{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:E46AT2N3NB4MU2SGFG3KAZC3EZ","short_pith_number":"pith:E46AT2N3","canonical_record":{"source":{"id":"2406.15244","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-21T15:29:31Z","cross_cats_sorted":["math.OC"],"title_canon_sha256":"549b0c110a784daffc2277fa7fb4f994dbc54577b1610933111b643da2483d7a","abstract_canon_sha256":"7015e0feabaea010d0151ec3e334db2c1bdf2fb166cd9ad013e580fd9b704aee"},"schema_version":"1.0"},"canonical_sha256":"273c09e9bb6878ca6a4629b6a0645b265859ba902d9433b30fd9f3ff0e272e01","source":{"kind":"arxiv","id":"2406.15244","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.15244","created_at":"2026-07-05T09:19:59Z"},{"alias_kind":"arxiv_version","alias_value":"2406.15244v2","created_at":"2026-07-05T09:19:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.15244","created_at":"2026-07-05T09:19:59Z"},{"alias_kind":"pith_short_12","alias_value":"E46AT2N3NB4M","created_at":"2026-07-05T09:19:59Z"},{"alias_kind":"pith_short_16","alias_value":"E46AT2N3NB4MU2SG","created_at":"2026-07-05T09:19:59Z"},{"alias_kind":"pith_short_8","alias_value":"E46AT2N3","created_at":"2026-07-05T09:19:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:E46AT2N3NB4MU2SGFG3KAZC3EZ","target":"record","payload":{"canonical_record":{"source":{"id":"2406.15244","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-21T15:29:31Z","cross_cats_sorted":["math.OC"],"title_canon_sha256":"549b0c110a784daffc2277fa7fb4f994dbc54577b1610933111b643da2483d7a","abstract_canon_sha256":"7015e0feabaea010d0151ec3e334db2c1bdf2fb166cd9ad013e580fd9b704aee"},"schema_version":"1.0"},"canonical_sha256":"273c09e9bb6878ca6a4629b6a0645b265859ba902d9433b30fd9f3ff0e272e01","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:19:59.858808Z","signature_b64":"GwSBhkWoV9UF6rKWeSd0CqO2eh5zeqBoMIsGEIZuB82HthtyVkGh/VRAHre/UEKotmKoMkq5cQHAPAa6Q14YBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"273c09e9bb6878ca6a4629b6a0645b265859ba902d9433b30fd9f3ff0e272e01","last_reissued_at":"2026-07-05T09:19:59.858285Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:19:59.858285Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.15244","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":"2026-07-05T09:19:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+vKxdcKGHoIXgNCLHigcGV0yfXhUC+cBk4a/ABL1MV57C+AG3TJgMR8XM1FW06vSmQAOPg7wW9C6GB8aUKteAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T04:46:36.354770Z"},"content_sha256":"2d162aa5fcf4e02f94980c9484251564ae16127bb6e82eb9fe8eb4816a0cf702","schema_version":"1.0","event_id":"sha256:2d162aa5fcf4e02f94980c9484251564ae16127bb6e82eb9fe8eb4816a0cf702"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:E46AT2N3NB4MU2SGFG3KAZC3EZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"AdaGrad under Anisotropic Smoothness","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["math.OC"],"primary_cat":"cs.LG","authors_text":"Rui Pan, Tong Zhang, Yuxing Liu","submitted_at":"2024-06-21T15:29:31Z","abstract_excerpt":"Adaptive gradient methods have been widely adopted in training large-scale deep neural networks, especially large foundation models. Despite the huge success in practice, their theoretical advantages over classical gradient methods with uniform step sizes across all coordinates (e.g. SGD) have not been fully understood, especially in the large batch-size setting commonly used in practice. This is because the only theoretical result that can demonstrate this benefit was obtained in the original paper of Adagrad for convex nonsmooth objective functions, which is insufficient for large batch algo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.15244","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/2406.15244/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":"2026-07-05T09:19:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"z8jdgbXlnjye+4G129nu4Vgka3FhUeZA7zEMeqBgTMMLExs110s0ZwZ7lv3g3NClLLjvYmZOAYv36JbF1mE/Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T04:46:36.355168Z"},"content_sha256":"8199ac34f589b6912743644af254cf9457aad0d0a74e2e9e9857177e74c57521","schema_version":"1.0","event_id":"sha256:8199ac34f589b6912743644af254cf9457aad0d0a74e2e9e9857177e74c57521"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/E46AT2N3NB4MU2SGFG3KAZC3EZ/bundle.json","state_url":"https://pith.science