{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:R7SUGJJDB2NEDU7PPOTIMDWTMZ","short_pith_number":"pith:R7SUGJJD","schema_version":"1.0","canonical_sha256":"8fe54325230e9a41d3ef7ba6860ed3664de793cbb7ff484727fa82df2e993865","source":{"kind":"arxiv","id":"1710.02650","version":2},"attestation_state":"computed","paper":{"title":"Topic Modeling based on Keywords and Context","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR","cs.LG"],"primary_cat":"cs.CL","authors_text":"Johannes Schneider","submitted_at":"2017-10-07T08:18:12Z","abstract_excerpt":"Current topic models often suffer from discovering topics not matching human intuition, unnatural switching of topics within documents and high computational demands. We address these concerns by proposing a topic model and an inference algorithm based on automatically identifying characteristic keywords for topics. Keywords influence topic-assignments of nearby words. Our algorithm learns (key)word-topic scores and it self-regulates the number of topics. Inference is simple and easily parallelizable. Qualitative analysis yields comparable results to state-of-the-art models (eg. LDA), but with"},"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":"1710.02650","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-10-07T08:18:12Z","cross_cats_sorted":["cs.IR","cs.LG"],"title_canon_sha256":"c33ae2d7401af3335e156b5de98ecfe8d00cb905268d7454fea03d2577b9a29f","abstract_canon_sha256":"d80df4705c1312a8fc7447aa518d568a9a2289611dc29491d1c6c9323677a617"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:24:30.624434Z","signature_b64":"h6obYX8AJf2Z42cw6ypOvmkZGlIMne8aESv7nRQIDrXgrkgFIRZSvA6+lur+T9gLkzHNROEcBwGiZ8A594n9CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8fe54325230e9a41d3ef7ba6860ed3664de793cbb7ff484727fa82df2e993865","last_reissued_at":"2026-05-18T00:24:30.623962Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:24:30.623962Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Topic Modeling based on Keywords and Context","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR","cs.LG"],"primary_cat":"cs.CL","authors_text":"Johannes Schneider","submitted_at":"2017-10-07T08:18:12Z","abstract_excerpt":"Current topic models often suffer from discovering topics not matching human intuition, unnatural switching of topics within documents and high computational demands. We address these concerns by proposing a topic model and an inference algorithm based on automatically identifying characteristic keywords for topics. Keywords influence topic-assignments of nearby words. Our algorithm learns (key)word-topic scores and it self-regulates the number of topics. Inference is simple and easily parallelizable. Qualitative analysis yields comparable results to state-of-the-art models (eg. LDA), but with"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1710.02650","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":""},"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":"1710.02650","created_at":"2026-05-18T00:24:30.624040+00:00"},{"alias_kind":"arxiv_version","alias_value":"1710.02650v2","created_at":"2026-05-18T00:24:30.624040+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1710.02650","created_at":"2026-05-18T00:24:30.624040+00:00"},{"alias_kind":"pith_short_12","alias_value":"R7SUGJJDB2NE","created_at":"2026-05-18T12:31:39.905425+00:00"},{"alias_kind":"pith_short_16","alias_value":"R7SUGJJDB2NEDU7P","created_at":"2026-05-18T12:31:39.905425+00:00"},{"alias_kind":"pith_short_8","alias_value":"R7SUGJJD","created_at":"2026-05-18T12:31:39.905425+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/R7SUGJJDB2NEDU7PPOTIMDWTMZ","json":"https://pith.science/pith/R7SUGJJDB2NEDU7PPOTIMDWTMZ.json","graph_json":"https://pith.science/api/pith-number/R7SUGJJDB2NEDU7PPOTIMDWTMZ/graph.json","events_json":"https://pith.science/api/pith-number/R7SUGJJDB2NEDU7PPOTIMDWTMZ/events.json","paper":"https://pith.science/paper/R7SUGJJD"},"agent_actions":{"view_html":"https://pith.science/pith/R7SUGJJDB2NEDU7PPOTIMDWTMZ","download_json":"https://pith.science/pith/R7SUGJJDB2NEDU7PPOTIMDWTMZ.json","view_paper":"https://pith.science/paper/R7SUGJJD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1710.02650&json=true","fetch_graph":"https://pith.science/api/pith-number/R7SUGJJDB2NEDU7PPOTIMDWTMZ/graph.json","fetch_events":"https://pith.science/api/pith-number/R7SUGJJDB2NEDU7PPOTIMDWTMZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/R7SUGJJDB2NEDU7PPOTIMDWTMZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/R7SUGJJDB2NEDU7PPOTIMDWTMZ/action/storage_attestation","attest_author":"https://pith.science/pith/R7SUGJJDB2NEDU7PPOTIMDWTMZ/action/author_attestation","sign_citation":"https://pith.science/pith/R7SUGJJDB2NEDU7PPOTIMDWTMZ/action/citation_signature","submit_replication":"https://pith.science/pith/R7SUGJJDB2NEDU7PPOTIMDWTMZ/action/replication_record"}},"created_at":"2026-05-18T00:24:30.624040+00:00","updated_at":"2026-05-18T00:24:30.624040+00:00"}