{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:TYAUKOAYBJDJXLBJXSNZPWRTQP","short_pith_number":"pith:TYAUKOAY","canonical_record":{"source":{"id":"1907.12374","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2019-07-24T14:08:23Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"3946067ccd53708839c4ad6ed86bc18c57b0d37f842f1a32568c3ce12bd71eb2","abstract_canon_sha256":"32ba08230c3638361b71c55e3ed19361afada6eb14b11970b2f4ba8b4a27ec6a"},"schema_version":"1.0"},"canonical_sha256":"9e014538180a469bac29bc9b97da3383cd06fbdaf8a6253f056fd67b280514e0","source":{"kind":"arxiv","id":"1907.12374","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:TYAUKOAYBJDJXLBJXSNZPWRTQP","target":"record","payload":{"canonical_record":{"source":{"id":"1907.12374","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2019-07-24T14:08:23Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"3946067ccd53708839c4ad6ed86bc18c57b0d37f842f1a32568c3ce12bd71eb2","abstract_canon_sha256":"32ba08230c3638361b71c55e3ed19361afada6eb14b11970b2f4ba8b4a27ec6a"},"schema_version":"1.0"},"canonical_sha256":"9e014538180a469bac29bc9b97da3383cd06fbdaf8a6253f056fd67b280514e0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:24:39.900424Z","signature_b64":"ScwoEhmSdG+Z8ll71609/cIi//j8uwX+dVw5h4Lsl2vmzlr7dXk8atsd2yUsn2DpJQYhos25ZKdi5g6vu2XQCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9e014538180a469bac29bc9b97da3383cd06fbdaf8a6253f056fd67b280514e0","last_reissued_at":"2026-07-05T00:24:39.899934Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:24:39.899934Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1907.12374","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T00:24:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"15XJ2qUq/NAd/odL6o/19Z+v9aNoK7f7KtZEvVV/PNBw6LAtLVHJZGf2vGoSq7qayEOuYbsfy3l0xe6pTdbWCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T09:32:20.426784Z"},"content_sha256":"90856af7f5877e66ea482023f9eb9c4b3ca65c81d8c1e1e7aab0ae72edddd825","schema_version":"1.0","event_id":"sha256:90856af7f5877e66ea482023f9eb9c4b3ca65c81d8c1e1e7aab0ae72edddd825"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:TYAUKOAYBJDJXLBJXSNZPWRTQP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Topic Modeling with Wasserstein Autoencoders","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.IR","authors_text":"Bing Xiang, Feng Nan, Ramesh Nallapati, Ran Ding","submitted_at":"2019-07-24T14:08:23Z","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 "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.12374","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1907.12374/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T00:24:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jMOVwxpb93YkL7pHTNnIYDHFGQoTk2ppJFerMTQjbvS2WNth3oqFP83GZuew6ePVucAomk4Y0I4CI60yOeOtBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T09:32:20.427280Z"},"content_sha256":"40f5001ecc1573d8ed5de0902ce2306214cbaf4c3153c3e50a46bbb60c9706f6","schema_version":"1.0","event_id":"sha256:40f5001ecc1573d8ed5de0902ce2306214cbaf4c3153c3e50a46bbb60c9706f6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TYAUKOAYBJDJXLBJXSNZPWRTQP/bundle.json","state_url":"https://pith.science/pith/TYAUKOAYBJDJXLBJXSNZPWRTQP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TYAUKOAYBJDJXLBJXSNZPWRTQP/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-08T09:32:20Z","links":{"resolver":"https://pith.science/pith/TYAUKOAYBJDJXLBJXSNZPWRTQP","bundle":"https://pith.science/pith/TYAUKOAYBJDJXLBJXSNZPWRTQP/bundle.json","state":"https://pith.science/pith/TYAUKOAYBJDJXLBJXSNZPWRTQP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TYAUKOAYBJDJXLBJXSNZPWRTQP/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7xy25WhKSaemg1fxevQCincYQowT/nhHxpav8Bj07sZprrlIlCFpvHsjL0lnzsvRfve0ShCpwIfuHSCa+tN2BA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T09:32:20.432231Z","bundle_sha256":"c0b911725562d45870fd01f035d24927e678c5d7b7ace776c11b5d578d57e5fe"}}