{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:AKWPZ5GAJV2YSHPUKSVP6U5JRM","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":"637c6b745a1add3a72e010c5553a0f4f5e4af75e9a197b029fea753892fbd5a9","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-21T23:45:57Z","title_canon_sha256":"2a57cd5ab70157022df43389778605e854eb5cd4dc117a0af23391b53388d8c3"},"schema_version":"1.0","source":{"id":"2402.14180","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.14180","created_at":"2026-07-05T09:28:10Z"},{"alias_kind":"arxiv_version","alias_value":"2402.14180v2","created_at":"2026-07-05T09:28:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.14180","created_at":"2026-07-05T09:28:10Z"},{"alias_kind":"pith_short_12","alias_value":"AKWPZ5GAJV2Y","created_at":"2026-07-05T09:28:10Z"},{"alias_kind":"pith_short_16","alias_value":"AKWPZ5GAJV2YSHPU","created_at":"2026-07-05T09:28:10Z"},{"alias_kind":"pith_short_8","alias_value":"AKWPZ5GA","created_at":"2026-07-05T09:28:10Z"}],"graph_snapshots":[{"event_id":"sha256:4d507cd4eee38903f09fe02a5b6027bec3e0c374de722e71f16c863f164cdad6","target":"graph","created_at":"2026-07-05T09:28:10Z","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/2402.14180/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent research has demonstrated that transformers, particularly linear attention models, implicitly execute gradient-descent-like algorithms on data provided in-context during their forward inference step. However, their capability in handling more complex problems remains unexplored. In this paper, we prove that each layer of a linear transformer maintains a weight vector for an implicit linear regression problem and can be interpreted as performing a variant of preconditioned gradient descent. We also investigate the use of linear transformers in a challenging scenario where the training da","authors_text":"Johannes von Oswald, Mark Sandler, Max Vladymyrov, Rong Ge","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-21T23:45:57Z","title":"Linear Transformers are Versatile In-Context Learners"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.14180","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:f39c40138bfa9acbef9ec137aaf51b87f7a6552c1db411346497c341e43754eb","target":"record","created_at":"2026-07-05T09:28:10Z","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":"637c6b745a1add3a72e010c5553a0f4f5e4af75e9a197b029fea753892fbd5a9","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-21T23:45:57Z","title_canon_sha256":"2a57cd5ab70157022df43389778605e854eb5cd4dc117a0af23391b53388d8c3"},"schema_version":"1.0","source":{"id":"2402.14180","kind":"arxiv","version":2}},"canonical_sha256":"02acfcf4c04d75891df454aaff53a98b26a4ab6cd71e1505d01174600fd9447b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"02acfcf4c04d75891df454aaff53a98b26a4ab6cd71e1505d01174600fd9447b","first_computed_at":"2026-07-05T09:28:10.827986Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:28:10.827986Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"h9TOxouWisCWMs05nBfghHwLEcpUjDYznPWQ4oro/RtLTu0V877NilsoVy+cP+Ge+Jgie+M9QxpRdwsPeCJnBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:28:10.828508Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.14180","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f39c40138bfa9acbef9ec137aaf51b87f7a6552c1db411346497c341e43754eb","sha256:4d507cd4eee38903f09fe02a5b6027bec3e0c374de722e71f16c863f164cdad6"],"state_sha256":"bb9c2ed6506cac158f46390d488f110f81e48ee353d746cd86f2ccc26817a121"}