{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:JOXG7JTU6FDUNSFE4B3WKBHMMO","short_pith_number":"pith:JOXG7JTU","schema_version":"1.0","canonical_sha256":"4bae6fa674f14746c8a4e0776504ec63b164caa373af7fece240953fb1103a0f","source":{"kind":"arxiv","id":"1503.08329","version":2},"attestation_state":"computed","paper":{"title":"Risk Bounds for the Majority Vote: From a PAC-Bayesian Analysis to a Learning Algorithm","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Alexandre Lacasse, Fran\\c{c}ois Laviolette, Jean-Francis Roy, Mario Marchand, Pascal Germain","submitted_at":"2015-03-28T17:19:49Z","abstract_excerpt":"We propose an extensive analysis of the behavior of majority votes in binary classification. In particular, we introduce a risk bound for majority votes, called the C-bound, that takes into account the average quality of the voters and their average disagreement. We also propose an extensive PAC-Bayesian analysis that shows how the C-bound can be estimated from various observations contained in the training data. The analysis intends to be self-contained and can be used as introductory material to PAC-Bayesian statistical learning theory. It starts from a general PAC-Bayesian perspective and e"},"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":"1503.08329","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2015-03-28T17:19:49Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"ac34415a3158b5cafea0ac289528476772fcf3c3ebe42251118bfa83af0daf63","abstract_canon_sha256":"a989d0d1b76f64f25d83f8645eda35ff554234f2f82cc15d3d13bb9cd0fbfabc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:36:10.830937Z","signature_b64":"C5biKw1iO7ur1oMsRYFb3WgDHeAn6cXmTLJOz+m16wxRFChuffjqbMHMrPluyXpvz9Wv165AhWFA8uW/hmo7Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4bae6fa674f14746c8a4e0776504ec63b164caa373af7fece240953fb1103a0f","last_reissued_at":"2026-05-18T01:36:10.830541Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:36:10.830541Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Risk Bounds for the Majority Vote: From a PAC-Bayesian Analysis to a Learning Algorithm","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Alexandre Lacasse, Fran\\c{c}ois Laviolette, Jean-Francis Roy, Mario Marchand, Pascal Germain","submitted_at":"2015-03-28T17:19:49Z","abstract_excerpt":"We propose an extensive analysis of the behavior of majority votes in binary classification. In particular, we introduce a risk bound for majority votes, called the C-bound, that takes into account the average quality of the voters and their average disagreement. We also propose an extensive PAC-Bayesian analysis that shows how the C-bound can be estimated from various observations contained in the training data. The analysis intends to be self-contained and can be used as introductory material to PAC-Bayesian statistical learning theory. It starts from a general PAC-Bayesian perspective and e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1503.08329","kind":"arxiv","version":2},"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":"1503.08329","created_at":"2026-05-18T01:36:10.830595+00:00"},{"alias_kind":"arxiv_version","alias_value":"1503.08329v2","created_at":"2026-05-18T01:36:10.830595+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1503.08329","created_at":"2026-05-18T01:36:10.830595+00:00"},{"alias_kind":"pith_short_12","alias_value":"JOXG7JTU6FDU","created_at":"2026-05-18T12:29:27.538025+00:00"},{"alias_kind":"pith_short_16","alias_value":"JOXG7JTU6FDUNSFE","created_at":"2026-05-18T12:29:27.538025+00:00"},{"alias_kind":"pith_short_8","alias_value":"JOXG7JTU","created_at":"2026-05-18T12:29:27.538025+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.15416","citing_title":"Margin-Adaptive Confidence Ranking for Reliable LLM Judgement","ref_index":265,"is_internal_anchor":true},{"citing_arxiv_id":"2605.00455","citing_title":"Concentration and Calibration in Predictive Bayesian Inference","ref_index":205,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JOXG7JTU6FDUNSFE4B3WKBHMMO","json":"https://pith.science/pith/JOXG7JTU6FDUNSFE4B3WKBHMMO.json","graph_json":"https://pith.science/api/pith-number/JOXG7JTU6FDUNSFE4B3WKBHMMO/graph.json","events_json":"https://pith.science/api/pith-number/JOXG7JTU6FDUNSFE4B3WKBHMMO/events.json","paper":"https://pith.science/paper/JOXG7JTU"},"agent_actions":{"view_html":"https://pith.science/pith/JOXG7JTU6FDUNSFE4B3WKBHMMO","download_json":"https://pith.science/pith/JOXG7JTU6FDUNSFE4B3WKBHMMO.json","view_paper":"https://pith.science/paper/JOXG7JTU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1503.08329&json=true","fetch_graph":"https://pith.science/api/pith-number/JOXG7JTU6FDUNSFE4B3WKBHMMO/graph.json","fetch_events":"https://pith.science/api/pith-number/JOXG7JTU6FDUNSFE4B3WKBHMMO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JOXG7JTU6FDUNSFE4B3WKBHMMO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JOXG7JTU6FDUNSFE4B3WKBHMMO/action/storage_attestation","attest_author":"https://pith.science/pith/JOXG7JTU6FDUNSFE4B3WKBHMMO/action/author_attestation","sign_citation":"https://pith.science/pith/JOXG7JTU6FDUNSFE4B3WKBHMMO/action/citation_signature","submit_replication":"https://pith.science/pith/JOXG7JTU6FDUNSFE4B3WKBHMMO/action/replication_record"}},"created_at":"2026-05-18T01:36:10.830595+00:00","updated_at":"2026-05-18T01:36:10.830595+00:00"}