{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:QPVP3C7OVAB554VMB6ZWMVSDKI","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":"24c8c650fd85fec0664e6362d354db84e5341a9f49e86fb4551eb1de995d2a0e","cross_cats_sorted":["cs.AI","math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-08T17:55:33Z","title_canon_sha256":"4ee1241368906b254cd7b7ffbc9eb1b93e35063e9b163eb7e96d83a2691704a3"},"schema_version":"1.0","source":{"id":"2310.05249","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.05249","created_at":"2026-07-05T06:58:28Z"},{"alias_kind":"arxiv_version","alias_value":"2310.05249v1","created_at":"2026-07-05T06:58:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.05249","created_at":"2026-07-05T06:58:28Z"},{"alias_kind":"pith_short_12","alias_value":"QPVP3C7OVAB5","created_at":"2026-07-05T06:58:28Z"},{"alias_kind":"pith_short_16","alias_value":"QPVP3C7OVAB554VM","created_at":"2026-07-05T06:58:28Z"},{"alias_kind":"pith_short_8","alias_value":"QPVP3C7O","created_at":"2026-07-05T06:58:28Z"}],"graph_snapshots":[{"event_id":"sha256:1a82addc51d373532e4b142d8ab2f9740d8d4cf6438d7ac61b75f16f45cf550d","target":"graph","created_at":"2026-07-05T06:58:28Z","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/2310.05249/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Transformers have recently revolutionized many domains in modern machine learning and one salient discovery is their remarkable in-context learning capability, where models can solve an unseen task by utilizing task-specific prompts without further parameters fine-tuning. This also inspired recent theoretical studies aiming to understand the in-context learning mechanism of transformers, which however focused only on linear transformers. In this work, we take the first step toward studying the learning dynamics of a one-layer transformer with softmax attention trained via gradient descent in o","authors_text":"Yingbin Liang, Yuan Cheng, Yu Huang","cross_cats":["cs.AI","math.OC","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-08T17:55:33Z","title":"In-Context Convergence of Transformers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.05249","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:fad51509aa837b14bbe72085d65eae6a7ee960a072ca04d845b54cf39054f209","target":"record","created_at":"2026-07-05T06:58:28Z","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":"24c8c650fd85fec0664e6362d354db84e5341a9f49e86fb4551eb1de995d2a0e","cross_cats_sorted":["cs.AI","math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-08T17:55:33Z","title_canon_sha256":"4ee1241368906b254cd7b7ffbc9eb1b93e35063e9b163eb7e96d83a2691704a3"},"schema_version":"1.0","source":{"id":"2310.05249","kind":"arxiv","version":1}},"canonical_sha256":"83eafd8beea803def2ac0fb366564352303742b668326c2601c2bab4b6d927ae","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"83eafd8beea803def2ac0fb366564352303742b668326c2601c2bab4b6d927ae","first_computed_at":"2026-07-05T06:58:28.675777Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:58:28.675777Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9lyZV2JLYCJrqb2vZCSIZCin5pLLCmTFWqmKNd6ESfvu9vt0kHc1akxSPEL3dpmPZFtePUXSzZVLPNKyXGVRCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:58:28.676200Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.05249","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fad51509aa837b14bbe72085d65eae6a7ee960a072ca04d845b54cf39054f209","sha256:1a82addc51d373532e4b142d8ab2f9740d8d4cf6438d7ac61b75f16f45cf550d"],"state_sha256":"02f21d68524362acb1a38c45c69a1195108c45b5646fb215013704e26199b55a"}