{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:AP6OKNEK73T57CEWIYZYGOC67D","short_pith_number":"pith:AP6OKNEK","schema_version":"1.0","canonical_sha256":"03fce5348afee7df8896463383385ef8fa573f091f24dabb24b13ad4c7af7e7e","source":{"kind":"arxiv","id":"2502.04294","version":2},"attestation_state":"computed","paper":{"title":"Prediction-Powered E-Values","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","stat.ME"],"primary_cat":"stat.ML","authors_text":"Claudio Jos\\'e Struchiner, Daniel Csillag, Guilherme Tegoni Goedert","submitted_at":"2025-02-06T18:36:01Z","abstract_excerpt":"Quality statistical inference requires a sufficient amount of data, which can be missing or hard to obtain. To this end, prediction-powered inference has risen as a promising methodology, but existing approaches are largely limited to Z-estimation problems such as inference of means and quantiles. In this paper, we apply ideas of prediction-powered inference to e-values. By doing so, we inherit all the usual benefits of e-values -- such as anytime-validity, post-hoc validity and versatile sequential inference -- as well as greatly expand the set of inferences achievable in a prediction-powered"},"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":"2502.04294","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2025-02-06T18:36:01Z","cross_cats_sorted":["cs.LG","stat.ME"],"title_canon_sha256":"e644797e2d42ec96c3d8ada3aca9f57d745417365daa0b0a8caa335326496321","abstract_canon_sha256":"edd4a68ebcb947a05892ef6cde76be249716ea485ae11bb2f634c7d304084d89"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:09:45.054598Z","signature_b64":"5bUkaZLjT2uMxISRbo8sKdwLsArZxyt9LWGxkCS6CJ8UNVAy434H98UScQKGZSbkEEnNv7wTbrtY7PKNPewsAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"03fce5348afee7df8896463383385ef8fa573f091f24dabb24b13ad4c7af7e7e","last_reissued_at":"2026-07-05T11:09:45.054015Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:09:45.054015Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Prediction-Powered E-Values","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","stat.ME"],"primary_cat":"stat.ML","authors_text":"Claudio Jos\\'e Struchiner, Daniel Csillag, Guilherme Tegoni Goedert","submitted_at":"2025-02-06T18:36:01Z","abstract_excerpt":"Quality statistical inference requires a sufficient amount of data, which can be missing or hard to obtain. To this end, prediction-powered inference has risen as a promising methodology, but existing approaches are largely limited to Z-estimation problems such as inference of means and quantiles. In this paper, we apply ideas of prediction-powered inference to e-values. By doing so, we inherit all the usual benefits of e-values -- such as anytime-validity, post-hoc validity and versatile sequential inference -- as well as greatly expand the set of inferences achievable in a prediction-powered"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.04294","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/2502.04294/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":"2502.04294","created_at":"2026-07-05T11:09:45.054087+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.04294v2","created_at":"2026-07-05T11:09:45.054087+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.04294","created_at":"2026-07-05T11:09:45.054087+00:00"},{"alias_kind":"pith_short_12","alias_value":"AP6OKNEK73T5","created_at":"2026-07-05T11:09:45.054087+00:00"},{"alias_kind":"pith_short_16","alias_value":"AP6OKNEK73T57CEW","created_at":"2026-07-05T11:09:45.054087+00:00"},{"alias_kind":"pith_short_8","alias_value":"AP6OKNEK","created_at":"2026-07-05T11:09:45.054087+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.28533","citing_title":"Semi-Supervised Hypothesis Testing by Betting on Predictions","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2605.31278","citing_title":"Industrializing Prediction-Powered Inference: The GLIDE Library for Reliable GenAI and Agentic Systems Evaluation","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2602.01733","citing_title":"Improving Backward Conformal Prediction via Non-Conformity Score Transformation","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07964","citing_title":"Asymptotically Log-Optimal Bayes-Assisted Confidence Sequences for Bounded Means","ref_index":75,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07964","citing_title":"Asymptotically Log-Optimal Bayes-Assisted Confidence Sequences for Bounded Means","ref_index":75,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AP6OKNEK73T57CEWIYZYGOC67D","json":"https://pith.science/pith/AP6OKNEK73T57CEWIYZYGOC67D.json","graph_json":"https://pith.science/api/pith-number/AP6OKNEK73T57CEWIYZYGOC67D/graph.json","events_json":"https://pith.science/api/pith-number/AP6OKNEK73T57CEWIYZYGOC67D/events.json","paper":"https://pith.science/paper/AP6OKNEK"},"agent_actions":{"view_html":"https://pith.science/pith/AP6OKNEK73T57CEWIYZYGOC67D","download_json":"https://pith.science/pith/AP6OKNEK73T57CEWIYZYGOC67D.json","view_paper":"https://pith.science/paper/AP6OKNEK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.04294&json=true","fetch_graph":"https://pith.science/api/pith-number/AP6OKNEK73T57CEWIYZYGOC67D/graph.json","fetch_events":"https://pith.science/api/pith-number/AP6OKNEK73T57CEWIYZYGOC67D/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AP6OKNEK73T57CEWIYZYGOC67D/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AP6OKNEK73T57CEWIYZYGOC67D/action/storage_attestation","attest_author":"https://pith.science/pith/AP6OKNEK73T57CEWIYZYGOC67D/action/author_attestation","sign_citation":"https://pith.science/pith/AP6OKNEK73T57CEWIYZYGOC67D/action/citation_signature","submit_replication":"https://pith.science/pith/AP6OKNEK73T57CEWIYZYGOC67D/action/replication_record"}},"created_at":"2026-07-05T11:09:45.054087+00:00","updated_at":"2026-07-05T11:09:45.054087+00:00"}