{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:HPZFVXZ5XMNIQA3QEML5XFVCM6","short_pith_number":"pith:HPZFVXZ5","schema_version":"1.0","canonical_sha256":"3bf25adf3dbb1a8803702317db96a267932d9531b34d13b5dd06033aa779b119","source":{"kind":"arxiv","id":"2606.12552","version":1},"attestation_state":"computed","paper":{"title":"Crossing the Validation Crisis: Cross-Validation Reduces Benchmarking Variance Surprisingly Well","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"C\\'elestin Eve, Ga\\\"el Varoquaux, Thomas Moreau","submitted_at":"2026-06-10T18:03:19Z","abstract_excerpt":"Modern machine learning progresses through empirical work, benchmarking new methods to evaluate relative performance. However, the statistical variability inherent to evaluation - exacerbated by the stochastic nature of many algorithms - often makes performance estimation unreliable due to the limited test samples available, leading to a validation crisis in which genuine advances are difficult to discern. In this work, we show that cross-validation improves markedly confidence when evaluating and comparing learning algorithm performances. We introduce the concept of sample gain, which quantif"},"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":"2606.12552","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-10T18:03:19Z","cross_cats_sorted":[],"title_canon_sha256":"55bb0b2220e4706bf927ba9288d6fe9843217b4d04fdf223ae52fb238c13ef66","abstract_canon_sha256":"b891ca503526fd49ecbca3882f38b56826d868c585390c40ded014ea24ade2e1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-12T00:07:54.376235Z","signature_b64":"whGCTMx6ofIk/XeS1M6d82Tc0szb1gbR8z87ugsEqJoCD94cdEH/OWYO77//B2Gm0Kf69WtTL36JUxp22/I3AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3bf25adf3dbb1a8803702317db96a267932d9531b34d13b5dd06033aa779b119","last_reissued_at":"2026-06-12T00:07:54.375849Z","signature_status":"signed_v1","first_computed_at":"2026-06-12T00:07:54.375849Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Crossing the Validation Crisis: Cross-Validation Reduces Benchmarking Variance Surprisingly Well","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"C\\'elestin Eve, Ga\\\"el Varoquaux, Thomas Moreau","submitted_at":"2026-06-10T18:03:19Z","abstract_excerpt":"Modern machine learning progresses through empirical work, benchmarking new methods to evaluate relative performance. However, the statistical variability inherent to evaluation - exacerbated by the stochastic nature of many algorithms - often makes performance estimation unreliable due to the limited test samples available, leading to a validation crisis in which genuine advances are difficult to discern. In this work, we show that cross-validation improves markedly confidence when evaluating and comparing learning algorithm performances. We introduce the concept of sample gain, which quantif"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.12552","kind":"arxiv","version":1},"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/2606.12552/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":"2606.12552","created_at":"2026-06-12T00:07:54.375906+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.12552v1","created_at":"2026-06-12T00:07:54.375906+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.12552","created_at":"2026-06-12T00:07:54.375906+00:00"},{"alias_kind":"pith_short_12","alias_value":"HPZFVXZ5XMNI","created_at":"2026-06-12T00:07:54.375906+00:00"},{"alias_kind":"pith_short_16","alias_value":"HPZFVXZ5XMNIQA3Q","created_at":"2026-06-12T00:07:54.375906+00:00"},{"alias_kind":"pith_short_8","alias_value":"HPZFVXZ5","created_at":"2026-06-12T00:07:54.375906+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/HPZFVXZ5XMNIQA3QEML5XFVCM6","json":"https://pith.science/pith/HPZFVXZ5XMNIQA3QEML5XFVCM6.json","graph_json":"https://pith.science/api/pith-number/HPZFVXZ5XMNIQA3QEML5XFVCM6/graph.json","events_json":"https://pith.science/api/pith-number/HPZFVXZ5XMNIQA3QEML5XFVCM6/events.json","paper":"https://pith.science/paper/HPZFVXZ5"},"agent_actions":{"view_html":"https://pith.science/pith/HPZFVXZ5XMNIQA3QEML5XFVCM6","download_json":"https://pith.science/pith/HPZFVXZ5XMNIQA3QEML5XFVCM6.json","view_paper":"https://pith.science/paper/HPZFVXZ5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.12552&json=true","fetch_graph":"https://pith.science/api/pith-number/HPZFVXZ5XMNIQA3QEML5XFVCM6/graph.json","fetch_events":"https://pith.science/api/pith-number/HPZFVXZ5XMNIQA3QEML5XFVCM6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HPZFVXZ5XMNIQA3QEML5XFVCM6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HPZFVXZ5XMNIQA3QEML5XFVCM6/action/storage_attestation","attest_author":"https://pith.science/pith/HPZFVXZ5XMNIQA3QEML5XFVCM6/action/author_attestation","sign_citation":"https://pith.science/pith/HPZFVXZ5XMNIQA3QEML5XFVCM6/action/citation_signature","submit_replication":"https://pith.science/pith/HPZFVXZ5XMNIQA3QEML5XFVCM6/action/replication_record"}},"created_at":"2026-06-12T00:07:54.375906+00:00","updated_at":"2026-06-12T00:07:54.375906+00:00"}