430a80813164801533edb1cdab0fde3ae628308338a9b4e51c93962794095","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-27T18:52:19Z","title_canon_sha256":"b3c1718af27f0745169270d2aab5a243abf76e132ecd9d83615080e2290d54bc"},"schema_version":"1.0","source":{"id":"2402.17759","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.17759","created_at":"2026-07-05T07:51:40Z"},{"alias_kind":"arxiv_version","alias_value":"2402.17759v2","created_at":"2026-07-05T07:51:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.17759","created_at":"2026-07-05T07:51:40Z"},{"alias_kind":"pith_short_12","alias_value":"KA5534IKF7GI","created_at":"2026-07-05T07:51:40Z"},{"alias_kind":"pith_short_16","alias_value":"KA5534IKF7GIBQXV","created_at":"2026-07-05T07:51:40Z"},{"alias_kind":"pith_short_8","alias_value":"KA5534IK","created_at":"2026-07-05T07:51:40Z"}],"graph_snapshots":[{"event_id":"sha256:6e6c1016b6f40acb8892438311dc30cd56b77a6c605fe9c37c07a70f5dc1b17b","target":"graph","created_at":"2026-07-05T07:51:40Z","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/2402.17759/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This work studies the general principles of improving the learning of language models (LMs), which aims at reducing the necessary training steps for achieving superior performance. Specifically, we present a theory for the optimal learning of LMs. We first propose an objective that optimizes LM learning by maximizing the data compression ratio in an \"LM-training-as-lossless-compression\" view. Then, we derive a theorem, named Learning Law, to reveal the properties of the dynamics in the optimal learning process under our objective. The theorem is then validated by experiments on a linear classi","authors_text":"Furu Wei, Li Dong, Minlie Huang, Qingxiu Dong, Yaru Hao, Yuxian Gu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-27T18:52:19Z","title":"Towards Optimal Learning of Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.17759","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":"sha256:0460846f2ea1292bc591a8d2be91a518ba31dafc8e0931bfede8dce4fd5b36d3","target":"record","created_at":"2026-07-05T07:51:40Z","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":"64e430a80813164801533edb1cdab0fde3ae628308338a9b4e51c93962794095","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-27T18:52:19Z","title_canon_sha256":"b3c1718af27f0745169270d2aab5a243abf76e132ecd9d83615080e2290d54bc"},"schema_version":"1.0","source":{"id":"2402.17759","kind":"arxiv","version":2}},"canonical_sha256":"503bddf10a2fcc80c2f5bdf59361ec6d117c5b54a2fec028c68ed75558469aa4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"503bddf10a2fcc80c2f5bdf59361ec6d117c5b54a2fec028c68ed75558469aa4","first_computed_at":"2026-07-05T07:51:40.260737Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:51:40.260737Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tyVpacrK6/VGusHdPURqvPQchFJRVuIowaSVDy36Ql+8mIZyUdL3HnBqYMb+DQZosjrpDinGRGQevPx4FH1wAg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:51:40.261176Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.17759","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0460846f2ea1292bc591a8d2be91a518ba31dafc8e0931bfede8dce4fd5b36d3","sha256:6e6c1016b6f40acb8892438311dc30cd56b77a6c605fe9c37c07a70f5dc1b17b"],"state_sha256":"d186675ab8dd1c1b6b69ac703e69d7f266d8b67d8acb18d7d4f129b979d738d0"}