{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:PE6VZBQFAGQZCBUV7ATRE67RTX","short_pith_number":"pith:PE6VZBQF","canonical_record":{"source":{"id":"2407.07972","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-07-10T18:11:40Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"90e08be39dcc38bfd4eecb77f672a35f140d22d1cd8e6e24a36606a0ac53a851","abstract_canon_sha256":"0fda091f70fdae1b3136d28c8d96a9220ebf343dddf6625ef059514f198d32ac"},"schema_version":"1.0"},"canonical_sha256":"793d5c860501a1910695f827127bf19de36e1bcf61853281cdd5c5829379c809","source":{"kind":"arxiv","id":"2407.07972","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.07972","created_at":"2026-07-05T10:21:21Z"},{"alias_kind":"arxiv_version","alias_value":"2407.07972v2","created_at":"2026-07-05T10:21:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.07972","created_at":"2026-07-05T10:21:21Z"},{"alias_kind":"pith_short_12","alias_value":"PE6VZBQFAGQZ","created_at":"2026-07-05T10:21:21Z"},{"alias_kind":"pith_short_16","alias_value":"PE6VZBQFAGQZCBUV","created_at":"2026-07-05T10:21:21Z"},{"alias_kind":"pith_short_8","alias_value":"PE6VZBQF","created_at":"2026-07-05T10:21:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:PE6VZBQFAGQZCBUV7ATRE67RTX","target":"record","payload":{"canonical_record":{"source":{"id":"2407.07972","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-07-10T18:11:40Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"90e08be39dcc38bfd4eecb77f672a35f140d22d1cd8e6e24a36606a0ac53a851","abstract_canon_sha256":"0fda091f70fdae1b3136d28c8d96a9220ebf343dddf6625ef059514f198d32ac"},"schema_version":"1.0"},"canonical_sha256":"793d5c860501a1910695f827127bf19de36e1bcf61853281cdd5c5829379c809","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:21:21.517133Z","signature_b64":"mFBkgz65ECpq9uvYbtBieWlRkHzZJ8diZuFQx5s/YIKgMDed1HhxyIoAh41qYeMdRwamNgf6kp7LbRS5549MAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"793d5c860501a1910695f827127bf19de36e1bcf61853281cdd5c5829379c809","last_reissued_at":"2026-07-05T10:21:21.516591Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:21:21.516591Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.07972","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:21:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2hzdUCJC2LxhBhqoGjyuARSKGFZ9gh0RFYazERuhA1DFVIJ/ffYC2+IoeGxIEC60FinHBwgS2h+kNwGhOyzUCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T16:00:36.356933Z"},"content_sha256":"a79185ec80d4bd4a4f7040e4d64e0efe2bff36ce3264f026d9a351d804f01066","schema_version":"1.0","event_id":"sha256:a79185ec80d4bd4a4f7040e4d64e0efe2bff36ce3264f026d9a351d804f01066"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:PE6VZBQFAGQZCBUV7ATRE67RTX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Deconstructing What Makes a Good Optimizer for Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"David Brandfonbrener, Depen Morwani, Nikhil Vyas, Rosie Zhao, Sham Kakade","submitted_at":"2024-07-10T18:11:40Z","abstract_excerpt":"Training language models becomes increasingly expensive with scale, prompting numerous attempts to improve optimization efficiency. Despite these efforts, the Adam optimizer remains the most widely used, due to a prevailing view that it is the most effective approach. We aim to compare several optimization algorithms, including SGD, Adafactor, Adam, Lion, and Sophia in the context of autoregressive language modeling across a range of model sizes, hyperparameters, and architecture variants. Our findings indicate that, except for SGD, these algorithms all perform comparably both in their optimal"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.07972","kind":"arxiv","version":2},"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/2407.07972/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":"2026-07-05T10:21:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aJB/et2Va5urCTgW06hBO3aCC1MKUpRu/FFQqjhdpx1r5XLLJqkeK0zGReG3fF/fs0YN1pdy0Hhx8kAzDXKcCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T16:00:36.357502Z"},"content_sha256":"a757820f57937ca13c9edf168c8cfdc9f6e152fd13ecc2edf3eed1217506de5a","schema_version":"1.0","event_id":"sha256:a757820f57937ca13c9edf168c8cfdc9f6e152fd13ecc2edf3eed1217506de5a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PE6VZBQFAGQZCBUV7ATRE67RTX/bundle.json","state_url":"