{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:RL3ZAZYHLSMKEPYNYYQRQUTJT5","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":"4e4e1f581a05c43e2d00a650d774de1494a1b44f3f03b8fe59866b844bd859a3","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-07-08T12:32:51Z","title_canon_sha256":"476e1a11fd78f642353fad8096a6739d1b0bcca7100d47088cbc587c4a96f0be"},"schema_version":"1.0","source":{"id":"2407.05872","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.05872","created_at":"2026-07-05T08:44:39Z"},{"alias_kind":"arxiv_version","alias_value":"2407.05872v2","created_at":"2026-07-05T08:44:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.05872","created_at":"2026-07-05T08:44:39Z"},{"alias_kind":"pith_short_12","alias_value":"RL3ZAZYHLSMK","created_at":"2026-07-05T08:44:39Z"},{"alias_kind":"pith_short_16","alias_value":"RL3ZAZYHLSMKEPYN","created_at":"2026-07-05T08:44:39Z"},{"alias_kind":"pith_short_8","alias_value":"RL3ZAZYH","created_at":"2026-07-05T08:44:39Z"}],"graph_snapshots":[{"event_id":"sha256:e2f2feca5a96f776b6fa8aa355508554694f778634b3259e33a8129759b0771f","target":"graph","created_at":"2026-07-05T08:44:39Z","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/2407.05872/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Robust and effective scaling of models from small to large width typically requires the precise adjustment of many algorithmic and architectural details, such as parameterization and optimizer choices. In this work, we propose a new perspective on parameterization by investigating a key assumption in prior work about the alignment between parameters and data and derive new theoretical results under weaker assumptions and a broader set of optimizers. Our extensive empirical investigation includes tens of thousands of models trained with all combinations of three optimizers, four parameterizatio","authors_text":"Alexander A. Alemi, Izzeddin Gur, Jaehoon Lee, Jascha Sohl-Dickstein, Jeffrey Pennington, Katie Everett, Lechao Xiao, Leslie Pack Kaelbling, Mitchell Wortsman, Peter J. Liu, Roman Novak","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-07-08T12:32:51Z","title":"Scaling Exponents Across Parameterizations and Optimizers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.05872","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":"sha256:80120eb26d5bf5e579c48f5744e0dc882495ba496b1ddc5cf7c2156adb387286","target":"record","created_at":"2026-07-05T08:44:39Z","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":"4e4e1f581a05c43e2d00a650d774de1494a1b44f3f03b8fe59866b844bd859a3","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-07-08T12:32:51Z","title_canon_sha256":"476e1a11fd78f642353fad8096a6739d1b0bcca7100d47088cbc587c4a96f0be"},"schema_version":"1.0","source":{"id":"2407.05872","kind":"arxiv","version":2}},"canonical_sha256":"8af79067075c98a23f0dc6211852699f6e25ad98824c1c3dde95129be67c7774","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8af79067075c98a23f0dc6211852699f6e25ad98824c1c3dde95129be67c7774","first_computed_at":"2026-07-05T08:44:39.244004Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:44:39.244004Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pgBmzfM2GUaYdMmD8tI7tjRsJ20IeJf+jX6xH8+VcmDZXr1GQauRA/SGUupKlnMWR9ocoGM/TEAp9hof+vlgBA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:44:39.244459Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.05872","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:80120eb26d5bf5e579c48f5744e0dc882495ba496b1ddc5cf7c2156adb387286","sha256:e2f2feca5a96f776b6fa8aa355508554694f778634b3259e33a8129759b0771f"],"state_sha256":"9bff05e21fd99f020031a73d1b37fe456b2bf18540605c100c0f78dba8ba80b2"}