{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:LFV2MWI235LTZQQPKSOM4XNY5N","short_pith_number":"pith:LFV2MWI2","schema_version":"1.0","canonical_sha256":"596ba6591adf573cc20f549cce5db8eb5ba46a5123e9a17ed1a8d03eea3b356a","source":{"kind":"arxiv","id":"1608.06412","version":1},"attestation_state":"computed","paper":{"title":"Stability revisited: new generalisation bounds for the Leave-one-Out","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["math.ST","stat.TH"],"primary_cat":"stat.ML","authors_text":"Alain Celisse, Benjamin Guedj","submitted_at":"2016-08-23T08:11:29Z","abstract_excerpt":"The present paper provides a new generic strategy leading to non-asymptotic theoretical guarantees on the Leave-one-Out procedure applied to a broad class of learning algorithms. This strategy relies on two main ingredients: the new notion of $L^q$ stability, and the strong use of moment inequalities. $L^q$ stability extends the ongoing notion of hypothesis stability while remaining weaker than the uniform stability. It leads to new PAC exponential generalisation bounds for Leave-one-Out under mild assumptions. In the literature, such bounds are available only for uniform stable algorithms und"},"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":"1608.06412","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"stat.ML","submitted_at":"2016-08-23T08:11:29Z","cross_cats_sorted":["math.ST","stat.TH"],"title_canon_sha256":"c19f9d21f899a3f53cf7c3277b8e2356e40d942b49dabdc0ccde98a508635b26","abstract_canon_sha256":"aeadecaa31698dd1d3444048a6bb0868f413318213d8a5058d623950811f1a87"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:08:14.096061Z","signature_b64":"8WAds4Kgfy9lGqRvxrqfWEjU46G1SteHyVGriEzXQmwBFezBMQy3TAW6GpLI16w+8RcLnAtSQfacOtzETTfWDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"596ba6591adf573cc20f549cce5db8eb5ba46a5123e9a17ed1a8d03eea3b356a","last_reissued_at":"2026-05-18T01:08:14.095480Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:08:14.095480Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Stability revisited: new generalisation bounds for the Leave-one-Out","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["math.ST","stat.TH"],"primary_cat":"stat.ML","authors_text":"Alain Celisse, Benjamin Guedj","submitted_at":"2016-08-23T08:11:29Z","abstract_excerpt":"The present paper provides a new generic strategy leading to non-asymptotic theoretical guarantees on the Leave-one-Out procedure applied to a broad class of learning algorithms. This strategy relies on two main ingredients: the new notion of $L^q$ stability, and the strong use of moment inequalities. $L^q$ stability extends the ongoing notion of hypothesis stability while remaining weaker than the uniform stability. It leads to new PAC exponential generalisation bounds for Leave-one-Out under mild assumptions. In the literature, such bounds are available only for uniform stable algorithms und"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1608.06412","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":""},"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":"1608.06412","created_at":"2026-05-18T01:08:14.095580+00:00"},{"alias_kind":"arxiv_version","alias_value":"1608.06412v1","created_at":"2026-05-18T01:08:14.095580+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1608.06412","created_at":"2026-05-18T01:08:14.095580+00:00"},{"alias_kind":"pith_short_12","alias_value":"LFV2MWI235LT","created_at":"2026-05-18T12:30:29.479603+00:00"},{"alias_kind":"pith_short_16","alias_value":"LFV2MWI235LTZQQP","created_at":"2026-05-18T12:30:29.479603+00:00"},{"alias_kind":"pith_short_8","alias_value":"LFV2MWI2","created_at":"2026-05-18T12:30:29.479603+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.20194","citing_title":"Identification and Semiparametric Estimation of Conditional Means from Aggregate Data","ref_index":5,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LFV2MWI235LTZQQPKSOM4XNY5N","json":"https://pith.science/pith/LFV2MWI235LTZQQPKSOM4XNY5N.json","graph_json":"https://pith.science/api/pith-number/LFV2MWI235LTZQQPKSOM4XNY5N/graph.json","events_json":"https://pith.science/api/pith-number/LFV2MWI235LTZQQPKSOM4XNY5N/events.json","paper":"https://pith.science/paper/LFV2MWI2"},"agent_actions":{"view_html":"https://pith.science/pith/LFV2MWI235LTZQQPKSOM4XNY5N","download_json":"https://pith.science/pith/LFV2MWI235LTZQQPKSOM4XNY5N.json","view_paper":"https://pith.science/paper/LFV2MWI2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1608.06412&json=true","fetch_graph":"https://pith.science/api/pith-number/LFV2MWI235LTZQQPKSOM4XNY5N/graph.json","fetch_events":"https://pith.science/api/pith-number/LFV2MWI235LTZQQPKSOM4XNY5N/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LFV2MWI235LTZQQPKSOM4XNY5N/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LFV2MWI235LTZQQPKSOM4XNY5N/action/storage_attestation","attest_author":"https://pith.science/pith/LFV2MWI235LTZQQPKSOM4XNY5N/action/author_attestation","sign_citation":"https://pith.science/pith/LFV2MWI235LTZQQPKSOM4XNY5N/action/citation_signature","submit_replication":"https://pith.science/pith/LFV2MWI235LTZQQPKSOM4XNY5N/action/replication_record"}},"created_at":"2026-05-18T01:08:14.095580+00:00","updated_at":"2026-05-18T01:08:14.095580+00:00"}