{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:GC7JLPI42Y5NCFTOCQPRSKAORT","short_pith_number":"pith:GC7JLPI4","schema_version":"1.0","canonical_sha256":"30be95bd1cd63ad1166e141f19280e8ceaa8eee74f018dc591339dc3ed7f58a1","source":{"kind":"arxiv","id":"2502.17741","version":2},"attestation_state":"computed","paper":{"title":"A Unified Framework for Semiparametrically Efficient Semi-Supervised Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ME","stat.TH"],"primary_cat":"math.ST","authors_text":"Ali Shojaie, Daniela Witten, Zichun Xu","submitted_at":"2025-02-25T00:34:59Z","abstract_excerpt":"We consider statistical inference under a semi-supervised setting where we have access to both a labeled dataset consisting of pairs $\\{X_i, Y_i \\}_{i=1}^n$ and an unlabeled dataset $\\{ X_i \\}_{i=n+1}^{n+N}$. We ask the question: under what circumstances, and by how much, can incorporating the unlabeled dataset improve upon inference using the labeled data? To answer this question, we investigate semi-supervised learning through the lens of semiparametric efficiency theory. We characterize the efficiency lower bound under the semi-supervised setting for an arbitrary inferential problem, and sh"},"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":"2502.17741","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.ST","submitted_at":"2025-02-25T00:34:59Z","cross_cats_sorted":["stat.ME","stat.TH"],"title_canon_sha256":"bbd0b84e5dc129937202609028d935449fd131d4d55ffe1d5d6c9155eb1e81b7","abstract_canon_sha256":"ff3295984544c48fd7f935084eef17340a5738d4efd2d4129898000d9e17572c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:34:17.100050Z","signature_b64":"93z4HZLQk6oSrKLIL09gLVjMC/9KleJLZTADSZLV7EFlTqDBak3kLjCfHhPgAolLU0xVtoGvO1tYUvVpf5BUCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"30be95bd1cd63ad1166e141f19280e8ceaa8eee74f018dc591339dc3ed7f58a1","last_reissued_at":"2026-07-05T10:34:17.099550Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:34:17.099550Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Unified Framework for Semiparametrically Efficient Semi-Supervised Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ME","stat.TH"],"primary_cat":"math.ST","authors_text":"Ali Shojaie, Daniela Witten, Zichun Xu","submitted_at":"2025-02-25T00:34:59Z","abstract_excerpt":"We consider statistical inference under a semi-supervised setting where we have access to both a labeled dataset consisting of pairs $\\{X_i, Y_i \\}_{i=1}^n$ and an unlabeled dataset $\\{ X_i \\}_{i=n+1}^{n+N}$. We ask the question: under what circumstances, and by how much, can incorporating the unlabeled dataset improve upon inference using the labeled data? To answer this question, we investigate semi-supervised learning through the lens of semiparametric efficiency theory. We characterize the efficiency lower bound under the semi-supervised setting for an arbitrary inferential problem, and sh"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.17741","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/2502.17741/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":"2502.17741","created_at":"2026-07-05T10:34:17.099608+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.17741v2","created_at":"2026-07-05T10:34:17.099608+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.17741","created_at":"2026-07-05T10:34:17.099608+00:00"},{"alias_kind":"pith_short_12","alias_value":"GC7JLPI42Y5N","created_at":"2026-07-05T10:34:17.099608+00:00"},{"alias_kind":"pith_short_16","alias_value":"GC7JLPI42Y5NCFTO","created_at":"2026-07-05T10:34:17.099608+00:00"},{"alias_kind":"pith_short_8","alias_value":"GC7JLPI4","created_at":"2026-07-05T10:34:17.099608+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":16,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.17232","citing_title":"Semiparametric Mediation Analysis with Separately Observed Mediator and Outcome under Unmeasured Confounding","ref_index":112,"is_internal_anchor":false},{"citing_arxiv_id":"2606.08730","citing_title":"Statistical Optimality of Prediction-Powered Inference","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2607.00350","citing_title":"Robust Estimation and Inference with Selective Borrowing in Hybrid Controlled Trials: A Tutorial with SelectiveIntegrative and intFRT","ref_index":78,"is_internal_anchor":false},{"citing_arxiv_id":"2606.03211","citing_title":"Optimized Labeling Resource Allocation for Prediction-Assisted Inference via OPAL","ref_index":61,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05076","citing_title":"High-Dimensional Statistics: Reflections on Progress and Open Problems","ref_index":106,"is_internal_anchor":false},{"citing_arxiv_id":"2505.06452","citing_title":"Semiparametric semi-supervised learning for general targets under distribution shift and decaying overlap","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07285","citing_title":"Transporting treatment effects by calibrating large-scale observational outcomes","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17126","citing_title":"Multi-task Linear Regression without Eigenvalue Lower Bounds: Adaptivity, Robustness, and Safety","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03282","citing_title":"Externally Controlled Trials: A Review of Design and Borrowing Through a Causal Lens","ref_index":201,"is_internal_anchor":false},{"citing_arxiv_id":"2604.27892","citing_title":"Prediction-powered Inference by Mixture of Experts","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08773","citing_title":"Prediction-Powered Linear Regression: A Balance Between Interpretation and Prediction","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05076","citing_title":"High-Dimensional Statistics: Reflections on Progress and Open Problems","ref_index":106,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21260","citing_title":"Calibeating Prediction-Powered Inference","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21020","citing_title":"A Functional-Class Meta-Analytic Framework for Quantifying Surrogate Resilience","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07285","citing_title":"Transporting treatment effects by calibrating large-scale observational outcomes","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18569","citing_title":"Revisiting Active Sequential Prediction-Powered Mean Estimation","ref_index":21,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GC7JLPI42Y5NCFTOCQPRSKAORT","json":"https://pith.science/pith/GC7JLPI42Y5NCFTOCQPRSKAORT.json","graph_json":"https://pith.science/api/pith-number/GC7JLPI42Y5NCFTOCQPRSKAORT/graph.json","events_json":"https://pith.science/api/pith-number/GC7JLPI42Y5NCFTOCQPRSKAORT/events.json","paper":"https://pith.science/paper/GC7JLPI4"},"agent_actions":{"view_html":"https://pith.science/pith/GC7JLPI42Y5NCFTOCQPRSKAORT","download_json":"https://pith.science/pith/GC7JLPI42Y5NCFTOCQPRSKAORT.json","view_paper":"https://pith.science/paper/GC7JLPI4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.17741&json=true","fetch_graph":"https://pith.science/api/pith-number/GC7JLPI42Y5NCFTOCQPRSKAORT/graph.json","fetch_events":"https://pith.science/api/pith-number/GC7JLPI42Y5NCFTOCQPRSKAORT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GC7JLPI42Y5NCFTOCQPRSKAORT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GC7JLPI42Y5NCFTOCQPRSKAORT/action/storage_attestation","attest_author":"https://pith.science/pith/GC7JLPI42Y5NCFTOCQPRSKAORT/action/author_attestation","sign_citation":"https://pith.science/pith/GC7JLPI42Y5NCFTOCQPRSKAORT/action/citation_signature","submit_replication":"https://pith.science/pith/GC7JLPI42Y5NCFTOCQPRSKAORT/action/replication_record"}},"created_at":"2026-07-05T10:34:17.099608+00:00","updated_at":"2026-07-05T10:34:17.099608+00:00"}