{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:ACZNFCNIXLMHJ2L4HUHETXUUMF","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":"02fb5c6bd8ba1dc56e2e16cd37f176938a608d1658652ae96a842c3f8a2d0dc5","cross_cats_sorted":["math.ST","stat.ML","stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-05T16:12:51Z","title_canon_sha256":"9645b595940f769f2c9768b712421e5d6c9852441fcc859b7ff5155a8f6930d8"},"schema_version":"1.0","source":{"id":"2506.05200","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.05200","created_at":"2026-07-05T12:00:50Z"},{"alias_kind":"arxiv_version","alias_value":"2506.05200v2","created_at":"2026-07-05T12:00:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.05200","created_at":"2026-07-05T12:00:50Z"},{"alias_kind":"pith_short_12","alias_value":"ACZNFCNIXLMH","created_at":"2026-07-05T12:00:50Z"},{"alias_kind":"pith_short_16","alias_value":"ACZNFCNIXLMHJ2L4","created_at":"2026-07-05T12:00:50Z"},{"alias_kind":"pith_short_8","alias_value":"ACZNFCNI","created_at":"2026-07-05T12:00:50Z"}],"graph_snapshots":[{"event_id":"sha256:1c97ebfff68bc867cf30ff8f79dab6cf2ad4d306de9123601308e71090c46a2c","target":"graph","created_at":"2026-07-05T12:00:50Z","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/2506.05200/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models are capable of in-context learning, the ability to perform new tasks at test time using a handful of input-output examples, without parameter updates. We develop a universal approximation theory to elucidate how transformers enable in-context learning. For a general class of functions (each representing a distinct task), we demonstrate how to construct a transformer that, without any further weight updates, can predict based on a few noisy in-context examples with vanishingly small risk. Unlike prior work that frames transformers as approximators of optimization algorithm","authors_text":"Gen Li, Yuchen Jiao, Yu Huang, Yuting Wei, Yuxin Chen","cross_cats":["math.ST","stat.ML","stat.TH"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-05T16:12:51Z","title":"Transformers Meet In-Context Learning: A Universal Approximation Theory"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.05200","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":"sha256:7a5adc7ac782f29137ba7d2eb46c67a931a6cfc0b5b51bd76ff4b8e64e94cb4c","target":"record","created_at":"2026-07-05T12:00:50Z","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":"02fb5c6bd8ba1dc56e2e16cd37f176938a608d1658652ae96a842c3f8a2d0dc5","cross_cats_sorted":["math.ST","stat.ML","stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-05T16:12:51Z","title_canon_sha256":"9645b595940f769f2c9768b712421e5d6c9852441fcc859b7ff5155a8f6930d8"},"schema_version":"1.0","source":{"id":"2506.05200","kind":"arxiv","version":2}},"canonical_sha256":"00b2d289a8bad874e97c3d0e49de94616f045511314a769ddabf0cf6883ef19a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"00b2d289a8bad874e97c3d0e49de94616f045511314a769ddabf0cf6883ef19a","first_computed_at":"2026-07-05T12:00:50.496138Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:00:50.496138Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qGqBemJXBA76pex7rEiKfrYyf7Yp3sdWpmQQ/b3JTRfWTD6Rjz0Jbm3S2Wq8yHMLBT/JhNTSpKFqkvWwNQZeBA==","signature_status":"signed_v1","signed_at":"2026-07-05T12:00:50.496680Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.05200","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7a5adc7ac782f29137ba7d2eb46c67a931a6cfc0b5b51bd76ff4b8e64e94cb4c","sha256:1c97ebfff68bc867cf30ff8f79dab6cf2ad4d306de9123601308e71090c46a2c"],"state_sha256":"42321ce0ec599403efad523690507797fd49c2b0cde57f3128b73a4305643e83"}