{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:IYF37MGSTLGRWYUVC6QWOLC2BR","short_pith_number":"pith:IYF37MGS","schema_version":"1.0","canonical_sha256":"460bbfb0d29acd1b629517a1672c5a0c4291d625ee9c65af87afc5f98307714a","source":{"kind":"arxiv","id":"1906.06719","version":4},"attestation_state":"computed","paper":{"title":"Dispersed Exponential Family Mixture VAEs for Interpretable Text Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","stat.ML"],"primary_cat":"cs.LG","authors_text":"Hao Zhou, Lei Li, Ning Miao, Wenxian Shi","submitted_at":"2019-06-16T15:41:07Z","abstract_excerpt":"Deep generative models are commonly used for generating images and text. Interpretability of these models is one important pursuit, other than the generation quality. Variational auto-encoder (VAE) with Gaussian distribution as prior has been successfully applied in text generation, but it is hard to interpret the meaning of the latent variable. To enhance the controllability and interpretability, one can replace the Gaussian prior with a mixture of Gaussian distributions (GM-VAE), whose mixture components could be related to hidden semantic aspects of data. In this paper, we generalize the pr"},"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":"1906.06719","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-16T15:41:07Z","cross_cats_sorted":["cs.CL","stat.ML"],"title_canon_sha256":"0787e42621e58ba340024fbf944520523e5d7d1aba872f3a1a7f30652470112c","abstract_canon_sha256":"cdcf50d995b9682e7e4753becc89a6d4a26d65d3d3c8f2ef74d29c82687e87e4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:28:48.421542Z","signature_b64":"uIWxRzL7YQIYEKcQ+IbBDxjVE6ZeVM1WNSFTQLqBXQUfdpP1oVP5E0exyD0dJtHIfVuYSeoVPJO5/PC5tffFBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"460bbfb0d29acd1b629517a1672c5a0c4291d625ee9c65af87afc5f98307714a","last_reissued_at":"2026-07-05T01:28:48.421010Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:28:48.421010Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dispersed Exponential Family Mixture VAEs for Interpretable Text Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","stat.ML"],"primary_cat":"cs.LG","authors_text":"Hao Zhou, Lei Li, Ning Miao, Wenxian Shi","submitted_at":"2019-06-16T15:41:07Z","abstract_excerpt":"Deep generative models are commonly used for generating images and text. Interpretability of these models is one important pursuit, other than the generation quality. Variational auto-encoder (VAE) with Gaussian distribution as prior has been successfully applied in text generation, but it is hard to interpret the meaning of the latent variable. To enhance the controllability and interpretability, one can replace the Gaussian prior with a mixture of Gaussian distributions (GM-VAE), whose mixture components could be related to hidden semantic aspects of data. In this paper, we generalize the pr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.06719","kind":"arxiv","version":4},"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/1906.06719/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":"1906.06719","created_at":"2026-07-05T01:28:48.421081+00:00"},{"alias_kind":"arxiv_version","alias_value":"1906.06719v4","created_at":"2026-07-05T01:28:48.421081+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.06719","created_at":"2026-07-05T01:28:48.421081+00:00"},{"alias_kind":"pith_short_12","alias_value":"IYF37MGSTLGR","created_at":"2026-07-05T01:28:48.421081+00:00"},{"alias_kind":"pith_short_16","alias_value":"IYF37MGSTLGRWYUV","created_at":"2026-07-05T01:28:48.421081+00:00"},{"alias_kind":"pith_short_8","alias_value":"IYF37MGS","created_at":"2026-07-05T01:28:48.421081+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"1910.03771","citing_title":"HuggingFace's Transformers: State-of-the-art Natural Language Processing","ref_index":136,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IYF37MGSTLGRWYUVC6QWOLC2BR","json":"https://pith.science/pith/IYF37MGSTLGRWYUVC6QWOLC2BR.json","graph_json":"https://pith.science/api/pith-number/IYF37MGSTLGRWYUVC6QWOLC2BR/graph.json","events_json":"https://pith.science/api/pith-number/IYF37MGSTLGRWYUVC6QWOLC2BR/events.json","paper":"https://pith.science/paper/IYF37MGS"},"agent_actions":{"view_html":"https://pith.science/pith/IYF37MGSTLGRWYUVC6QWOLC2BR","download_json":"https://pith.science/pith/IYF37MGSTLGRWYUVC6QWOLC2BR.json","view_paper":"https://pith.science/paper/IYF37MGS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1906.06719&json=true","fetch_graph":"https://pith.science/api/pith-number/IYF37MGSTLGRWYUVC6QWOLC2BR/graph.json","fetch_events":"https://pith.science/api/pith-number/IYF37MGSTLGRWYUVC6QWOLC2BR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IYF37MGSTLGRWYUVC6QWOLC2BR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IYF37MGSTLGRWYUVC6QWOLC2BR/action/storage_attestation","attest_author":"https://pith.science/pith/IYF37MGSTLGRWYUVC6QWOLC2BR/action/author_attestation","sign_citation":"https://pith.science/pith/IYF37MGSTLGRWYUVC6QWOLC2BR/action/citation_signature","submit_replication":"https://pith.science/pith/IYF37MGSTLGRWYUVC6QWOLC2BR/action/replication_record"}},"created_at":"2026-07-05T01:28:48.421081+00:00","updated_at":"2026-07-05T01:28:48.421081+00:00"}