{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:ODTGLRQMF4ICUGGH3IKQUQXJNR","short_pith_number":"pith:ODTGLRQM","schema_version":"1.0","canonical_sha256":"70e665c60c2f102a18c7da150a42e96c5c74c85f624bed361a9fdce6918f59fc","source":{"kind":"arxiv","id":"2202.05560","version":3},"attestation_state":"computed","paper":{"title":"Controlling Multiple Errors Simultaneously with a PAC-Bayes Bound","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG","math.ST","stat.TH"],"primary_cat":"stat.ML","authors_text":"Benjamin Guedj, John Shawe-Taylor, Reuben Adams","submitted_at":"2022-02-11T11:35:21Z","abstract_excerpt":"Current PAC-Bayes generalisation bounds are restricted to scalar metrics of performance, such as the loss or error rate. However, one ideally wants more information-rich certificates that control the entire distribution of possible outcomes, such as the distribution of the test loss in regression, or the probabilities of different mis-classifications. We provide the first PAC-Bayes bound capable of providing such rich information by bounding the Kullback-Leibler divergence between the empirical and true probabilities of a set of $M$ error types, which can either be discretized loss values for "},"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":"2202.05560","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"stat.ML","submitted_at":"2022-02-11T11:35:21Z","cross_cats_sorted":["cs.LG","math.ST","stat.TH"],"title_canon_sha256":"388259f49e54c6678aaad33e859237dbe15881c2147fd1ad41754f3d90bb160f","abstract_canon_sha256":"6b871b1c910aa9c7c51940527bb539962d23bda2ccb1e922a2ff2f173e56cfe7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:45:36.761786Z","signature_b64":"kdAxRbKn9Yk+TQddNtWTnsOXsOkgl5PpY67gFzZxSoMxG/2AaErsRpv95wmGlOmL1N8ejqQxM9eJNn4+qGCnCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"70e665c60c2f102a18c7da150a42e96c5c74c85f624bed361a9fdce6918f59fc","last_reissued_at":"2026-07-05T09:45:36.761292Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:45:36.761292Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Controlling Multiple Errors Simultaneously with a PAC-Bayes Bound","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG","math.ST","stat.TH"],"primary_cat":"stat.ML","authors_text":"Benjamin Guedj, John Shawe-Taylor, Reuben Adams","submitted_at":"2022-02-11T11:35:21Z","abstract_excerpt":"Current PAC-Bayes generalisation bounds are restricted to scalar metrics of performance, such as the loss or error rate. However, one ideally wants more information-rich certificates that control the entire distribution of possible outcomes, such as the distribution of the test loss in regression, or the probabilities of different mis-classifications. We provide the first PAC-Bayes bound capable of providing such rich information by bounding the Kullback-Leibler divergence between the empirical and true probabilities of a set of $M$ error types, which can either be discretized loss values for "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.05560","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2202.05560/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":"2202.05560","created_at":"2026-07-05T09:45:36.761362+00:00"},{"alias_kind":"arxiv_version","alias_value":"2202.05560v3","created_at":"2026-07-05T09:45:36.761362+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.05560","created_at":"2026-07-05T09:45:36.761362+00:00"},{"alias_kind":"pith_short_12","alias_value":"ODTGLRQMF4IC","created_at":"2026-07-05T09:45:36.761362+00:00"},{"alias_kind":"pith_short_16","alias_value":"ODTGLRQMF4ICUGGH","created_at":"2026-07-05T09:45:36.761362+00:00"},{"alias_kind":"pith_short_8","alias_value":"ODTGLRQM","created_at":"2026-07-05T09:45:36.761362+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.15626","citing_title":"Aligning Generalisation Between Humans and Machines","ref_index":2,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ODTGLRQMF4ICUGGH3IKQUQXJNR","json":"https://pith.science/pith/ODTGLRQMF4ICUGGH3IKQUQXJNR.json","graph_json":"https://pith.science/api/pith-number/ODTGLRQMF4ICUGGH3IKQUQXJNR/graph.json","events_json":"https://pith.science/api/pith-number/ODTGLRQMF4ICUGGH3IKQUQXJNR/events.json","paper":"https://pith.science/paper/ODTGLRQM"},"agent_actions":{"view_html":"https://pith.science/pith/ODTGLRQMF4ICUGGH3IKQUQXJNR","download_json":"https://pith.science/pith/ODTGLRQMF4ICUGGH3IKQUQXJNR.json","view_paper":"https://pith.science/paper/ODTGLRQM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2202.05560&json=true","fetch_graph":"https://pith.science/api/pith-number/ODTGLRQMF4ICUGGH3IKQUQXJNR/graph.json","fetch_events":"https://pith.science/api/pith-number/ODTGLRQMF4ICUGGH3IKQUQXJNR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ODTGLRQMF4ICUGGH3IKQUQXJNR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ODTGLRQMF4ICUGGH3IKQUQXJNR/action/storage_attestation","attest_author":"https://pith.science/pith/ODTGLRQMF4ICUGGH3IKQUQXJNR/action/author_attestation","sign_citation":"https://pith.science/pith/ODTGLRQMF4ICUGGH3IKQUQXJNR/action/citation_signature","submit_replication":"https://pith.science/pith/ODTGLRQMF4ICUGGH3IKQUQXJNR/action/replication_record"}},"created_at":"2026-07-05T09:45:36.761362+00:00","updated_at":"2026-07-05T09:45:36.761362+00:00"}