{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:EXA7RSNMKXCFSGMK7AKK654RMA","short_pith_number":"pith:EXA7RSNM","canonical_record":{"source":{"id":"2605.18694","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2026-05-18T17:30:15Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"852e2397aad318b10a1b88e86207caf685195447248fc7e88593e68e5d6d3571","abstract_canon_sha256":"9d11a8679fb220d64409b8c6390d03e4fb52b64b002dfbe5759cd879e9188753"},"schema_version":"1.0"},"canonical_sha256":"25c1f8c9ac55c459198af814af7791602fcfe8d8feb89e7dc6b46f4a46c7cfe5","source":{"kind":"arxiv","id":"2605.18694","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.18694","created_at":"2026-05-20T00:06:15Z"},{"alias_kind":"arxiv_version","alias_value":"2605.18694v1","created_at":"2026-05-20T00:06:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.18694","created_at":"2026-05-20T00:06:15Z"},{"alias_kind":"pith_short_12","alias_value":"EXA7RSNMKXCF","created_at":"2026-05-20T00:06:15Z"},{"alias_kind":"pith_short_16","alias_value":"EXA7RSNMKXCFSGMK","created_at":"2026-05-20T00:06:15Z"},{"alias_kind":"pith_short_8","alias_value":"EXA7RSNM","created_at":"2026-05-20T00:06:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:EXA7RSNMKXCFSGMK7AKK654RMA","target":"record","payload":{"canonical_record":{"source":{"id":"2605.18694","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2026-05-18T17:30:15Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"852e2397aad318b10a1b88e86207caf685195447248fc7e88593e68e5d6d3571","abstract_canon_sha256":"9d11a8679fb220d64409b8c6390d03e4fb52b64b002dfbe5759cd879e9188753"},"schema_version":"1.0"},"canonical_sha256":"25c1f8c9ac55c459198af814af7791602fcfe8d8feb89e7dc6b46f4a46c7cfe5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:06:15.420379Z","signature_b64":"tam8w8EpiJPnwcm1wbBrdPnpj3UacHNe1ahCdKeTsPgzJZleZxzKUx+gqSaIUwRoHJIfnVksSXfY2D7t9L55BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"25c1f8c9ac55c459198af814af7791602fcfe8d8feb89e7dc6b46f4a46c7cfe5","last_reissued_at":"2026-05-20T00:06:15.419472Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:06:15.419472Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.18694","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":"2026-05-20T00:06:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HVKg/2fFp2+LbQlEaaF5EiAKYQGbcuyG2n3Ph4M66mZOQ7VWiIjErkqLQubk2DuufG5TEEBjPoW4t0y6zP9GAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T16:34:45.617215Z"},"content_sha256":"e0fa614de5da9a24c3170c0430c975d75e39f8c98c9e6e6b66f97791a4fd1f17","schema_version":"1.0","event_id":"sha256:e0fa614de5da9a24c3170c0430c975d75e39f8c98c9e6e6b66f97791a4fd1f17"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:EXA7RSNMKXCFSGMK7AKK654RMA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Can Adaptive Gradient Methods Converge under Heavy-Tailed Noise? A Case Study of AdaGrad","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"math.OC","authors_text":"Zijian Liu","submitted_at":"2026-05-18T17:30:15Z","abstract_excerpt":"Many tasks in modern machine learning are observed to involve heavy-tailed gradient noise during the optimization process. To manage this realistic and challenging setting, new mechanisms, such as gradient clipping and gradient normalization, have been introduced to ensure the convergence of first-order algorithms. However, adaptive gradient methods, a famous class of modern optimizers that includes popular $\\mathtt{Adam}$ and $\\mathtt{AdamW}$, often perform well even without any extra operations mentioned above. It is therefore natural to ask whether adaptive gradient methods can converge und"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.18694","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/2605.18694/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"claim_evidence","ran_at":"2026-05-20T00:01:59.090592Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"0ee12c7285d16d2c60647522e18db5ec70733384bb7c6f327af9051aaea64718"},"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":"2026-05-20T00:06:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kgJITyqPMhs74WiFbXoOyKVNi0Ta5Gb36DJlxOSXwv9K7Ao9aZR2y9+gvqz9o6XnQGG8OgPfSld5/t0A4qNHDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T16:34:45.617952Z"},"content_sha256":"44b3bbd28ef80255b29be295182524144670e65ffd68a55f237a57d35cadb5d5","schema_version":"1.0","event_id":"sha256:44b3bbd28ef80255b29be295182524144670e65ffd68a55f237a57d35cadb5d5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EXA7RSNMKXCFSGMK7AKK654RMA/bundle.json","state_url":"https://pith.science/pith/