{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:FERHZO2E7I2OJN6CXHAYAINZYQ","short_pith_number":"pith:FERHZO2E","schema_version":"1.0","canonical_sha256":"29227cbb44fa34e4b7c2b9c18021b9c40b2b44138cf482716da37fa1eadb5335","source":{"kind":"arxiv","id":"2310.08049","version":3},"attestation_state":"computed","paper":{"title":"Is attention required for ICL? Exploring the Relationship Between Model Architecture and In-Context Learning Ability","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ivan Lee, Nan Jiang, Taylor Berg-Kirkpatrick","submitted_at":"2023-10-12T05:43:06Z","abstract_excerpt":"What is the relationship between model architecture and the ability to perform in-context learning? In this empirical study, we take the first steps toward answering this question. We evaluate thirteen model architectures capable of causal language modeling across a suite of synthetic in-context learning tasks. These selected architectures represent a broad range of paradigms, including recurrent and convolution-based neural networks, transformers, state space model inspired, and other emerging attention alternatives. We discover that all the considered architectures can perform in-context lea"},"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":"2310.08049","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-12T05:43:06Z","cross_cats_sorted":[],"title_canon_sha256":"d2b1745d0321b7d0b029176e59ce9e1e86ab6c6e0cb818c0acd332f1db7bf4b8","abstract_canon_sha256":"90a69f9f30d60d3afb840a69ab68d83f5f931bcfb8628559ca98378cd8065640"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:03:07.482776Z","signature_b64":"taedxP3Tahh1Y6bwZDf0fkI0iPon6nSIN1UI04qeVHmxVvOXjkbC21oi6pIm11hGf/5NKwHOJiJv10HeoihlCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"29227cbb44fa34e4b7c2b9c18021b9c40b2b44138cf482716da37fa1eadb5335","last_reissued_at":"2026-07-05T08:03:07.482287Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:03:07.482287Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Is attention required for ICL? Exploring the Relationship Between Model Architecture and In-Context Learning Ability","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ivan Lee, Nan Jiang, Taylor Berg-Kirkpatrick","submitted_at":"2023-10-12T05:43:06Z","abstract_excerpt":"What is the relationship between model architecture and the ability to perform in-context learning? In this empirical study, we take the first steps toward answering this question. We evaluate thirteen model architectures capable of causal language modeling across a suite of synthetic in-context learning tasks. These selected architectures represent a broad range of paradigms, including recurrent and convolution-based neural networks, transformers, state space model inspired, and other emerging attention alternatives. We discover that all the considered architectures can perform in-context lea"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.08049","kind":"arxiv","version":3},"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/2310.08049/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":"2310.08049","created_at":"2026-07-05T08:03:07.482354+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.08049v3","created_at":"2026-07-05T08:03:07.482354+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.08049","created_at":"2026-07-05T08:03:07.482354+00:00"},{"alias_kind":"pith_short_12","alias_value":"FERHZO2E7I2O","created_at":"2026-07-05T08:03:07.482354+00:00"},{"alias_kind":"pith_short_16","alias_value":"FERHZO2E7I2OJN6C","created_at":"2026-07-05T08:03:07.482354+00:00"},{"alias_kind":"pith_short_8","alias_value":"FERHZO2E","created_at":"2026-07-05T08:03:07.482354+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2404.14294","citing_title":"A Survey on Efficient Inference for Large Language Models","ref_index":299,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FERHZO2E7I2OJN6CXHAYAINZYQ","json":"https://pith.science/pith/FERHZO2E7I2OJN6CXHAYAINZYQ.json","graph_json":"https://pith.science/api/pith-number/FERHZO2E7I2OJN6CXHAYAINZYQ/graph.json","events_json":"https://pith.science/api/pith-number/FERHZO2E7I2OJN6CXHAYAINZYQ/events.json","paper":"https://pith.science/paper/FERHZO2E"},"agent_actions":{"view_html":"https://pith.science/pith/FERHZO2E7I2OJN6CXHAYAINZYQ","download_json":"https://pith.science/pith/FERHZO2E7I2OJN6CXHAYAINZYQ.json","view_paper":"https://pith.science/paper/FERHZO2E","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.08049&json=true","fetch_graph":"https://pith.science/api/pith-number/FERHZO2E7I2OJN6CXHAYAINZYQ/graph.json","fetch_events":"https://pith.science/api/pith-number/FERHZO2E7I2OJN6CXHAYAINZYQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FERHZO2E7I2OJN6CXHAYAINZYQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FERHZO2E7I2OJN6CXHAYAINZYQ/action/storage_attestation","attest_author":"https://pith.science/pith/FERHZO2E7I2OJN6CXHAYAINZYQ/action/author_attestation","sign_citation":"https://pith.science/pith/FERHZO2E7I2OJN6CXHAYAINZYQ/action/citation_signature","submit_replication":"https://pith.science/pith/FERHZO2E7I2OJN6CXHAYAINZYQ/action/replication_record"}},"created_at":"2026-07-05T08:03:07.482354+00:00","updated_at":"2026-07-05T08:03:07.482354+00:00"}