{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:X33ZOZI35WRXHLUDKT2PECRGGX","short_pith_number":"pith:X33ZOZI3","schema_version":"1.0","canonical_sha256":"bef797651beda373ae8354f4f20a2635cf02533cda1e86fca440d30e55f18776","source":{"kind":"arxiv","id":"2305.15025","version":2},"attestation_state":"computed","paper":{"title":"Dior-CVAE: Pre-trained Language Models and Diffusion Priors for Variational Dialog Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Iryna Gurevych, Thy Thy Tran, Tianyu Yang","submitted_at":"2023-05-24T11:06:52Z","abstract_excerpt":"Current variational dialog models have employed pre-trained language models (PLMs) to parameterize the likelihood and posterior distributions. However, the Gaussian assumption made on the prior distribution is incompatible with these distributions, thus restricting the diversity of generated responses. These models also suffer from posterior collapse, i.e., the decoder tends to ignore latent variables and directly access information captured in the encoder through the cross-attention mechanism. In this work, we propose Dior-CVAE, a hierarchical conditional variational autoencoder (CVAE) with d"},"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":"2305.15025","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-24T11:06:52Z","cross_cats_sorted":[],"title_canon_sha256":"26fc35c6545b05c8ef80074100210001d10e389a2f603065b26f306b9c3ebedf","abstract_canon_sha256":"4b8f74839389ea1b1944403c32779612b4eb81bb4f257f4c6b4bebb3c0286678"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:04:16.436907Z","signature_b64":"1pi3RnqHRjSEpoelXNdNOLs4D42OWg64P7uZ/qlvgR/UDuIb1b5s5VKqphNqx69K0WjXU10kVzTiyOHmrtE7BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bef797651beda373ae8354f4f20a2635cf02533cda1e86fca440d30e55f18776","last_reissued_at":"2026-07-05T07:04:16.436493Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:04:16.436493Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dior-CVAE: Pre-trained Language Models and Diffusion Priors for Variational Dialog Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Iryna Gurevych, Thy Thy Tran, Tianyu Yang","submitted_at":"2023-05-24T11:06:52Z","abstract_excerpt":"Current variational dialog models have employed pre-trained language models (PLMs) to parameterize the likelihood and posterior distributions. However, the Gaussian assumption made on the prior distribution is incompatible with these distributions, thus restricting the diversity of generated responses. These models also suffer from posterior collapse, i.e., the decoder tends to ignore latent variables and directly access information captured in the encoder through the cross-attention mechanism. In this work, we propose Dior-CVAE, a hierarchical conditional variational autoencoder (CVAE) with d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.15025","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/2305.15025/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":"2305.15025","created_at":"2026-07-05T07:04:16.436547+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.15025v2","created_at":"2026-07-05T07:04:16.436547+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.15025","created_at":"2026-07-05T07:04:16.436547+00:00"},{"alias_kind":"pith_short_12","alias_value":"X33ZOZI35WRX","created_at":"2026-07-05T07:04:16.436547+00:00"},{"alias_kind":"pith_short_16","alias_value":"X33ZOZI35WRXHLUD","created_at":"2026-07-05T07:04:16.436547+00:00"},{"alias_kind":"pith_short_8","alias_value":"X33ZOZI3","created_at":"2026-07-05T07:04:16.436547+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/X33ZOZI35WRXHLUDKT2PECRGGX","json":"https://pith.science/pith/X33ZOZI35WRXHLUDKT2PECRGGX.json","graph_json":"https://pith.science/api/pith-number/X33ZOZI35WRXHLUDKT2PECRGGX/graph.json","events_json":"https://pith.science/api/pith-number/X33ZOZI35WRXHLUDKT2PECRGGX/events.json","paper":"https://pith.science/paper/X33ZOZI3"},"agent_actions":{"view_html":"https://pith.science/pith/X33ZOZI35WRXHLUDKT2PECRGGX","download_json":"https://pith.science/pith/X33ZOZI35WRXHLUDKT2PECRGGX.json","view_paper":"https://pith.science/paper/X33ZOZI3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.15025&json=true","fetch_graph":"https://pith.science/api/pith-number/X33ZOZI35WRXHLUDKT2PECRGGX/graph.json","fetch_events":"https://pith.science/api/pith-number/X33ZOZI35WRXHLUDKT2PECRGGX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/X33ZOZI35WRXHLUDKT2PECRGGX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/X33ZOZI35WRXHLUDKT2PECRGGX/action/storage_attestation","attest_author":"https://pith.science/pith/X33ZOZI35WRXHLUDKT2PECRGGX/action/author_attestation","sign_citation":"https://pith.science/pith/X33ZOZI35WRXHLUDKT2PECRGGX/action/citation_signature","submit_replication":"https://pith.science/pith/X33ZOZI35WRXHLUDKT2PECRGGX/action/replication_record"}},"created_at":"2026-07-05T07:04:16.436547+00:00","updated_at":"2026-07-05T07:04:16.436547+00:00"}