{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:NIRGHDTQJFPAHKIG73CEXACGY6","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":"1dcb81c04289b4a6085a03dbb775466610f2d6b6fc9a22b7fae5fea86d019eef","cross_cats_sorted":["cs.AI","stat.ME","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-04-16T03:10:37Z","title_canon_sha256":"d9c619a92c0d53f6b5a9d04053daa8fd2309908cc50408b2cee96620c744fc09"},"schema_version":"1.0","source":{"id":"2604.14575","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.14575","created_at":"2026-06-04T00:06:50Z"},{"alias_kind":"arxiv_version","alias_value":"2604.14575v2","created_at":"2026-06-04T00:06:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.14575","created_at":"2026-06-04T00:06:50Z"},{"alias_kind":"pith_short_12","alias_value":"NIRGHDTQJFPA","created_at":"2026-06-04T00:06:50Z"},{"alias_kind":"pith_short_16","alias_value":"NIRGHDTQJFPAHKIG","created_at":"2026-06-04T00:06:50Z"},{"alias_kind":"pith_short_8","alias_value":"NIRGHDTQ","created_at":"2026-06-04T00:06:50Z"}],"graph_snapshots":[{"event_id":"sha256:dac1baefd53339f4e6002927a3aef56f3b15b0f033bfed09de430938aea92f15","target":"graph","created_at":"2026-06-04T00:06:50Z","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":"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."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","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."}],"snapshot_sha256":"e19521fdd97f35606ce6b3c2cf5c2352f23f640480a6608e131b9ab7a56dc9ab"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2604.14575/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Cheng Lu, Dennis J. Zhang, Heng Zhang, Mengxin Wang","cross_cats":["cs.AI","stat.ME","stat.ML"],"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.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-04-16T03:10:37Z","title":"Generative Augmented Inference"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2604.14575","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-10T11:59:03.757757Z","id":"4ec378b2-5688-4956-9d3e-05f70ed75dde","model_set":{"reader":"grok-4.3"},"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","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.","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.","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."}},"verdict_id":"4ec378b2-5688-4956-9d3e-05f70ed75dde"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:a6b7e2f393a3e2f198318af177c691f35e91b6bd1f2d8039053e904c41962f89","target":"record","created_at":"2026-06-04T00:06:50Z","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":"1dcb81c04289b4a6085a03dbb775466610f2d6b6fc9a22b7fae5fea86d019eef","cross_cats_sorted":["cs.AI","stat.ME","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-04-16T03:10:37Z","title_canon_sha256":"d9c619a92c0d53f6b5a9d04053daa8fd2309908cc50408b2cee96620c744fc09"},"schema_version":"1.0","source":{"id":"2604.14575","kind":"arxiv","version":2}},"canonical_sha256":"6a22638e70495e03a906fec44b8046c7bdd8c27187a2836faeac1756c79bf6ca","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6a22638e70495e03a906fec44b8046c7bdd8c27187a2836faeac1756c79bf6ca","first_computed_at":"2026-06-04T00:06:50.836025Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-04T00:06:50.836025Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bxbLaDlpe+jl4y49AcHkdjafSUTa+CHbGTkt1Ny/n9JhxGiEBKt+o6UibbrnHHtZmMo2dDJK0rlhqKIDXzBAAw==","signature_status":"signed_v1","signed_at":"2026-06-04T00:06:50.836503Z","signed_message":"canonical_sha256_bytes"},"source_id":"2604.14575","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a6b7e2f393a3e2f198318af177c691f35e91b6bd1f2d8039053e904c41962f89","sha256:dac1baefd53339f4e6002927a3aef56f3b15b0f033bfed09de430938aea92f15"],"state_sha256":"206dbc6b4a2940fffdc5e3e20e2491b06a3afa13fd0e6aa60e6454072a0bd582"}