{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2013:M4JUX4MBHLLHPFHYXZV5Y434UZ","short_pith_number":"pith:M4JUX4MB","schema_version":"1.0","canonical_sha256":"67134bf1813ad67794f8be6bdc737ca64fd5cf1f9c26dd2d93c23244ce7a2b8b","source":{"kind":"arxiv","id":"1307.2118","version":1},"attestation_state":"computed","paper":{"title":"A PAC-Bayesian Tutorial with A Dropout Bound","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"David McAllester","submitted_at":"2013-07-08T15:03:03Z","abstract_excerpt":"This tutorial gives a concise overview of existing PAC-Bayesian theory focusing on three generalization bounds. The first is an Occam bound which handles rules with finite precision parameters and which states that generalization loss is near training loss when the number of bits needed to write the rule is small compared to the sample size. The second is a PAC-Bayesian bound providing a generalization guarantee for posterior distributions rather than for individual rules. The PAC-Bayesian bound naturally handles infinite precision rule parameters, $L_2$ regularization, {\\em provides a bound f"},"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":"1307.2118","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2013-07-08T15:03:03Z","cross_cats_sorted":[],"title_canon_sha256":"d22b30ae37dbf9d24b09915dd819a2c0c1b2c25be09e54ecb01f240088f4e31c","abstract_canon_sha256":"a946dd0432133fd2c688e70740badca7316e85a6304d8cbe7f05283198068388"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:19:02.355802Z","signature_b64":"LdLtynzhXbfqUPa3zvFGiEiPK62xofjEnUF3xdFiR0h1NSamyRlJqoYJEmjbe3Dc1A5qwd9CmDal3Qgngg6ZDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"67134bf1813ad67794f8be6bdc737ca64fd5cf1f9c26dd2d93c23244ce7a2b8b","last_reissued_at":"2026-05-18T03:19:02.355385Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:19:02.355385Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A PAC-Bayesian Tutorial with A Dropout Bound","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"David McAllester","submitted_at":"2013-07-08T15:03:03Z","abstract_excerpt":"This tutorial gives a concise overview of existing PAC-Bayesian theory focusing on three generalization bounds. The first is an Occam bound which handles rules with finite precision parameters and which states that generalization loss is near training loss when the number of bits needed to write the rule is small compared to the sample size. The second is a PAC-Bayesian bound providing a generalization guarantee for posterior distributions rather than for individual rules. The PAC-Bayesian bound naturally handles infinite precision rule parameters, $L_2$ regularization, {\\em provides a bound f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1307.2118","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":"1307.2118","created_at":"2026-05-18T03:19:02.355451+00:00"},{"alias_kind":"arxiv_version","alias_value":"1307.2118v1","created_at":"2026-05-18T03:19:02.355451+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1307.2118","created_at":"2026-05-18T03:19:02.355451+00:00"},{"alias_kind":"pith_short_12","alias_value":"M4JUX4MBHLLH","created_at":"2026-05-18T12:27:51.066281+00:00"},{"alias_kind":"pith_short_16","alias_value":"M4JUX4MBHLLHPFHY","created_at":"2026-05-18T12:27:51.066281+00:00"},{"alias_kind":"pith_short_8","alias_value":"M4JUX4MB","created_at":"2026-05-18T12:27:51.066281+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":4,"sample":[{"citing_arxiv_id":"2401.16407","citing_title":"Is K-fold cross validation the best model selection method for Machine Learning?","ref_index":45,"is_internal_anchor":true},{"citing_arxiv_id":"2505.11025","citing_title":"Generalization Bounds for Quantum Learning via R\\'enyi Divergences","ref_index":14,"is_internal_anchor":true},{"citing_arxiv_id":"2605.21056","citing_title":"On Unified and Sharpened CMI Bounds for Generalization Errors","ref_index":20,"is_internal_anchor":true},{"citing_arxiv_id":"2605.15416","citing_title":"Margin-Adaptive Confidence Ranking for Reliable LLM Judgement","ref_index":174,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/M4JUX4MBHLLHPFHYXZV5Y434UZ","json":"https://pith.science/pith/M4JUX4MBHLLHPFHYXZV5Y434UZ.json","graph_json":"https://pith.science/api/pith-number/M4JUX4MBHLLHPFHYXZV5Y434UZ/graph.json","events_json":"https://pith.science/api/pith-number/M4JUX4MBHLLHPFHYXZV5Y434UZ/events.json","paper":"https://pith.science/paper/M4JUX4MB"},"agent_actions":{"view_html":"https://pith.science/pith/M4JUX4MBHLLHPFHYXZV5Y434UZ","download_json":"https://pith.science/pith/M4JUX4MBHLLHPFHYXZV5Y434UZ.json","view_paper":"https://pith.science/paper/M4JUX4MB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1307.2118&json=true","fetch_graph":"https://pith.science/api/pith-number/M4JUX4MBHLLHPFHYXZV5Y434UZ/graph.json","fetch_events":"https://pith.science/api/pith-number/M4JUX4MBHLLHPFHYXZV5Y434UZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/M4JUX4MBHLLHPFHYXZV5Y434UZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/M4JUX4MBHLLHPFHYXZV5Y434UZ/action/storage_attestation","attest_author":"https://pith.science/pith/M4JUX4MBHLLHPFHYXZV5Y434UZ/action/author_attestation","sign_citation":"https://pith.science/pith/M4JUX4MBHLLHPFHYXZV5Y434UZ/action/citation_signature","submit_replication":"https://pith.science/pith/M4JUX4MBHLLHPFHYXZV5Y434UZ/action/replication_record"}},"created_at":"2026-05-18T03:19:02.355451+00:00","updated_at":"2026-05-18T03:19:02.355451+00:00"}