{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:ZFJZ3I43XNMN27QJK2Z2TE6QSN","short_pith_number":"pith:ZFJZ3I43","canonical_record":{"source":{"id":"2208.04935","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-08-09T17:59:06Z","cross_cats_sorted":["stat.ME","stat.ML"],"title_canon_sha256":"867f21181e0b0278849f4fb25614e67822490ba1887b868a7d19eddc35136d55","abstract_canon_sha256":"675eaa4a94f1d6ab9cf0b12a6cfee2ad6596910437c957525a7c861a2b45e340"},"schema_version":"1.0"},"canonical_sha256":"c9539da39bbb58dd7e0956b3a993d093413f61c98a1b26f15e565798403571a5","source":{"kind":"arxiv","id":"2208.04935","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2208.04935","created_at":"2026-07-05T06:31:04Z"},{"alias_kind":"arxiv_version","alias_value":"2208.04935v2","created_at":"2026-07-05T06:31:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.04935","created_at":"2026-07-05T06:31:04Z"},{"alias_kind":"pith_short_12","alias_value":"ZFJZ3I43XNMN","created_at":"2026-07-05T06:31:04Z"},{"alias_kind":"pith_short_16","alias_value":"ZFJZ3I43XNMN27QJ","created_at":"2026-07-05T06:31:04Z"},{"alias_kind":"pith_short_8","alias_value":"ZFJZ3I43","created_at":"2026-07-05T06:31:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:ZFJZ3I43XNMN27QJK2Z2TE6QSN","target":"record","payload":{"canonical_record":{"source":{"id":"2208.04935","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-08-09T17:59:06Z","cross_cats_sorted":["stat.ME","stat.ML"],"title_canon_sha256":"867f21181e0b0278849f4fb25614e67822490ba1887b868a7d19eddc35136d55","abstract_canon_sha256":"675eaa4a94f1d6ab9cf0b12a6cfee2ad6596910437c957525a7c861a2b45e340"},"schema_version":"1.0"},"canonical_sha256":"c9539da39bbb58dd7e0956b3a993d093413f61c98a1b26f15e565798403571a5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:31:04.942389Z","signature_b64":"1cVlDSYmO+YAKx3y+fTU4JejQQwSeSwn0bmMeKtwjrwwT1wEFRBHOzx1bXLbmQ+DYY8wNXTyRJdvtREgr+LJAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c9539da39bbb58dd7e0956b3a993d093413f61c98a1b26f15e565798403571a5","last_reissued_at":"2026-07-05T06:31:04.941860Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:31:04.941860Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2208.04935","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:31:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EFXcWOXlWvXemTNsdSmQ4xCXbdBdwNC4a5anBMbm1URFeskRp7nbCCTdIw8yk8npNHtRK5yLd1HwPHIq0JBmCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T01:20:18.163684Z"},"content_sha256":"c6122b220d1e2ac8fc40b5b1831e90d6ac1f27161ad222541bc1a22aea00a497","schema_version":"1.0","event_id":"sha256:c6122b220d1e2ac8fc40b5b1831e90d6ac1f27161ad222541bc1a22aea00a497"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:ZFJZ3I43XNMN27QJK2Z2TE6QSN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Bayesian Bradley-Terry model to compare multiple ML algorithms on multiple data sets","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ME","stat.ML"],"primary_cat":"cs.LG","authors_text":"Jacques Wainer","submitted_at":"2022-08-09T17:59:06Z","abstract_excerpt":"This paper proposes a Bayesian model to compare multiple algorithms on multiple data sets, on any metric. The model is based on the Bradley-Terry model, that counts the number of times one algorithm performs better than another on different data sets. Because of its Bayesian foundations, the Bayesian Bradley Terry model (BBT) has different characteristics than frequentist approaches to comparing multiple algorithms on multiple data sets, such as Demsar (2006) tests on mean rank, and Benavoli et al. (2016) multiple pairwise Wilcoxon tests with p-adjustment procedures. In particular, a Bayesian "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.04935","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/2208.04935/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:31:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lAm6x3BQOLtsoxosU/I39Aj50Uk5MkXXOl0DZ6PjnM9h95TS69HexbWtXAKu04z0xeHiVq0QrUXRbq/weocsCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T01:20:18.164246Z"},"content_sha256":"2bb2fc24369ede9caa8bb00df353cbaeba375bfbdb79291b23618d46c91ef76f","schema_version":"1.0","event_id":"sha256:2bb2fc24369ede9caa8bb00df353cbaeba375bfbdb79291b23618d46c91ef76f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZFJZ3I43XNMN27QJK2Z2TE6QSN/bundle.json","state_url":"https://pith.science