{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:IDO7Z4NGNLT3FXMZFHIJFIZAAS","short_pith_number":"pith:IDO7Z4NG","schema_version":"1.0","canonical_sha256":"40ddfcf1a66ae7b2dd9929d092a320048f8641f30d54e12a3645d06faf94eed5","source":{"kind":"arxiv","id":"2604.05446","version":2},"attestation_state":"computed","paper":{"title":"MEC: Machine-Learning-Assisted Generalized Entropy Calibration for Semi-Supervised Mean Estimation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Machine-learning-assisted generalized entropy calibration attains the semiparametric efficiency bound for semi-supervised mean estimation under weaker assumptions than prior PPI variants.","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Jae Kwang Kim, Se Yoon Lee","submitted_at":"2026-04-07T05:30:11Z","abstract_excerpt":"Obtaining high-quality labels is costly, whereas unlabeled covariates are often abundant, motivating semi-supervised inference methods with reliable uncertainty quantification. Prediction-powered inference (PPI) leverages a machine-learning predictor trained on a small labeled sample to improve efficiency, but it can lose efficiency under model misspecification and suffer from coverage distortions due to label reuse. We introduce Machine-Learning-Assisted Generalized Entropy Calibration (MEC), a cross-fitted, calibration-weighted variant of PPI. MEC improves efficiency by reweighting labeled s"},"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":true},"canonical_record":{"source":{"id":"2604.05446","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2026-04-07T05:30:11Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"b3354b7b9be40f76beec5e3f52b40231b74ddafe5e46b3d6b6c8b91e8f7b228b","abstract_canon_sha256":"82d6db1583d4cbbd1df42f620d7978eaa38a28779dcefb83ff2a0270e3cc5013"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-29T01:05:08.743681Z","signature_b64":"u0P/IACjIBb1+118M35cpHE381lo8BeLa3Od+nMuYs3TiG0p3r1MYtJxAzAIDRx5xBrXQCjm+uQLdSSIh5lbDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"40ddfcf1a66ae7b2dd9929d092a320048f8641f30d54e12a3645d06faf94eed5","last_reissued_at":"2026-05-29T01:05:08.743108Z","signature_status":"signed_v1","first_computed_at":"2026-05-29T01:05:08.743108Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MEC: Machine-Learning-Assisted Generalized Entropy Calibration for Semi-Supervised Mean Estimation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Machine-learning-assisted generalized entropy calibration attains the semiparametric efficiency bound for semi-supervised mean estimation under weaker assumptions than prior PPI variants.","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Jae Kwang Kim, Se Yoon Lee","submitted_at":"2026-04-07T05:30:11Z","abstract_excerpt":"Obtaining high-quality labels is costly, whereas unlabeled covariates are often abundant, motivating semi-supervised inference methods with reliable uncertainty quantification. Prediction-powered inference (PPI) leverages a machine-learning predictor trained on a small labeled sample to improve efficiency, but it can lose efficiency under model misspecification and suffer from coverage distortions due to label reuse. We introduce Machine-Learning-Assisted Generalized Entropy Calibration (MEC), a cross-fitted, calibration-weighted variant of PPI. MEC improves efficiency by reweighting labeled s"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"MEC attains the semiparametric efficiency bound under weaker assumptions than existing PPI variants.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The calibration framework based on Bregman projections produces weights that align labeled samples with the target population and that the weaker projection-error conditions suffice for validity and efficiency.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"MEC attains the semiparametric efficiency bound for mean estimation under weaker projection-error conditions than prior PPI methods by using generalized entropy calibration.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Machine-learning-assisted generalized entropy calibration attains the semiparametric efficiency bound for semi-supervised mean estimation under weaker assumptions than prior PPI variants.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"317bc9966679cd489acee878cdbe4063443b8b0c654e9c809c37384718da90f1"},"source":{"id":"2604.05446","kind":"arxiv","version":2},"verdict":{"id":"b5be9364-8b06-4e8a-abc9-3016a6ff49a7","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-10T19:29:58.890349Z","strongest_claim":"MEC attains the semiparametric efficiency bound under weaker assumptions than existing PPI variants.","one_line_summary":"MEC attains the semiparametric efficiency bound for mean estimation under weaker projection-error conditions than prior PPI methods by using generalized entropy calibration.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The calibration framework based on Bregman projections produces weights that align labeled samples with the target population and that the weaker projection-error conditions suffice for validity and efficiency.","pith_extraction_headline":"Machine-learning-assisted generalized entropy calibration attains the semiparametric efficiency bound for semi-supervised mean estimation under weaker assumptions than prior PPI variants."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2604.05446/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":2,"snapshot_sha256":"092a132ebccc11e0f274390f9e147d7ac23d2b1e9642034bf715dee7c4686e51"},"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":"2604.05446","created_at":"2026-05-29T01:05:08.743185+00:00"},{"alias_kind":"arxiv_version","alias_value":"2604.05446v2","created_at":"2026-05-29T01:05:08.743185+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.05446","created_at":"2026-05-29T01:05:08.743185+00:00"},{"alias_kind":"pith_short_12","alias_value":"IDO7Z4NGNLT3","created_at":"2026-05-29T01:05:08.743185+00:00"},{"alias_kind":"pith_short_16","alias_value":"IDO7Z4NGNLT3FXMZ","created_at":"2026-05-29T01:05:08.743185+00:00"},{"alias_kind":"pith_short_8","alias_value":"IDO7Z4NG","created_at":"2026-05-29T01:05:08.743185+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2604.21260","citing_title":"Calibeating Prediction-Powered Inference","ref_index":15,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IDO7Z4NGNLT3FXMZFHIJFIZAAS","json":"https://pith.science/pith/IDO7Z4NGNLT3FXMZFHIJFIZAAS.json","graph_json":"https://pith.science/api/pith-number/IDO7Z4NGNLT3FXMZFHIJFIZAAS/graph.json","events_json":"https://pith.science/api/pith-number/IDO7Z4NGNLT3FXMZFHIJFIZAAS/events.json","paper":"https://pith.science/paper/IDO7Z4NG"},"agent_actions":{"view_html":"https://pith.science/pith/IDO7Z4NGNLT3FXMZFHIJFIZAAS","download_json":"https://pith.science/pith/IDO7Z4NGNLT3FXMZFHIJFIZAAS.json","view_paper":"https://pith.science/paper/IDO7Z4NG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2604.05446&json=true","fetch_graph":"https://pith.science/api/pith-number/IDO7Z4NGNLT3FXMZFHIJFIZAAS/graph.json","fetch_events":"https://pith.science/api/pith-number/IDO7Z4NGNLT3FXMZFHIJFIZAAS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IDO7Z4NGNLT3FXMZFHIJFIZAAS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IDO7Z4NGNLT3FXMZFHIJFIZAAS/action/storage_attestation","attest_author":"https://pith.science/pith/IDO7Z4NGNLT3FXMZFHIJFIZAAS/action/author_attestation","sign_citation":"https://pith.science/pith/IDO7Z4NGNLT3FXMZFHIJFIZAAS/action/citation_signature","submit_replication":"https://pith.science/pith/IDO7Z4NGNLT3FXMZFHIJFIZAAS/action/replication_record"}},"created_at":"2026-05-29T01:05:08.743185+00:00","updated_at":"2026-05-29T01:05:08.743185+00:00"}