{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:S2BDTAGNHB5KJHBFP6MBLTUANV","short_pith_number":"pith:S2BDTAGN","schema_version":"1.0","canonical_sha256":"96823980cd387aa49c257f9815ce806d48b19b2f0fefa5bfc9744df0f40d847d","source":{"kind":"arxiv","id":"1702.05985","version":3},"attestation_state":"computed","paper":{"title":"Fano's inequality for random variables","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IT","math.IT","stat.TH"],"primary_cat":"math.ST","authors_text":"Gilles Stoltz (GREGHEC, LMO), Pierre M\\'enard (IMT), Sebastien Gerchinovitz (IMT)","submitted_at":"2017-02-20T14:34:46Z","abstract_excerpt":"We extend Fano's inequality, which controls the average probability of events in terms of the average of some $f$--divergences, to work with arbitrary events (not necessarily forming a partition) and even with arbitrary $[0,1]$--valued random variables, possibly in continuously infinite number. We provide two applications of these extensions, in which the consideration of random variables is particularly handy: we offer new and elegant proofs for existing lower bounds, on Bayesian posterior concentration (minimax or distribution-dependent) rates and on the regret in non-stochastic sequential l"},"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":"1702.05985","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.ST","submitted_at":"2017-02-20T14:34:46Z","cross_cats_sorted":["cs.IT","math.IT","stat.TH"],"title_canon_sha256":"8288dc53ada7a1d2387f220b7e4ec2d3df20c68e1a7ea9e965f4462e67a93f83","abstract_canon_sha256":"06eb76d0c14bb887b83607490f7e1bb9ab927bf9d12aff4ca209b0fe6cd6f338"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:43:43.531671Z","signature_b64":"YPeOWv4C1LtEky4E4JVBYqhyr66Ld8Y0BRqtgox/nFjWrgIggFrJe1Ego2sLIm5DuspJ3v5acnT2kSKawL5zBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"96823980cd387aa49c257f9815ce806d48b19b2f0fefa5bfc9744df0f40d847d","last_reissued_at":"2026-05-17T23:43:43.531196Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:43:43.531196Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fano's inequality for random variables","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IT","math.IT","stat.TH"],"primary_cat":"math.ST","authors_text":"Gilles Stoltz (GREGHEC, LMO), Pierre M\\'enard (IMT), Sebastien Gerchinovitz (IMT)","submitted_at":"2017-02-20T14:34:46Z","abstract_excerpt":"We extend Fano's inequality, which controls the average probability of events in terms of the average of some $f$--divergences, to work with arbitrary events (not necessarily forming a partition) and even with arbitrary $[0,1]$--valued random variables, possibly in continuously infinite number. We provide two applications of these extensions, in which the consideration of random variables is particularly handy: we offer new and elegant proofs for existing lower bounds, on Bayesian posterior concentration (minimax or distribution-dependent) rates and on the regret in non-stochastic sequential l"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1702.05985","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":"1702.05985","created_at":"2026-05-17T23:43:43.531271+00:00"},{"alias_kind":"arxiv_version","alias_value":"1702.05985v3","created_at":"2026-05-17T23:43:43.531271+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1702.05985","created_at":"2026-05-17T23:43:43.531271+00:00"},{"alias_kind":"pith_short_12","alias_value":"S2BDTAGNHB5K","created_at":"2026-05-18T12:31:43.269735+00:00"},{"alias_kind":"pith_short_16","alias_value":"S2BDTAGNHB5KJHBF","created_at":"2026-05-18T12:31:43.269735+00:00"},{"alias_kind":"pith_short_8","alias_value":"S2BDTAGN","created_at":"2026-05-18T12:31:43.269735+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2603.15842","citing_title":"Informationally Compressive Anonymization: Non-Degrading Sensitive Input Protection for Privacy-Preserving Supervised Machine Learning","ref_index":47,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/S2BDTAGNHB5KJHBFP6MBLTUANV","json":"https://pith.science/pith/S2BDTAGNHB5KJHBFP6MBLTUANV.json","graph_json":"https://pith.science/api/pith-number/S2BDTAGNHB5KJHBFP6MBLTUANV/graph.json","events_json":"https://pith.science/api/pith-number/S2BDTAGNHB5KJHBFP6MBLTUANV/events.json","paper":"https://pith.science/paper/S2BDTAGN"},"agent_actions":{"view_html":"https://pith.science/pith/S2BDTAGNHB5KJHBFP6MBLTUANV","download_json":"https://pith.science/pith/S2BDTAGNHB5KJHBFP6MBLTUANV.json","view_paper":"https://pith.science/paper/S2BDTAGN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1702.05985&json=true","fetch_graph":"https://pith.science/api/pith-number/S2BDTAGNHB5KJHBFP6MBLTUANV/graph.json","fetch_events":"https://pith.science/api/pith-number/S2BDTAGNHB5KJHBFP6MBLTUANV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/S2BDTAGNHB5KJHBFP6MBLTUANV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/S2BDTAGNHB5KJHBFP6MBLTUANV/action/storage_attestation","attest_author":"https://pith.science/pith/S2BDTAGNHB5KJHBFP6MBLTUANV/action/author_attestation","sign_citation":"https://pith.science/pith/S2BDTAGNHB5KJHBFP6MBLTUANV/action/citation_signature","submit_replication":"https://pith.science/pith/S2BDTAGNHB5KJHBFP6MBLTUANV/action/replication_record"}},"created_at":"2026-05-17T23:43:43.531271+00:00","updated_at":"2026-05-17T23:43:43.531271+00:00"}