{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:4FLOZH33FZP4TDWUK4AOHL3LRF","short_pith_number":"pith:4FLOZH33","canonical_record":{"source":{"id":"2402.16788","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-26T18:01:41Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"fe654156e0cba35de74ba411c2d5cf129de4bbcf7629ec7c1983267930c32071","abstract_canon_sha256":"fc598aa92335a1dfa8530fac6cfb009aaebba392f91a09d4ecbfa9f33a751053"},"schema_version":"1.0"},"canonical_sha256":"e156ec9f7b2e5fc98ed45700e3af6b897c345011c7afbf87c3becb8a9790bc6e","source":{"kind":"arxiv","id":"2402.16788","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.16788","created_at":"2026-07-05T09:23:03Z"},{"alias_kind":"arxiv_version","alias_value":"2402.16788v4","created_at":"2026-07-05T09:23:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.16788","created_at":"2026-07-05T09:23:03Z"},{"alias_kind":"pith_short_12","alias_value":"4FLOZH33FZP4","created_at":"2026-07-05T09:23:03Z"},{"alias_kind":"pith_short_16","alias_value":"4FLOZH33FZP4TDWU","created_at":"2026-07-05T09:23:03Z"},{"alias_kind":"pith_short_8","alias_value":"4FLOZH33","created_at":"2026-07-05T09:23:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:4FLOZH33FZP4TDWUK4AOHL3LRF","target":"record","payload":{"canonical_record":{"source":{"id":"2402.16788","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-26T18:01:41Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"fe654156e0cba35de74ba411c2d5cf129de4bbcf7629ec7c1983267930c32071","abstract_canon_sha256":"fc598aa92335a1dfa8530fac6cfb009aaebba392f91a09d4ecbfa9f33a751053"},"schema_version":"1.0"},"canonical_sha256":"e156ec9f7b2e5fc98ed45700e3af6b897c345011c7afbf87c3becb8a9790bc6e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:23:03.602137Z","signature_b64":"WjG32tMz7mRUf09FN7wMF6Z4volnEEmjuSojWjFndUFDB8nBnp5PvQTTcXsndTTF1hSOPU8iruWEeobWxulICw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e156ec9f7b2e5fc98ed45700e3af6b897c345011c7afbf87c3becb8a9790bc6e","last_reissued_at":"2026-07-05T09:23:03.601659Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:23:03.601659Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.16788","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:23:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gQWf2YuYE2h/f6QsK5X6IqVCZWr7OQ1L5ZdYBoQquk5Pj/dOthbhNWo7aSZjS9s75exixH1+3TLjWpTiTHf2AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T07:49:51.545646Z"},"content_sha256":"3f67b413d94f0665d991277a95af43901dd519d76fe2306d1149fb816e6b8a8e","schema_version":"1.0","event_id":"sha256:3f67b413d94f0665d991277a95af43901dd519d76fe2306d1149fb816e6b8a8e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:4FLOZH33FZP4TDWUK4AOHL3LRF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Why Transformers Need Adam: A Hessian Perspective","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Congliang Chen, Ruoyu Sun, Tian Ding, Yushun Zhang, Zhi-Quan Luo, Ziniu Li","submitted_at":"2024-02-26T18:01:41Z","abstract_excerpt":"SGD performs worse than Adam by a significant margin on Transformers, but the reason remains unclear. In this work, we provide an explanation through the lens of Hessian: (i) Transformers are \"heterogeneous\": the Hessian spectrum across parameter blocks vary dramatically, a phenomenon we call \"block heterogeneity\"; (ii) Heterogeneity hampers SGD: SGD performs worse than Adam on problems with block heterogeneity. To validate (i) and (ii), we check various Transformers, CNNs, MLPs, and quadratic problems, and find that SGD can perform on par with Adam on problems without block heterogeneity, but"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.16788","kind":"arxiv","version":4},"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/2402.16788/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":"2026-07-05T09:23:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rdlp1ske/NJ/f+3bO7E7P6bJrjtAJmETwVkmCh+/ekWSpP0qCFBrVmXgOA7QWtERXUqzOs76+iHf12+CVNsqDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T07:49:51.546587Z"},"content_sha256":"a65051d3a592618ecc3d799565e86a44c4963c6d6230de87843cb6b843232094","schema_version":"1.0","event_id":"sha256:a65051d3a592618ecc3d799565e86a44c4963c6d6230de87843cb6b843232094"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4FLOZH33FZP4TDWUK4AOHL3LRF/bundle.json","state_url":"https://pith.science