{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:7U5HWE3QYKJHJVALUOFHX2SBT6","short_pith_number":"pith:7U5HWE3Q","schema_version":"1.0","canonical_sha256":"fd3a7b1370c29274d40ba38a7bea419f9016a58a6c84bb14eaeeb5db92f5d3ae","source":{"kind":"arxiv","id":"2311.11922","version":2},"attestation_state":"computed","paper":{"title":"Evaluating the Surrogate Index as a Decision-Making Tool Using 200 A/B Tests at Netflix","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ME"],"primary_cat":"stat.AP","authors_text":"and Maria Dimakopoulou, Anh Le, Michael Zhao, Nathan Kallus, Vickie Zhang","submitted_at":"2023-11-20T16:59:18Z","abstract_excerpt":"Surrogate index approaches have recently become a popular method of estimating longer-term impact from shorter-term outcomes. In this paper, we leverage 1098 test arms from 200 A/B tests at Netflix to empirically investigate to what degree would decisions made using a surrogate index utilizing 14 days of data would align with those made using direct measurement of day 63 treatment effects. Focusing specifically on linear \"auto-surrogate\" models that utilize the shorter-term observations of the long-term outcome of interest, we find that the statistical inferences that we would draw from using "},"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":"2311.11922","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.AP","submitted_at":"2023-11-20T16:59:18Z","cross_cats_sorted":["stat.ME"],"title_canon_sha256":"aced16c2e27d0fb987e3a7f477e70b6c762c39b167edca4494e94cffdf3baa9e","abstract_canon_sha256":"b09a3917aa77d4ffc64f2a0c23f40d9b60807c1d1c9417419fcf21bdf2b6e0ae"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:39:31.632561Z","signature_b64":"HumD3PcRnyk6zyU2AqbXzT2+3EXshPA3NNv7v/wZcJU9ljZir9KcD6gRzP2yYJ49Xov3yLz0VTL5vhK8XS8SAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fd3a7b1370c29274d40ba38a7bea419f9016a58a6c84bb14eaeeb5db92f5d3ae","last_reissued_at":"2026-07-05T07:39:31.632100Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:39:31.632100Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Evaluating the Surrogate Index as a Decision-Making Tool Using 200 A/B Tests at Netflix","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ME"],"primary_cat":"stat.AP","authors_text":"and Maria Dimakopoulou, Anh Le, Michael Zhao, Nathan Kallus, Vickie Zhang","submitted_at":"2023-11-20T16:59:18Z","abstract_excerpt":"Surrogate index approaches have recently become a popular method of estimating longer-term impact from shorter-term outcomes. In this paper, we leverage 1098 test arms from 200 A/B tests at Netflix to empirically investigate to what degree would decisions made using a surrogate index utilizing 14 days of data would align with those made using direct measurement of day 63 treatment effects. Focusing specifically on linear \"auto-surrogate\" models that utilize the shorter-term observations of the long-term outcome of interest, we find that the statistical inferences that we would draw from using "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.11922","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/2311.11922/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":"2311.11922","created_at":"2026-07-05T07:39:31.632157+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.11922v2","created_at":"2026-07-05T07:39:31.632157+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.11922","created_at":"2026-07-05T07:39:31.632157+00:00"},{"alias_kind":"pith_short_12","alias_value":"7U5HWE3QYKJH","created_at":"2026-07-05T07:39:31.632157+00:00"},{"alias_kind":"pith_short_16","alias_value":"7U5HWE3QYKJHJVAL","created_at":"2026-07-05T07:39:31.632157+00:00"},{"alias_kind":"pith_short_8","alias_value":"7U5HWE3Q","created_at":"2026-07-05T07:39:31.632157+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.21745","citing_title":"Blending Proxy Metrics with a North Star","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12051","citing_title":"Learning plug-in surrogate endpoints for randomized experiments","ref_index":41,"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":28,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7U5HWE3QYKJHJVALUOFHX2SBT6","json":"https://pith.science/pith/7U5HWE3QYKJHJVALUOFHX2SBT6.json","graph_json":"https://pith.science/api/pith-number/7U5HWE3QYKJHJVALUOFHX2SBT6/graph.json","events_json":"https://pith.science/api/pith-number/7U5HWE3QYKJHJVALUOFHX2SBT6/events.json","paper":"https://pith.science/paper/7U5HWE3Q"},"agent_actions":{"view_html":"https://pith.science/pith/7U5HWE3QYKJHJVALUOFHX2SBT6","download_json":"https://pith.science/pith/7U5HWE3QYKJHJVALUOFHX2SBT6.json","view_paper":"https://pith.science/paper/7U5HWE3Q","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.11922&json=true","fetch_graph":"https://pith.science/api/pith-number/7U5HWE3QYKJHJVALUOFHX2SBT6/graph.json","fetch_events":"https://pith.science/api/pith-number/7U5HWE3QYKJHJVALUOFHX2SBT6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7U5HWE3QYKJHJVALUOFHX2SBT6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7U5HWE3QYKJHJVALUOFHX2SBT6/action/storage_attestation","attest_author":"https://pith.science/pith/7U5HWE3QYKJHJVALUOFHX2SBT6/action/author_attestation","sign_citation":"https://pith.science/pith/7U5HWE3QYKJHJVALUOFHX2SBT6/action/citation_signature","submit_replication":"https://pith.science/pith/7U5HWE3QYKJHJVALUOFHX2SBT6/action/replication_record"}},"created_at":"2026-07-05T07:39:31.632157+00:00","updated_at":"2026-07-05T07:39:31.632157+00:00"}