{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:TTRPYHQCRWCIZXPPWXT4X5MX2C","short_pith_number":"pith:TTRPYHQC","schema_version":"1.0","canonical_sha256":"9ce2fc1e028d848cddefb5e7cbf597d0badffd3d806b7838084720485bef1b3d","source":{"kind":"arxiv","id":"2507.09440","version":1},"attestation_state":"computed","paper":{"title":"Transformers Don't In-Context Learn Least Squares Regression","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Benjamin Eyre, Elliot Creager, Joshua Hill","submitted_at":"2025-07-13T01:09:26Z","abstract_excerpt":"In-context learning (ICL) has emerged as a powerful capability of large pretrained transformers, enabling them to solve new tasks implicit in example input-output pairs without any gradient updates. Despite its practical success, the mechanisms underlying ICL remain largely mysterious. In this work we study synthetic linear regression to probe how transformers implement learning at inference time. Previous works have demonstrated that transformers match the performance of learning rules such as Ordinary Least Squares (OLS) regression or gradient descent and have suggested ICL is facilitated in"},"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":"2507.09440","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-13T01:09:26Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8185d0deb60bf717212b23573c6816044b9fb5bf7f3a8e9f2ca1504db388bde9","abstract_canon_sha256":"24ec658abfdf0bdc221cdf58211bc89099ece8685e805787e766a9a96e15ea6a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:36:09.069223Z","signature_b64":"MaHXbCFGzySQdEUvHLQ8gnxGiRUSD0deW17u819OReUkaeRODaozCyDPe74e8aNp2HHGkBlwI/E67LV1wOnTBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9ce2fc1e028d848cddefb5e7cbf597d0badffd3d806b7838084720485bef1b3d","last_reissued_at":"2026-07-05T11:36:09.068828Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:36:09.068828Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Transformers Don't In-Context Learn Least Squares Regression","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Benjamin Eyre, Elliot Creager, Joshua Hill","submitted_at":"2025-07-13T01:09:26Z","abstract_excerpt":"In-context learning (ICL) has emerged as a powerful capability of large pretrained transformers, enabling them to solve new tasks implicit in example input-output pairs without any gradient updates. Despite its practical success, the mechanisms underlying ICL remain largely mysterious. In this work we study synthetic linear regression to probe how transformers implement learning at inference time. Previous works have demonstrated that transformers match the performance of learning rules such as Ordinary Least Squares (OLS) regression or gradient descent and have suggested ICL is facilitated in"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.09440","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/2507.09440/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":"2507.09440","created_at":"2026-07-05T11:36:09.068883+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.09440v1","created_at":"2026-07-05T11:36:09.068883+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.09440","created_at":"2026-07-05T11:36:09.068883+00:00"},{"alias_kind":"pith_short_12","alias_value":"TTRPYHQCRWCI","created_at":"2026-07-05T11:36:09.068883+00:00"},{"alias_kind":"pith_short_16","alias_value":"TTRPYHQCRWCIZXPP","created_at":"2026-07-05T11:36:09.068883+00:00"},{"alias_kind":"pith_short_8","alias_value":"TTRPYHQC","created_at":"2026-07-05T11:36:09.068883+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TTRPYHQCRWCIZXPPWXT4X5MX2C","json":"https://pith.science/pith/TTRPYHQCRWCIZXPPWXT4X5MX2C.json","graph_json":"https://pith.science/api/pith-number/TTRPYHQCRWCIZXPPWXT4X5MX2C/graph.json","events_json":"https://pith.science/api/pith-number/TTRPYHQCRWCIZXPPWXT4X5MX2C/events.json","paper":"https://pith.science/paper/TTRPYHQC"},"agent_actions":{"view_html":"https://pith.science/pith/TTRPYHQCRWCIZXPPWXT4X5MX2C","download_json":"https://pith.science/pith/TTRPYHQCRWCIZXPPWXT4X5MX2C.json","view_paper":"https://pith.science/paper/TTRPYHQC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.09440&json=true","fetch_graph":"https://pith.science/api/pith-number/TTRPYHQCRWCIZXPPWXT4X5MX2C/graph.json","fetch_events":"https://pith.science/api/pith-number/TTRPYHQCRWCIZXPPWXT4X5MX2C/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TTRPYHQCRWCIZXPPWXT4X5MX2C/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TTRPYHQCRWCIZXPPWXT4X5MX2C/action/storage_attestation","attest_author":"https://pith.science/pith/TTRPYHQCRWCIZXPPWXT4X5MX2C/action/author_attestation","sign_citation":"https://pith.science/pith/TTRPYHQCRWCIZXPPWXT4X5MX2C/action/citation_signature","submit_replication":"https://pith.science/pith/TTRPYHQCRWCIZXPPWXT4X5MX2C/action/replication_record"}},"created_at":"2026-07-05T11:36:09.068883+00:00","updated_at":"2026-07-05T11:36:09.068883+00:00"}