{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:OZMXQ4JYXEEHJLQXDZFK7BSEUX","short_pith_number":"pith:OZMXQ4JY","canonical_record":{"source":{"id":"2502.01763","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-03T19:08:32Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"a6f8bdc972ba68b38f238834f8a1651f1382d2b4999fd83a2364d81cf760f57d","abstract_canon_sha256":"2009a615ee3ef15f5dc49ff6a690f92283eb9da2a7d5b5dfc61fe0c067b489f2"},"schema_version":"1.0"},"canonical_sha256":"7659787138b90874ae171e4aaf8644a5d7787599811101953820a45148d6ea30","source":{"kind":"arxiv","id":"2502.01763","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.01763","created_at":"2026-07-05T10:09:18Z"},{"alias_kind":"arxiv_version","alias_value":"2502.01763v1","created_at":"2026-07-05T10:09:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.01763","created_at":"2026-07-05T10:09:18Z"},{"alias_kind":"pith_short_12","alias_value":"OZMXQ4JYXEEH","created_at":"2026-07-05T10:09:18Z"},{"alias_kind":"pith_short_16","alias_value":"OZMXQ4JYXEEHJLQX","created_at":"2026-07-05T10:09:18Z"},{"alias_kind":"pith_short_8","alias_value":"OZMXQ4JY","created_at":"2026-07-05T10:09:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:OZMXQ4JYXEEHJLQXDZFK7BSEUX","target":"record","payload":{"canonical_record":{"source":{"id":"2502.01763","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-03T19:08:32Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"a6f8bdc972ba68b38f238834f8a1651f1382d2b4999fd83a2364d81cf760f57d","abstract_canon_sha256":"2009a615ee3ef15f5dc49ff6a690f92283eb9da2a7d5b5dfc61fe0c067b489f2"},"schema_version":"1.0"},"canonical_sha256":"7659787138b90874ae171e4aaf8644a5d7787599811101953820a45148d6ea30","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:09:18.681299Z","signature_b64":"1Ma2vHBErUZXDGouJ04kL3f7NWW8Din23ix0TYciytaV+Cn5097bQhTCuOgtUI4nOUMClEZ6ImEMz0b14Z0DBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7659787138b90874ae171e4aaf8644a5d7787599811101953820a45148d6ea30","last_reissued_at":"2026-07-05T10:09:18.680808Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:09:18.680808Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.01763","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:09:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fNWdTN7O5Ua7Xu0oQUqe6aVOMGnShN8V0CNLXSCuzEu/fvEiXkC+5aiS7PpbB4qBIopeg4J8Frr9EFHo6tq6CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T23:14:46.154686Z"},"content_sha256":"6e8b2294e5cc17a812df59c232e7e17c11bf3935ac5166602ded5f75db174628","schema_version":"1.0","event_id":"sha256:6e8b2294e5cc17a812df59c232e7e17c11bf3935ac5166602ded5f75db174628"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:OZMXQ4JYXEEHJLQXDZFK7BSEUX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"On The Concurrence of Layer-wise Preconditioning Methods and Provable Feature Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Ansh Nagwekar, Anton Xue, Behrad Moniri, Faraz Rahman, Hamed Hassani, Nikolai Matni, Thomas T. Zhang","submitted_at":"2025-02-03T19:08:32Z","abstract_excerpt":"Layer-wise preconditioning methods are a family of memory-efficient optimization algorithms that introduce preconditioners per axis of each layer's weight tensors. These methods have seen a recent resurgence, demonstrating impressive performance relative to entry-wise (\"diagonal\") preconditioning methods such as Adam(W) on a wide range of neural network optimization tasks. Complementary to their practical performance, we demonstrate that layer-wise preconditioning methods are provably necessary from a statistical perspective. To showcase this, we consider two prototypical models, linear repres"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.01763","kind":"arxiv","version":1},"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/2502.01763/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":"2026-07-05T10:09:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hlO9Oex6Xr/P+LCvtx/O8BlHyG9V7NoY+0buWooOUCYXXySKHY6q3suy0dKAJd5+HjYymaQUiIf5PGk8lGquBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T23:14:46.155195Z"},"content_sha256":"8317b3d4a27d2e37d74bcdb78ce28508b6317b19c81c578a4e7476bcf751b5ed","schema_version":"1.0","event_id":"sha256:8317b3d4a27d2e37d74bcdb78ce28508b6317b19c81c578a4e7476bcf751b5ed"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OZMXQ4JYXEEHJLQXDZFK7BSEUX/bundle.json","state_url":"https://pith.science/pith/OZMXQ4JYXEEHJLQXDZFK7BSEUX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OZMXQ4JYXEEHJLQXDZFK7BSEUX/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":"2026-08-16T23:14:46Z","links":{"resolver":"https://pith.science/pith/OZMXQ4JYXEEHJLQXDZFK7BSEUX","bundle":"https://pith.science/pith/OZMXQ4JYXEEHJLQXDZFK7BSEUX/bundle.json","state":"https://pith.science/pith/OZMXQ4JYXEEHJLQXDZFK7BSEUX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OZMXQ4JYXEEHJLQXDZFK7BSEUX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:OZMXQ4JYXEEHJLQXDZFK7BSEUX","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":"2009a615ee3ef15f5dc49ff6a690f92283eb9da2a7d5b5dfc61fe0c067b489f2","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-03T19:08:32Z","title_canon_sha256":"a6f8bdc972ba68b38f238834f8a1651f1382d2b4999fd83a2364d81cf760f57d"},"schema_version":"1.0","source":{"id":"2502.01763","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.01763","created_at":"2026-07-05T10:09:18Z"},{"alias_kind":"arxiv_version","alias_value":"2502.01763v1","created_at":"2026-07-05T10:09:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.01763","created_at":"2026-07-05T10:09:18Z"},{"alias_kind":"pith_short_12","alias_value":"OZMXQ4JYXEEH","created_at":"2026-07-05T10:09:18Z"},{"alias_kind":"pith_short_16","alias_value":"OZMXQ4JYXEEHJLQX","created_at":"2026-07-05T10:09:18Z"},{"alias_kind":"pith_short_8","alias_value":"OZMXQ4JY","created_at":"2026-07-05T10:09:18Z"}],"graph_snapshots":[{"event_id":"sha256:8317b3d4a27d2e37d74bcdb78ce28508b6317b19c81c578a4e7476bcf751b5ed","target":"graph","created_at":"2026-07-05T10:09:18Z","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/2502.01763/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Layer-wise preconditioning methods are a family of memory-efficient optimization algorithms that introduce preconditioners per axis of each layer's weight tensors. These methods have seen a recent resurgence, demonstrating impressive performance relative to entry-wise (\"diagonal\") preconditioning methods such as Adam(W) on a wide range of neural network optimization tasks. Complementary to their practical performance, we demonstrate that layer-wise preconditioning methods are provably necessary from a statistical perspective. To showcase this, we consider two prototypical models, linear repres","authors_text":"Ansh Nagwekar, Anton Xue, Behrad Moniri, Faraz Rahman, Hamed Hassani, Nikolai Matni, Thomas T. Zhang","cross_cats":["math.OC","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-03T19:08:32Z","title":"On The Concurrence of Layer-wise Preconditioning Methods and Provable Feature Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.01763","kind":"arxiv","version":1},"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":"sha256:6e8b2294e5cc17a812df59c232e7e17c11bf3935ac5166602ded5f75db174628","target":"record","created_at":"2026-07-05T10:09:18Z","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":"2009a615ee3ef15f5dc49ff6a690f92283eb9da2a7d5b5dfc61fe0c067b489f2","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-03T19:08:32Z","title_canon_sha256":"a6f8bdc972ba68b38f238834f8a1651f1382d2b4999fd83a2364d81cf760f57d"},"schema_version":"1.0","source":{"id":"2502.01763","kind":"arxiv","version":1}},"canonical_sha256":"7659787138b90874ae171e4aaf8644a5d7787599811101953820a45148d6ea30","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7659787138b90874ae171e4aaf8644a5d7787599811101953820a45148d6ea30","first_computed_at":"2026-07-05T10:09:18.680808Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:09:18.680808Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1Ma2vHBErUZXDGouJ04kL3f7NWW8Din23ix0TYciytaV+Cn5097bQhTCuOgtUI4nOUMClEZ6ImEMz0b14Z0DBg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:09:18.681299Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.01763","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6e8b2294e5cc17a812df59c232e7e17c11bf3935ac5166602ded5f75db174628","sha256:8317b3d4a27d2e37d74bcdb78ce28508b6317b19c81c578a4e7476bcf751b5ed"],"state_sha256":"d37f33ffdc0292c1f792f8e0d71f58234e60cda2ebf9f80e5ab3f820391c70d6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wBjkSnJbBMdxFxSgk9Sl/YeQalxxXigRtRoPf9/Ux9q9bdW8yY1u0g6xbwbuigf1iwpVzJaDqW85NhiHKmS4Dw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-16T23:14:46.158594Z","bundle_sha256":"1a30fd3698d2f7d14504fc6db966d06e05a37254bd34367af45fbf712db17210"}}