{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:5IM3U267ZFFJZSLQ74E6PHQQ57","short_pith_number":"pith:5IM3U267","canonical_record":{"source":{"id":"2304.13960","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-04-27T05:41:13Z","cross_cats_sorted":["math.OC"],"title_canon_sha256":"bc450947089ea27bcdff3cad3130b4b6ba720793156fdc7e34a0c77e918f569c","abstract_canon_sha256":"b37c59f169ca4b69b6df3c26df36d74fa042cf60b7943f2e005a362a864ed590"},"schema_version":"1.0"},"canonical_sha256":"ea19ba6bdfc94a9cc970ff09e79e10efdd8dacf65ddd161b0d8f75c60c9a4e22","source":{"kind":"arxiv","id":"2304.13960","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.13960","created_at":"2026-07-05T06:04:59Z"},{"alias_kind":"arxiv_version","alias_value":"2304.13960v1","created_at":"2026-07-05T06:04:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.13960","created_at":"2026-07-05T06:04:59Z"},{"alias_kind":"pith_short_12","alias_value":"5IM3U267ZFFJ","created_at":"2026-07-05T06:04:59Z"},{"alias_kind":"pith_short_16","alias_value":"5IM3U267ZFFJZSLQ","created_at":"2026-07-05T06:04:59Z"},{"alias_kind":"pith_short_8","alias_value":"5IM3U267","created_at":"2026-07-05T06:04:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:5IM3U267ZFFJZSLQ74E6PHQQ57","target":"record","payload":{"canonical_record":{"source":{"id":"2304.13960","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-04-27T05:41:13Z","cross_cats_sorted":["math.OC"],"title_canon_sha256":"bc450947089ea27bcdff3cad3130b4b6ba720793156fdc7e34a0c77e918f569c","abstract_canon_sha256":"b37c59f169ca4b69b6df3c26df36d74fa042cf60b7943f2e005a362a864ed590"},"schema_version":"1.0"},"canonical_sha256":"ea19ba6bdfc94a9cc970ff09e79e10efdd8dacf65ddd161b0d8f75c60c9a4e22","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:04:59.035695Z","signature_b64":"oZBerIg9LR/mrelz9steP8UkOkbLyN+FVE72P3d1NfgDTlqMd8g3WRPJb+81P6Sh5ATwmEr5gSKmyGzjIK2WCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ea19ba6bdfc94a9cc970ff09e79e10efdd8dacf65ddd161b0d8f75c60c9a4e22","last_reissued_at":"2026-07-05T06:04:59.035221Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:04:59.035221Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2304.13960","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":"2026-07-05T06:04:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yXRSN5V7ySbj8rHeS32g9+1S+mJuB4rcWSBQ8yXajWMdj2p4he5i/GTZSr39LBT0CM/oOOezxcvj7xFvGjqzCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T12:43:13.691954Z"},"content_sha256":"b7aa9593c0d56e6836ff7aa42a924f35c7758a178420d15cf4d354cab66dd33f","schema_version":"1.0","event_id":"sha256:b7aa9593c0d56e6836ff7aa42a924f35c7758a178420d15cf4d354cab66dd33f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:5IM3U267ZFFJZSLQ74E6PHQQ57","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Noise Is Not the Main Factor Behind the Gap Between SGD and Adam on Transformers, but Sign Descent Might Be","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC"],"primary_cat":"cs.LG","authors_text":"Frederik Kunstner, Jacques Chen, Jonathan Wilder Lavington, Mark Schmidt","submitted_at":"2023-04-27T05:41:13Z","abstract_excerpt":"The success of the Adam optimizer on a wide array of architectures has made it the default in settings where stochastic gradient descent (SGD) performs poorly. However, our theoretical understanding of this discrepancy is lagging, preventing the development of significant improvements on either algorithm. Recent work advances the hypothesis that Adam and other heuristics like gradient clipping outperform SGD on language tasks because the distribution of the error induced by sampling has heavy tails. This suggests that Adam outperform SGD because it uses a more robust gradient estimate. We eval"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.13960","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/2304.13960/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":"2026-07-05T06:04:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"beVzHaqhskb5E12uEqGsmA7/IkXspEoI8xaI6iDIkqRvvfun4g/AZHfcvmQ4rddySIk3jgxdhIxW0Tg3Ydw4DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T12:43:13.692338Z"},"content_sha256":"30dd0d11ed9ac7033e1ed25ea4f56c6319686b6587375fbcb38329197fffe947","schema_version":"1.0","event_id":"sha256:30dd0d11ed9ac7033e1ed25ea4f56c6319686b6587375fbcb38329197fffe947"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5IM3U267ZFFJZSLQ74E6PHQQ57/bundle.json","state_url":"https://pith.science/