{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:ECXQBL4VUMUMYZQY7WRMTLH3IK","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":"d414b4a70d9980d75a6c80c49e37b22fd22c84ab0b4da168ea5b30276616e33e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-02T09:50:58Z","title_canon_sha256":"8dde0b459287bfa48af36fa13c7838403b1a28309dd783cde17d8ed46b23890a"},"schema_version":"1.0","source":{"id":"2607.01958","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.01958","created_at":"2026-07-03T01:17:35Z"},{"alias_kind":"arxiv_version","alias_value":"2607.01958v1","created_at":"2026-07-03T01:17:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.01958","created_at":"2026-07-03T01:17:35Z"},{"alias_kind":"pith_short_12","alias_value":"ECXQBL4VUMUM","created_at":"2026-07-03T01:17:35Z"},{"alias_kind":"pith_short_16","alias_value":"ECXQBL4VUMUMYZQY","created_at":"2026-07-03T01:17:35Z"},{"alias_kind":"pith_short_8","alias_value":"ECXQBL4V","created_at":"2026-07-03T01:17:35Z"}],"graph_snapshots":[{"event_id":"sha256:571461f22633b878c470b0ddb1b71809dd1eb84526af8c4baaa2c467e798edb7","target":"graph","created_at":"2026-07-03T01:17:35Z","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/2607.01958/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"A/B testing is the gold standard for selecting the better algorithm in online services. While offline evaluation has attracted attention as a safer alternative due to the high experimental costs and the potential risk of degrading user experience and revenue in A/B testing, it is widely recognized that the estimation accuracy of offline evaluation is substantially lower. As a result, final selection decisions are typically made through A/B testing. Contrary to this conventional view, we reveal a counterintuitive phenomenon in which A/B testing can produce a higher algorithm selection error rat","authors_text":"Koki Konishi, Masataka Ushiku, Yuta Saito","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-02T09:50:58Z","title":"A More Accurate Algorithm Comparison through A/B Testing using Offline Evaluation Methods"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.01958","kind":"arxiv","version":1},"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:b3e013966cc9c203accc884cf425fcba6769dab9c246cdee94c3029944cfc58f","target":"record","created_at":"2026-07-03T01:17:35Z","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":"d414b4a70d9980d75a6c80c49e37b22fd22c84ab0b4da168ea5b30276616e33e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-02T09:50:58Z","title_canon_sha256":"8dde0b459287bfa48af36fa13c7838403b1a28309dd783cde17d8ed46b23890a"},"schema_version":"1.0","source":{"id":"2607.01958","kind":"arxiv","version":1}},"canonical_sha256":"20af00af95a328cc6618fda2c9acfb42999ce2ceba8c7e20a5d5e2c7a011496c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"20af00af95a328cc6618fda2c9acfb42999ce2ceba8c7e20a5d5e2c7a011496c","first_computed_at":"2026-07-03T01:17:35.217546Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-03T01:17:35.217546Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VajgjX4EKgjaxGxV5I3SI83pm0wWKXYikjUXVylZe5QNXrH3Bw1Z+C6+xGqEpZJ8UxgD6DKw5pZOpvW7qGE+CA==","signature_status":"signed_v1","signed_at":"2026-07-03T01:17:35.217972Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.01958","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b3e013966cc9c203accc884cf425fcba6769dab9c246cdee94c3029944cfc58f","sha256:571461f22633b878c470b0ddb1b71809dd1eb84526af8c4baaa2c467e798edb7"],"state_sha256":"cfd059765438d99bccc3e37ada78a938b875959b07806ff8f02dc27ff97f1686"}