{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:MQH65QFNDP2Z6MOJ3ENCOCLDOB","short_pith_number":"pith:MQH65QFN","schema_version":"1.0","canonical_sha256":"640feec0ad1bf59f31c9d91a27096370539ffc5c2a602c264aacc7e4955a6a33","source":{"kind":"arxiv","id":"2410.02164","version":2},"attestation_state":"computed","paper":{"title":"Universality in Transfer Learning for Linear Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Babak Hassibi, Danil Akhtiamov, Reza Ghane","submitted_at":"2024-10-03T03:09:09Z","abstract_excerpt":"We study the problem of transfer learning and fine-tuning in linear models for both regression and binary classification. In particular, we consider the use of stochastic gradient descent (SGD) on a linear model initialized with pretrained weights and using a small training data set from the target distribution. In the asymptotic regime of large models, we provide an exact and rigorous analysis and relate the generalization errors (in regression) and classification errors (in binary classification) for the pretrained and fine-tuned models. In particular, we give conditions under which the fine"},"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":"2410.02164","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-03T03:09:09Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"d32ccfad112471bf746f69249bded2ae0f2aee3c8cffc660e8aaf5b75d3ef0ad","abstract_canon_sha256":"7324ebbd264b13c37f4854e1fdb7fe6aad6ad632bc309e8e17337df71ec725e5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:18:42.251442Z","signature_b64":"bHZxWJlUBPJCrQLAt+q2q5k5cWDhx5QmjL5mVWZ9QIe6U/s+dYx0vvjms9NNCpoTzw2wqDQ2QzjQZofSBFs/AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"640feec0ad1bf59f31c9d91a27096370539ffc5c2a602c264aacc7e4955a6a33","last_reissued_at":"2026-07-05T10:18:42.250909Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:18:42.250909Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Universality in Transfer Learning for Linear Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Babak Hassibi, Danil Akhtiamov, Reza Ghane","submitted_at":"2024-10-03T03:09:09Z","abstract_excerpt":"We study the problem of transfer learning and fine-tuning in linear models for both regression and binary classification. In particular, we consider the use of stochastic gradient descent (SGD) on a linear model initialized with pretrained weights and using a small training data set from the target distribution. In the asymptotic regime of large models, we provide an exact and rigorous analysis and relate the generalization errors (in regression) and classification errors (in binary classification) for the pretrained and fine-tuned models. In particular, we give conditions under which the fine"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.02164","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/2410.02164/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":"2410.02164","created_at":"2026-07-05T10:18:42.250976+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.02164v2","created_at":"2026-07-05T10:18:42.250976+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.02164","created_at":"2026-07-05T10:18:42.250976+00:00"},{"alias_kind":"pith_short_12","alias_value":"MQH65QFNDP2Z","created_at":"2026-07-05T10:18:42.250976+00:00"},{"alias_kind":"pith_short_16","alias_value":"MQH65QFNDP2Z6MOJ","created_at":"2026-07-05T10:18:42.250976+00:00"},{"alias_kind":"pith_short_8","alias_value":"MQH65QFN","created_at":"2026-07-05T10:18:42.250976+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/MQH65QFNDP2Z6MOJ3ENCOCLDOB","json":"https://pith.science/pith/MQH65QFNDP2Z6MOJ3ENCOCLDOB.json","graph_json":"https://pith.science/api/pith-number/MQH65QFNDP2Z6MOJ3ENCOCLDOB/graph.json","events_json":"https://pith.science/api/pith-number/MQH65QFNDP2Z6MOJ3ENCOCLDOB/events.json","paper":"https://pith.science/paper/MQH65QFN"},"agent_actions":{"view_html":"https://pith.science/pith/MQH65QFNDP2Z6MOJ3ENCOCLDOB","download_json":"https://pith.science/pith/MQH65QFNDP2Z6MOJ3ENCOCLDOB.json","view_paper":"https://pith.science/paper/MQH65QFN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.02164&json=true","fetch_graph":"https://pith.science/api/pith-number/MQH65QFNDP2Z6MOJ3ENCOCLDOB/graph.json","fetch_events":"https://pith.science/api/pith-number/MQH65QFNDP2Z6MOJ3ENCOCLDOB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MQH65QFNDP2Z6MOJ3ENCOCLDOB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MQH65QFNDP2Z6MOJ3ENCOCLDOB/action/storage_attestation","attest_author":"https://pith.science/pith/MQH65QFNDP2Z6MOJ3ENCOCLDOB/action/author_attestation","sign_citation":"https://pith.science/pith/MQH65QFNDP2Z6MOJ3ENCOCLDOB/action/citation_signature","submit_replication":"https://pith.science/pith/MQH65QFNDP2Z6MOJ3ENCOCLDOB/action/replication_record"}},"created_at":"2026-07-05T10:18:42.250976+00:00","updated_at":"2026-07-05T10:18:42.250976+00:00"}