{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:ZJWWUDDWI4IZX3KMXE7EDVFHQ3","short_pith_number":"pith:ZJWWUDDW","schema_version":"1.0","canonical_sha256":"ca6d6a0c7647119bed4cb93e41d4a786fd324ca6833f9a5442238c454e840a75","source":{"kind":"arxiv","id":"2305.16704","version":1},"attestation_state":"computed","paper":{"title":"A Closer Look at In-Context Learning under Distribution Shifts","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"David Lopez-Paz, Kartik Ahuja","submitted_at":"2023-05-26T07:47:21Z","abstract_excerpt":"In-context learning, a capability that enables a model to learn from input examples on the fly without necessitating weight updates, is a defining characteristic of large language models. In this work, we follow the setting proposed in (Garg et al., 2022) to better understand the generality and limitations of in-context learning from the lens of the simple yet fundamental task of linear regression. The key question we aim to address is: Are transformers more adept than some natural and simpler architectures at performing in-context learning under varying distribution shifts? To compare transfo"},"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":"2305.16704","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-05-26T07:47:21Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"cd57bd093fb582593bccc9b80a06f4f6d08b77d31df4772693f3fcbe7d9207c1","abstract_canon_sha256":"95b61347cb3f645a26e7fecdbf313d4fbd7a7adc6ead7bd346510e6f5077ee30"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:14:16.578835Z","signature_b64":"VvChc7atyxwKn192Ha6vpMACQ6tfILoltEY9q4woKNX3nsDGUkck1DiG9KAANsttaeNnivM7mCu/p8UJzUOpAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ca6d6a0c7647119bed4cb93e41d4a786fd324ca6833f9a5442238c454e840a75","last_reissued_at":"2026-07-05T06:14:16.578371Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:14:16.578371Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Closer Look at In-Context Learning under Distribution Shifts","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"David Lopez-Paz, Kartik Ahuja","submitted_at":"2023-05-26T07:47:21Z","abstract_excerpt":"In-context learning, a capability that enables a model to learn from input examples on the fly without necessitating weight updates, is a defining characteristic of large language models. In this work, we follow the setting proposed in (Garg et al., 2022) to better understand the generality and limitations of in-context learning from the lens of the simple yet fundamental task of linear regression. The key question we aim to address is: Are transformers more adept than some natural and simpler architectures at performing in-context learning under varying distribution shifts? To compare transfo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.16704","kind":"arxiv","version":1},"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/2305.16704/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":"2305.16704","created_at":"2026-07-05T06:14:16.578423+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.16704v1","created_at":"2026-07-05T06:14:16.578423+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.16704","created_at":"2026-07-05T06:14:16.578423+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZJWWUDDWI4IZ","created_at":"2026-07-05T06:14:16.578423+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZJWWUDDWI4IZX3KM","created_at":"2026-07-05T06:14:16.578423+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZJWWUDDW","created_at":"2026-07-05T06:14:16.578423+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.06814","citing_title":"The Effect of Training Task Diversity on In-Context Learning through the Lens of Low-Dimensional Subspaces","ref_index":34,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZJWWUDDWI4IZX3KMXE7EDVFHQ3","json":"https://pith.science/pith/ZJWWUDDWI4IZX3KMXE7EDVFHQ3.json","graph_json":"https://pith.science/api/pith-number/ZJWWUDDWI4IZX3KMXE7EDVFHQ3/graph.json","events_json":"https://pith.science/api/pith-number/ZJWWUDDWI4IZX3KMXE7EDVFHQ3/events.json","paper":"https://pith.science/paper/ZJWWUDDW"},"agent_actions":{"view_html":"https://pith.science/pith/ZJWWUDDWI4IZX3KMXE7EDVFHQ3","download_json":"https://pith.science/pith/ZJWWUDDWI4IZX3KMXE7EDVFHQ3.json","view_paper":"https://pith.science/paper/ZJWWUDDW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.16704&json=true","fetch_graph":"https://pith.science/api/pith-number/ZJWWUDDWI4IZX3KMXE7EDVFHQ3/graph.json","fetch_events":"https://pith.science/api/pith-number/ZJWWUDDWI4IZX3KMXE7EDVFHQ3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZJWWUDDWI4IZX3KMXE7EDVFHQ3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZJWWUDDWI4IZX3KMXE7EDVFHQ3/action/storage_attestation","attest_author":"https://pith.science/pith/ZJWWUDDWI4IZX3KMXE7EDVFHQ3/action/author_attestation","sign_citation":"https://pith.science/pith/ZJWWUDDWI4IZX3KMXE7EDVFHQ3/action/citation_signature","submit_replication":"https://pith.science/pith/ZJWWUDDWI4IZX3KMXE7EDVFHQ3/action/replication_record"}},"created_at":"2026-07-05T06:14:16.578423+00:00","updated_at":"2026-07-05T06:14:16.578423+00:00"}