{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:MVZYBKXAAV5VHVMQLR2QYRJITQ","short_pith_number":"pith:MVZYBKXA","schema_version":"1.0","canonical_sha256":"657380aae0057b53d5905c750c45289c286191fbdfdc21c706c1d88b2e108737","source":{"kind":"arxiv","id":"2505.11006","version":6},"attestation_state":"computed","paper":{"title":"Is Supervised Learning Really That Different from Unsupervised?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Oskar Allerbo, Thomas B. Sch\\\"on","submitted_at":"2025-05-16T08:51:44Z","abstract_excerpt":"We demonstrate how supervised learning can be decomposed into a two-stage procedure, where (1) all model parameters are selected in an unsupervised manner, and (2) the outputs y are added to the model, without changing the parameter values. This is achieved by a new model selection criterion that - in contrast to cross-validation - can be used also without access to y. For linear ridge regression, we bound the asymptotic out-of-sample risk of our method in terms of the optimal asymptotic risk. We also demonstrate that versions of linear and kernel ridge regression, smoothing splines, k-nearest"},"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":"2505.11006","kind":"arxiv","version":6},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2025-05-16T08:51:44Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"49e47699198ee65285aeb54b591a44d5d6d56c5d35e0a9ae6892f5933feb6a22","abstract_canon_sha256":"0ec24bde563f4510cc842e62be24f666e74bdd500b4e3eff68648f044d7bb4c3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-05T01:15:13.814204Z","signature_b64":"HR1GyYJH/hn5R9Z6fTPy5086lNbn8bcXMSFdooELIXx3UvL5gXRrGPRcYimNP1UC4Pb49moq8UfLtyCsET6jCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"657380aae0057b53d5905c750c45289c286191fbdfdc21c706c1d88b2e108737","last_reissued_at":"2026-06-05T01:15:13.813400Z","signature_status":"signed_v1","first_computed_at":"2026-06-05T01:15:13.813400Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Is Supervised Learning Really That Different from Unsupervised?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Oskar Allerbo, Thomas B. Sch\\\"on","submitted_at":"2025-05-16T08:51:44Z","abstract_excerpt":"We demonstrate how supervised learning can be decomposed into a two-stage procedure, where (1) all model parameters are selected in an unsupervised manner, and (2) the outputs y are added to the model, without changing the parameter values. This is achieved by a new model selection criterion that - in contrast to cross-validation - can be used also without access to y. For linear ridge regression, we bound the asymptotic out-of-sample risk of our method in terms of the optimal asymptotic risk. We also demonstrate that versions of linear and kernel ridge regression, smoothing splines, k-nearest"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.11006","kind":"arxiv","version":6},"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/2505.11006/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":"2505.11006","created_at":"2026-06-05T01:15:13.813491+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.11006v6","created_at":"2026-06-05T01:15:13.813491+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.11006","created_at":"2026-06-05T01:15:13.813491+00:00"},{"alias_kind":"pith_short_12","alias_value":"MVZYBKXAAV5V","created_at":"2026-06-05T01:15:13.813491+00:00"},{"alias_kind":"pith_short_16","alias_value":"MVZYBKXAAV5VHVMQ","created_at":"2026-06-05T01:15:13.813491+00:00"},{"alias_kind":"pith_short_8","alias_value":"MVZYBKXA","created_at":"2026-06-05T01:15:13.813491+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.21167","citing_title":"A Rigorous, Tractable Measure of Model Complexity","ref_index":1,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MVZYBKXAAV5VHVMQLR2QYRJITQ","json":"https://pith.science/pith/MVZYBKXAAV5VHVMQLR2QYRJITQ.json","graph_json":"https://pith.science/api/pith-number/MVZYBKXAAV5VHVMQLR2QYRJITQ/graph.json","events_json":"https://pith.science/api/pith-number/MVZYBKXAAV5VHVMQLR2QYRJITQ/events.json","paper":"https://pith.science/paper/MVZYBKXA"},"agent_actions":{"view_html":"https://pith.science/pith/MVZYBKXAAV5VHVMQLR2QYRJITQ","download_json":"https://pith.science/pith/MVZYBKXAAV5VHVMQLR2QYRJITQ.json","view_paper":"https://pith.science/paper/MVZYBKXA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.11006&json=true","fetch_graph":"https://pith.science/api/pith-number/MVZYBKXAAV5VHVMQLR2QYRJITQ/graph.json","fetch_events":"https://pith.science/api/pith-number/MVZYBKXAAV5VHVMQLR2QYRJITQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MVZYBKXAAV5VHVMQLR2QYRJITQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MVZYBKXAAV5VHVMQLR2QYRJITQ/action/storage_attestation","attest_author":"https://pith.science/pith/MVZYBKXAAV5VHVMQLR2QYRJITQ/action/author_attestation","sign_citation":"https://pith.science/pith/MVZYBKXAAV5VHVMQLR2QYRJITQ/action/citation_signature","submit_replication":"https://pith.science/pith/MVZYBKXAAV5VHVMQLR2QYRJITQ/action/replication_record"}},"created_at":"2026-06-05T01:15:13.813491+00:00","updated_at":"2026-06-05T01:15:13.813491+00:00"}