{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:F3CWLV4YJ2TJ5Z3TPXBZUYLLT7","short_pith_number":"pith:F3CWLV4Y","schema_version":"1.0","canonical_sha256":"2ec565d7984ea69ee7737dc39a616b9fd18ca322b2413a69c5cad55ffc6f6ec0","source":{"kind":"arxiv","id":"2604.12288","version":2},"attestation_state":"computed","paper":{"title":"SMART Fine-tuning Factor Augmented Neural Lasso","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Fine-tuning the factor-augmented neural Lasso yields minimax-optimal excess risk bounds and statistical acceleration over single-task learning when relative sample sizes and function complexities align in high-dimensional nonparametric reg","cross_cats":["cs.LG","stat.ME"],"primary_cat":"stat.ML","authors_text":"Cheng Gao, Jianqing Fan, Jinhang Chai, Qishuo Yin","submitted_at":"2026-04-14T05:01:18Z","abstract_excerpt":"Fine-tuning is a widely used strategy for adapting pre-trained models to new tasks, yet its methodology and theoretical properties in high-dimensional nonparametric settings with variable selection have not yet been developed. We propose a source-model-augmented residual tuning (SMART) framework, which incorporates the pre-trained source model as an augmented feature into the target learner and estimates only the residual target-specific component. The approach is widely applicable, from parametric and sparse models to neural networks and blackbox machine learning models. We focus on the devel"},"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":"2604.12288","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2026-04-14T05:01:18Z","cross_cats_sorted":["cs.LG","stat.ME"],"title_canon_sha256":"980a89b06e37953743886640d4c3649515de6f13d2c1c8b0d764dc9022de0ea5","abstract_canon_sha256":"b3ddaf0f39198f614c5518bfbd256b1bd8c3718714bdc4834eacd3bb07da6819"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:04:31.391875Z","signature_b64":"iT3MQFO3Q9bkvczjih6ALZ+D3OmQ6LTlcEzuGn1Qzemk78QgVIrmJ5lb6uKelfITELNgXxuCtD2QX6fr5kxgDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2ec565d7984ea69ee7737dc39a616b9fd18ca322b2413a69c5cad55ffc6f6ec0","last_reissued_at":"2026-05-20T00:04:31.390907Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:04:31.390907Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SMART Fine-tuning Factor Augmented Neural Lasso","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Fine-tuning the factor-augmented neural Lasso yields minimax-optimal excess risk bounds and statistical acceleration over single-task learning when relative sample sizes and function complexities align in high-dimensional nonparametric reg","cross_cats":["cs.LG","stat.ME"],"primary_cat":"stat.ML","authors_text":"Cheng Gao, Jianqing Fan, Jinhang Chai, Qishuo Yin","submitted_at":"2026-04-14T05:01:18Z","abstract_excerpt":"Fine-tuning is a widely used strategy for adapting pre-trained models to new tasks, yet its methodology and theoretical properties in high-dimensional nonparametric settings with variable selection have not yet been developed. We propose a source-model-augmented residual tuning (SMART) framework, which incorporates the pre-trained source model as an augmented feature into the target learner and estimates only the residual target-specific component. The approach is widely applicable, from parametric and sparse models to neural networks and blackbox machine learning models. We focus on the devel"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"We derive minimax-optimal excess risk bounds for the fine-tuning FAN-Lasso, characterizing the precise conditions, in terms of relative sample sizes and function complexities, under which fine-tuning yields statistical acceleration over single-task learning.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The target function admits a residual fine-tuning decomposition as a transformation of a frozen source function plus other variables, combined with a low-rank factor structure adequately capturing high-dimensional dependent covariates.