{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:L5WMPGKEWYBTLACQTNEHOQNLOQ","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":"1ced4614cd6a34e89cec737cf4ee3be3c9876dddbf2bc89a71fa4b5bc8ac28dd","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-26T01:08:47Z","title_canon_sha256":"fe6ee8c8b80d8cb7c44a803edfbb07e127d1737e97a41f95f23be9ccb73f2ef6"},"schema_version":"1.0","source":{"id":"2310.17086","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.17086","created_at":"2026-07-05T09:36:08Z"},{"alias_kind":"arxiv_version","alias_value":"2310.17086v3","created_at":"2026-07-05T09:36:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.17086","created_at":"2026-07-05T09:36:08Z"},{"alias_kind":"pith_short_12","alias_value":"L5WMPGKEWYBT","created_at":"2026-07-05T09:36:08Z"},{"alias_kind":"pith_short_16","alias_value":"L5WMPGKEWYBTLACQ","created_at":"2026-07-05T09:36:08Z"},{"alias_kind":"pith_short_8","alias_value":"L5WMPGKE","created_at":"2026-07-05T09:36:08Z"}],"graph_snapshots":[{"event_id":"sha256:b1fddd00f5d3ee229c26fc28918f690c9d92b406ff86ebfb231a404f108309de","target":"graph","created_at":"2026-07-05T09:36:08Z","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/2310.17086/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Transformers excel at in-context learning (ICL) -- learning from demonstrations without parameter updates -- but how they do so remains a mystery. Recent work suggests that Transformers may internally run Gradient Descent (GD), a first-order optimization method, to perform ICL. In this paper, we instead demonstrate that Transformers learn to approximate second-order optimization methods for ICL. For in-context linear regression, Transformers share a similar convergence rate as Iterative Newton's Method, both exponentially faster than GD. Empirically, predictions from successive Transformer lay","authors_text":"Deqing Fu, Robin Jia, Tian-Qi Chen, Vatsal Sharan","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-26T01:08:47Z","title":"Transformers Learn to Achieve Second-Order Convergence Rates for In-Context Linear Regression"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.17086","kind":"arxiv","version":3},"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":"sha256:8bac8ca8c9208aa6575cf87848fc012037208af762e869f3cbc10e4b91db4f4c","target":"record","created_at":"2026-07-05T09:36:08Z","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":"1ced4614cd6a34e89cec737cf4ee3be3c9876dddbf2bc89a71fa4b5bc8ac28dd","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-26T01:08:47Z","title_canon_sha256":"fe6ee8c8b80d8cb7c44a803edfbb07e127d1737e97a41f95f23be9ccb73f2ef6"},"schema_version":"1.0","source":{"id":"2310.17086","kind":"arxiv","version":3}},"canonical_sha256":"5f6cc79944b6033580509b487741ab740171e9e38ea03ce315f1ab3542b5dfc7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5f6cc79944b6033580509b487741ab740171e9e38ea03ce315f1ab3542b5dfc7","first_computed_at":"2026-07-05T09:36:08.075521Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:36:08.075521Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"cfApKM6ssj5vhtaaOYk1FLJ5vvVxjR4RfGMim9S5uCSoNtRtinQMkbsLucI6B52kYmXQjY/tJIy30Y9xeEHbCg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:36:08.076015Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.17086","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8bac8ca8c9208aa6575cf87848fc012037208af762e869f3cbc10e4b91db4f4c","sha256:b1fddd00f5d3ee229c26fc28918f690c9d92b406ff86ebfb231a404f108309de"],"state_sha256":"8d80677e42d9112001d0724527a6ec42c6ed400f2174ba0f52b9a7629dc413b6"}