/pith/ZFJZ3I43XNMN27QJK2Z2TE6QSN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZFJZ3I43XNMN27QJK2Z2TE6QSN/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-10T01:20:18Z","links":{"resolver":"https://pith.science/pith/ZFJZ3I43XNMN27QJK2Z2TE6QSN","bundle":"https://pith.science/pith/ZFJZ3I43XNMN27QJK2Z2TE6QSN/bundle.json","state":"https://pith.science/pith/ZFJZ3I43XNMN27QJK2Z2TE6QSN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZFJZ3I43XNMN27QJK2Z2TE6QSN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:ZFJZ3I43XNMN27QJK2Z2TE6QSN","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"675eaa4a94f1d6ab9cf0b12a6cfee2ad6596910437c957525a7c861a2b45e340","cross_cats_sorted":["stat.ME","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-08-09T17:59:06Z","title_canon_sha256":"867f21181e0b0278849f4fb25614e67822490ba1887b868a7d19eddc35136d55"},"schema_version":"1.0","source":{"id":"2208.04935","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2208.04935","created_at":"2026-07-05T06:31:04Z"},{"alias_kind":"arxiv_version","alias_value":"2208.04935v2","created_at":"2026-07-05T06:31:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.04935","created_at":"2026-07-05T06:31:04Z"},{"alias_kind":"pith_short_12","alias_value":"ZFJZ3I43XNMN","created_at":"2026-07-05T06:31:04Z"},{"alias_kind":"pith_short_16","alias_value":"ZFJZ3I43XNMN27QJ","created_at":"2026-07-05T06:31:04Z"},{"alias_kind":"pith_short_8","alias_value":"ZFJZ3I43","created_at":"2026-07-05T06:31:04Z"}],"graph_snapshots":[{"event_id":"sha256:2bb2fc24369ede9caa8bb00df353cbaeba375bfbdb79291b23618d46c91ef76f","target":"graph","created_at":"2026-07-05T06:31:04Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2208.04935/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper proposes a Bayesian model to compare multiple algorithms on multiple data sets, on any metric. The model is based on the Bradley-Terry model, that counts the number of times one algorithm performs better than another on different data sets. Because of its Bayesian foundations, the Bayesian Bradley Terry model (BBT) has different characteristics than frequentist approaches to comparing multiple algorithms on multiple data sets, such as Demsar (2006) tests on mean rank, and Benavoli et al. (2016) multiple pairwise Wilcoxon tests with p-adjustment procedures. In particular, a Bayesian ","authors_text":"Jacques Wainer","cross_cats":["stat.ME","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-08-09T17:59:06Z","title":"A Bayesian Bradley-Terry model to compare multiple ML algorithms on multiple data sets"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.04935","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:c6122b220d1e2ac8fc40b5b1831e90d6ac1f27161ad222541bc1a22aea00a497","target":"record","created_at":"2026-07-05T06:31:04Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"675eaa4a94f1d6ab9cf0b12a6cfee2ad6596910437c957525a7c861a2b45e340","cross_cats_sorted":["stat.ME","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-08-09T17:59:06Z","title_canon_sha256":"867f21181e0b0278849f4fb25614e67822490ba1887b868a7d19eddc35136d55"},"schema_version":"1.0","source":{"id":"2208.04935","kind":"arxiv","version":2}},"canonical_sha256":"c9539da39bbb58dd7e0956b3a993d093413f61c98a1b26f15e565798403571a5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c9539da39bbb58dd7e0956b3a993d093413f61c98a1b26f15e565798403571a5","first_computed_at":"2026-07-05T06:31:04.941860Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:31:04.941860Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1cVlDSYmO+YAKx3y+fTU4JejQQwSeSwn0bmMeKtwjrwwT1wEFRBHOzx1bXLbmQ+DYY8wNXTyRJdvtREgr+LJAA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:31:04.942389Z","signed_message":"canonical_sha256_bytes"},"source_id":"2208.04935","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c6122b220d1e2ac8fc40b5b1831e90d6ac1f27161ad222541bc1a22aea00a497","sha256:2bb2fc24369ede9caa8bb00df353cbaeba375bfbdb79291b23618d46c91ef76f"],"state_sha256":"6aaa43f393fd8c098b27604c496954c3d66ac70673766abbeda6faa736de81ae"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1pnYg/HDFg6dnGuOHYrSsheQtJSjmYXjpvavdnrB+1ol9cIeIr3K2zYbDtOzxZQK8vA1+mubl/QC+z9zbE35AA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T01:20:18.169649Z","bundle_sha256":"fe0b544916c2ad0f38b80bb300456b8ea8fbf647c0d5c1eab67666da6f0914e6"}}