{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2008:6KRNFT46CIIGJTDKSSBQZWQ4OU","short_pith_number":"pith:6KRNFT46","schema_version":"1.0","canonical_sha256":"f2a2d2cf9e121064cc6a94830cda1c751d32725324031d455db6a0d4907759de","source":{"kind":"arxiv","id":"0804.2937","version":3},"attestation_state":"computed","paper":{"title":"Margin-adaptive model selection in statistical learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML","stat.TH"],"primary_cat":"math.ST","authors_text":"Peter L. Bartlett, Sylvain Arlot","submitted_at":"2008-04-18T04:24:42Z","abstract_excerpt":"A classical condition for fast learning rates is the margin condition, first introduced by Mammen and Tsybakov. We tackle in this paper the problem of adaptivity to this condition in the context of model selection, in a general learning framework. Actually, we consider a weaker version of this condition that allows one to take into account that learning within a small model can be much easier than within a large one. Requiring this \"strong margin adaptivity\" makes the model selection problem more challenging. We first prove, in a general framework, that some penalization procedures (including "},"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":"0804.2937","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.ST","submitted_at":"2008-04-18T04:24:42Z","cross_cats_sorted":["stat.ML","stat.TH"],"title_canon_sha256":"9f749b95555d6e0fb687c8c1ba85cb0f56014b86deee37dd0d1f464f82382738","abstract_canon_sha256":"f8cb06dda161db74eed79d814724966b4abd0fe7a74ed04541c3fe1ca8101ac5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T04:23:21.344069Z","signature_b64":"/3tCgFYZu0RV8wnYtzPaOTwXPfh9N41NENy2Jd7vMRKcDEwW52UsoZlww3v5AWjsKvlxXStfDqY6IBlh41ZPDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f2a2d2cf9e121064cc6a94830cda1c751d32725324031d455db6a0d4907759de","last_reissued_at":"2026-05-18T04:23:21.343500Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T04:23:21.343500Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Margin-adaptive model selection in statistical learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML","stat.TH"],"primary_cat":"math.ST","authors_text":"Peter L. Bartlett, Sylvain Arlot","submitted_at":"2008-04-18T04:24:42Z","abstract_excerpt":"A classical condition for fast learning rates is the margin condition, first introduced by Mammen and Tsybakov. We tackle in this paper the problem of adaptivity to this condition in the context of model selection, in a general learning framework. Actually, we consider a weaker version of this condition that allows one to take into account that learning within a small model can be much easier than within a large one. Requiring this \"strong margin adaptivity\" makes the model selection problem more challenging. We first prove, in a general framework, that some penalization procedures (including "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"0804.2937","kind":"arxiv","version":3},"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":"0804.2937","created_at":"2026-05-18T04:23:21.343575+00:00"},{"alias_kind":"arxiv_version","alias_value":"0804.2937v3","created_at":"2026-05-18T04:23:21.343575+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.0804.2937","created_at":"2026-05-18T04:23:21.343575+00:00"},{"alias_kind":"pith_short_12","alias_value":"6KRNFT46CIIG","created_at":"2026-05-18T12:25:56.245647+00:00"},{"alias_kind":"pith_short_16","alias_value":"6KRNFT46CIIGJTDK","created_at":"2026-05-18T12:25:56.245647+00:00"},{"alias_kind":"pith_short_8","alias_value":"6KRNFT46","created_at":"2026-05-18T12:25:56.245647+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/6KRNFT46CIIGJTDKSSBQZWQ4OU","json":"https://pith.science/pith/6KRNFT46CIIGJTDKSSBQZWQ4OU.json","graph_json":"https://pith.science/api/pith-number/6KRNFT46CIIGJTDKSSBQZWQ4OU/graph.json","events_json":"https://pith.science/api/pith-number/6KRNFT46CIIGJTDKSSBQZWQ4OU/events.json","paper":"https://pith.science/paper/6KRNFT46"},"agent_actions":{"view_html":"https://pith.science/pith/6KRNFT46CIIGJTDKSSBQZWQ4OU","download_json":"https://pith.science/pith/6KRNFT46CIIGJTDKSSBQZWQ4OU.json","view_paper":"https://pith.science/paper/6KRNFT46","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=0804.2937&json=true","fetch_graph":"https://pith.science/api/pith-number/6KRNFT46CIIGJTDKSSBQZWQ4OU/graph.json","fetch_events":"https://pith.science/api/pith-number/6KRNFT46CIIGJTDKSSBQZWQ4OU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6KRNFT46CIIGJTDKSSBQZWQ4OU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6KRNFT46CIIGJTDKSSBQZWQ4OU/action/storage_attestation","attest_author":"https://pith.science/pith/6KRNFT46CIIGJTDKSSBQZWQ4OU/action/author_attestation","sign_citation":"https://pith.science/pith/6KRNFT46CIIGJTDKSSBQZWQ4OU/action/citation_signature","submit_replication":"https://pith.science/pith/6KRNFT46CIIGJTDKSSBQZWQ4OU/action/replication_record"}},"created_at":"2026-05-18T04:23:21.343575+00:00","updated_at":"2026-05-18T04:23:21.343575+00:00"}