{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:NFZGS7BDFWNR2UBDYKPXZDGOM7","short_pith_number":"pith:NFZGS7BD","canonical_record":{"source":{"id":"2409.19913","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-09-30T03:32:02Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"3964b1083d4e42bc457b3c238c32b1e756bdec30479658ad126f7c9874fca040","abstract_canon_sha256":"40283f870db5d43f03bc5bc9c34d1cd4c38294eeff187af29bc7e24e02db7b4a"},"schema_version":"1.0"},"canonical_sha256":"6972697c232d9b1d5023c29f7c8cce67e803eafdd945f09277c80697cd0a201f","source":{"kind":"arxiv","id":"2409.19913","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.19913","created_at":"2026-07-05T10:18:42Z"},{"alias_kind":"arxiv_version","alias_value":"2409.19913v3","created_at":"2026-07-05T10:18:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.19913","created_at":"2026-07-05T10:18:42Z"},{"alias_kind":"pith_short_12","alias_value":"NFZGS7BDFWNR","created_at":"2026-07-05T10:18:42Z"},{"alias_kind":"pith_short_16","alias_value":"NFZGS7BDFWNR2UBD","created_at":"2026-07-05T10:18:42Z"},{"alias_kind":"pith_short_8","alias_value":"NFZGS7BD","created_at":"2026-07-05T10:18:42Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:NFZGS7BDFWNR2UBDYKPXZDGOM7","target":"record","payload":{"canonical_record":{"source":{"id":"2409.19913","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-09-30T03:32:02Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"3964b1083d4e42bc457b3c238c32b1e756bdec30479658ad126f7c9874fca040","abstract_canon_sha256":"40283f870db5d43f03bc5bc9c34d1cd4c38294eeff187af29bc7e24e02db7b4a"},"schema_version":"1.0"},"canonical_sha256":"6972697c232d9b1d5023c29f7c8cce67e803eafdd945f09277c80697cd0a201f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:18:42.087033Z","signature_b64":"Xyyu+RX47yok/CNhn0gcF3twMwuLfWxNTqI5VTKdOq1bGmbWuQgiXgNoVNU5Iqyc6Npyi0eBO/VHMu7CDSRZAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6972697c232d9b1d5023c29f7c8cce67e803eafdd945f09277c80697cd0a201f","last_reissued_at":"2026-07-05T10:18:42.086203Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:18:42.086203Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2409.19913","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:18:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"onf0IgT1VATrZtdoDdN2yPHdXsfgI65cyM6UNOaslFG0uxt+ihd/h31A4glRlXME3AbB32tYUPUtm0tIPPQPAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T14:25:56.336171Z"},"content_sha256":"365905f78711bbee402e90ac85d6ab32c33580587b4a3ec0aec0b400c9b52eae","schema_version":"1.0","event_id":"sha256:365905f78711bbee402e90ac85d6ab32c33580587b4a3ec0aec0b400c9b52eae"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:NFZGS7BDFWNR2UBDYKPXZDGOM7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Scaling Optimal LR Across Token Horizons","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Alon Benhaim, Furu Wei, Johan Bjorck, Vishrav Chaudhary, Xia Song","submitted_at":"2024-09-30T03:32:02Z","abstract_excerpt":"State-of-the-art LLMs are powered by scaling -- scaling model size, dataset size and cluster size. It is economically infeasible to extensively tune hyperparameter for the largest runs. Instead, approximately optimal hyperparameters must be inferred or \\textit{transferred} from smaller experiments. Hyperparameter transfer across model sizes has been studied in Yang et al. However, hyperparameter transfer across dataset size -- or token horizon -- has not been studied yet. To remedy this we conduct a large scale empirical study on how optimal learning rate (LR) depends on token horizon in LLM t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.19913","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2409.19913/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:18:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HbGJlA90I8uGi8Epg5pB98fejBYLPc6y93JiLeTmYK6KhZp5xZQrihhLdPcD/TS74m5BHe+eNjyazvwQGFLTDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T14:25:56.336658Z"},"content_sha256":"d0913f40dfe6f946946533f83c73b384050325d933b54f45d1194ff17878c326","schema_version":"1.0","event_id":"sha256:d0913f40dfe6f946946533f83c73b384050325d933b54f45d1194ff17878c326"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NFZGS7BDFWNR2UBDYKPXZDGOM7/bundle.json","state_url":"https://pith.science/pith/NFZGS7BDFWNR2UBDYKPXZDGOM7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NFZGS7BDFWNR2UBDYKPXZDGOM7/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-07T14:25:56Z","links":{"resolver":"https://pith.science/pith/NFZGS7BDFWNR2UBDYKPXZDGOM7","bundle":"https://pith.science/pith/NFZGS7BDFWNR2UBDYKPXZDGOM7/bundle.json","state":"https://pith.science/pith/NFZGS7BDFWNR2UBDYKPXZDGOM7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NFZGS7BDFWNR2UBDYKPXZDGOM7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:NFZGS7BDFWNR2UBDYKPXZDGOM7","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":"40283f870db5d43f03bc5bc9c34d1cd4c38294eeff187af29bc7e24e02db7b4a","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-09-30T03:32:02Z","title_canon_sha256":"3964b1083d4e42bc457b3c238c32b1e756bdec30479658ad126f7c9874fca040"},"schema_version":"1.0","source":{"id":"2409.19913","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.19913","created_at":"2026-07-05T10:18:42Z"},{"alias_kind":"arxiv_version","alias_value":"2409.19913v3","created_at":"2026-07-05T10:18:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.19913","created_at":"2026-07-05T10:18:42Z"},{"alias_kind":"pith_short_12","alias_value":"NFZGS7BDFWNR","created_at":"2026-07-05T10:18:42Z"},{"alias_kind":"pith_short_16","alias_value":"NFZGS7BDFWNR2UBD","created_at":"2026-07-05T10:18:42Z"},{"alias_kind":"pith_short_8","alias_value":"NFZGS7BD","created_at":"2026-07-05T10:18:42Z"}],"graph_snapshots":[{"event_id":"sha256:d0913f40dfe6f946946533f83c73b384050325d933b54f45d1194ff17878c326","target":"graph","created_at":"2026-07-05T10:18:42Z","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/2409.19913/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"State-of-the-art LLMs are powered by scaling -- scaling model size, dataset size and cluster size. It is economically infeasible to extensively tune hyperparameter for the largest runs. Instead, approximately optimal hyperparameters must be inferred or \\textit{transferred} from smaller experiments. Hyperparameter transfer across model sizes has been studied in Yang et al. However, hyperparameter transfer across dataset size -- or token horizon -- has not been studied yet. To remedy this we conduct a large scale empirical study on how optimal learning rate (LR) depends on token horizon in LLM t","authors_text":"Alon Benhaim, Furu Wei, Johan Bjorck, Vishrav Chaudhary, Xia Song","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-09-30T03:32:02Z","title":"Scaling Optimal LR Across Token Horizons"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.19913","kind":"arxiv","version":3},"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":"sha256:365905f78711bbee402e90ac85d6ab32c33580587b4a3ec0aec0b400c9b52eae","target":"record","created_at":"2026-07-05T10:18:42Z","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":"40283f870db5d43f03bc5bc9c34d1cd4c38294eeff187af29bc7e24e02db7b4a","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-09-30T03:32:02Z","title_canon_sha256":"3964b1083d4e42bc457b3c238c32b1e756bdec30479658ad126f7c9874fca040"},"schema_version":"1.0","source":{"id":"2409.19913","kind":"arxiv","version":3}},"canonical_sha256":"6972697c232d9b1d5023c29f7c8cce67e803eafdd945f09277c80697cd0a201f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6972697c232d9b1d5023c29f7c8cce67e803eafdd945f09277c80697cd0a201f","first_computed_at":"2026-07-05T10:18:42.086203Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:18:42.086203Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Xyyu+RX47yok/CNhn0gcF3twMwuLfWxNTqI5VTKdOq1bGmbWuQgiXgNoVNU5Iqyc6Npyi0eBO/VHMu7CDSRZAw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:18:42.087033Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.19913","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:365905f78711bbee402e90ac85d6ab32c33580587b4a3ec0aec0b400c9b52eae","sha256:d0913f40dfe6f946946533f83c73b384050325d933b54f45d1194ff17878c326"],"state_sha256":"8cf261279e33311bb5891436b6654d2f0204a0b0c1e410637732384c3dca90ed"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wWVR8RLZ8L2omJuWb/ADlOXxc8bqYRVB8kq25g6OSI43fVG4xEl8pIL37h0LFXwhY+tZKM7cLUqQMlcpvLmnAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T14:25:56.341251Z","bundle_sha256":"944a5f61ad7570c36b2460b3b1ec0aa6f6abe0abf84a4060bc2f4848b87a4137"}}