{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:VLFIUOWSE77VAJ3FYM2IDAISE4","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":"1605d0dca51f2a559fa6d9d99198818a8454af14e9a33ffe1579c01a45c73a60","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-27T18:03:00Z","title_canon_sha256":"6d5f37db3377250d5c1c4a5c5f305f68d42ea3bb5a2723bb6ef8d1f6dbde5b6f"},"schema_version":"1.0","source":{"id":"2501.16265","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.16265","created_at":"2026-07-05T11:10:50Z"},{"alias_kind":"arxiv_version","alias_value":"2501.16265v2","created_at":"2026-07-05T11:10:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.16265","created_at":"2026-07-05T11:10:50Z"},{"alias_kind":"pith_short_12","alias_value":"VLFIUOWSE77V","created_at":"2026-07-05T11:10:50Z"},{"alias_kind":"pith_short_16","alias_value":"VLFIUOWSE77VAJ3F","created_at":"2026-07-05T11:10:50Z"},{"alias_kind":"pith_short_8","alias_value":"VLFIUOWS","created_at":"2026-07-05T11:10:50Z"}],"graph_snapshots":[{"event_id":"sha256:a8ed017d68e8aea5cbcf70a10c0c11ee57e0120f6188d15266c964f75fb37f9f","target":"graph","created_at":"2026-07-05T11:10:50Z","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/2501.16265/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While attention-based models have demonstrated the remarkable ability of in-context learning (ICL), the theoretical understanding of how these models acquired this ability through gradient descent training is still preliminary. Towards answering this question, we study the gradient descent dynamics of multi-head linear self-attention trained for in-context linear regression. We examine two parametrizations of linear self-attention: one with the key and query weights merged as a single matrix (common in theoretical studies), and one with separate key and query matrices (closer to practical sett","authors_text":"Aaditya K. Singh, Andrew Saxe, Peter E. Latham, Yedi Zhang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-27T18:03:00Z","title":"Training Dynamics of In-Context Learning in Linear Attention"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.16265","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":"sha256:21aee115230adbfbbe7121a8a1499d1d3adaa4fccad19e43ff2b60bbba85ff04","target":"record","created_at":"2026-07-05T11:10:50Z","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":"1605d0dca51f2a559fa6d9d99198818a8454af14e9a33ffe1579c01a45c73a60","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-27T18:03:00Z","title_canon_sha256":"6d5f37db3377250d5c1c4a5c5f305f68d42ea3bb5a2723bb6ef8d1f6dbde5b6f"},"schema_version":"1.0","source":{"id":"2501.16265","kind":"arxiv","version":2}},"canonical_sha256":"aaca8a3ad227ff502765c3348181122736e684ffcd7b727ea118fa8072d6960d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"aaca8a3ad227ff502765c3348181122736e684ffcd7b727ea118fa8072d6960d","first_computed_at":"2026-07-05T11:10:50.772927Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:10:50.772927Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SpsvEcP6g5N0E1fjX9H/bHnVOcG3chgquI9rpTJJM++dXRMBuQxR4kUbGd/05stkwoFF2pI6T6u9VSEbmW4nCw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:10:50.773429Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.16265","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:21aee115230adbfbbe7121a8a1499d1d3adaa4fccad19e43ff2b60bbba85ff04","sha256:a8ed017d68e8aea5cbcf70a10c0c11ee57e0120f6188d15266c964f75fb37f9f"],"state_sha256":"0c624d18e1178bd363b1a6a0da07d8e5b0f2c4d7f7ed76e2042c27cf65ac67ac"}