/pith/4FLOZH33FZP4TDWUK4AOHL3LRF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4FLOZH33FZP4TDWUK4AOHL3LRF/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":"2026-08-04T07:49:51Z","links":{"resolver":"https://pith.science/pith/4FLOZH33FZP4TDWUK4AOHL3LRF","bundle":"https://pith.science/pith/4FLOZH33FZP4TDWUK4AOHL3LRF/bundle.json","state":"https://pith.science/pith/4FLOZH33FZP4TDWUK4AOHL3LRF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4FLOZH33FZP4TDWUK4AOHL3LRF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:4FLOZH33FZP4TDWUK4AOHL3LRF","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":"fc598aa92335a1dfa8530fac6cfb009aaebba392f91a09d4ecbfa9f33a751053","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-26T18:01:41Z","title_canon_sha256":"fe654156e0cba35de74ba411c2d5cf129de4bbcf7629ec7c1983267930c32071"},"schema_version":"1.0","source":{"id":"2402.16788","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.16788","created_at":"2026-07-05T09:23:03Z"},{"alias_kind":"arxiv_version","alias_value":"2402.16788v4","created_at":"2026-07-05T09:23:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.16788","created_at":"2026-07-05T09:23:03Z"},{"alias_kind":"pith_short_12","alias_value":"4FLOZH33FZP4","created_at":"2026-07-05T09:23:03Z"},{"alias_kind":"pith_short_16","alias_value":"4FLOZH33FZP4TDWU","created_at":"2026-07-05T09:23:03Z"},{"alias_kind":"pith_short_8","alias_value":"4FLOZH33","created_at":"2026-07-05T09:23:03Z"}],"graph_snapshots":[{"event_id":"sha256:a65051d3a592618ecc3d799565e86a44c4963c6d6230de87843cb6b843232094","target":"graph","created_at":"2026-07-05T09:23:03Z","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/2402.16788/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"SGD performs worse than Adam by a significant margin on Transformers, but the reason remains unclear. In this work, we provide an explanation through the lens of Hessian: (i) Transformers are \"heterogeneous\": the Hessian spectrum across parameter blocks vary dramatically, a phenomenon we call \"block heterogeneity\"; (ii) Heterogeneity hampers SGD: SGD performs worse than Adam on problems with block heterogeneity. To validate (i) and (ii), we check various Transformers, CNNs, MLPs, and quadratic problems, and find that SGD can perform on par with Adam on problems without block heterogeneity, but","authors_text":"Congliang Chen, Ruoyu Sun, Tian Ding, Yushun Zhang, Zhi-Quan Luo, Ziniu Li","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-26T18:01:41Z","title":"Why Transformers Need Adam: A Hessian Perspective"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.16788","kind":"arxiv","version":4},"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":"sha256:3f67b413d94f0665d991277a95af43901dd519d76fe2306d1149fb816e6b8a8e","target":"record","created_at":"2026-07-05T09:23:03Z","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":"fc598aa92335a1dfa8530fac6cfb009aaebba392f91a09d4ecbfa9f33a751053","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-26T18:01:41Z","title_canon_sha256":"fe654156e0cba35de74ba411c2d5cf129de4bbcf7629ec7c1983267930c32071"},"schema_version":"1.0","source":{"id":"2402.16788","kind":"arxiv","version":4}},"canonical_sha256":"e156ec9f7b2e5fc98ed45700e3af6b897c345011c7afbf87c3becb8a9790bc6e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e156ec9f7b2e5fc98ed45700e3af6b897c345011c7afbf87c3becb8a9790bc6e","first_computed_at":"2026-07-05T09:23:03.601659Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:23:03.601659Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WjG32tMz7mRUf09FN7wMF6Z4volnEEmjuSojWjFndUFDB8nBnp5PvQTTcXsndTTF1hSOPU8iruWEeobWxulICw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:23:03.602137Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.16788","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3f67b413d94f0665d991277a95af43901dd519d76fe2306d1149fb816e6b8a8e","sha256:a65051d3a592618ecc3d799565e86a44c4963c6d6230de87843cb6b843232094"],"state_sha256":"8c6cf580e0b952b3015589cf8dc05dcd3244d59f590eeffaf6872c9444211b7e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"n+66lxfJfh8jMVJvU1/HkQ2Mw8D3HFCPPNxWRjqjyqpmtBr9kVvMyfourfNhxUUe8BZQP2frIjApaG6jL9YbAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T07:49:51.554097Z","bundle_sha256":"aba85addae30b94b17ab8234187c0d2c9cdeb2976bd73f516622bbeb78e1a004"}}