{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:HWAO567LE7KRXD6RLS4UZMB7CG","short_pith_number":"pith:HWAO567L","schema_version":"1.0","canonical_sha256":"3d80eefbeb27d51b8fd15cb94cb03f11a01a0c887efcfea5bf13c1ef09bd9301","source":{"kind":"arxiv","id":"1803.01328","version":2},"attestation_state":"computed","paper":{"title":"WHAI: Weibull Hybrid Autoencoding Inference for Deep Topic Modeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.AP","stat.CO"],"primary_cat":"stat.ML","authors_text":"Bo Chen, Dandan Guo, Hao Zhang, Mingyuan Zhou","submitted_at":"2018-03-04T09:53:59Z","abstract_excerpt":"To train an inference network jointly with a deep generative topic model, making it both scalable to big corpora and fast in out-of-sample prediction, we develop Weibull hybrid autoencoding inference (WHAI) for deep latent Dirichlet allocation, which infers posterior samples via a hybrid of stochastic-gradient MCMC and autoencoding variational Bayes. The generative network of WHAI has a hierarchy of gamma distributions, while the inference network of WHAI is a Weibull upward-downward variational autoencoder, which integrates a deterministic-upward deep neural network, and a stochastic-downward"},"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":"1803.01328","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-03-04T09:53:59Z","cross_cats_sorted":["stat.AP","stat.CO"],"title_canon_sha256":"0ec737c5add2656bfb05a8e777430c8ec2d6b3558d294264bce6c9bfd8f22416","abstract_canon_sha256":"119e4d8a5608f80a614be59f8784a6f6f101d41e7b4936493adf869eeb48fcd6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:58:00.562657Z","signature_b64":"4VKBy9QGa0z7jHhtraZfMuejkUJcLlRy0zGfEP84Ty04Bepl23McpsU3Uhzp7CuaRYX/7ZcmKczjilZaFLL5DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3d80eefbeb27d51b8fd15cb94cb03f11a01a0c887efcfea5bf13c1ef09bd9301","last_reissued_at":"2026-07-05T00:58:00.562156Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:58:00.562156Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"WHAI: Weibull Hybrid Autoencoding Inference for Deep Topic Modeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.AP","stat.CO"],"primary_cat":"stat.ML","authors_text":"Bo Chen, Dandan Guo, Hao Zhang, Mingyuan Zhou","submitted_at":"2018-03-04T09:53:59Z","abstract_excerpt":"To train an inference network jointly with a deep generative topic model, making it both scalable to big corpora and fast in out-of-sample prediction, we develop Weibull hybrid autoencoding inference (WHAI) for deep latent Dirichlet allocation, which infers posterior samples via a hybrid of stochastic-gradient MCMC and autoencoding variational Bayes. The generative network of WHAI has a hierarchy of gamma distributions, while the inference network of WHAI is a Weibull upward-downward variational autoencoder, which integrates a deterministic-upward deep neural network, and a stochastic-downward"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.01328","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/1803.01328/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1803.01328","created_at":"2026-07-05T00:58:00.562215+00:00"},{"alias_kind":"arxiv_version","alias_value":"1803.01328v2","created_at":"2026-07-05T00:58:00.562215+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.01328","created_at":"2026-07-05T00:58:00.562215+00:00"},{"alias_kind":"pith_short_12","alias_value":"HWAO567LE7KR","created_at":"2026-07-05T00:58:00.562215+00:00"},{"alias_kind":"pith_short_16","alias_value":"HWAO567LE7KRXD6R","created_at":"2026-07-05T00:58:00.562215+00:00"},{"alias_kind":"pith_short_8","alias_value":"HWAO567L","created_at":"2026-07-05T00:58:00.562215+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2408.13471","citing_title":"Disentangled Generative Graph Representation Learning","ref_index":8,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HWAO567LE7KRXD6RLS4UZMB7CG","json":"https://pith.science/pith/HWAO567LE7KRXD6RLS4UZMB7CG.json","graph_json":"https://pith.science/api/pith-number/HWAO567LE7KRXD6RLS4UZMB7CG/graph.json","events_json":"https://pith.science/api/pith-number/HWAO567LE7KRXD6RLS4UZMB7CG/events.json","paper":"https://pith.science/paper/HWAO567L"},"agent_actions":{"view_html":"https://pith.science/pith/HWAO567LE7KRXD6RLS4UZMB7CG","download_json":"https://pith.science/pith/HWAO567LE7KRXD6RLS4UZMB7CG.json","view_paper":"https://pith.science/paper/HWAO567L","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1803.01328&json=true","fetch_graph":"https://pith.science/api/pith-number/HWAO567LE7KRXD6RLS4UZMB7CG/graph.json","fetch_events":"https://pith.science/api/pith-number/HWAO567LE7KRXD6RLS4UZMB7CG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HWAO567LE7KRXD6RLS4UZMB7CG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HWAO567LE7KRXD6RLS4UZMB7CG/action/storage_attestation","attest_author":"https://pith.science/pith/HWAO567LE7KRXD6RLS4UZMB7CG/action/author_attestation","sign_citation":"https://pith.science/pith/HWAO567LE7KRXD6RLS4UZMB7CG/action/citation_signature","submit_replication":"https://pith.science/pith/HWAO567LE7KRXD6RLS4UZMB7CG/action/replication_record"}},"created_at":"2026-07-05T00:58:00.562215+00:00","updated_at":"2026-07-05T00:58:00.562215+00:00"}