{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:WEMGAX6T45MAKSKXIRDK5GSFYR","short_pith_number":"pith:WEMGAX6T","canonical_record":{"source":{"id":"2405.18392","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-28T17:33:54Z","cross_cats_sorted":[],"title_canon_sha256":"825d1405377257d6f9a085bfd2a47f158dab060b670170e384f583cfdb196a94","abstract_canon_sha256":"baa577191773a807f46bd48637e14148ecb8f83dd927212c0d3e8cfbf1602e74"},"schema_version":"1.0"},"canonical_sha256":"b118605fd3e7580549574446ae9a45c443aad23b5d8e09edb0bf40700aa1ec2c","source":{"kind":"arxiv","id":"2405.18392","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.18392","created_at":"2026-07-05T09:21:44Z"},{"alias_kind":"arxiv_version","alias_value":"2405.18392v3","created_at":"2026-07-05T09:21:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.18392","created_at":"2026-07-05T09:21:44Z"},{"alias_kind":"pith_short_12","alias_value":"WEMGAX6T45MA","created_at":"2026-07-05T09:21:44Z"},{"alias_kind":"pith_short_16","alias_value":"WEMGAX6T45MAKSKX","created_at":"2026-07-05T09:21:44Z"},{"alias_kind":"pith_short_8","alias_value":"WEMGAX6T","created_at":"2026-07-05T09:21:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:WEMGAX6T45MAKSKXIRDK5GSFYR","target":"record","payload":{"canonical_record":{"source":{"id":"2405.18392","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-28T17:33:54Z","cross_cats_sorted":[],"title_canon_sha256":"825d1405377257d6f9a085bfd2a47f158dab060b670170e384f583cfdb196a94","abstract_canon_sha256":"baa577191773a807f46bd48637e14148ecb8f83dd927212c0d3e8cfbf1602e74"},"schema_version":"1.0"},"canonical_sha256":"b118605fd3e7580549574446ae9a45c443aad23b5d8e09edb0bf40700aa1ec2c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:21:44.780149Z","signature_b64":"pFPdTEXVdCWxzCYg5NDc6LvARBkwUStNeG2pT2duM6qmhc+sjr59baoondvPbD9G9V/72LkqDpmT+7KNaAgUDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b118605fd3e7580549574446ae9a45c443aad23b5d8e09edb0bf40700aa1ec2c","last_reissued_at":"2026-07-05T09:21:44.779662Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:21:44.779662Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2405.18392","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":"2026-07-05T09:21:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"J/0Xk0VUXtaTb6SWEoBtx5GubzNOgkY5T6ROkQ5QOu4C+wXRkYeK0joiNxi/+PgjqDUO6NqXAaYxKDh3QKVgAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T19:03:00.141500Z"},"content_sha256":"c4705efcb6e28582e37045772195965870c1e7489e645e8c972463bec44a550a","schema_version":"1.0","event_id":"sha256:c4705efcb6e28582e37045772195965870c1e7489e645e8c972463bec44a550a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:WEMGAX6T45MAKSKXIRDK5GSFYR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Scaling Laws and Compute-Optimal Training Beyond Fixed Training Durations","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Alexander H\\\"agele, Atli Kosson, Elie Bakouch, Leandro Von Werra, Loubna Ben Allal, Martin Jaggi","submitted_at":"2024-05-28T17:33:54Z","abstract_excerpt":"Scale has become a main ingredient in obtaining strong machine learning models. As a result, understanding a model's scaling properties is key to effectively designing both the right training setup as well as future generations of architectures. In this work, we argue that scale and training research has been needlessly complex due to reliance on the cosine schedule, which prevents training across different lengths for the same model size. We investigate the training behavior of a direct alternative -- constant learning rate and cooldowns -- and find that it scales predictably and reliably sim"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.18392","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/2405.18392/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":"2026-07-05T09:21:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"c6SbiVPEZ6vce8HEG3sHT9zZaKQfNGFhq00AS0WQAFvGw6jSwB3ZDQVer1lohc7VdTmlQmb0ISLbDUwSFp/bCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T19:03:00.142461Z"},"content_sha256":"41fdf74973a1c566d0551bf7238ac10d81ac2c65044807b4b4896bfacc6279a6","schema_version":"1.0","event_id":"sha256:41fdf74973a1c566d0551bf7238ac10d81ac2c65044807b4b4896bfacc6279a6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WEMGAX6T45MAKSKXIRDK5GSFYR/bundle.json","state_url":"https://