{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:5SICW4MTVVCMAGXWU7XIP4FEEB","short_pith_number":"pith:5SICW4MT","schema_version":"1.0","canonical_sha256":"ec902b7193ad44c01af6a7ee87f0a4204edb215fca7d3fdbca7df657b7279c8f","source":{"kind":"arxiv","id":"2004.05964","version":3},"attestation_state":"computed","paper":{"title":"Keyword Assisted Topic Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.AP","stat.ME"],"primary_cat":"cs.CL","authors_text":"Kosuke Imai, Shusei Eshima, Tomoya Sasaki","submitted_at":"2020-04-13T14:35:28Z","abstract_excerpt":"In recent years, fully automated content analysis based on probabilistic topic models has become popular among social scientists because of their scalability. The unsupervised nature of the models makes them suitable for exploring topics in a corpus without prior knowledge. However, researchers find that these models often fail to measure specific concepts of substantive interest by inadvertently creating multiple topics with similar content and combining distinct themes into a single topic. In this paper, we empirically demonstrate that providing a small number of keywords can substantially e"},"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":"2004.05964","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-13T14:35:28Z","cross_cats_sorted":["stat.AP","stat.ME"],"title_canon_sha256":"734aa3fe0c103e62fc49b0810eaabfffbd8c4a42758ff51cd89b53240dcf9d69","abstract_canon_sha256":"95804fb32ef871ee7f3dac93e2bf2ab542d981ca7113cdf32bc27c8732a35aec"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:38:25.517356Z","signature_b64":"5V0bVe64Dl9Bes+eHs76X8h6PxnX66DgmQ3Y64OCvy6rLZPSg0eSUI7LFr5VxFgDazxB+bIjqjU1tN04YptcAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ec902b7193ad44c01af6a7ee87f0a4204edb215fca7d3fdbca7df657b7279c8f","last_reissued_at":"2026-07-05T05:38:25.516801Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:38:25.516801Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Keyword Assisted Topic Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.AP","stat.ME"],"primary_cat":"cs.CL","authors_text":"Kosuke Imai, Shusei Eshima, Tomoya Sasaki","submitted_at":"2020-04-13T14:35:28Z","abstract_excerpt":"In recent years, fully automated content analysis based on probabilistic topic models has become popular among social scientists because of their scalability. The unsupervised nature of the models makes them suitable for exploring topics in a corpus without prior knowledge. However, researchers find that these models often fail to measure specific concepts of substantive interest by inadvertently creating multiple topics with similar content and combining distinct themes into a single topic. In this paper, we empirically demonstrate that providing a small number of keywords can substantially e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.05964","kind":"arxiv","version":3},"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/2004.05964/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":"2004.05964","created_at":"2026-07-05T05:38:25.516859+00:00"},{"alias_kind":"arxiv_version","alias_value":"2004.05964v3","created_at":"2026-07-05T05:38:25.516859+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.05964","created_at":"2026-07-05T05:38:25.516859+00:00"},{"alias_kind":"pith_short_12","alias_value":"5SICW4MTVVCM","created_at":"2026-07-05T05:38:25.516859+00:00"},{"alias_kind":"pith_short_16","alias_value":"5SICW4MTVVCMAGXW","created_at":"2026-07-05T05:38:25.516859+00:00"},{"alias_kind":"pith_short_8","alias_value":"5SICW4MT","created_at":"2026-07-05T05:38:25.516859+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/5SICW4MTVVCMAGXWU7XIP4FEEB","json":"https://pith.science/pith/5SICW4MTVVCMAGXWU7XIP4FEEB.json","graph_json":"https://pith.science/api/pith-number/5SICW4MTVVCMAGXWU7XIP4FEEB/graph.json","events_json":"https://pith.science/api/pith-number/5SICW4MTVVCMAGXWU7XIP4FEEB/events.json","paper":"https://pith.science/paper/5SICW4MT"},"agent_actions":{"view_html":"https://pith.science/pith/5SICW4MTVVCMAGXWU7XIP4FEEB","download_json":"https://pith.science/pith/5SICW4MTVVCMAGXWU7XIP4FEEB.json","view_paper":"https://pith.science/paper/5SICW4MT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2004.05964&json=true","fetch_graph":"https://pith.science/api/pith-number/5SICW4MTVVCMAGXWU7XIP4FEEB/graph.json","fetch_events":"https://pith.science/api/pith-number/5SICW4MTVVCMAGXWU7XIP4FEEB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5SICW4MTVVCMAGXWU7XIP4FEEB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5SICW4MTVVCMAGXWU7XIP4FEEB/action/storage_attestation","attest_author":"https://pith.science/pith/5SICW4MTVVCMAGXWU7XIP4FEEB/action/author_attestation","sign_citation":"https://pith.science/pith/5SICW4MTVVCMAGXWU7XIP4FEEB/action/citation_signature","submit_replication":"https://pith.science/pith/5SICW4MTVVCMAGXWU7XIP4FEEB/action/replication_record"}},"created_at":"2026-07-05T05:38:25.516859+00:00","updated_at":"2026-07-05T05:38:25.516859+00:00"}