{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:R7BWDAPIIZQX2JQXDHHRLZJ5Q3","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":"7227c8fef1f62770421543f9dd7dd94efe39574532ecbadd7e55b0a85a50b12b","cross_cats_sorted":["cs.AI","math.OC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-02T10:48:42Z","title_canon_sha256":"659128ca13bf2790e3429f3dc94867785bb22b7fde0a62c69bc03879a628364c"},"schema_version":"1.0","source":{"id":"2310.01082","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.01082","created_at":"2026-07-05T07:55:24Z"},{"alias_kind":"arxiv_version","alias_value":"2310.01082v2","created_at":"2026-07-05T07:55:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.01082","created_at":"2026-07-05T07:55:24Z"},{"alias_kind":"pith_short_12","alias_value":"R7BWDAPIIZQX","created_at":"2026-07-05T07:55:24Z"},{"alias_kind":"pith_short_16","alias_value":"R7BWDAPIIZQX2JQX","created_at":"2026-07-05T07:55:24Z"},{"alias_kind":"pith_short_8","alias_value":"R7BWDAPI","created_at":"2026-07-05T07:55:24Z"}],"graph_snapshots":[{"event_id":"sha256:9021e2bb5608794d1d3712c9639cfb212629bc2e4c90d910a6163c118e3f3cf2","target":"graph","created_at":"2026-07-05T07:55:24Z","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/2310.01082/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Transformer training is notoriously difficult, requiring a careful design of optimizers and use of various heuristics. We make progress towards understanding the subtleties of training Transformers by carefully studying a simple yet canonical linearized shallow Transformer model. Specifically, we train linear Transformers to solve regression tasks, inspired by J.~von Oswald et al.~(ICML 2023), and K.~Ahn et al.~(NeurIPS 2023). Most importantly, we observe that our proposed linearized models can reproduce several prominent aspects of Transformer training dynamics. Consequently, the results obta","authors_text":"Ali Jadbabaie, Chulhee Yun, Kwangjun Ahn, Minhak Song, Suvrit Sra, Xiang Cheng","cross_cats":["cs.AI","math.OC"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-02T10:48:42Z","title":"Linear attention is (maybe) all you need (to understand transformer optimization)"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.01082","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":"sha256:5984def76e8ba77d4dfbf89407bbcf55896a3d5f82664ef480f9efcc10f91cdc","target":"record","created_at":"2026-07-05T07:55:24Z","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":"7227c8fef1f62770421543f9dd7dd94efe39574532ecbadd7e55b0a85a50b12b","cross_cats_sorted":["cs.AI","math.OC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-02T10:48:42Z","title_canon_sha256":"659128ca13bf2790e3429f3dc94867785bb22b7fde0a62c69bc03879a628364c"},"schema_version":"1.0","source":{"id":"2310.01082","kind":"arxiv","version":2}},"canonical_sha256":"8fc36181e846617d261719cf15e53d86d80955564c8d1a3479afb3ccfb02acac","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8fc36181e846617d261719cf15e53d86d80955564c8d1a3479afb3ccfb02acac","first_computed_at":"2026-07-05T07:55:24.870278Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:55:24.870278Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Xpk97+Ha9OJ11xV5qi408A78XEoDfsg7lvC5Ib4PxkcKgLpnmm4FAp0t9Yj9wxzw3tPi3PKz1fDfole9nr1GBg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:55:24.870715Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.01082","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5984def76e8ba77d4dfbf89407bbcf55896a3d5f82664ef480f9efcc10f91cdc","sha256:9021e2bb5608794d1d3712c9639cfb212629bc2e4c90d910a6163c118e3f3cf2"],"state_sha256":"b06ac2420dd26a8cf7217a9222ab2540806daf9ac902f6859f4c8bc16d7b4ffc"}