{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ZKAQEUDXFK564AJXBFXYJVGDD6","short_pith_number":"pith:ZKAQEUDX","schema_version":"1.0","canonical_sha256":"ca810250772abbee0137096f84d4c31fb76b6392530632314a30d65085627a51","source":{"kind":"arxiv","id":"2501.09731","version":2},"attestation_state":"computed","paper":{"title":"Predictions as Surrogates: Revisiting Surrogate Outcomes in the Age of AI","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Lihua Lei, Tijana Zrnic, Wenlong Ji","submitted_at":"2025-01-16T18:30:33Z","abstract_excerpt":"We establish a formal connection between the decades-old surrogate outcome model in biostatistics and economics and the emerging field of prediction-powered inference (PPI). The connection treats predictions from pre-trained models, prevalent in the age of AI, as cost-effective surrogates for expensive outcomes. Building on the surrogate outcomes literature, we develop recalibrated prediction-powered inference, a more efficient approach to statistical inference than existing PPI proposals. Our method departs from the existing proposals by using flexible machine learning techniques to learn the"},"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":"2501.09731","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2025-01-16T18:30:33Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"6db82029cdb7d1cf0a4fcce62b6437919f19217ba45a2304f2bb070961fe183c","abstract_canon_sha256":"08e41deb599e854b5028b25606344bd7ed3565a0235d9c1da9fcc5d28129d070"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T02:13:13.700136Z","signature_b64":"RQidyur9RqwleS4Z+IFh5nIQ2UV+XGHcszzpq6hfreMPzWVEgL0D0nS3LOs9/AvXpk/DnZz2A15w7zmpe20MCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ca810250772abbee0137096f84d4c31fb76b6392530632314a30d65085627a51","last_reissued_at":"2026-06-23T02:13:13.699670Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T02:13:13.699670Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Predictions as Surrogates: Revisiting Surrogate Outcomes in the Age of AI","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Lihua Lei, Tijana Zrnic, Wenlong Ji","submitted_at":"2025-01-16T18:30:33Z","abstract_excerpt":"We establish a formal connection between the decades-old surrogate outcome model in biostatistics and economics and the emerging field of prediction-powered inference (PPI). The connection treats predictions from pre-trained models, prevalent in the age of AI, as cost-effective surrogates for expensive outcomes. Building on the surrogate outcomes literature, we develop recalibrated prediction-powered inference, a more efficient approach to statistical inference than existing PPI proposals. Our method departs from the existing proposals by using flexible machine learning techniques to learn the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.09731","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/2501.09731/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":"2501.09731","created_at":"2026-06-23T02:13:13.699730+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.09731v2","created_at":"2026-06-23T02:13:13.699730+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.09731","created_at":"2026-06-23T02:13:13.699730+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZKAQEUDXFK56","created_at":"2026-06-23T02:13:13.699730+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZKAQEUDXFK564AJX","created_at":"2026-06-23T02:13:13.699730+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZKAQEUDX","created_at":"2026-06-23T02:13:13.699730+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":8,"sample":[{"citing_arxiv_id":"2605.29249","citing_title":"Prediction-Powered Inference Across Many Tasks for AI Evaluation & Social Science Research","ref_index":6,"is_internal_anchor":true},{"citing_arxiv_id":"2605.31278","citing_title":"Industrializing Prediction-Powered Inference: The GLIDE Library for Reliable GenAI and Agentic Systems Evaluation","ref_index":8,"is_internal_anchor":true},{"citing_arxiv_id":"2505.06452","citing_title":"Semiparametric semi-supervised learning for general targets under distribution shift and decaying overlap","ref_index":5,"is_internal_anchor":true},{"citing_arxiv_id":"2506.16658","citing_title":"Multi-Armed Bandits With Machine Learning-Generated Surrogate Rewards","ref_index":20,"is_internal_anchor":true},{"citing_arxiv_id":"2512.01423","citing_title":"Active Hypothesis Testing under Computational Budgets with Applications to GWAS and LLM","ref_index":20,"is_internal_anchor":true},{"citing_arxiv_id":"2605.06484","citing_title":"Estimate Level Adjustment For Inference With Proxies Under Random Distribution Shifts","ref_index":19,"is_internal_anchor":true},{"citing_arxiv_id":"2604.21260","citing_title":"Calibeating Prediction-Powered Inference","ref_index":13,"is_internal_anchor":true},{"citing_arxiv_id":"2604.12497","citing_title":"Allocating Human Oversight in AI-Enabled Analytics","ref_index":21,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZKAQEUDXFK564AJXBFXYJVGDD6","json":"https://pith.science/pith/ZKAQEUDXFK564AJXBFXYJVGDD6.json","graph_json":"https://pith.science/api/pith-number/ZKAQEUDXFK564AJXBFXYJVGDD6/graph.json","events_json":"https://pith.science/api/pith-number/ZKAQEUDXFK564AJXBFXYJVGDD6/events.json","paper":"https://pith.science/paper/ZKAQEUDX"},"agent_actions":{"view_html":"https://pith.science/pith/ZKAQEUDXFK564AJXBFXYJVGDD6","download_json":"https://pith.science/pith/ZKAQEUDXFK564AJXBFXYJVGDD6.json","view_paper":"https://pith.science/paper/ZKAQEUDX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.09731&json=true","fetch_graph":"https://pith.science/api/pith-number/ZKAQEUDXFK564AJXBFXYJVGDD6/graph.json","fetch_events":"https://pith.science/api/pith-number/ZKAQEUDXFK564AJXBFXYJVGDD6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZKAQEUDXFK564AJXBFXYJVGDD6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZKAQEUDXFK564AJXBFXYJVGDD6/action/storage_attestation","attest_author":"https://pith.science/pith/ZKAQEUDXFK564AJXBFXYJVGDD6/action/author_attestation","sign_citation":"https://pith.science/pith/ZKAQEUDXFK564AJXBFXYJVGDD6/action/citation_signature","submit_replication":"https://pith.science/pith/ZKAQEUDXFK564AJXBFXYJVGDD6/action/replication_record"}},"created_at":"2026-06-23T02:13:13.699730+00:00","updated_at":"2026-06-23T02:13:13.699730+00:00"}