https://pith.science/pith/PE6VZBQFAGQZCBUV7ATRE67RTX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PE6VZBQFAGQZCBUV7ATRE67RTX/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":"2026-08-07T16:00:36Z","links":{"resolver":"https://pith.science/pith/PE6VZBQFAGQZCBUV7ATRE67RTX","bundle":"https://pith.science/pith/PE6VZBQFAGQZCBUV7ATRE67RTX/bundle.json","state":"https://pith.science/pith/PE6VZBQFAGQZCBUV7ATRE67RTX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PE6VZBQFAGQZCBUV7ATRE67RTX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:PE6VZBQFAGQZCBUV7ATRE67RTX","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":"0fda091f70fdae1b3136d28c8d96a9220ebf343dddf6625ef059514f198d32ac","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-07-10T18:11:40Z","title_canon_sha256":"90e08be39dcc38bfd4eecb77f672a35f140d22d1cd8e6e24a36606a0ac53a851"},"schema_version":"1.0","source":{"id":"2407.07972","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.07972","created_at":"2026-07-05T10:21:21Z"},{"alias_kind":"arxiv_version","alias_value":"2407.07972v2","created_at":"2026-07-05T10:21:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.07972","created_at":"2026-07-05T10:21:21Z"},{"alias_kind":"pith_short_12","alias_value":"PE6VZBQFAGQZ","created_at":"2026-07-05T10:21:21Z"},{"alias_kind":"pith_short_16","alias_value":"PE6VZBQFAGQZCBUV","created_at":"2026-07-05T10:21:21Z"},{"alias_kind":"pith_short_8","alias_value":"PE6VZBQF","created_at":"2026-07-05T10:21:21Z"}],"graph_snapshots":[{"event_id":"sha256:a757820f57937ca13c9edf168c8cfdc9f6e152fd13ecc2edf3eed1217506de5a","target":"graph","created_at":"2026-07-05T10:21:21Z","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/2407.07972/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Training language models becomes increasingly expensive with scale, prompting numerous attempts to improve optimization efficiency. Despite these efforts, the Adam optimizer remains the most widely used, due to a prevailing view that it is the most effective approach. We aim to compare several optimization algorithms, including SGD, Adafactor, Adam, Lion, and Sophia in the context of autoregressive language modeling across a range of model sizes, hyperparameters, and architecture variants. Our findings indicate that, except for SGD, these algorithms all perform comparably both in their optimal","authors_text":"David Brandfonbrener, Depen Morwani, Nikhil Vyas, Rosie Zhao, Sham Kakade","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-07-10T18:11:40Z","title":"Deconstructing What Makes a Good Optimizer for Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.07972","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:a79185ec80d4bd4a4f7040e4d64e0efe2bff36ce3264f026d9a351d804f01066","target":"record","created_at":"2026-07-05T10:21:21Z","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":"0fda091f70fdae1b3136d28c8d96a9220ebf343dddf6625ef059514f198d32ac","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-07-10T18:11:40Z","title_canon_sha256":"90e08be39dcc38bfd4eecb77f672a35f140d22d1cd8e6e24a36606a0ac53a851"},"schema_version":"1.0","source":{"id":"2407.07972","kind":"arxiv","version":2}},"canonical_sha256":"793d5c860501a1910695f827127bf19de36e1bcf61853281cdd5c5829379c809","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"793d5c860501a1910695f827127bf19de36e1bcf61853281cdd5c5829379c809","first_computed_at":"2026-07-05T10:21:21.516591Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:21:21.516591Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mFBkgz65ECpq9uvYbtBieWlRkHzZJ8diZuFQx5s/YIKgMDed1HhxyIoAh41qYeMdRwamNgf6kp7LbRS5549MAw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:21:21.517133Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.07972","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a79185ec80d4bd4a4f7040e4d64e0efe2bff36ce3264f026d9a351d804f01066","sha256:a757820f57937ca13c9edf168c8cfdc9f6e152fd13ecc2edf3eed1217506de5a"],"state_sha256":"5b34735d08c6e27b5f660eacc062d41d1c3b55a3640abeda998c3a3363b60d20"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gU+XcZxGinliLsojja1NeAERsk13UFwiiytsj3grHy6CW07UFwuRHsvytKrhgJUpLQKtrpgktD52WDCC4GhtBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T16:00:36.373018Z","bundle_sha256":"a32f2f55590815e69e60267a5ad75ee7e40def5ec92020f1ec43bafac8130998"}}