{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:T55M4OFHVXXSJBWL4UF7JTWGOM","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":"50e202b55586e383c2bbf7086c5e258d9454cf259e44f6475cebd617daaeb501","cross_cats_sorted":["cs.CL","cs.IT","math.IT","math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-08-19T16:47:46Z","title_canon_sha256":"09a4ce0abc2cf158fd9d8f87980ee3840049f5305a041df66074a5d21367d5cb"},"schema_version":"1.0","source":{"id":"2408.10147","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.10147","created_at":"2026-07-05T09:11:48Z"},{"alias_kind":"arxiv_version","alias_value":"2408.10147v2","created_at":"2026-07-05T09:11:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.10147","created_at":"2026-07-05T09:11:48Z"},{"alias_kind":"pith_short_12","alias_value":"T55M4OFHVXXS","created_at":"2026-07-05T09:11:48Z"},{"alias_kind":"pith_short_16","alias_value":"T55M4OFHVXXSJBWL","created_at":"2026-07-05T09:11:48Z"},{"alias_kind":"pith_short_8","alias_value":"T55M4OFH","created_at":"2026-07-05T09:11:48Z"}],"graph_snapshots":[{"event_id":"sha256:4d3805d2646681e8b7aacb5d5256e4d431fb63e29b0fa6d49ae17da6e59dc141","target":"graph","created_at":"2026-07-05T09:11:48Z","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/2408.10147/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In-context learning (ICL) refers to a remarkable capability of pretrained large language models, which can learn a new task given a few examples during inference. However, theoretical understanding of ICL is largely under-explored, particularly whether transformers can be trained to generalize to unseen examples in a prompt, which will require the model to acquire contextual knowledge of the prompt for generalization. This paper investigates the training dynamics of transformers by gradient descent through the lens of non-linear regression tasks. The contextual generalization here can be attai","authors_text":"Tong Yang, Yingbin Liang, Yuejie Chi, Yu Huang","cross_cats":["cs.CL","cs.IT","math.IT","math.OC","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-08-19T16:47:46Z","title":"In-Context Learning with Representations: Contextual Generalization of Trained Transformers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.10147","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":"sha256:16bb8facd2a9ed2cc58130ec4b004dc5f37b82e01f3a7c340f8a5fbffe7ea7fb","target":"record","created_at":"2026-07-05T09:11:48Z","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":"50e202b55586e383c2bbf7086c5e258d9454cf259e44f6475cebd617daaeb501","cross_cats_sorted":["cs.CL","cs.IT","math.IT","math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-08-19T16:47:46Z","title_canon_sha256":"09a4ce0abc2cf158fd9d8f87980ee3840049f5305a041df66074a5d21367d5cb"},"schema_version":"1.0","source":{"id":"2408.10147","kind":"arxiv","version":2}},"canonical_sha256":"9f7ace38a7adef2486cbe50bf4cec673029de4b69a9f00fcb1e8719d79e3d229","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9f7ace38a7adef2486cbe50bf4cec673029de4b69a9f00fcb1e8719d79e3d229","first_computed_at":"2026-07-05T09:11:48.042321Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:11:48.042321Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NXxQ0pjgmdutjFD5NpRvG/x0tzD1WWnJfrCQHFT0Bl3fVf/9WfKkiWUvcYtCIZQtqC8CPH0ORDd5E4U0HQMXBw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:11:48.042807Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.10147","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:16bb8facd2a9ed2cc58130ec4b004dc5f37b82e01f3a7c340f8a5fbffe7ea7fb","sha256:4d3805d2646681e8b7aacb5d5256e4d431fb63e29b0fa6d49ae17da6e59dc141"],"state_sha256":"fa4994be839c6613c2c23d8b7a85082638fa0c14448dd4a6662554741816b761"}