{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:ZOZK53W2EYFQVK7ML3HEN7BHBX","short_pith_number":"pith:ZOZK53W2","schema_version":"1.0","canonical_sha256":"cbb2aeeeda260b0aabec5ece46fc270dcb4ba6716883962c2a46c1e36a8fad93","source":{"kind":"arxiv","id":"2107.08112","version":2},"attestation_state":"computed","paper":{"title":"Hamiltonian Monte Carlo for Regression with High-Dimensional Categorical Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ME"],"primary_cat":"econ.EM","authors_text":"Laura Battaglia, Stephen Hansen, Szymon Sacher","submitted_at":"2021-07-16T20:40:54Z","abstract_excerpt":"Latent variable models are increasingly used in economics for high-dimensional categorical data like text and surveys. We demonstrate the effectiveness of Hamiltonian Monte Carlo (HMC) with parallelized automatic differentiation for analyzing such data in a computationally efficient and methodologically sound manner. Our new model, Supervised Topic Model with Covariates, shows that carefully modeling this type of data can have significant implications on conclusions compared to a simpler, frequently used, yet methodologically problematic, two-step approach. A simulation study and revisiting Ba"},"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":"2107.08112","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"econ.EM","submitted_at":"2021-07-16T20:40:54Z","cross_cats_sorted":["stat.ME"],"title_canon_sha256":"808d77f2f46f44444458b30e92341e6db552b9b81f9c85c9833dd7f0b954221c","abstract_canon_sha256":"ec72b86a2a62168c1c82467840b41d9b96b3ec29f38b3752d4dafe15fc3d7024"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:50:47.195679Z","signature_b64":"EB213KSVwnFVb8IpMQE99gUX8g47lG61d9rSfCGS56/Rd2RtcfpC6gflC6RWxLfj+rJNwVdnaxTrEjRkMaDcBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cbb2aeeeda260b0aabec5ece46fc270dcb4ba6716883962c2a46c1e36a8fad93","last_reissued_at":"2026-07-05T07:50:47.195269Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:50:47.195269Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hamiltonian Monte Carlo for Regression with High-Dimensional Categorical Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ME"],"primary_cat":"econ.EM","authors_text":"Laura Battaglia, Stephen Hansen, Szymon Sacher","submitted_at":"2021-07-16T20:40:54Z","abstract_excerpt":"Latent variable models are increasingly used in economics for high-dimensional categorical data like text and surveys. We demonstrate the effectiveness of Hamiltonian Monte Carlo (HMC) with parallelized automatic differentiation for analyzing such data in a computationally efficient and methodologically sound manner. Our new model, Supervised Topic Model with Covariates, shows that carefully modeling this type of data can have significant implications on conclusions compared to a simpler, frequently used, yet methodologically problematic, two-step approach. A simulation study and revisiting Ba"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.08112","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/2107.08112/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":"2107.08112","created_at":"2026-07-05T07:50:47.195326+00:00"},{"alias_kind":"arxiv_version","alias_value":"2107.08112v2","created_at":"2026-07-05T07:50:47.195326+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.08112","created_at":"2026-07-05T07:50:47.195326+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZOZK53W2EYFQ","created_at":"2026-07-05T07:50:47.195326+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZOZK53W2EYFQVK7M","created_at":"2026-07-05T07:50:47.195326+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZOZK53W2","created_at":"2026-07-05T07:50:47.195326+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.21723","citing_title":"Dynamic Bayesian Item Response Model with Decomposition (D-BIRD): Modeling Cohort and Individual Learning Over Time","ref_index":17,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZOZK53W2EYFQVK7ML3HEN7BHBX","json":"https://pith.science/pith/ZOZK53W2EYFQVK7ML3HEN7BHBX.json","graph_json":"https://pith.science/api/pith-number/ZOZK53W2EYFQVK7ML3HEN7BHBX/graph.json","events_json":"https://pith.science/api/pith-number/ZOZK53W2EYFQVK7ML3HEN7BHBX/events.json","paper":"https://pith.science/paper/ZOZK53W2"},"agent_actions":{"view_html":"https://pith.science/pith/ZOZK53W2EYFQVK7ML3HEN7BHBX","download_json":"https://pith.science/pith/ZOZK53W2EYFQVK7ML3HEN7BHBX.json","view_paper":"https://pith.science/paper/ZOZK53W2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2107.08112&json=true","fetch_graph":"https://pith.science/api/pith-number/ZOZK53W2EYFQVK7ML3HEN7BHBX/graph.json","fetch_events":"https://pith.science/api/pith-number/ZOZK53W2EYFQVK7ML3HEN7BHBX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZOZK53W2EYFQVK7ML3HEN7BHBX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZOZK53W2EYFQVK7ML3HEN7BHBX/action/storage_attestation","attest_author":"https://pith.science/pith/ZOZK53W2EYFQVK7ML3HEN7BHBX/action/author_attestation","sign_citation":"https://pith.science/pith/ZOZK53W2EYFQVK7ML3HEN7BHBX/action/citation_signature","submit_replication":"https://pith.science/pith/ZOZK53W2EYFQVK7ML3HEN7BHBX/action/replication_record"}},"created_at":"2026-07-05T07:50:47.195326+00:00","updated_at":"2026-07-05T07:50:47.195326+00:00"}