{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:HXMCEBCREX6CWBZQPZTLDK3TES","short_pith_number":"pith:HXMCEBCR","schema_version":"1.0","canonical_sha256":"3dd822045125fc2b07307e66b1ab7324badb3943535c9357359020f9e2bbb058","source":{"kind":"arxiv","id":"2210.12326","version":1},"attestation_state":"computed","paper":{"title":"Transformer-Based Conditioned Variational Autoencoder for Dialogue Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Huihui Yang","submitted_at":"2022-10-22T01:57:16Z","abstract_excerpt":"In human dialogue, a single query may elicit numerous appropriate responses. The Transformer-based dialogue model produces frequently occurring sentences in the corpus since it is a one-to-one mapping function. CVAE is a technique for reducing generic replies. In this paper, we create a new dialogue model (CVAE-T) based on the Transformer with CVAE structure. We use a pre-trained MLM model to rewrite some key n-grams in responses to obtain a series of negative examples, and introduce a regularization term during training to explicitly guide the latent variable in learning the semantic differen"},"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":"2210.12326","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-10-22T01:57:16Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"8c6ad6ac7c7a82caa61e66ea27008c87880f58f2e2afacd6f72d4c216d26a9e0","abstract_canon_sha256":"366c0202ecdcfd7d42b7946176212f1fbf94ea3c6b250354cc1e4644a2f10a53"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:09:26.674519Z","signature_b64":"olxPp1RAw7Itv/tQ4YS78SBZ9mF9O1k2hytEJMBQTVJuthKcPRppT2bmGJu0hYZrG4a/0s4BBylNq1gBZc+2AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3dd822045125fc2b07307e66b1ab7324badb3943535c9357359020f9e2bbb058","last_reissued_at":"2026-07-05T05:09:26.674099Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:09:26.674099Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Transformer-Based Conditioned Variational Autoencoder for Dialogue Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Huihui Yang","submitted_at":"2022-10-22T01:57:16Z","abstract_excerpt":"In human dialogue, a single query may elicit numerous appropriate responses. The Transformer-based dialogue model produces frequently occurring sentences in the corpus since it is a one-to-one mapping function. CVAE is a technique for reducing generic replies. In this paper, we create a new dialogue model (CVAE-T) based on the Transformer with CVAE structure. We use a pre-trained MLM model to rewrite some key n-grams in responses to obtain a series of negative examples, and introduce a regularization term during training to explicitly guide the latent variable in learning the semantic differen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.12326","kind":"arxiv","version":1},"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/2210.12326/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":"2210.12326","created_at":"2026-07-05T05:09:26.674166+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.12326v1","created_at":"2026-07-05T05:09:26.674166+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.12326","created_at":"2026-07-05T05:09:26.674166+00:00"},{"alias_kind":"pith_short_12","alias_value":"HXMCEBCREX6C","created_at":"2026-07-05T05:09:26.674166+00:00"},{"alias_kind":"pith_short_16","alias_value":"HXMCEBCREX6CWBZQ","created_at":"2026-07-05T05:09:26.674166+00:00"},{"alias_kind":"pith_short_8","alias_value":"HXMCEBCR","created_at":"2026-07-05T05:09:26.674166+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.09995","citing_title":"Annotations Mitigate Post-Training Mode Collapse","ref_index":21,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HXMCEBCREX6CWBZQPZTLDK3TES","json":"https://pith.science/pith/HXMCEBCREX6CWBZQPZTLDK3TES.json","graph_json":"https://pith.science/api/pith-number/HXMCEBCREX6CWBZQPZTLDK3TES/graph.json","events_json":"https://pith.science/api/pith-number/HXMCEBCREX6CWBZQPZTLDK3TES/events.json","paper":"https://pith.science/paper/HXMCEBCR"},"agent_actions":{"view_html":"https://pith.science/pith/HXMCEBCREX6CWBZQPZTLDK3TES","download_json":"https://pith.science/pith/HXMCEBCREX6CWBZQPZTLDK3TES.json","view_paper":"https://pith.science/paper/HXMCEBCR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.12326&json=true","fetch_graph":"https://pith.science/api/pith-number/HXMCEBCREX6CWBZQPZTLDK3TES/graph.json","fetch_events":"https://pith.science/api/pith-number/HXMCEBCREX6CWBZQPZTLDK3TES/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HXMCEBCREX6CWBZQPZTLDK3TES/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HXMCEBCREX6CWBZQPZTLDK3TES/action/storage_attestation","attest_author":"https://pith.science/pith/HXMCEBCREX6CWBZQPZTLDK3TES/action/author_attestation","sign_citation":"https://pith.science/pith/HXMCEBCREX6CWBZQPZTLDK3TES/action/citation_signature","submit_replication":"https://pith.science/pith/HXMCEBCREX6CWBZQPZTLDK3TES/action/replication_record"}},"created_at":"2026-07-05T05:09:26.674166+00:00","updated_at":"2026-07-05T05:09:26.674166+00:00"}