{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ETUQABQPPCYAFG6SZGRJS5GND6","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":"d056d2b87b9bdc7a6127f6b0e48bbdb19a743c00d2cd10f709e16ac2ae19b9c5","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-08-20T17:30:48Z","title_canon_sha256":"0785522b6b06b36dfef8c2aa0e4cbb336c6c4a3c19744f38bf5efdd76084051f"},"schema_version":"1.0","source":{"id":"2408.11029","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.11029","created_at":"2026-07-05T09:25:46Z"},{"alias_kind":"arxiv_version","alias_value":"2408.11029v2","created_at":"2026-07-05T09:25:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.11029","created_at":"2026-07-05T09:25:46Z"},{"alias_kind":"pith_short_12","alias_value":"ETUQABQPPCYA","created_at":"2026-07-05T09:25:46Z"},{"alias_kind":"pith_short_16","alias_value":"ETUQABQPPCYAFG6S","created_at":"2026-07-05T09:25:46Z"},{"alias_kind":"pith_short_8","alias_value":"ETUQABQP","created_at":"2026-07-05T09:25:46Z"}],"graph_snapshots":[{"event_id":"sha256:460bbf3cb8f964b27f8d710133d8073f3c1526f6716d3853b7fb11fa3f5e26c8","target":"graph","created_at":"2026-07-05T09:25:46Z","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/2408.11029/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We find that the cross-entropy loss curves of neural language models empirically adhere to a scaling law with learning rate (LR) annealing over training steps: $$L(s) = L_0 + A\\cdot S_1^{-\\alpha} - C\\cdot S_2,$$ where $L(s)$ is the validation loss at step $s$, $S_1$ is the area under the LR curve, $S_2$ is the LR annealing area, and $L_0$, $A$, $C$, $\\alpha$ are constant parameters. This formulation takes into account two factors: (1) power-law scaling over data size, and (2) the additional loss reduction during LR annealing. Therefore, this formulation can describe the full loss curve at each","authors_text":"Howe Tissue, Lu Wang, Venus Wang","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-08-20T17:30:48Z","title":"Scaling Law with Learning Rate Annealing"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.11029","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":"sha256:47cedf2c7d3a6bd45608f7074bfb4e6157c07fb5bc82b9c6ceb9b17084f7a640","target":"record","created_at":"2026-07-05T09:25:46Z","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":"d056d2b87b9bdc7a6127f6b0e48bbdb19a743c00d2cd10f709e16ac2ae19b9c5","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-08-20T17:30:48Z","title_canon_sha256":"0785522b6b06b36dfef8c2aa0e4cbb336c6c4a3c19744f38bf5efdd76084051f"},"schema_version":"1.0","source":{"id":"2408.11029","kind":"arxiv","version":2}},"canonical_sha256":"24e900060f78b0029bd2c9a29974cd1fb82947970b42ee9febfeadd0a83ed499","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"24e900060f78b0029bd2c9a29974cd1fb82947970b42ee9febfeadd0a83ed499","first_computed_at":"2026-07-05T09:25:46.566202Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:25:46.566202Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xLc6eoH5cV3hwrE49ze5ZbS6NsMBjaDiwDnxjuskGAj/mTeyxlLr3uuoF7v1lXofzbWh0tCyQuPfUGt2EtadCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:25:46.566721Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.11029","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:47cedf2c7d3a6bd45608f7074bfb4e6157c07fb5bc82b9c6ceb9b17084f7a640","sha256:460bbf3cb8f964b27f8d710133d8073f3c1526f6716d3853b7fb11fa3f5e26c8"],"state_sha256":"dc0beaa932c3bd4de74092b864de28a91a4249d5659d80b1014cc4767c15ea6e"}