{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:ORUPN5TFSLSC4T7UBF2HEVR7QS","short_pith_number":"pith:ORUPN5TF","schema_version":"1.0","canonical_sha256":"7468f6f66592e42e4ff4097472563f8497604ebf5aeb894a3fcdd36515652443","source":{"kind":"arxiv","id":"2307.01000","version":2},"attestation_state":"computed","paper":{"title":"Pareto optimal proxy metrics","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ME","authors_text":"Alessandro Zito, Dylan Greaves, Jacopo Soriano, Lee Richardson","submitted_at":"2023-07-03T13:29:14Z","abstract_excerpt":"North star metrics and online experimentation play a central role in how technology companies improve their products. In many practical settings, however, evaluating experiments based on the north star metric directly can be difficult. The two most significant issues are 1) low sensitivity of the north star metric and 2) differences between the short-term and long-term impact on the north star metric. A common solution is to rely on proxy metrics rather than the north star in experiment evaluation and launch decisions. Existing literature on proxy metrics concentrates mainly on the estimation "},"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":"2307.01000","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ME","submitted_at":"2023-07-03T13:29:14Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"04313bfc0a502b6d0123d8a630cfa4e4cc6c7b2a5a32e19fbde1e9f94330f07f","abstract_canon_sha256":"ae19e2659a52a4fcee8e287dcac9ba5855f956bb245765c83338a676971f060e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:16:31.300689Z","signature_b64":"zYG9cuAL2/6zOhs/LSV3N8DjJ3iqGsFyBxFg6VnMTr0SLwe6oxkPoOjuvfDMoKlyZZgihSY75jzdPqMYFNwEDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7468f6f66592e42e4ff4097472563f8497604ebf5aeb894a3fcdd36515652443","last_reissued_at":"2026-07-05T10:16:31.300131Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:16:31.300131Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Pareto optimal proxy metrics","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ME","authors_text":"Alessandro Zito, Dylan Greaves, Jacopo Soriano, Lee Richardson","submitted_at":"2023-07-03T13:29:14Z","abstract_excerpt":"North star metrics and online experimentation play a central role in how technology companies improve their products. In many practical settings, however, evaluating experiments based on the north star metric directly can be difficult. The two most significant issues are 1) low sensitivity of the north star metric and 2) differences between the short-term and long-term impact on the north star metric. A common solution is to rely on proxy metrics rather than the north star in experiment evaluation and launch decisions. Existing literature on proxy metrics concentrates mainly on the estimation "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.01000","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/2307.01000/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":"2307.01000","created_at":"2026-07-05T10:16:31.300209+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.01000v2","created_at":"2026-07-05T10:16:31.300209+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.01000","created_at":"2026-07-05T10:16:31.300209+00:00"},{"alias_kind":"pith_short_12","alias_value":"ORUPN5TFSLSC","created_at":"2026-07-05T10:16:31.300209+00:00"},{"alias_kind":"pith_short_16","alias_value":"ORUPN5TFSLSC4T7U","created_at":"2026-07-05T10:16:31.300209+00:00"},{"alias_kind":"pith_short_8","alias_value":"ORUPN5TF","created_at":"2026-07-05T10:16:31.300209+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2408.02667","citing_title":"An Online Meta-Level Adaptive Design Framework with Targeted Learning Inference: Applications to Evaluating and Utilizing Surrogate Outcomes in Adaptive Designs","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14352","citing_title":"PROXIMA: A Reliability Scoring Framework for Proxy Metrics in Online Controlled Experiments","ref_index":19,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ORUPN5TFSLSC4T7UBF2HEVR7QS","json":"https://pith.science/pith/ORUPN5TFSLSC4T7UBF2HEVR7QS.json","graph_json":"https://pith.science/api/pith-number/ORUPN5TFSLSC4T7UBF2HEVR7QS/graph.json","events_json":"https://pith.science/api/pith-number/ORUPN5TFSLSC4T7UBF2HEVR7QS/events.json","paper":"https://pith.science/paper/ORUPN5TF"},"agent_actions":{"view_html":"https://pith.science/pith/ORUPN5TFSLSC4T7UBF2HEVR7QS","download_json":"https://pith.science/pith/ORUPN5TFSLSC4T7UBF2HEVR7QS.json","view_paper":"https://pith.science/paper/ORUPN5TF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.01000&json=true","fetch_graph":"https://pith.science/api/pith-number/ORUPN5TFSLSC4T7UBF2HEVR7QS/graph.json","fetch_events":"https://pith.science/api/pith-number/ORUPN5TFSLSC4T7UBF2HEVR7QS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ORUPN5TFSLSC4T7UBF2HEVR7QS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ORUPN5TFSLSC4T7UBF2HEVR7QS/action/storage_attestation","attest_author":"https://pith.science/pith/ORUPN5TFSLSC4T7UBF2HEVR7QS/action/author_attestation","sign_citation":"https://pith.science/pith/ORUPN5TFSLSC4T7UBF2HEVR7QS/action/citation_signature","submit_replication":"https://pith.science/pith/ORUPN5TFSLSC4T7UBF2HEVR7QS/action/replication_record"}},"created_at":"2026-07-05T10:16:31.300209+00:00","updated_at":"2026-07-05T10:16:31.300209+00:00"}