{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:GD6NLT7LEYGA7RODXSHH7ARBCG","short_pith_number":"pith:GD6NLT7L","schema_version":"1.0","canonical_sha256":"30fcd5cfeb260c0fc5c3bc8e7f82211197b1d590e90ca9564352df9c55d69a8e","source":{"kind":"arxiv","id":"1907.04907","version":1},"attestation_state":"computed","paper":{"title":"Topic Modeling in Embedding Spaces","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG","stat.ML"],"primary_cat":"cs.IR","authors_text":"Adji B. Dieng, David M. Blei, Francisco J. R. Ruiz","submitted_at":"2019-07-08T03:50:57Z","abstract_excerpt":"Topic modeling analyzes documents to learn meaningful patterns of words. However, existing topic models fail to learn interpretable topics when working with large and heavy-tailed vocabularies. To this end, we develop the Embedded Topic Model (ETM), a generative model of documents that marries traditional topic models with word embeddings. In particular, it models each word with a categorical distribution whose natural parameter is the inner product between a word embedding and an embedding of its assigned topic. To fit the ETM, we develop an efficient amortized variational inference algorithm"},"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":"1907.04907","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2019-07-08T03:50:57Z","cross_cats_sorted":["cs.CL","cs.LG","stat.ML"],"title_canon_sha256":"a9c30067999f3c2be5c69797aa740c29232ce72cdea3b9abf2dd6c46b7d8a5d9","abstract_canon_sha256":"465bd6a953ace085ea713e40ca9a206dd1039b6067a3cc835ed6be38faba30f2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:40:54.569242Z","signature_b64":"sZz62K+oUmyGXhwx+LWPwX4HXeSIBgTuS07IiXuzX6fks4jRjYY3fkftKXKjEjagh1BeyJasSJewWRtw9mSECw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"30fcd5cfeb260c0fc5c3bc8e7f82211197b1d590e90ca9564352df9c55d69a8e","last_reissued_at":"2026-05-17T23:40:54.568554Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:40:54.568554Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Topic Modeling in Embedding Spaces","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG","stat.ML"],"primary_cat":"cs.IR","authors_text":"Adji B. Dieng, David M. Blei, Francisco J. R. Ruiz","submitted_at":"2019-07-08T03:50:57Z","abstract_excerpt":"Topic modeling analyzes documents to learn meaningful patterns of words. However, existing topic models fail to learn interpretable topics when working with large and heavy-tailed vocabularies. To this end, we develop the Embedded Topic Model (ETM), a generative model of documents that marries traditional topic models with word embeddings. In particular, it models each word with a categorical distribution whose natural parameter is the inner product between a word embedding and an embedding of its assigned topic. To fit the ETM, we develop an efficient amortized variational inference algorithm"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.04907","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":""},"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":"1907.04907","created_at":"2026-05-17T23:40:54.568671+00:00"},{"alias_kind":"arxiv_version","alias_value":"1907.04907v1","created_at":"2026-05-17T23:40:54.568671+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.04907","created_at":"2026-05-17T23:40:54.568671+00:00"},{"alias_kind":"pith_short_12","alias_value":"GD6NLT7LEYGA","created_at":"2026-05-18T12:33:18.533446+00:00"},{"alias_kind":"pith_short_16","alias_value":"GD6NLT7LEYGA7ROD","created_at":"2026-05-18T12:33:18.533446+00:00"},{"alias_kind":"pith_short_8","alias_value":"GD6NLT7L","created_at":"2026-05-18T12:33:18.533446+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/GD6NLT7LEYGA7RODXSHH7ARBCG","json":"https://pith.science/pith/GD6NLT7LEYGA7RODXSHH7ARBCG.json","graph_json":"https://pith.science/api/pith-number/GD6NLT7LEYGA7RODXSHH7ARBCG/graph.json","events_json":"https://pith.science/api/pith-number/GD6NLT7LEYGA7RODXSHH7ARBCG/events.json","paper":"https://pith.science/paper/GD6NLT7L"},"agent_actions":{"view_html":"https://pith.science/pith/GD6NLT7LEYGA7RODXSHH7ARBCG","download_json":"https://pith.science/pith/GD6NLT7LEYGA7RODXSHH7ARBCG.json","view_paper":"https://pith.science/paper/GD6NLT7L","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1907.04907&json=true","fetch_graph":"https://pith.science/api/pith-number/GD6NLT7LEYGA7RODXSHH7ARBCG/graph.json","fetch_events":"https://pith.science/api/pith-number/GD6NLT7LEYGA7RODXSHH7ARBCG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GD6NLT7LEYGA7RODXSHH7ARBCG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GD6NLT7LEYGA7RODXSHH7ARBCG/action/storage_attestation","attest_author":"https://pith.science/pith/GD6NLT7LEYGA7RODXSHH7ARBCG/action/author_attestation","sign_citation":"https://pith.science/pith/GD6NLT7LEYGA7RODXSHH7ARBCG/action/citation_signature","submit_replication":"https://pith.science/pith/GD6NLT7LEYGA7RODXSHH7ARBCG/action/replication_record"}},"created_at":"2026-05-17T23:40:54.568671+00:00","updated_at":"2026-05-17T23:40:54.568671+00:00"}