EXA7RSNMKXCFSGMK7AKK654RMA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EXA7RSNMKXCFSGMK7AKK654RMA/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":"2026-05-27T16:34:45Z","links":{"resolver":"https://pith.science/pith/EXA7RSNMKXCFSGMK7AKK654RMA","bundle":"https://pith.science/pith/EXA7RSNMKXCFSGMK7AKK654RMA/bundle.json","state":"https://pith.science/pith/EXA7RSNMKXCFSGMK7AKK654RMA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EXA7RSNMKXCFSGMK7AKK654RMA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:EXA7RSNMKXCFSGMK7AKK654RMA","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":"9d11a8679fb220d64409b8c6390d03e4fb52b64b002dfbe5759cd879e9188753","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2026-05-18T17:30:15Z","title_canon_sha256":"852e2397aad318b10a1b88e86207caf685195447248fc7e88593e68e5d6d3571"},"schema_version":"1.0","source":{"id":"2605.18694","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.18694","created_at":"2026-05-20T00:06:15Z"},{"alias_kind":"arxiv_version","alias_value":"2605.18694v1","created_at":"2026-05-20T00:06:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.18694","created_at":"2026-05-20T00:06:15Z"},{"alias_kind":"pith_short_12","alias_value":"EXA7RSNMKXCF","created_at":"2026-05-20T00:06:15Z"},{"alias_kind":"pith_short_16","alias_value":"EXA7RSNMKXCFSGMK","created_at":"2026-05-20T00:06:15Z"},{"alias_kind":"pith_short_8","alias_value":"EXA7RSNM","created_at":"2026-05-20T00:06:15Z"}],"graph_snapshots":[{"event_id":"sha256:44b3bbd28ef80255b29be295182524144670e65ffd68a55f237a57d35cadb5d5","target":"graph","created_at":"2026-05-20T00:06:15Z","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":[{"findings_count":0,"name":"claim_evidence","ran_at":"2026-05-20T00:01:59.090592Z","status":"completed","version":"1.0.0"}],"endpoint":"/pith/2605.18694/integrity.json","findings":[],"snapshot_sha256":"0ee12c7285d16d2c60647522e18db5ec70733384bb7c6f327af9051aaea64718","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Many tasks in modern machine learning are observed to involve heavy-tailed gradient noise during the optimization process. To manage this realistic and challenging setting, new mechanisms, such as gradient clipping and gradient normalization, have been introduced to ensure the convergence of first-order algorithms. However, adaptive gradient methods, a famous class of modern optimizers that includes popular $\\mathtt{Adam}$ and $\\mathtt{AdamW}$, often perform well even without any extra operations mentioned above. It is therefore natural to ask whether adaptive gradient methods can converge und","authors_text":"Zijian Liu","cross_cats":["cs.LG","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2026-05-18T17:30:15Z","title":"Can Adaptive Gradient Methods Converge under Heavy-Tailed Noise? A Case Study of AdaGrad"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.18694","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:e0fa614de5da9a24c3170c0430c975d75e39f8c98c9e6e6b66f97791a4fd1f17","target":"record","created_at":"2026-05-20T00:06:15Z","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":"9d11a8679fb220d64409b8c6390d03e4fb52b64b002dfbe5759cd879e9188753","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2026-05-18T17:30:15Z","title_canon_sha256":"852e2397aad318b10a1b88e86207caf685195447248fc7e88593e68e5d6d3571"},"schema_version":"1.0","source":{"id":"2605.18694","kind":"arxiv","version":1}},"canonical_sha256":"25c1f8c9ac55c459198af814af7791602fcfe8d8feb89e7dc6b46f4a46c7cfe5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"25c1f8c9ac55c459198af814af7791602fcfe8d8feb89e7dc6b46f4a46c7cfe5","first_computed_at":"2026-05-20T00:06:15.419472Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:06:15.419472Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tam8w8EpiJPnwcm1wbBrdPnpj3UacHNe1ahCdKeTsPgzJZleZxzKUx+gqSaIUwRoHJIfnVksSXfY2D7t9L55BA==","signature_status":"signed_v1","signed_at":"2026-05-20T00:06:15.420379Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.18694","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e0fa614de5da9a24c3170c0430c975d75e39f8c98c9e6e6b66f97791a4fd1f17","sha256:44b3bbd28ef80255b29be295182524144670e65ffd68a55f237a57d35cadb5d5"],"state_sha256":"93d691437a1fb1020bcdb6f98c73e502eee23be72775c6864e497a8d5910d77d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WAVrJW/Bpg4I033lzR89ua5NtqWtMRODHqwbq2XwLSpREWzEzWugDBTuHumY1MoNEI23kf99Ez5y82gc6/P9AQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T16:34:45.621395Z","bundle_sha256":"ca730837d7dd249cc4ed0b1b8155f088febfda7e65e91cd3cbb989e1b4c8b8ea"}}