{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:GC7JLPI42Y5NCFTOCQPRSKAORT","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":"ff3295984544c48fd7f935084eef17340a5738d4efd2d4129898000d9e17572c","cross_cats_sorted":["stat.ME","stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.ST","submitted_at":"2025-02-25T00:34:59Z","title_canon_sha256":"bbd0b84e5dc129937202609028d935449fd131d4d55ffe1d5d6c9155eb1e81b7"},"schema_version":"1.0","source":{"id":"2502.17741","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.17741","created_at":"2026-07-05T10:34:17Z"},{"alias_kind":"arxiv_version","alias_value":"2502.17741v2","created_at":"2026-07-05T10:34:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.17741","created_at":"2026-07-05T10:34:17Z"},{"alias_kind":"pith_short_12","alias_value":"GC7JLPI42Y5N","created_at":"2026-07-05T10:34:17Z"},{"alias_kind":"pith_short_16","alias_value":"GC7JLPI42Y5NCFTO","created_at":"2026-07-05T10:34:17Z"},{"alias_kind":"pith_short_8","alias_value":"GC7JLPI4","created_at":"2026-07-05T10:34:17Z"}],"graph_snapshots":[{"event_id":"sha256:1a863af0dac3b701a2350e825a146dcfaf387a2aa45ab04534abcb2904edea87","target":"graph","created_at":"2026-07-05T10:34:17Z","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":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2502.17741/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Ali Shojaie, Daniela Witten, Zichun Xu","cross_cats":["stat.ME","stat.TH"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.ST","submitted_at":"2025-02-25T00:34:59Z","title":"A Unified Framework for Semiparametrically Efficient Semi-Supervised Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.17741","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:04ed27b65a1247098a9113e1364080a5f8e62c9adcf07ac7035784fbf811218c","target":"record","created_at":"2026-07-05T10:34:17Z","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":"ff3295984544c48fd7f935084eef17340a5738d4efd2d4129898000d9e17572c","cross_cats_sorted":["stat.ME","stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.ST","submitted_at":"2025-02-25T00:34:59Z","title_canon_sha256":"bbd0b84e5dc129937202609028d935449fd131d4d55ffe1d5d6c9155eb1e81b7"},"schema_version":"1.0","source":{"id":"2502.17741","kind":"arxiv","version":2}},"canonical_sha256":"30be95bd1cd63ad1166e141f19280e8ceaa8eee74f018dc591339dc3ed7f58a1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"30be95bd1cd63ad1166e141f19280e8ceaa8eee74f018dc591339dc3ed7f58a1","first_computed_at":"2026-07-05T10:34:17.099550Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:34:17.099550Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"93z4HZLQk6oSrKLIL09gLVjMC/9KleJLZTADSZLV7EFlTqDBak3kLjCfHhPgAolLU0xVtoGvO1tYUvVpf5BUCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:34:17.100050Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.17741","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:04ed27b65a1247098a9113e1364080a5f8e62c9adcf07ac7035784fbf811218c","sha256:1a863af0dac3b701a2350e825a146dcfaf387a2aa45ab04534abcb2904edea87"],"state_sha256":"e65ba519b764fece19fc024ea71c23080aa9a4c25e29c7582d6d6e524e1f116f"}