pith/5IM3U267ZFFJZSLQ74E6PHQQ57/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5IM3U267ZFFJZSLQ74E6PHQQ57/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":"2026-07-07T12:43:13Z","links":{"resolver":"https://pith.science/pith/5IM3U267ZFFJZSLQ74E6PHQQ57","bundle":"https://pith.science/pith/5IM3U267ZFFJZSLQ74E6PHQQ57/bundle.json","state":"https://pith.science/pith/5IM3U267ZFFJZSLQ74E6PHQQ57/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5IM3U267ZFFJZSLQ74E6PHQQ57/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:5IM3U267ZFFJZSLQ74E6PHQQ57","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":"b37c59f169ca4b69b6df3c26df36d74fa042cf60b7943f2e005a362a864ed590","cross_cats_sorted":["math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-04-27T05:41:13Z","title_canon_sha256":"bc450947089ea27bcdff3cad3130b4b6ba720793156fdc7e34a0c77e918f569c"},"schema_version":"1.0","source":{"id":"2304.13960","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.13960","created_at":"2026-07-05T06:04:59Z"},{"alias_kind":"arxiv_version","alias_value":"2304.13960v1","created_at":"2026-07-05T06:04:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.13960","created_at":"2026-07-05T06:04:59Z"},{"alias_kind":"pith_short_12","alias_value":"5IM3U267ZFFJ","created_at":"2026-07-05T06:04:59Z"},{"alias_kind":"pith_short_16","alias_value":"5IM3U267ZFFJZSLQ","created_at":"2026-07-05T06:04:59Z"},{"alias_kind":"pith_short_8","alias_value":"5IM3U267","created_at":"2026-07-05T06:04:59Z"}],"graph_snapshots":[{"event_id":"sha256:30dd0d11ed9ac7033e1ed25ea4f56c6319686b6587375fbcb38329197fffe947","target":"graph","created_at":"2026-07-05T06:04:59Z","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/2304.13960/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The success of the Adam optimizer on a wide array of architectures has made it the default in settings where stochastic gradient descent (SGD) performs poorly. However, our theoretical understanding of this discrepancy is lagging, preventing the development of significant improvements on either algorithm. Recent work advances the hypothesis that Adam and other heuristics like gradient clipping outperform SGD on language tasks because the distribution of the error induced by sampling has heavy tails. This suggests that Adam outperform SGD because it uses a more robust gradient estimate. We eval","authors_text":"Frederik Kunstner, Jacques Chen, Jonathan Wilder Lavington, Mark Schmidt","cross_cats":["math.OC"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-04-27T05:41:13Z","title":"Noise Is Not the Main Factor Behind the Gap Between SGD and Adam on Transformers, but Sign Descent Might Be"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.13960","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:b7aa9593c0d56e6836ff7aa42a924f35c7758a178420d15cf4d354cab66dd33f","target":"record","created_at":"2026-07-05T06:04:59Z","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":"b37c59f169ca4b69b6df3c26df36d74fa042cf60b7943f2e005a362a864ed590","cross_cats_sorted":["math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-04-27T05:41:13Z","title_canon_sha256":"bc450947089ea27bcdff3cad3130b4b6ba720793156fdc7e34a0c77e918f569c"},"schema_version":"1.0","source":{"id":"2304.13960","kind":"arxiv","version":1}},"canonical_sha256":"ea19ba6bdfc94a9cc970ff09e79e10efdd8dacf65ddd161b0d8f75c60c9a4e22","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ea19ba6bdfc94a9cc970ff09e79e10efdd8dacf65ddd161b0d8f75c60c9a4e22","first_computed_at":"2026-07-05T06:04:59.035221Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:04:59.035221Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"oZBerIg9LR/mrelz9steP8UkOkbLyN+FVE72P3d1NfgDTlqMd8g3WRPJb+81P6Sh5ATwmEr5gSKmyGzjIK2WCw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:04:59.035695Z","signed_message":"canonical_sha256_bytes"},"source_id":"2304.13960","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b7aa9593c0d56e6836ff7aa42a924f35c7758a178420d15cf4d354cab66dd33f","sha256:30dd0d11ed9ac7033e1ed25ea4f56c6319686b6587375fbcb38329197fffe947"],"state_sha256":"cd0d2367f476523b9b3823bdafea042139f6ab1c7ac37003290cfc3f81d6f600"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yXuDWTwVX82UQrFNO7sNLJdakHttSXj9gKQ60nVGzGCRC7ufOk1gmx1t2FSfGCgnBddtG/06EuLt6kW5TmvkCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T12:43:13.694282Z","bundle_sha256":"9fb1d94e06e6bd526cdbaa30ccb0f1f11bceebd52a40a01cc273320b5c377853"}}