{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:3R2LV3LQJ5E6MZHGZ4UGSE5TSC","short_pith_number":"pith:3R2LV3LQ","canonical_record":{"source":{"id":"2409.04777","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-09-07T09:37:19Z","cross_cats_sorted":["math.OC"],"title_canon_sha256":"4524f68d244ec9f20a5190ee3f03149e2e64cf250bec1c0c10566b9cb0a4271b","abstract_canon_sha256":"3705dcb74fd394b57d86f31cf05ba2704473be1f49db0aab536f079142b03114"},"schema_version":"1.0"},"canonical_sha256":"dc74baed704f49e664e6cf286913b390884da0c5f7bcf00facf1ecb12fc01f42","source":{"kind":"arxiv","id":"2409.04777","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.04777","created_at":"2026-05-21T01:05:02Z"},{"alias_kind":"arxiv_version","alias_value":"2409.04777v4","created_at":"2026-05-21T01:05:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.04777","created_at":"2026-05-21T01:05:02Z"},{"alias_kind":"pith_short_12","alias_value":"3R2LV3LQJ5E6","created_at":"2026-05-21T01:05:02Z"},{"alias_kind":"pith_short_16","alias_value":"3R2LV3LQJ5E6MZHG","created_at":"2026-05-21T01:05:02Z"},{"alias_kind":"pith_short_8","alias_value":"3R2LV3LQ","created_at":"2026-05-21T01:05:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:3R2LV3LQJ5E6MZHGZ4UGSE5TSC","target":"record","payload":{"canonical_record":{"source":{"id":"2409.04777","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-09-07T09:37:19Z","cross_cats_sorted":["math.OC"],"title_canon_sha256":"4524f68d244ec9f20a5190ee3f03149e2e64cf250bec1c0c10566b9cb0a4271b","abstract_canon_sha256":"3705dcb74fd394b57d86f31cf05ba2704473be1f49db0aab536f079142b03114"},"schema_version":"1.0"},"canonical_sha256":"dc74baed704f49e664e6cf286913b390884da0c5f7bcf00facf1ecb12fc01f42","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-21T01:05:02.947404Z","signature_b64":"2sIFyEN2gVErV2degeqsk+p/qfpbCe1vO0jRSzDp8ErHR4+2WlH0TR5CzXEoP5LBCHkyDulyzBRqPNTYku3LAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dc74baed704f49e664e6cf286913b390884da0c5f7bcf00facf1ecb12fc01f42","last_reissued_at":"2026-05-21T01:05:02.945771Z","signature_status":"signed_v1","first_computed_at":"2026-05-21T01:05:02.945771Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2409.04777","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-21T01:05:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VisFmzs2dxkEvvCQVONKD0l/DCbfyyoOoKTFvAb+mMNXiT0+hg6H0K+KohPBgCP3WvI7pKRAYFARN7WdBbRNBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T22:57:18.756655Z"},"content_sha256":"6152faaf52e1757e450d1f982e8337fb99599c6b9813a843496c7138321c050f","schema_version":"1.0","event_id":"sha256:6152faaf52e1757e450d1f982e8337fb99599c6b9813a843496c7138321c050f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:3R2LV3LQJ5E6MZHGZ4UGSE5TSC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Optimization Hyper-parameter Laws for Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC"],"primary_cat":"cs.LG","authors_text":"Kim-Chuan Toh, Kuangyu Ding, Shuicheng Yan, Tianwen Wei, Xingyu Xie","submitted_at":"2024-09-07T09:37:19Z","abstract_excerpt":"Large Language Models have driven significant AI advancements, yet their training is resource-intensive and highly sensitive to hyper-parameter selection. While scaling laws provide valuable guidance on model size and data requirements, they fall short in choosing dynamic hyper-parameters, such as learning-rate (LR) schedules, that evolve during training. To bridge this gap, we present Optimization Hyper-parameter Laws (Opt-Laws), a framework that predicts final training loss as a function of LR schedule, model size, and data size. Grounded in SDE-based convergence and escape analyses, Opt-Law"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.04777","kind":"arxiv","version":4},"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/2409.04777/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":"2026-05-21T01:05:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"K6jU6VFPpNDTQ/0vs9YJRVOCiPhCQG5DX4WrSCuXif7Xe0iQTghJXwez+IujpU3RS8za3iqkcxo20sM8RnJ0Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T22:57:18.757430Z"},"content_sha256":"4c9817ffed9c8223c33a97de739bdf3cba79c70fe69b1ac686d4d8ab179d9a9f","schema_version":"1.0","event_id":"sha256:4c9817ffed9c8223c33a97de739bdf3cba79c70fe69b1ac686d4d8ab179d9a9f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3R2LV3LQJ5E6MZHGZ4UGSE5TSC/bundle.json","state_url":"https://pith.science