{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:TYAUKOAYBJDJXLBJXSNZPWRTQP","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":"32ba08230c3638361b71c55e3ed19361afada6eb14b11970b2f4ba8b4a27ec6a","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2019-07-24T14:08:23Z","title_canon_sha256":"3946067ccd53708839c4ad6ed86bc18c57b0d37f842f1a32568c3ce12bd71eb2"},"schema_version":"1.0","source":{"id":"1907.12374","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1907.12374","created_at":"2026-07-05T00:24:39Z"},{"alias_kind":"arxiv_version","alias_value":"1907.12374v2","created_at":"2026-07-05T00:24:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.12374","created_at":"2026-07-05T00:24:39Z"},{"alias_kind":"pith_short_12","alias_value":"TYAUKOAYBJDJ","created_at":"2026-07-05T00:24:39Z"},{"alias_kind":"pith_short_16","alias_value":"TYAUKOAYBJDJXLBJ","created_at":"2026-07-05T00:24:39Z"},{"alias_kind":"pith_short_8","alias_value":"TYAUKOAY","created_at":"2026-07-05T00:24:39Z"}],"graph_snapshots":[{"event_id":"sha256:40f5001ecc1573d8ed5de0902ce2306214cbaf4c3153c3e50a46bbb60c9706f6","target":"graph","created_at":"2026-07-05T00:24:39Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/1907.12374/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose a novel neural topic model in the Wasserstein autoencoders (WAE) framework. Unlike existing variational autoencoder based models, we directly enforce Dirichlet prior on the latent document-topic vectors. We exploit the structure of the latent space and apply a suitable kernel in minimizing the Maximum Mean Discrepancy (MMD) to perform distribution matching. We discover that MMD performs much better than the Generative Adversarial Network (GAN) in matching high dimensional Dirichlet distribution. We further discover that incorporating randomness in the encoder output during training ","authors_text":"Bing Xiang, Feng Nan, Ramesh Nallapati, Ran Ding","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2019-07-24T14:08:23Z","title":"Topic Modeling with Wasserstein Autoencoders"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.12374","kind":"arxiv","version":2},"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":"sha256:90856af7f5877e66ea482023f9eb9c4b3ca65c81d8c1e1e7aab0ae72edddd825","target":"record","created_at":"2026-07-05T00:24:39Z","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":"32ba08230c3638361b71c55e3ed19361afada6eb14b11970b2f4ba8b4a27ec6a","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2019-07-24T14:08:23Z","title_canon_sha256":"3946067ccd53708839c4ad6ed86bc18c57b0d37f842f1a32568c3ce12bd71eb2"},"schema_version":"1.0","source":{"id":"1907.12374","kind":"arxiv","version":2}},"canonical_sha256":"9e014538180a469bac29bc9b97da3383cd06fbdaf8a6253f056fd67b280514e0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9e014538180a469bac29bc9b97da3383cd06fbdaf8a6253f056fd67b280514e0","first_computed_at":"2026-07-05T00:24:39.899934Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:24:39.899934Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ScwoEhmSdG+Z8ll71609/cIi//j8uwX+dVw5h4Lsl2vmzlr7dXk8atsd2yUsn2DpJQYhos25ZKdi5g6vu2XQCg==","signature_status":"signed_v1","signed_at":"2026-07-05T00:24:39.900424Z","signed_message":"canonical_sha256_bytes"},"source_id":"1907.12374","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:90856af7f5877e66ea482023f9eb9c4b3ca65c81d8c1e1e7aab0ae72edddd825","sha256:40f5001ecc1573d8ed5de0902ce2306214cbaf4c3153c3e50a46bbb60c9706f6"],"state_sha256":"b02a51dc433afafa6d952820c7d7f808c4ab4a46ee4c4ad06596c0ecc5d07ca2"}