{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:F3CWLV4YJ2TJ5Z3TPXBZUYLLT7","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"b3ddaf0f39198f614c5518bfbd256b1bd8c3718714bdc4834eacd3bb07da6819","cross_cats_sorted":["cs.LG","stat.ME"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2026-04-14T05:01:18Z","title_canon_sha256":"980a89b06e37953743886640d4c3649515de6f13d2c1c8b0d764dc9022de0ea5"},"schema_version":"1.0","source":{"id":"2604.12288","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.12288","created_at":"2026-05-20T00:04:31Z"},{"alias_kind":"arxiv_version","alias_value":"2604.12288v2","created_at":"2026-05-20T00:04:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.12288","created_at":"2026-05-20T00:04:31Z"},{"alias_kind":"pith_short_12","alias_value":"F3CWLV4YJ2TJ","created_at":"2026-05-20T00:04:31Z"},{"alias_kind":"pith_short_16","alias_value":"F3CWLV4YJ2TJ5Z3T","created_at":"2026-05-20T00:04:31Z"},{"alias_kind":"pith_short_8","alias_value":"F3CWLV4Y","created_at":"2026-05-20T00:04:31Z"}],"graph_snapshots":[{"event_id":"sha256:b866bd7183f9bf588ab18985141fcbc1821f539a20808bfb899d328439d2e57a","target":"graph","created_at":"2026-05-20T00:04:31Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","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"}],"snapshot_sha256":"98cd2638b89f3e0c48f9e13615f5d2fa0963726b000125350bfa787305edf58e"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2604.12288/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Cheng Gao, Jianqing Fan, Jinhang Chai, Qishuo Yin","cross_cats":["cs.LG","stat.ME"],"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","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2026-04-14T05:01:18Z","title":"SMART Fine-tuning Factor Augmented Neural Lasso"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2604.12288","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-10T15:41:45.219528Z","id":"94061665-dfa6-42d1-b24f-e7122688538b","model_set":{"reader":"grok-4.3"},"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","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","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.","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."}},"verdict_id":"94061665-dfa6-42d1-b24f-e7122688538b"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:cc60dd8e189555fb3a0c0f3e02f58cfc6d781321d3653cfb155a914a187e17eb","target":"record","created_at":"2026-05-20T00:04:31Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"b3ddaf0f39198f614c5518bfbd256b1bd8c3718714bdc4834eacd3bb07da6819","cross_cats_sorted":["cs.LG","stat.ME"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2026-04-14T05:01:18Z","title_canon_sha256":"980a89b06e37953743886640d4c3649515de6f13d2c1c8b0d764dc9022de0ea5"},"schema_version":"1.0","source":{"id":"2604.12288","kind":"arxiv","version":2}},"canonical_sha256":"2ec565d7984ea69ee7737dc39a616b9fd18ca322b2413a69c5cad55ffc6f6ec0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2ec565d7984ea69ee7737dc39a616b9fd18ca322b2413a69c5cad55ffc6f6ec0","first_computed_at":"2026-05-20T00:04:31.390907Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:04:31.390907Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"iT3MQFO3Q9bkvczjih6ALZ+D3OmQ6LTlcEzuGn1Qzemk78QgVIrmJ5lb6uKelfITELNgXxuCtD2QX6fr5kxgDg==","signature_status":"signed_v1","signed_at":"2026-05-20T00:04:31.391875Z","signed_message":"canonical_sha256_bytes"},"source_id":"2604.12288","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cc60dd8e189555fb3a0c0f3e02f58cfc6d781321d3653cfb155a914a187e17eb","sha256:b866bd7183f9bf588ab18985141fcbc1821f539a20808bfb899d328439d2e57a"],"state_sha256":"fe193876b983c85d50fa5ee26bed2f4f4750fed5c1d105439182b67bdd612bf1"}