{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:RA3ZFOWM5455QDXXKZ7YMN3N7N","short_pith_number":"pith:RA3ZFOWM","schema_version":"1.0","canonical_sha256":"883792baccef3bd80ef7567f86376dfb7a18fee4fe0e886c102591d12b189a40","source":{"kind":"arxiv","id":"2405.02462","version":2},"attestation_state":"computed","paper":{"title":"Finite Sample Analysis and Bounds of Generalization Error of Gradient Descent in In-Context Linear Regression","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.NA","math.NA","math.PR","stat.TH"],"primary_cat":"math.ST","authors_text":"Karthik Duraisamy","submitted_at":"2024-05-03T19:52:07Z","abstract_excerpt":"Recent studies show that transformer-based architectures emulate gradient descent during a forward pass, contributing to in-context learning capabilities - an ability where the model adapts to new tasks based on a sequence of prompt examples without being explicitly trained or fine tuned to do so. This work investigates the generalization properties of a single step of gradient descent in the context of linear regression with well-specified models. A random design setting is considered and analytical expressions are derived for the statistical properties and bounds of generalization error in a"},"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":"2405.02462","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.ST","submitted_at":"2024-05-03T19:52:07Z","cross_cats_sorted":["cs.NA","math.NA","math.PR","stat.TH"],"title_canon_sha256":"2d55c080249ad3127940f8d6dc04001d4cfe9ff749d668e812b26ae23a6d477a","abstract_canon_sha256":"773a3ff35aae733f26deeed62c29301ad19b0b8b2a42623ef37916c8ac8c0e1d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:17:32.830590Z","signature_b64":"v5+V3E8MdbUJbiicuUh+Jc7la2u78ADpO55IxxPn0Xqxdt8IxfEeqgjvb1uW+SqISZIRChWtNjRGrJAgRoOkBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"883792baccef3bd80ef7567f86376dfb7a18fee4fe0e886c102591d12b189a40","last_reissued_at":"2026-07-05T08:17:32.830035Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:17:32.830035Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Finite Sample Analysis and Bounds of Generalization Error of Gradient Descent in In-Context Linear Regression","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.NA","math.NA","math.PR","stat.TH"],"primary_cat":"math.ST","authors_text":"Karthik Duraisamy","submitted_at":"2024-05-03T19:52:07Z","abstract_excerpt":"Recent studies show that transformer-based architectures emulate gradient descent during a forward pass, contributing to in-context learning capabilities - an ability where the model adapts to new tasks based on a sequence of prompt examples without being explicitly trained or fine tuned to do so. This work investigates the generalization properties of a single step of gradient descent in the context of linear regression with well-specified models. A random design setting is considered and analytical expressions are derived for the statistical properties and bounds of generalization error in a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.02462","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/2405.02462/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":"2405.02462","created_at":"2026-07-05T08:17:32.830109+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.02462v2","created_at":"2026-07-05T08:17:32.830109+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.02462","created_at":"2026-07-05T08:17:32.830109+00:00"},{"alias_kind":"pith_short_12","alias_value":"RA3ZFOWM5455","created_at":"2026-07-05T08:17:32.830109+00:00"},{"alias_kind":"pith_short_16","alias_value":"RA3ZFOWM5455QDXX","created_at":"2026-07-05T08:17:32.830109+00:00"},{"alias_kind":"pith_short_8","alias_value":"RA3ZFOWM","created_at":"2026-07-05T08:17:32.830109+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.03327","citing_title":"Is In-Context Universality Enough? MLPs are Also Universal In-Context","ref_index":22,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RA3ZFOWM5455QDXXKZ7YMN3N7N","json":"https://pith.science/pith/RA3ZFOWM5455QDXXKZ7YMN3N7N.json","graph_json":"https://pith.science/api/pith-number/RA3ZFOWM5455QDXXKZ7YMN3N7N/graph.json","events_json":"https://pith.science/api/pith-number/RA3ZFOWM5455QDXXKZ7YMN3N7N/events.json","paper":"https://pith.science/paper/RA3ZFOWM"},"agent_actions":{"view_html":"https://pith.science/pith/RA3ZFOWM5455QDXXKZ7YMN3N7N","download_json":"https://pith.science/pith/RA3ZFOWM5455QDXXKZ7YMN3N7N.json","view_paper":"https://pith.science/paper/RA3ZFOWM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.02462&json=true","fetch_graph":"https://pith.science/api/pith-number/RA3ZFOWM5455QDXXKZ7YMN3N7N/graph.json","fetch_events":"https://pith.science/api/pith-number/RA3ZFOWM5455QDXXKZ7YMN3N7N/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RA3ZFOWM5455QDXXKZ7YMN3N7N/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RA3ZFOWM5455QDXXKZ7YMN3N7N/action/storage_attestation","attest_author":"https://pith.science/pith/RA3ZFOWM5455QDXXKZ7YMN3N7N/action/author_attestation","sign_citation":"https://pith.science/pith/RA3ZFOWM5455QDXXKZ7YMN3N7N/action/citation_signature","submit_replication":"https://pith.science/pith/RA3ZFOWM5455QDXXKZ7YMN3N7N/action/replication_record"}},"created_at":"2026-07-05T08:17:32.830109+00:00","updated_at":"2026-07-05T08:17:32.830109+00:00"}