pith.science/pith/WEMGAX6T45MAKSKXIRDK5GSFYR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WEMGAX6T45MAKSKXIRDK5GSFYR/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":"2026-08-04T19:03:00Z","links":{"resolver":"https://pith.science/pith/WEMGAX6T45MAKSKXIRDK5GSFYR","bundle":"https://pith.science/pith/WEMGAX6T45MAKSKXIRDK5GSFYR/bundle.json","state":"https://pith.science/pith/WEMGAX6T45MAKSKXIRDK5GSFYR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WEMGAX6T45MAKSKXIRDK5GSFYR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:WEMGAX6T45MAKSKXIRDK5GSFYR","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":"baa577191773a807f46bd48637e14148ecb8f83dd927212c0d3e8cfbf1602e74","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-28T17:33:54Z","title_canon_sha256":"825d1405377257d6f9a085bfd2a47f158dab060b670170e384f583cfdb196a94"},"schema_version":"1.0","source":{"id":"2405.18392","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.18392","created_at":"2026-07-05T09:21:44Z"},{"alias_kind":"arxiv_version","alias_value":"2405.18392v3","created_at":"2026-07-05T09:21:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.18392","created_at":"2026-07-05T09:21:44Z"},{"alias_kind":"pith_short_12","alias_value":"WEMGAX6T45MA","created_at":"2026-07-05T09:21:44Z"},{"alias_kind":"pith_short_16","alias_value":"WEMGAX6T45MAKSKX","created_at":"2026-07-05T09:21:44Z"},{"alias_kind":"pith_short_8","alias_value":"WEMGAX6T","created_at":"2026-07-05T09:21:44Z"}],"graph_snapshots":[{"event_id":"sha256:41fdf74973a1c566d0551bf7238ac10d81ac2c65044807b4b4896bfacc6279a6","target":"graph","created_at":"2026-07-05T09:21:44Z","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/2405.18392/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Scale has become a main ingredient in obtaining strong machine learning models. As a result, understanding a model's scaling properties is key to effectively designing both the right training setup as well as future generations of architectures. In this work, we argue that scale and training research has been needlessly complex due to reliance on the cosine schedule, which prevents training across different lengths for the same model size. We investigate the training behavior of a direct alternative -- constant learning rate and cooldowns -- and find that it scales predictably and reliably sim","authors_text":"Alexander H\\\"agele, Atli Kosson, Elie Bakouch, Leandro Von Werra, Loubna Ben Allal, Martin Jaggi","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-28T17:33:54Z","title":"Scaling Laws and Compute-Optimal Training Beyond Fixed Training Durations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.18392","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:c4705efcb6e28582e37045772195965870c1e7489e645e8c972463bec44a550a","target":"record","created_at":"2026-07-05T09:21:44Z","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":"baa577191773a807f46bd48637e14148ecb8f83dd927212c0d3e8cfbf1602e74","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-28T17:33:54Z","title_canon_sha256":"825d1405377257d6f9a085bfd2a47f158dab060b670170e384f583cfdb196a94"},"schema_version":"1.0","source":{"id":"2405.18392","kind":"arxiv","version":3}},"canonical_sha256":"b118605fd3e7580549574446ae9a45c443aad23b5d8e09edb0bf40700aa1ec2c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b118605fd3e7580549574446ae9a45c443aad23b5d8e09edb0bf40700aa1ec2c","first_computed_at":"2026-07-05T09:21:44.779662Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:21:44.779662Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pFPdTEXVdCWxzCYg5NDc6LvARBkwUStNeG2pT2duM6qmhc+sjr59baoondvPbD9G9V/72LkqDpmT+7KNaAgUDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:21:44.780149Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.18392","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c4705efcb6e28582e37045772195965870c1e7489e645e8c972463bec44a550a","sha256:41fdf74973a1c566d0551bf7238ac10d81ac2c65044807b4b4896bfacc6279a6"],"state_sha256":"559bd33fb5e6d52e2a3c9046d165a2250670f9e8eb1f8f4e2d33ed6c2db8c8be"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DlK8enF6wt4/uAqF1jAOcZhUnMzrs18N5ymt2LCxzce+wDtdZr5IfJOPX1J3dlrvevXF06qWypgYF+IpRDulDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T19:03:00.148664Z","bundle_sha256":"46829368c5a53e659a48a7512d465c7b74df0a9534426a8c0436fde02d928b82"}}