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"FAN-Lasso uses low-rank factor structures and a residual fine-tuning decomposition to enable transfer learning and variable selection in high-dimensional nonparametric regression, delivering minimax-optimal excess risk bounds under conditions on sample sizes and function complexity.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Fine-tuning the factor-augmented neural Lasso yields minimax-optimal excess risk bounds and statistical acceleration over single-task learning when relative sample sizes and function complexities align in high-dimensional nonparametric reg","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"98cd2638b89f3e0c48f9e13615f5d2fa0963726b000125350bfa787305edf58e"},"source":{"id":"2604.12288","kind":"arxiv","version":2},"verdict":{"id":"94061665-dfa6-42d1-b24f-e7122688538b","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-10T15:41:45.219528Z","strongest_claim":"We derive minimax-optimal excess risk bounds for the fine-tuning FAN-Lasso, characterizing the precise conditions, in terms of relative sample sizes and function complexities, under which fine-tuning yields statistical acceleration over single-task learning.","one_line_summary":"FAN-Lasso uses low-rank factor structures and a residual fine-tuning decomposition to enable transfer learning and variable selection in high-dimensional nonparametric regression, delivering minimax-optimal excess risk bounds under conditions on sample sizes and function complexity.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The target function admits a residual fine-tuning decomposition as a transformation of a frozen source function plus other variables, combined with a low-rank factor structure adequately capturing high-dimensional dependent covariates.","pith_extraction_headline":"Fine-tuning the factor-augmented neural Lasso yields minimax-optimal excess risk bounds and statistical acceleration over single-task learning when relative sample sizes and function complexities align in high-dimensional nonparametric reg"},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2604.12288/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":"2604.12288","created_at":"2026-05-20T00:04:31.391076+00:00"},{"alias_kind":"arxiv_version","alias_value":"2604.12288v2","created_at":"2026-05-20T00:04:31.391076+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.12288","created_at":"2026-05-20T00:04:31.391076+00:00"},{"alias_kind":"pith_short_12","alias_value":"F3CWLV4YJ2TJ","created_at":"2026-05-20T00:04:31.391076+00:00"},{"alias_kind":"pith_short_16","alias_value":"F3CWLV4YJ2TJ5Z3T","created_at":"2026-05-20T00:04:31.391076+00:00"},{"alias_kind":"pith_short_8","alias_value":"F3CWLV4Y","created_at":"2026-05-20T00:04:31.391076+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/F3CWLV4YJ2TJ5Z3TPXBZUYLLT7","json":"https://pith.science/pith/F3CWLV4YJ2TJ5Z3TPXBZUYLLT7.json","graph_json":"https://pith.science/api/pith-number/F3CWLV4YJ2TJ5Z3TPXBZUYLLT7/graph.json","events_json":"https://pith.science/api/pith-number/F3CWLV4YJ2TJ5Z3TPXBZUYLLT7/events.json","paper":"https://pith.science/paper/F3CWLV4Y"},"agent_actions":{"view_html":"https://pith.science/pith/F3CWLV4YJ2TJ5Z3TPXBZUYLLT7","download_json":"https://pith.science/pith/F3CWLV4YJ2TJ5Z3TPXBZUYLLT7.json","view_paper":"https://pith.science/paper/F3CWLV4Y","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2604.12288&json=true","fetch_graph":"https://pith.science/api/pith-number/F3CWLV4YJ2TJ5Z3TPXBZUYLLT7/graph.json","fetch_events":"https://pith.science/api/pith-number/F3CWLV4YJ2TJ5Z3TPXBZUYLLT7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/F3CWLV4YJ2TJ5Z3TPXBZUYLLT7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/F3CWLV4YJ2TJ5Z3TPXBZUYLLT7/action/storage_attestation","attest_author":"https://pith.science/pith/F3CWLV4YJ2TJ5Z3TPXBZUYLLT7/action/author_attestation","sign_citation":"https://pith.science/pith/F3CWLV4YJ2TJ5Z3TPXBZUYLLT7/action/citation_signature","submit_replication":"https://pith.science/pith/F3CWLV4YJ2TJ5Z3TPXBZUYLLT7/action/replication_record"}},"created_at":"2026-05-20T00:04:31.391076+00:00","updated_at":"2026-05-20T00:04:31.391076+00:00"}