{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:COB7HH6HWADJKMQ65BCLONGCVC","short_pith_number":"pith:COB7HH6H","canonical_record":{"source":{"id":"2402.19449","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-29T18:47:52Z","cross_cats_sorted":["cs.CL","math.OC","stat.ML"],"title_canon_sha256":"fbf939afc9c4ddcbb6611a0f3a3b30ce6a28d766294be4b33e869daa812d0713","abstract_canon_sha256":"49ca9f6ef3a45a0a529a374ced6bdee2057accf1be1a040704d6a0022e66f62a"},"schema_version":"1.0"},"canonical_sha256":"1383f39fc7b00695321ee844b734c2a8b83ac7bb2d2b5f55e627e1ee8909173d","source":{"kind":"arxiv","id":"2402.19449","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.19449","created_at":"2026-07-05T08:43:08Z"},{"alias_kind":"arxiv_version","alias_value":"2402.19449v2","created_at":"2026-07-05T08:43:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.19449","created_at":"2026-07-05T08:43:08Z"},{"alias_kind":"pith_short_12","alias_value":"COB7HH6HWADJ","created_at":"2026-07-05T08:43:08Z"},{"alias_kind":"pith_short_16","alias_value":"COB7HH6HWADJKMQ6","created_at":"2026-07-05T08:43:08Z"},{"alias_kind":"pith_short_8","alias_value":"COB7HH6H","created_at":"2026-07-05T08:43:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:COB7HH6HWADJKMQ65BCLONGCVC","target":"record","payload":{"canonical_record":{"source":{"id":"2402.19449","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-29T18:47:52Z","cross_cats_sorted":["cs.CL","math.OC","stat.ML"],"title_canon_sha256":"fbf939afc9c4ddcbb6611a0f3a3b30ce6a28d766294be4b33e869daa812d0713","abstract_canon_sha256":"49ca9f6ef3a45a0a529a374ced6bdee2057accf1be1a040704d6a0022e66f62a"},"schema_version":"1.0"},"canonical_sha256":"1383f39fc7b00695321ee844b734c2a8b83ac7bb2d2b5f55e627e1ee8909173d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:43:08.867486Z","signature_b64":"ExjkzUVheMDyJS9ATR7Kpe0VhYmEQo3kIAhzwvM0yLhJ2cFYWvKhnwiQV1o1yCSBAcFHFW355sq50Oo0BigYBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1383f39fc7b00695321ee844b734c2a8b83ac7bb2d2b5f55e627e1ee8909173d","last_reissued_at":"2026-07-05T08:43:08.867070Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:43:08.867070Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.19449","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":"2026-07-05T08:43:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0i4Cyxd7vGiKu2gTZGWp+yfTGSRw0FVxSC677z5K94xaXzi5CjfbaMGiGdRy9bTZMu1KWZIKGOA7W4jGl8GUAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T22:16:31.007738Z"},"content_sha256":"0ea4644cbd39eb233db129b1ae835be2697ff43e9497de8a9012e9154f092833","schema_version":"1.0","event_id":"sha256:0ea4644cbd39eb233db129b1ae835be2697ff43e9497de8a9012e9154f092833"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:COB7HH6HWADJKMQ65BCLONGCVC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Heavy-Tailed Class Imbalance and Why Adam Outperforms Gradient Descent on Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alan Milligan, Alberto Bietti, Frederik Kunstner, Mark Schmidt, Robin Yadav","submitted_at":"2024-02-29T18:47:52Z","abstract_excerpt":"Adam has been shown to outperform gradient descent on large language models by a larger margin than on other tasks, but it is unclear why. We show that a key factor in this performance gap is the heavy-tailed class imbalance found in language tasks. When trained with gradient descent, the loss of infrequent words decreases more slowly than the loss of frequent ones. This leads to a slow decrease on the average loss as most samples come from infrequent words. On the other hand, Adam and sign-based methods are less sensitive to this problem. To establish that this behavior is caused by class imb"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.19449","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/2402.19449/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":"2026-07-05T08:43:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CbjDjAFT1KvLCJUtFmZ3bOgKv5caP15dZV+HAH95HbBTJe31jo4+mPp7ssF2a3i6XX3wBAtQYkPSajuHWQBOAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T22:16:31.008897Z"},"content_sha256":"670780887476debc2d13aa707f24e5f2a72506cf1fdb455c8e961931af5a63fe","schema_version":"1.0","event_id":"sha256:670780887476debc2d13aa707f24e5f2a72506cf1fdb455c8e961931af5a63fe"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/COB7HH6HWADJKMQ65BCLONGCVC/bundle.json","state_url":"https://pith.science/pith/COB7HH6HWADJKMQ65BCLONGCVC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/COB7HH6HWADJKMQ65BCLONGCVC/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":"2026-08-07T22:16:31Z","links":{"resolver":"https://pith.science/pith/COB7HH6HWADJKMQ65BCLONGCVC","bundle":"https://pith.science/pith/COB7HH6HWADJKMQ65BCLONGCVC/bundle.json","state":"https://pith.science/pith/COB7HH6HWADJKMQ65BCLONGCVC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/COB7HH6HWADJKMQ65BCLONGCVC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:COB7HH6HWADJKMQ65BCLONGCVC","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":"49ca9f6ef3a45a0a529a374ced6bdee2057accf1be1a040704d6a0022e66f62a","cross_cats_sorted":["cs.CL","math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-29T18:47:52Z","title_canon_sha256":"fbf939afc9c4ddcbb6611a0f3a3b30ce6a28d766294be4b33e869daa812d0713"},"schema_version":"1.0","source":{"id":"2402.19449","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.19449","created_at":"2026-07-05T08:43:08Z"},{"alias_kind":"arxiv_version","alias_value":"2402.19449v2","created_at":"2026-07-05T08:43:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.19449","created_at":"2026-07-05T08:43:08Z"},{"alias_kind":"pith_short_12","alias_value":"COB7HH6HWADJ","created_at":"2026-07-05T08:43:08Z"},{"alias_kind":"pith_short_16","alias_value":"COB7HH6HWADJKMQ6","created_at":"2026-07-05T08:43:08Z"},{"alias_kind":"pith_short_8","alias_value":"COB7HH6H","created_at":"2026-07-05T08:43:08Z"}],"graph_snapshots":[{"event_id":"sha256:670780887476debc2d13aa707f24e5f2a72506cf1fdb455c8e961931af5a63fe","target":"graph","created_at":"2026-07-05T08:43:08Z","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/2402.19449/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Adam has been shown to outperform gradient descent on large language models by a larger margin than on other tasks, but it is unclear why. We show that a key factor in this performance gap is the heavy-tailed class imbalance found in language tasks. When trained with gradient descent, the loss of infrequent words decreases more slowly than the loss of frequent ones. This leads to a slow decrease on the average loss as most samples come from infrequent words. On the other hand, Adam and sign-based methods are less sensitive to this problem. To establish that this behavior is caused by class imb","authors_text":"Alan Milligan, Alberto Bietti, Frederik Kunstner, Mark Schmidt, Robin Yadav","cross_cats":["cs.CL","math.OC","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-29T18:47:52Z","title":"Heavy-Tailed Class Imbalance and Why Adam Outperforms Gradient Descent on Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.19449","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":"sha256:0ea4644cbd39eb233db129b1ae835be2697ff43e9497de8a9012e9154f092833","target":"record","created_at":"2026-07-05T08:43:08Z","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":"49ca9f6ef3a45a0a529a374ced6bdee2057accf1be1a040704d6a0022e66f62a","cross_cats_sorted":["cs.CL","math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-29T18:47:52Z","title_canon_sha256":"fbf939afc9c4ddcbb6611a0f3a3b30ce6a28d766294be4b33e869daa812d0713"},"schema_version":"1.0","source":{"id":"2402.19449","kind":"arxiv","version":2}},"canonical_sha256":"1383f39fc7b00695321ee844b734c2a8b83ac7bb2d2b5f55e627e1ee8909173d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1383f39fc7b00695321ee844b734c2a8b83ac7bb2d2b5f55e627e1ee8909173d","first_computed_at":"2026-07-05T08:43:08.867070Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:43:08.867070Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ExjkzUVheMDyJS9ATR7Kpe0VhYmEQo3kIAhzwvM0yLhJ2cFYWvKhnwiQV1o1yCSBAcFHFW355sq50Oo0BigYBA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:43:08.867486Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.19449","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0ea4644cbd39eb233db129b1ae835be2697ff43e9497de8a9012e9154f092833","sha256:670780887476debc2d13aa707f24e5f2a72506cf1fdb455c8e961931af5a63fe"],"state_sha256":"3f9c04901676a0669ad870b56ca7b23a38ead3c07320d56b1a99442e14c23f2f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HcpvUXEeHoTdx8U69A0WCx3R+0Vz6lLUbDdtHz+UWVNMhi0EGlPMmkw1gQb+fpCuO7PpJLoJhzjLnc7vAVzpCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T22:16:31.020234Z","bundle_sha256":"e3449eec6fb9ff758246ecbe80c3aad6be01397993368e95c35fb5b608c54ab3"}}