/pith/E46AT2N3NB4MU2SGFG3KAZC3EZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/E46AT2N3NB4MU2SGFG3KAZC3EZ/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":"2026-08-04T04:46:36Z","links":{"resolver":"https://pith.science/pith/E46AT2N3NB4MU2SGFG3KAZC3EZ","bundle":"https://pith.science/pith/E46AT2N3NB4MU2SGFG3KAZC3EZ/bundle.json","state":"https://pith.science/pith/E46AT2N3NB4MU2SGFG3KAZC3EZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/E46AT2N3NB4MU2SGFG3KAZC3EZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:E46AT2N3NB4MU2SGFG3KAZC3EZ","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":"7015e0feabaea010d0151ec3e334db2c1bdf2fb166cd9ad013e580fd9b704aee","cross_cats_sorted":["math.OC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-21T15:29:31Z","title_canon_sha256":"549b0c110a784daffc2277fa7fb4f994dbc54577b1610933111b643da2483d7a"},"schema_version":"1.0","source":{"id":"2406.15244","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.15244","created_at":"2026-07-05T09:19:59Z"},{"alias_kind":"arxiv_version","alias_value":"2406.15244v2","created_at":"2026-07-05T09:19:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.15244","created_at":"2026-07-05T09:19:59Z"},{"alias_kind":"pith_short_12","alias_value":"E46AT2N3NB4M","created_at":"2026-07-05T09:19:59Z"},{"alias_kind":"pith_short_16","alias_value":"E46AT2N3NB4MU2SG","created_at":"2026-07-05T09:19:59Z"},{"alias_kind":"pith_short_8","alias_value":"E46AT2N3","created_at":"2026-07-05T09:19:59Z"}],"graph_snapshots":[{"event_id":"sha256:8199ac34f589b6912743644af254cf9457aad0d0a74e2e9e9857177e74c57521","target":"graph","created_at":"2026-07-05T09:19:59Z","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/2406.15244/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Adaptive gradient methods have been widely adopted in training large-scale deep neural networks, especially large foundation models. Despite the huge success in practice, their theoretical advantages over classical gradient methods with uniform step sizes across all coordinates (e.g. SGD) have not been fully understood, especially in the large batch-size setting commonly used in practice. This is because the only theoretical result that can demonstrate this benefit was obtained in the original paper of Adagrad for convex nonsmooth objective functions, which is insufficient for large batch algo","authors_text":"Rui Pan, Tong Zhang, Yuxing Liu","cross_cats":["math.OC"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-21T15:29:31Z","title":"AdaGrad under Anisotropic Smoothness"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.15244","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":"sha256:2d162aa5fcf4e02f94980c9484251564ae16127bb6e82eb9fe8eb4816a0cf702","target":"record","created_at":"2026-07-05T09:19:59Z","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":"7015e0feabaea010d0151ec3e334db2c1bdf2fb166cd9ad013e580fd9b704aee","cross_cats_sorted":["math.OC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-21T15:29:31Z","title_canon_sha256":"549b0c110a784daffc2277fa7fb4f994dbc54577b1610933111b643da2483d7a"},"schema_version":"1.0","source":{"id":"2406.15244","kind":"arxiv","version":2}},"canonical_sha256":"273c09e9bb6878ca6a4629b6a0645b265859ba902d9433b30fd9f3ff0e272e01","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"273c09e9bb6878ca6a4629b6a0645b265859ba902d9433b30fd9f3ff0e272e01","first_computed_at":"2026-07-05T09:19:59.858285Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:19:59.858285Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GwSBhkWoV9UF6rKWeSd0CqO2eh5zeqBoMIsGEIZuB82HthtyVkGh/VRAHre/UEKotmKoMkq5cQHAPAa6Q14YBw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:19:59.858808Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.15244","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2d162aa5fcf4e02f94980c9484251564ae16127bb6e82eb9fe8eb4816a0cf702","sha256:8199ac34f589b6912743644af254cf9457aad0d0a74e2e9e9857177e74c57521"],"state_sha256":"c1d5dd8f9b01431becdfa09f5353e893af60abc9b2ac31b4d8421e1abd206102"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1zmAr0bk0sNyxPrx4idhADMeHquce8XGsXwM5ezmEU9IGng7IWGX313FCunTkhz+WERVz9hWxAXMFk8n/yLBCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T04:46:36.357992Z","bundle_sha256":"79696851004991d5591c8036e1dbacdd14990fe3531ce8f235fae498a8fd3ca0"}}