{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:6CBNLSB6M6DDN2LZ6P2K3ROE26","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":"689161ad9eaa7071d47d6609ecba745e51cc7dfb858f9f050c0e62238df93c8c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-23T21:07:20Z","title_canon_sha256":"56da070746b2c37ba8da3b3959f7f8d6c3b07e1f0406c29638572e27b0be168c"},"schema_version":"1.0","source":{"id":"2402.15607","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.15607","created_at":"2026-07-05T08:32:37Z"},{"alias_kind":"arxiv_version","alias_value":"2402.15607v3","created_at":"2026-07-05T08:32:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.15607","created_at":"2026-07-05T08:32:37Z"},{"alias_kind":"pith_short_12","alias_value":"6CBNLSB6M6DD","created_at":"2026-07-05T08:32:37Z"},{"alias_kind":"pith_short_16","alias_value":"6CBNLSB6M6DDN2LZ","created_at":"2026-07-05T08:32:37Z"},{"alias_kind":"pith_short_8","alias_value":"6CBNLSB6","created_at":"2026-07-05T08:32:37Z"}],"graph_snapshots":[{"event_id":"sha256:64fdef963408a8e696fd24f4089490a70e11d20f856cb9a3baf35709f41502a8","target":"graph","created_at":"2026-07-05T08:32:37Z","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/2402.15607/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Transformer-based large language models have displayed impressive in-context learning capabilities, where a pre-trained model can handle new tasks without fine-tuning by simply augmenting the query with some input-output examples from that task. Despite the empirical success, the mechanics of how to train a Transformer to achieve ICL and the corresponding ICL capacity is mostly elusive due to the technical challenges of analyzing the nonconvex training problems resulting from the nonlinear self-attention and nonlinear activation in Transformers. To the best of our knowledge, this paper provide","authors_text":"Hongkang Li, Meng Wang, Pin-Yu Chen, Songtao Lu, Xiaodong Cui","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-23T21:07:20Z","title":"How Do Nonlinear Transformers Learn and Generalize in In-Context Learning?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.15607","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:c3de1a09aa99ef1a6e4f03ec0d9a0803a556256cc39c786fab8e21e0cbc75ed5","target":"record","created_at":"2026-07-05T08:32:37Z","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":"689161ad9eaa7071d47d6609ecba745e51cc7dfb858f9f050c0e62238df93c8c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-23T21:07:20Z","title_canon_sha256":"56da070746b2c37ba8da3b3959f7f8d6c3b07e1f0406c29638572e27b0be168c"},"schema_version":"1.0","source":{"id":"2402.15607","kind":"arxiv","version":3}},"canonical_sha256":"f082d5c83e678636e979f3f4adc5c4d7af66becf81d6067598f6ac5fe8948634","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f082d5c83e678636e979f3f4adc5c4d7af66becf81d6067598f6ac5fe8948634","first_computed_at":"2026-07-05T08:32:37.508833Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:32:37.508833Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gQ9G5b6N76xfkB7VuDO8D1y6UeXu1kaPU8s1hg+e3g5A/XrhqeJFT/AtieInenJFhn9Ro3ELMK0yT21/iFXkCw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:32:37.509353Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.15607","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c3de1a09aa99ef1a6e4f03ec0d9a0803a556256cc39c786fab8e21e0cbc75ed5","sha256:64fdef963408a8e696fd24f4089490a70e11d20f856cb9a3baf35709f41502a8"],"state_sha256":"7d355ade50d9df22d21ed39e28a3da927986409aeead9392cd975efb489c070a"}