{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:4AFFH5ZOLJAPPXRLMCLKQT4V5A","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":"78db40950582b1cef379628dd31244c0819021c541401447a504683bd7a126e4","cross_cats_sorted":["cs.LG","eess.SP"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2026-05-13T14:23:00Z","title_canon_sha256":"a1552dc44d73c40b5fdf6ea1b93318c79cab22b0fb35be8a92443ffbca907b5c"},"schema_version":"1.0","source":{"id":"2605.13587","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.13587","created_at":"2026-05-18T02:44:23Z"},{"alias_kind":"arxiv_version","alias_value":"2605.13587v1","created_at":"2026-05-18T02:44:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.13587","created_at":"2026-05-18T02:44:23Z"},{"alias_kind":"pith_short_12","alias_value":"4AFFH5ZOLJAP","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"4AFFH5ZOLJAPPXRL","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"4AFFH5ZO","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:4ed1e7aef3f8f161ca9a0495af34e48e58fd15c3a31ef8564a18b21a1c89e15b","target":"graph","created_at":"2026-05-18T02:44:23Z","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":"Compact operator-adaptive PLS with ASLS branch preprocessing achieved a median RMSEP/PLS ratio of 0.960 with 42 wins on 57 datasets, while a deployable AOM-Ridge selector improved over tuned Ridge by a median 2.22% with 35 wins on 52 datasets."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That treating nonlinear or sample-adaptive corrections (SNV, MSC, ASLS) as fold-local branches fully prevents information leakage while still allowing the model to adaptively select effective preprocessing without introducing bias or overfitting to the specific dataset splits."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Operator-adaptive PLS and Ridge models internalize preprocessing selection via linear operators and fold-local branches, achieving median RMSEP/PLS ratio of 0.960 on 57 datasets and 2.22% improvement over tuned Ridge on 52 datasets."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Operator-adaptive models that fold preprocessing selection inside calibration outperform standard PLS and Ridge on most NIRS datasets."}],"snapshot_sha256":"311835b054f9422aee2e960e887c523409146246995301f00e29e71fc9c214ea"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"Near-infrared spectroscopy (NIRS) is rapid and non-destructive, but reliable calibration still depends heavily on spectral preprocessing. In routine practice, preprocessing is often selected by large external pipeline searches that are costly, unstable on small calibration sets, and difficult to audit. We introduce operator-adaptive calibration, a framework that moves linear preprocessing selection inside the calibration model. Candidate treatments are encoded as linear spectral operators, while nonlinear or sample-adaptive corrections such as SNV, MSC, and ASLS are handled as fold-local branc","authors_text":"Camille No\\^us, Denis Cornet, Gregory Beurier, Lauriane Rouan, Robin Reiter","cross_cats":["cs.LG","eess.SP"],"headline":"Operator-adaptive models that fold preprocessing selection inside calibration outperform standard PLS and Ridge on most NIRS datasets.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2026-05-13T14:23:00Z","title":"Reframing preprocessing selection as model-internal calibration in near-infrared spectroscopy: A large-scale benchmark of operator-adaptive PLS and Ridge models"},"references":{"count":54,"internal_anchors":0,"resolved_work":54,"sample":[{"cited_arxiv_id":"","doi":"10.1016/0003-2670(86)80028-9","is_internal_anchor":false,"ref_index":1,"title":"Kowalski , abstract =","work_id":"fd481190-8bd7-45ef-9fce-2c26fbbfa2b2","year":1986},{"cited_arxiv_id":"","doi":"10.1016/s0169-7439(01)00155-1","is_internal_anchor":false,"ref_index":2,"title":"Pls-regression: a basic tool of chemometrics","work_id":"f41c59e7-ad94-425a-8098-b8ac4e5c6d97","year":2001},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Simpls: an alternative approach to partial least squares regression","work_id":"e960206c-7312-4787-8201-1aa2e88bc83b","year":1993},{"cited_arxiv_id":"","doi":"10.1080/00401706.1970.10488634","is_internal_anchor":false,"ref_index":4,"title":"Hoerl and Robert W","work_id":"9301f413-f104-4514-b840-a10933899575","year":1970},{"cited_arxiv_id":"","doi":"10.1016/j.trac.2009.07.007","is_internal_anchor":false,"ref_index":5,"title":"Review of the most common pre-processing techniques for near-infrared spectra","work_id":"f4a50e00-2839-4cd5-814c-c52a027f4e52","year":2009}],"snapshot_sha256":"b83dc2fcb00d2112868ee745751ef26b9bbf0073f19a280f57f24598386a5480"},"source":{"id":"2605.13587","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-14T18:23:07.895277Z","id":"55da6eaa-ec87-43de-ba2d-07690dea3d6a","model_set":{"reader":"grok-4.3"},"one_line_summary":"Operator-adaptive PLS and Ridge models internalize preprocessing selection via linear operators and fold-local branches, achieving median RMSEP/PLS ratio of 0.960 on 57 datasets and 2.22% improvement over tuned Ridge on 52 datasets.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Operator-adaptive models that fold preprocessing selection inside calibration outperform standard PLS and Ridge on most NIRS datasets.","strongest_claim":"Compact operator-adaptive PLS with ASLS branch preprocessing achieved a median RMSEP/PLS ratio of 0.960 with 42 wins on 57 datasets, while a deployable AOM-Ridge selector improved over tuned Ridge by a median 2.22% with 35 wins on 52 datasets.","weakest_assumption":"That treating nonlinear or sample-adaptive corrections (SNV, MSC, ASLS) as fold-local branches fully prevents information leakage while still allowing the model to adaptively select effective preprocessing without introducing bias or overfitting to the specific dataset splits."}},"verdict_id":"55da6eaa-ec87-43de-ba2d-07690dea3d6a"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:76ff43f95019d5a009f02d534697d5c3b1a1c476025a152352688a56599a4928","target":"record","created_at":"2026-05-18T02:44:23Z","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":"78db40950582b1cef379628dd31244c0819021c541401447a504683bd7a126e4","cross_cats_sorted":["cs.LG","eess.SP"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2026-05-13T14:23:00Z","title_canon_sha256":"a1552dc44d73c40b5fdf6ea1b93318c79cab22b0fb35be8a92443ffbca907b5c"},"schema_version":"1.0","source":{"id":"2605.13587","kind":"arxiv","version":1}},"canonical_sha256":"e00a53f72e5a40f7de2b6096a84f95e82bb1fd01106a9f8946b1ef558ce12d6f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e00a53f72e5a40f7de2b6096a84f95e82bb1fd01106a9f8946b1ef558ce12d6f","first_computed_at":"2026-05-18T02:44:23.132509Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T02:44:23.132509Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"t8ygbG7yE5GgdQEOlgcOInEKHhiITfARiECeMe15nitG07EPSuVGtaSVA1sthEVsl9x6pQLCKKHimMvrEigHBQ==","signature_status":"signed_v1","signed_at":"2026-05-18T02:44:23.133061Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.13587","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:76ff43f95019d5a009f02d534697d5c3b1a1c476025a152352688a56599a4928","sha256:4ed1e7aef3f8f161ca9a0495af34e48e58fd15c3a31ef8564a18b21a1c89e15b"],"state_sha256":"13178705a42a79b0a9557c52cfc5430b114027db136fb45ed97119bd4b22f207"}