{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:WV2PWLPD7DIVMTKGSV64A2TUBT","short_pith_number":"pith:WV2PWLPD","schema_version":"1.0","canonical_sha256":"b574fb2de3f8d1564d46957dc06a740cdb7a97e186c756cbdb1988c02f5126ae","source":{"kind":"arxiv","id":"2207.11987","version":2},"attestation_state":"computed","paper":{"title":"Information Processing Equalities and the Information-Risk Bridge","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.IT","math.IT","stat.ML"],"primary_cat":"cs.LG","authors_text":"Robert C. Williamson, Zac Cranko","submitted_at":"2022-07-25T08:54:36Z","abstract_excerpt":"We introduce two new classes of measures of information for statistical experiments which generalise and subsume $\\phi$-divergences, integral probability metrics, $\\mathfrak{N}$-distances (MMD), and $(f,\\Gamma)$ divergences between two or more distributions. This enables us to derive a simple geometrical relationship between measures of information and the Bayes risk of a statistical decision problem, thus extending the variational $\\phi$-divergence representation to multiple distributions in an entirely symmetric manner. The new families of divergence are closed under the action of Markov ope"},"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":"2207.11987","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2022-07-25T08:54:36Z","cross_cats_sorted":["cs.IT","math.IT","stat.ML"],"title_canon_sha256":"758ec1fac3e3aab16b0c792789ad5eaab9425fb18469d873e1a593535d014c07","abstract_canon_sha256":"736bf9ac2dcdf27a506ec2855ee6ab397a56c368f67e7f2b0048530097eb04a4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:48:45.448441Z","signature_b64":"6NIjdXL+Nvy0rcJ46RP5C7QtqW4tMPTayoyRP14ScUoC+wpKvhJh97AOha+i+uP2V1MI8+VCAG2o1LRhf9BODQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b574fb2de3f8d1564d46957dc06a740cdb7a97e186c756cbdb1988c02f5126ae","last_reissued_at":"2026-07-05T06:48:45.447956Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:48:45.447956Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Information Processing Equalities and the Information-Risk Bridge","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.IT","math.IT","stat.ML"],"primary_cat":"cs.LG","authors_text":"Robert C. Williamson, Zac Cranko","submitted_at":"2022-07-25T08:54:36Z","abstract_excerpt":"We introduce two new classes of measures of information for statistical experiments which generalise and subsume $\\phi$-divergences, integral probability metrics, $\\mathfrak{N}$-distances (MMD), and $(f,\\Gamma)$ divergences between two or more distributions. This enables us to derive a simple geometrical relationship between measures of information and the Bayes risk of a statistical decision problem, thus extending the variational $\\phi$-divergence representation to multiple distributions in an entirely symmetric manner. The new families of divergence are closed under the action of Markov ope"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.11987","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2207.11987/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":"2207.11987","created_at":"2026-07-05T06:48:45.448023+00:00"},{"alias_kind":"arxiv_version","alias_value":"2207.11987v2","created_at":"2026-07-05T06:48:45.448023+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.11987","created_at":"2026-07-05T06:48:45.448023+00:00"},{"alias_kind":"pith_short_12","alias_value":"WV2PWLPD7DIV","created_at":"2026-07-05T06:48:45.448023+00:00"},{"alias_kind":"pith_short_16","alias_value":"WV2PWLPD7DIVMTKG","created_at":"2026-07-05T06:48:45.448023+00:00"},{"alias_kind":"pith_short_8","alias_value":"WV2PWLPD","created_at":"2026-07-05T06:48:45.448023+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.08377","citing_title":"Eigenvalue Calibration for Semantic Embeddings of Large Language Models","ref_index":3,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WV2PWLPD7DIVMTKGSV64A2TUBT","json":"https://pith.science/pith/WV2PWLPD7DIVMTKGSV64A2TUBT.json","graph_json":"https://pith.science/api/pith-number/WV2PWLPD7DIVMTKGSV64A2TUBT/graph.json","events_json":"https://pith.science/api/pith-number/WV2PWLPD7DIVMTKGSV64A2TUBT/events.json","paper":"https://pith.science/paper/WV2PWLPD"},"agent_actions":{"view_html":"https://pith.science/pith/WV2PWLPD7DIVMTKGSV64A2TUBT","download_json":"https://pith.science/pith/WV2PWLPD7DIVMTKGSV64A2TUBT.json","view_paper":"https://pith.science/paper/WV2PWLPD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2207.11987&json=true","fetch_graph":"https://pith.science/api/pith-number/WV2PWLPD7DIVMTKGSV64A2TUBT/graph.json","fetch_events":"https://pith.science/api/pith-number/WV2PWLPD7DIVMTKGSV64A2TUBT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WV2PWLPD7DIVMTKGSV64A2TUBT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WV2PWLPD7DIVMTKGSV64A2TUBT/action/storage_attestation","attest_author":"https://pith.science/pith/WV2PWLPD7DIVMTKGSV64A2TUBT/action/author_attestation","sign_citation":"https://pith.science/pith/WV2PWLPD7DIVMTKGSV64A2TUBT/action/citation_signature","submit_replication":"https://pith.science/pith/WV2PWLPD7DIVMTKGSV64A2TUBT/action/replication_record"}},"created_at":"2026-07-05T06:48:45.448023+00:00","updated_at":"2026-07-05T06:48:45.448023+00:00"}