{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:VWGEONGCB6M2QW54QWQVHZQ4GL","short_pith_number":"pith:VWGEONGC","schema_version":"1.0","canonical_sha256":"ad8c4734c20f99a85bbc85a153e61c32e0c035945e648e6ab5141f24f32c3511","source":{"kind":"arxiv","id":"2401.12973","version":2},"attestation_state":"computed","paper":{"title":"In-Context Language Learning: Architectures and Algorithms","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Bailin Wang, Ekin Aky\\\"urek, Jacob Andreas, Yoon Kim","submitted_at":"2024-01-23T18:59:21Z","abstract_excerpt":"Large-scale neural language models exhibit a remarkable capacity for in-context learning (ICL): they can infer novel functions from datasets provided as input. Most of our current understanding of when and how ICL arises comes from LMs trained on extremely simple learning problems like linear regression and associative recall. There remains a significant gap between these model problems and the \"real\" ICL exhibited by LMs trained on large text corpora, which involves not just retrieval and function approximation but free-form generation of language and other structured outputs. In this paper, "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2401.12973","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-01-23T18:59:21Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"053e73dd5dbc3f8ba52a093a0ebb703ddaca7259369959b8b40023a71e495d07","abstract_canon_sha256":"7da8e22e764c648aca344caf5a21aad31c5a8ada7e95b9d9fab44005effae0a1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:39:13.185156Z","signature_b64":"fAJrde0QH+nGGAgQ5+mKsSlsEIeidpkmg6bNaaZG7m9o/qokP6N07h9H/rZCMhusUvMu7pFzVPKNUwVUDp3JCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ad8c4734c20f99a85bbc85a153e61c32e0c035945e648e6ab5141f24f32c3511","last_reissued_at":"2026-07-05T07:39:13.184682Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:39:13.184682Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"In-Context Language Learning: Architectures and Algorithms","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Bailin Wang, Ekin Aky\\\"urek, Jacob Andreas, Yoon Kim","submitted_at":"2024-01-23T18:59:21Z","abstract_excerpt":"Large-scale neural language models exhibit a remarkable capacity for in-context learning (ICL): they can infer novel functions from datasets provided as input. Most of our current understanding of when and how ICL arises comes from LMs trained on extremely simple learning problems like linear regression and associative recall. There remains a significant gap between these model problems and the \"real\" ICL exhibited by LMs trained on large text corpora, which involves not just retrieval and function approximation but free-form generation of language and other structured outputs. In this paper, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.12973","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2401.12973/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2401.12973","created_at":"2026-07-05T07:39:13.184737+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.12973v2","created_at":"2026-07-05T07:39:13.184737+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.12973","created_at":"2026-07-05T07:39:13.184737+00:00"},{"alias_kind":"pith_short_12","alias_value":"VWGEONGCB6M2","created_at":"2026-07-05T07:39:13.184737+00:00"},{"alias_kind":"pith_short_16","alias_value":"VWGEONGCB6M2QW54","created_at":"2026-07-05T07:39:13.184737+00:00"},{"alias_kind":"pith_short_8","alias_value":"VWGEONGC","created_at":"2026-07-05T07:39:13.184737+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.07479","citing_title":"Supervision versus Demonstration-Based In-Context Learning for Multiword Expression Classification","ref_index":152,"is_internal_anchor":false},{"citing_arxiv_id":"2606.03979","citing_title":"Language Models Need Sleep: Learning to Self-Modify and Consolidate Memories","ref_index":68,"is_internal_anchor":false},{"citing_arxiv_id":"2601.22766","citing_title":"Sparse Attention as Compact Kernel Regression","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2412.06464","citing_title":"Gated Delta Networks: Improving Mamba2 with Delta Rule","ref_index":292,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12412","citing_title":"Stories in Space: In-Context Learning Trajectories in Conceptual Belief Space","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10946","citing_title":"Learning to Adapt: In-Context Learning Beyond Stationarity","ref_index":5,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VWGEONGCB6M2QW54QWQVHZQ4GL","json":"https://pith.science/pith/VWGEONGCB6M2QW54QWQVHZQ4GL.json","graph_json":"https://pith.science/api/pith-number/VWGEONGCB6M2QW54QWQVHZQ4GL/graph.json","events_json":"https://pith.science/api/pith-number/VWGEONGCB6M2QW54QWQVHZQ4GL/events.json","paper":"https://pith.science/paper/VWGEONGC"},"agent_actions":{"view_html":"https://pith.science/pith/VWGEONGCB6M2QW54QWQVHZQ4GL","download_json":"https://pith.science/pith/VWGEONGCB6M2QW54QWQVHZQ4GL.json","view_paper":"https://pith.science/paper/VWGEONGC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.12973&json=true","fetch_graph":"https://pith.science/api/pith-number/VWGEONGCB6M2QW54QWQVHZQ4GL/graph.json","fetch_events":"https://pith.science/api/pith-number/VWGEONGCB6M2QW54QWQVHZQ4GL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VWGEONGCB6M2QW54QWQVHZQ4GL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VWGEONGCB6M2QW54QWQVHZQ4GL/action/storage_attestation","attest_author":"https://pith.science/pith/VWGEONGCB6M2QW54QWQVHZQ4GL/action/author_attestation","sign_citation":"https://pith.science/pith/VWGEONGCB6M2QW54QWQVHZQ4GL/action/citation_signature","submit_replication":"https://pith.science/pith/VWGEONGCB6M2QW54QWQVHZQ4GL/action/replication_record"}},"created_at":"2026-07-05T07:39:13.184737+00:00","updated_at":"2026-07-05T07:39:13.184737+00:00"}