{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:NIRGHDTQJFPAHKIG73CEXACGY6","short_pith_number":"pith:NIRGHDTQ","schema_version":"1.0","canonical_sha256":"6a22638e70495e03a906fec44b8046c7bdd8c27187a2836faeac1756c79bf6ca","source":{"kind":"arxiv","id":"2604.14575","version":2},"attestation_state":"computed","paper":{"title":"Generative Augmented Inference","license":"http://creativecommons.org/licenses/by/4.0/","headline":"GAI uses an orthogonal moment construction to incorporate LLM-generated outputs for consistent estimation and valid inference on human-labeled outcomes with a nonparametric relationship.","cross_cats":["cs.AI","stat.ME","stat.ML"],"primary_cat":"cs.LG","authors_text":"Cheng Lu, Dennis J. Zhang, Heng Zhang, Mengxin Wang","submitted_at":"2026-04-16T03:10:37Z","abstract_excerpt":"Large language models enable inexpensive AI-generated annotations, but using them reliably for causal inference remains challenging. Naively pooling AI and human data induces bias, while existing methods such as Prediction-Powered Inference (PPI; Angelopoulos et al., 2023a) treat AI outputs as proxies of true labels -- an assumption often violated for generative model outputs in practice. We propose Generative Augmented Inference (GAI), a framework that treats AI outputs as general, potentially high-dimensional informative features for learning human labels rather than as surrogates. GAI flexi"},"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":"2604.14575","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-04-16T03:10:37Z","cross_cats_sorted":["cs.AI","stat.ME","stat.ML"],"title_canon_sha256":"d9c619a92c0d53f6b5a9d04053daa8fd2309908cc50408b2cee96620c744fc09","abstract_canon_sha256":"1dcb81c04289b4a6085a03dbb775466610f2d6b6fc9a22b7fae5fea86d019eef"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-04T00:06:50.836503Z","signature_b64":"bxbLaDlpe+jl4y49AcHkdjafSUTa+CHbGTkt1Ny/n9JhxGiEBKt+o6UibbrnHHtZmMo2dDJK0rlhqKIDXzBAAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6a22638e70495e03a906fec44b8046c7bdd8c27187a2836faeac1756c79bf6ca","last_reissued_at":"2026-06-04T00:06:50.836025Z","signature_status":"signed_v1","first_computed_at":"2026-06-04T00:06:50.836025Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Generative Augmented Inference","license":"http://creativecommons.org/licenses/by/4.0/","headline":"GAI uses an orthogonal moment construction to incorporate LLM-generated outputs for consistent estimation and valid inference on human-labeled outcomes with a nonparametric relationship.","cross_cats":["cs.AI","stat.ME","stat.ML"],"primary_cat":"cs.LG","authors_text":"Cheng Lu, Dennis J. Zhang, Heng Zhang, Mengxin Wang","submitted_at":"2026-04-16T03:10:37Z","abstract_excerpt":"Large language models enable inexpensive AI-generated annotations, but using them reliably for causal inference remains challenging. Naively pooling AI and human data induces bias, while existing methods such as Prediction-Powered Inference (PPI; Angelopoulos et al., 2023a) treat AI outputs as proxies of true labels -- an assumption often violated for generative model outputs in practice. We propose Generative Augmented Inference (GAI), a framework that treats AI outputs as general, potentially high-dimensional informative features for learning human labels rather than as surrogates. GAI flexi"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"GAI uses an orthogonal moment construction that enables consistent estimation and valid inference with flexible, nonparametric relationship between LLM-generated outputs and human labels. We establish asymptotic normality and show a 'safe default' property: relative to human-data-only estimators, GAI weakly improves estimation efficiency under arbitrary auxiliary signals and yields strict gains whenever the auxiliary information is predictive.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The auxiliary AI signals are generated independently of the human labeling process in a way that permits the orthogonal moment conditions to identify the target parameters without additional parametric restrictions on the relationship between AI outputs and human labels.