/pith/3R2LV3LQJ5E6MZHGZ4UGSE5TSC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3R2LV3LQJ5E6MZHGZ4UGSE5TSC/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":"2026-05-25T22:57:18Z","links":{"resolver":"https://pith.science/pith/3R2LV3LQJ5E6MZHGZ4UGSE5TSC","bundle":"https://pith.science/pith/3R2LV3LQJ5E6MZHGZ4UGSE5TSC/bundle.json","state":"https://pith.science/pith/3R2LV3LQJ5E6MZHGZ4UGSE5TSC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3R2LV3LQJ5E6MZHGZ4UGSE5TSC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:3R2LV3LQJ5E6MZHGZ4UGSE5TSC","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":"3705dcb74fd394b57d86f31cf05ba2704473be1f49db0aab536f079142b03114","cross_cats_sorted":["math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-09-07T09:37:19Z","title_canon_sha256":"4524f68d244ec9f20a5190ee3f03149e2e64cf250bec1c0c10566b9cb0a4271b"},"schema_version":"1.0","source":{"id":"2409.04777","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.04777","created_at":"2026-05-21T01:05:02Z"},{"alias_kind":"arxiv_version","alias_value":"2409.04777v4","created_at":"2026-05-21T01:05:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.04777","created_at":"2026-05-21T01:05:02Z"},{"alias_kind":"pith_short_12","alias_value":"3R2LV3LQJ5E6","created_at":"2026-05-21T01:05:02Z"},{"alias_kind":"pith_short_16","alias_value":"3R2LV3LQJ5E6MZHG","created_at":"2026-05-21T01:05:02Z"},{"alias_kind":"pith_short_8","alias_value":"3R2LV3LQ","created_at":"2026-05-21T01:05:02Z"}],"graph_snapshots":[{"event_id":"sha256:4c9817ffed9c8223c33a97de739bdf3cba79c70fe69b1ac686d4d8ab179d9a9f","target":"graph","created_at":"2026-05-21T01:05:02Z","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/2409.04777/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models have driven significant AI advancements, yet their training is resource-intensive and highly sensitive to hyper-parameter selection. While scaling laws provide valuable guidance on model size and data requirements, they fall short in choosing dynamic hyper-parameters, such as learning-rate (LR) schedules, that evolve during training. To bridge this gap, we present Optimization Hyper-parameter Laws (Opt-Laws), a framework that predicts final training loss as a function of LR schedule, model size, and data size. Grounded in SDE-based convergence and escape analyses, Opt-Law","authors_text":"Kim-Chuan Toh, Kuangyu Ding, Shuicheng Yan, Tianwen Wei, Xingyu Xie","cross_cats":["math.OC"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-09-07T09:37:19Z","title":"Optimization Hyper-parameter Laws for Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.04777","kind":"arxiv","version":4},"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":"sha256:6152faaf52e1757e450d1f982e8337fb99599c6b9813a843496c7138321c050f","target":"record","created_at":"2026-05-21T01:05:02Z","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":"3705dcb74fd394b57d86f31cf05ba2704473be1f49db0aab536f079142b03114","cross_cats_sorted":["math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-09-07T09:37:19Z","title_canon_sha256":"4524f68d244ec9f20a5190ee3f03149e2e64cf250bec1c0c10566b9cb0a4271b"},"schema_version":"1.0","source":{"id":"2409.04777","kind":"arxiv","version":4}},"canonical_sha256":"dc74baed704f49e664e6cf286913b390884da0c5f7bcf00facf1ecb12fc01f42","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dc74baed704f49e664e6cf286913b390884da0c5f7bcf00facf1ecb12fc01f42","first_computed_at":"2026-05-21T01:05:02.945771Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-21T01:05:02.945771Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2sIFyEN2gVErV2degeqsk+p/qfpbCe1vO0jRSzDp8ErHR4+2WlH0TR5CzXEoP5LBCHkyDulyzBRqPNTYku3LAQ==","signature_status":"signed_v1","signed_at":"2026-05-21T01:05:02.947404Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.04777","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6152faaf52e1757e450d1f982e8337fb99599c6b9813a843496c7138321c050f","sha256:4c9817ffed9c8223c33a97de739bdf3cba79c70fe69b1ac686d4d8ab179d9a9f"],"state_sha256":"ad8393920feb972614f881fb4f8972a60f99e855dac9d063e35966cfed418cb4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tPOIk4JMFLQdJiOl4JVsQY3w2Te4+YFCbFX25WzOBfJPPP5G9yHdAjmHNZH3M8Wet0NZPgVae01Li56SPl0hDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T22:57:18.761501Z","bundle_sha256":"8aee492c62beca4e2a49d0afee926e62a3453defa2bda0166b4a33c2d07783b4"}}