{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:IDO7Z4NGNLT3FXMZFHIJFIZAAS","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"82d6db1583d4cbbd1df42f620d7978eaa38a28779dcefb83ff2a0270e3cc5013","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2026-04-07T05:30:11Z","title_canon_sha256":"b3354b7b9be40f76beec5e3f52b40231b74ddafe5e46b3d6b6c8b91e8f7b228b"},"schema_version":"1.0","source":{"id":"2604.05446","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.05446","created_at":"2026-05-29T01:05:08Z"},{"alias_kind":"arxiv_version","alias_value":"2604.05446v2","created_at":"2026-05-29T01:05:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.05446","created_at":"2026-05-29T01:05:08Z"},{"alias_kind":"pith_short_12","alias_value":"IDO7Z4NGNLT3","created_at":"2026-05-29T01:05:08Z"},{"alias_kind":"pith_short_16","alias_value":"IDO7Z4NGNLT3FXMZ","created_at":"2026-05-29T01:05:08Z"},{"alias_kind":"pith_short_8","alias_value":"IDO7Z4NG","created_at":"2026-05-29T01:05:08Z"}],"graph_snapshots":[{"event_id":"sha256:08dccd75e8048737644070d33cbcdb73ad20815ee9735bf9adbc369f9bc70af9","target":"graph","created_at":"2026-05-29T01:05:08Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"MEC attains the semiparametric efficiency bound under weaker assumptions than existing PPI variants."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"MEC attains the semiparametric efficiency bound for mean estimation under weaker projection-error conditions than prior PPI methods by using generalized entropy calibration."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Machine-learning-assisted generalized entropy calibration attains the semiparametric efficiency bound for semi-supervised mean estimation under weaker assumptions than prior PPI variants."}],"snapshot_sha256":"317bc9966679cd489acee878cdbe4063443b8b0c654e9c809c37384718da90f1"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"092a132ebccc11e0f274390f9e147d7ac23d2b1e9642034bf715dee7c4686e51"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2604.05446/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Jae Kwang Kim, Se Yoon Lee","cross_cats":["cs.LG"],"headline":"Machine-learning-assisted generalized entropy calibration attains the semiparametric efficiency bound for semi-supervised mean estimation under weaker assumptions than prior PPI variants.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2026-04-07T05:30:11Z","title":"MEC: Machine-Learning-Assisted Generalized Entropy Calibration for Semi-Supervised Mean Estimation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2604.05446","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-10T19:29:58.890349Z","id":"b5be9364-8b06-4e8a-abc9-3016a6ff49a7","model_set":{"reader":"grok-4.3"},"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","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.","strongest_claim":"MEC attains the semiparametric efficiency bound under weaker assumptions than existing PPI variants.","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."}},"verdict_id":"b5be9364-8b06-4e8a-abc9-3016a6ff49a7"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:e4ecaf88fd916424ac25d37f57f3c95f030135a72bd00e6a89b04c2db3d8d7a7","target":"record","created_at":"2026-05-29T01:05:08Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"82d6db1583d4cbbd1df42f620d7978eaa38a28779dcefb83ff2a0270e3cc5013","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2026-04-07T05:30:11Z","title_canon_sha256":"b3354b7b9be40f76beec5e3f52b40231b74ddafe5e46b3d6b6c8b91e8f7b228b"},"schema_version":"1.0","source":{"id":"2604.05446","kind":"arxiv","version":2}},"canonical_sha256":"40ddfcf1a66ae7b2dd9929d092a320048f8641f30d54e12a3645d06faf94eed5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"40ddfcf1a66ae7b2dd9929d092a320048f8641f30d54e12a3645d06faf94eed5","first_computed_at":"2026-05-29T01:05:08.743108Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-29T01:05:08.743108Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"u0P/IACjIBb1+118M35cpHE381lo8BeLa3Od+nMuYs3TiG0p3r1MYtJxAzAIDRx5xBrXQCjm+uQLdSSIh5lbDw==","signature_status":"signed_v1","signed_at":"2026-05-29T01:05:08.743681Z","signed_message":"canonical_sha256_bytes"},"source_id":"2604.05446","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e4ecaf88fd916424ac25d37f57f3c95f030135a72bd00e6a89b04c2db3d8d7a7","sha256:08dccd75e8048737644070d33cbcdb73ad20815ee9735bf9adbc369f9bc70af9"],"state_sha256":"507d937ccfc67ea44e2629fba64c0b3301047c129b94148cde5ab88163a60c20"}