{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:OPYT3GUAOCO6PE5MX3OPBNA6LK","short_pith_number":"pith:OPYT3GUA","schema_version":"1.0","canonical_sha256":"73f13d9a80709de793acbedcf0b41e5aa34b370e151b189559b025f1c4fa4d1b","source":{"kind":"arxiv","id":"2605.30718","version":1},"attestation_state":"computed","paper":{"title":"Moment-Based Inference for Regression with Latent Dirichlet Covariates","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ME","stat.ML"],"primary_cat":"econ.EM","authors_text":"Ziyu Jiang","submitted_at":"2026-05-29T01:24:17Z","abstract_excerpt":"Topic models are often used as dimension-reduction tools before regression, with estimated document-level topic shares treated as observed covariates. This plug-in workflow creates two inferential difficulties: valid inference requires a regular first-stage-to-second-stage expansion that propagates topic-estimation uncertainty, and, at fixed document length, a document's topic mixture cannot be consistently recovered from its own words even when the population topic matrix is known. Corrected spectral moment methods for latent Dirichlet allocation (LDA) offer a starting point: when the total D"},"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":"2605.30718","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"econ.EM","submitted_at":"2026-05-29T01:24:17Z","cross_cats_sorted":["stat.ME","stat.ML"],"title_canon_sha256":"c3e0b07d77fe20658afcb369b3ff822104839a5668e0f47f7ad2fe430910a09e","abstract_canon_sha256":"1c00cc242e133c0d5c4cb128d6e708e932ed3d92a2b94182c94db61a6ea5ce7e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-01T01:03:12.083167Z","signature_b64":"cSr7nNqgVxqfsfW2RpJtxhKK6rp781GbtJcZ7s9SVKFwarvyrFELCV45Ui5R9PtfWN0NC4rMamHfgKg37/HxAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"73f13d9a80709de793acbedcf0b41e5aa34b370e151b189559b025f1c4fa4d1b","last_reissued_at":"2026-06-01T01:03:12.082523Z","signature_status":"signed_v1","first_computed_at":"2026-06-01T01:03:12.082523Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Moment-Based Inference for Regression with Latent Dirichlet Covariates","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ME","stat.ML"],"primary_cat":"econ.EM","authors_text":"Ziyu Jiang","submitted_at":"2026-05-29T01:24:17Z","abstract_excerpt":"Topic models are often used as dimension-reduction tools before regression, with estimated document-level topic shares treated as observed covariates. This plug-in workflow creates two inferential difficulties: valid inference requires a regular first-stage-to-second-stage expansion that propagates topic-estimation uncertainty, and, at fixed document length, a document's topic mixture cannot be consistently recovered from its own words even when the population topic matrix is known. Corrected spectral moment methods for latent Dirichlet allocation (LDA) offer a starting point: when the total D"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.30718","kind":"arxiv","version":1},"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/2605.30718/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":"2605.30718","created_at":"2026-06-01T01:03:12.082624+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.30718v1","created_at":"2026-06-01T01:03:12.082624+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.30718","created_at":"2026-06-01T01:03:12.082624+00:00"},{"alias_kind":"pith_short_12","alias_value":"OPYT3GUAOCO6","created_at":"2026-06-01T01:03:12.082624+00:00"},{"alias_kind":"pith_short_16","alias_value":"OPYT3GUAOCO6PE5M","created_at":"2026-06-01T01:03:12.082624+00:00"},{"alias_kind":"pith_short_8","alias_value":"OPYT3GUA","created_at":"2026-06-01T01:03:12.082624+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/OPYT3GUAOCO6PE5MX3OPBNA6LK","json":"https://pith.science/pith/OPYT3GUAOCO6PE5MX3OPBNA6LK.json","graph_json":"https://pith.science/api/pith-number/OPYT3GUAOCO6PE5MX3OPBNA6LK/graph.json","events_json":"https://pith.science/api/pith-number/OPYT3GUAOCO6PE5MX3OPBNA6LK/events.json","paper":"https://pith.science/paper/OPYT3GUA"},"agent_actions":{"view_html":"https://pith.science/pith/OPYT3GUAOCO6PE5MX3OPBNA6LK","download_json":"https://pith.science/pith/OPYT3GUAOCO6PE5MX3OPBNA6LK.json","view_paper":"https://pith.science/paper/OPYT3GUA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.30718&json=true","fetch_graph":"https://pith.science/api/pith-number/OPYT3GUAOCO6PE5MX3OPBNA6LK/graph.json","fetch_events":"https://pith.science/api/pith-number/OPYT3GUAOCO6PE5MX3OPBNA6LK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OPYT3GUAOCO6PE5MX3OPBNA6LK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OPYT3GUAOCO6PE5MX3OPBNA6LK/action/storage_attestation","attest_author":"https://pith.science/pith/OPYT3GUAOCO6PE5MX3OPBNA6LK/action/author_attestation","sign_citation":"https://pith.science/pith/OPYT3GUAOCO6PE5MX3OPBNA6LK/action/citation_signature","submit_replication":"https://pith.science/pith/OPYT3GUAOCO6PE5MX3OPBNA6LK/action/replication_record"}},"created_at":"2026-06-01T01:03:12.082624+00:00","updated_at":"2026-06-01T01:03:12.082624+00:00"}