{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:ZL33BJGSXS2UZIDL7XE5A3XWFM","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":"8cefd9893c974e40c907978a7ae10cff1263b79253e799c92d6c7b2693691ada","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-07-07T13:09:18Z","title_canon_sha256":"3cc35278798ce418cc7f2b504ff6c6c8d7df81560bd7f48b1d542af9dde3bd64"},"schema_version":"1.0","source":{"id":"2307.03576","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.03576","created_at":"2026-07-05T06:28:44Z"},{"alias_kind":"arxiv_version","alias_value":"2307.03576v1","created_at":"2026-07-05T06:28:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.03576","created_at":"2026-07-05T06:28:44Z"},{"alias_kind":"pith_short_12","alias_value":"ZL33BJGSXS2U","created_at":"2026-07-05T06:28:44Z"},{"alias_kind":"pith_short_16","alias_value":"ZL33BJGSXS2UZIDL","created_at":"2026-07-05T06:28:44Z"},{"alias_kind":"pith_short_8","alias_value":"ZL33BJGS","created_at":"2026-07-05T06:28:44Z"}],"graph_snapshots":[{"event_id":"sha256:49bc30b819ff3aa8065961236d01f534248fbbf27a8dd5c5fcd055d859e43a6d","target":"graph","created_at":"2026-07-05T06:28:44Z","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/2307.03576/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent works have empirically analyzed in-context learning and shown that transformers trained on synthetic linear regression tasks can learn to implement ridge regression, which is the Bayes-optimal predictor, given sufficient capacity [Aky\\\"urek et al., 2023], while one-layer transformers with linear self-attention and no MLP layer will learn to implement one step of gradient descent (GD) on a least-squares linear regression objective [von Oswald et al., 2022]. However, the theory behind these observations remains poorly understood. We theoretically study transformers with a single layer of ","authors_text":"Arvind Mahankali, Tatsunori B. Hashimoto, Tengyu Ma","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-07-07T13:09:18Z","title":"One Step of Gradient Descent is Provably the Optimal In-Context Learner with One Layer of Linear Self-Attention"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.03576","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:c3ce3da011b16619376c34fd0cbd7ada93d4d93638f2abbe072ff4f5b00bf8fd","target":"record","created_at":"2026-07-05T06:28:44Z","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":"8cefd9893c974e40c907978a7ae10cff1263b79253e799c92d6c7b2693691ada","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-07-07T13:09:18Z","title_canon_sha256":"3cc35278798ce418cc7f2b504ff6c6c8d7df81560bd7f48b1d542af9dde3bd64"},"schema_version":"1.0","source":{"id":"2307.03576","kind":"arxiv","version":1}},"canonical_sha256":"caf7b0a4d2bcb54ca06bfdc9d06ef62b0145c950af173d39c04b622972f1717d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"caf7b0a4d2bcb54ca06bfdc9d06ef62b0145c950af173d39c04b622972f1717d","first_computed_at":"2026-07-05T06:28:44.668635Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:28:44.668635Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rLET7en2Mf5fDK/bVZzuYSxDdFxU5aiga9tS8tXti2IkdvWtyMpqau727z423G/FxEI03biFhez5Fju2K6foDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:28:44.669127Z","signed_message":"canonical_sha256_bytes"},"source_id":"2307.03576","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c3ce3da011b16619376c34fd0cbd7ada93d4d93638f2abbe072ff4f5b00bf8fd","sha256:49bc30b819ff3aa8065961236d01f534248fbbf27a8dd5c5fcd055d859e43a6d"],"state_sha256":"062e0bcc57b5705534b830883e3e37f4482b283b125c67617919f4d46909d940"}