{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:GD6NLT7LEYGA7RODXSHH7ARBCG","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"465bd6a953ace085ea713e40ca9a206dd1039b6067a3cc835ed6be38faba30f2","cross_cats_sorted":["cs.CL","cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2019-07-08T03:50:57Z","title_canon_sha256":"a9c30067999f3c2be5c69797aa740c29232ce72cdea3b9abf2dd6c46b7d8a5d9"},"schema_version":"1.0","source":{"id":"1907.04907","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1907.04907","created_at":"2026-05-17T23:40:54Z"},{"alias_kind":"arxiv_version","alias_value":"1907.04907v1","created_at":"2026-05-17T23:40:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.04907","created_at":"2026-05-17T23:40:54Z"},{"alias_kind":"pith_short_12","alias_value":"GD6NLT7LEYGA","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_16","alias_value":"GD6NLT7LEYGA7ROD","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_8","alias_value":"GD6NLT7L","created_at":"2026-05-18T12:33:18Z"}],"graph_snapshots":[{"event_id":"sha256:5647cc1f5eb7de12cdbad1f5d5dede1ec1ae0878db3945635650c2d8342f6e1e","target":"graph","created_at":"2026-05-17T23:40:54Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"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","authors_text":"Adji B. Dieng, David M. Blei, Francisco J. R. Ruiz","cross_cats":["cs.CL","cs.LG","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2019-07-08T03:50:57Z","title":"Topic Modeling in Embedding Spaces"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.04907","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:f9bb9fe937fe97df37c6f774f4e19d52b2109879444ff42e29534b74d305e05b","target":"record","created_at":"2026-05-17T23:40:54Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"465bd6a953ace085ea713e40ca9a206dd1039b6067a3cc835ed6be38faba30f2","cross_cats_sorted":["cs.CL","cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2019-07-08T03:50:57Z","title_canon_sha256":"a9c30067999f3c2be5c69797aa740c29232ce72cdea3b9abf2dd6c46b7d8a5d9"},"schema_version":"1.0","source":{"id":"1907.04907","kind":"arxiv","version":1}},"canonical_sha256":"30fcd5cfeb260c0fc5c3bc8e7f82211197b1d590e90ca9564352df9c55d69a8e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"30fcd5cfeb260c0fc5c3bc8e7f82211197b1d590e90ca9564352df9c55d69a8e","first_computed_at":"2026-05-17T23:40:54.568554Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:40:54.568554Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"sZz62K+oUmyGXhwx+LWPwX4HXeSIBgTuS07IiXuzX6fks4jRjYY3fkftKXKjEjagh1BeyJasSJewWRtw9mSECw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:40:54.569242Z","signed_message":"canonical_sha256_bytes"},"source_id":"1907.04907","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f9bb9fe937fe97df37c6f774f4e19d52b2109879444ff42e29534b74d305e05b","sha256:5647cc1f5eb7de12cdbad1f5d5dede1ec1ae0878db3945635650c2d8342f6e1e"],"state_sha256":"b77df0e514305cd32ca979835cc920a77f94db73db5d3461c573b423a9101672"}