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"GAI uses orthogonal moment conditions to integrate arbitrary AI-generated auxiliary data into human-label models, delivering consistent estimates, asymptotic normality, and a safe-default efficiency improvement over human-data-only methods.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"GAI uses an orthogonal moment construction to incorporate LLM-generated outputs for consistent estimation and valid inference on human-labeled outcomes with a nonparametric relationship.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"e19521fdd97f35606ce6b3c2cf5c2352f23f640480a6608e131b9ab7a56dc9ab"},"source":{"id":"2604.14575","kind":"arxiv","version":2},"verdict":{"id":"4ec378b2-5688-4956-9d3e-05f70ed75dde","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-10T11:59:03.757757Z","strongest_claim":"GAI uses an orthogonal moment construction that enables consistent estimation and valid inference with flexible, nonparametric relationship between LLM-generated outputs and human labels. We establish asymptotic normality and show a 'safe default' property: relative to human-data-only estimators, GAI weakly improves estimation efficiency under arbitrary auxiliary signals and yields strict gains whenever the auxiliary information is predictive.","one_line_summary":"GAI uses orthogonal moment conditions to integrate arbitrary AI-generated auxiliary data into human-label models, delivering consistent estimates, asymptotic normality, and a safe-default efficiency improvement over human-data-only methods.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The auxiliary AI signals are generated independently of the human labeling process in a way that permits the orthogonal moment conditions to identify the target parameters without additional parametric restrictions on the relationship between AI outputs and human labels.","pith_extraction_headline":"GAI uses an orthogonal moment construction to incorporate LLM-generated outputs for consistent estimation and valid inference on human-labeled outcomes with a nonparametric relationship."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2604.14575/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":"2604.14575","created_at":"2026-06-04T00:06:50.836086+00:00"},{"alias_kind":"arxiv_version","alias_value":"2604.14575v2","created_at":"2026-06-04T00:06:50.836086+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.14575","created_at":"2026-06-04T00:06:50.836086+00:00"},{"alias_kind":"pith_short_12","alias_value":"NIRGHDTQJFPA","created_at":"2026-06-04T00:06:50.836086+00:00"},{"alias_kind":"pith_short_16","alias_value":"NIRGHDTQJFPAHKIG","created_at":"2026-06-04T00:06:50.836086+00:00"},{"alias_kind":"pith_short_8","alias_value":"NIRGHDTQ","created_at":"2026-06-04T00:06:50.836086+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NIRGHDTQJFPAHKIG73CEXACGY6","json":"https://pith.science/pith/NIRGHDTQJFPAHKIG73CEXACGY6.json","graph_json":"https://pith.science/api/pith-number/NIRGHDTQJFPAHKIG73CEXACGY6/graph.json","events_json":"https://pith.science/api/pith-number/NIRGHDTQJFPAHKIG73CEXACGY6/events.json","paper":"https://pith.science/paper/NIRGHDTQ"},"agent_actions":{"view_html":"https://pith.science/pith/NIRGHDTQJFPAHKIG73CEXACGY6","download_json":"https://pith.science/pith/NIRGHDTQJFPAHKIG73CEXACGY6.json","view_paper":"https://pith.science/paper/NIRGHDTQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2604.14575&json=true","fetch_graph":"https://pith.science/api/pith-number/NIRGHDTQJFPAHKIG73CEXACGY6/graph.json","fetch_events":"https://pith.science/api/pith-number/NIRGHDTQJFPAHKIG73CEXACGY6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NIRGHDTQJFPAHKIG73CEXACGY6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NIRGHDTQJFPAHKIG73CEXACGY6/action/storage_attestation","attest_author":"https://pith.science/pith/NIRGHDTQJFPAHKIG73CEXACGY6/action/author_attestation","sign_citation":"https://pith.science/pith/NIRGHDTQJFPAHKIG73CEXACGY6/action/citation_signature","submit_replication":"https://pith.science/pith/NIRGHDTQJFPAHKIG73CEXACGY6/action/replication_record"}},"created_at":"2026-06-04T00:06:50.836086+00:00","updated_at":"2026-06-04T00:06:50.836086+00:00"}