{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:6WR2LY5IVL5JXUK4FZD2HRK232","short_pith_number":"pith:6WR2LY5I","schema_version":"1.0","canonical_sha256":"f5a3a5e3a8aafa9bd15c2e47a3c55adea4a462efc921767f819fc3e2f9475eac","source":{"kind":"arxiv","id":"1703.10960","version":3},"attestation_state":"computed","paper":{"title":"Learning Discourse-level Diversity for Neural Dialog Models using Conditional Variational Autoencoders","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Maxine Eskenazi, Ran Zhao, Tiancheng Zhao","submitted_at":"2017-03-31T15:55:00Z","abstract_excerpt":"While recent neural encoder-decoder models have shown great promise in modeling open-domain conversations, they often generate dull and generic responses. Unlike past work that has focused on diversifying the output of the decoder at word-level to alleviate this problem, we present a novel framework based on conditional variational autoencoders that captures the discourse-level diversity in the encoder. Our model uses latent variables to learn a distribution over potential conversational intents and generates diverse responses using only greedy decoders. We have further developed a novel varia"},"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":"1703.10960","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-03-31T15:55:00Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3a4f68e4328af009d0ef10870dab6a45c68c54c6512f04cb07e05929e507078a","abstract_canon_sha256":"f49e49f2deceb166ab8de401507ea5dabab054b78a8ade93a103712ee289eff1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:32:20.696102Z","signature_b64":"eZnJhcD3zJS7vWZsyKpw3UvpTH4fnWc27I3mGrZU7OFgZECNtZqLGai8ShUv87pi9KR+CRzlfm7OIwlnJNrvAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f5a3a5e3a8aafa9bd15c2e47a3c55adea4a462efc921767f819fc3e2f9475eac","last_reissued_at":"2026-05-18T00:32:20.695534Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:32:20.695534Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Discourse-level Diversity for Neural Dialog Models using Conditional Variational Autoencoders","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Maxine Eskenazi, Ran Zhao, Tiancheng Zhao","submitted_at":"2017-03-31T15:55:00Z","abstract_excerpt":"While recent neural encoder-decoder models have shown great promise in modeling open-domain conversations, they often generate dull and generic responses. Unlike past work that has focused on diversifying the output of the decoder at word-level to alleviate this problem, we present a novel framework based on conditional variational autoencoders that captures the discourse-level diversity in the encoder. Our model uses latent variables to learn a distribution over potential conversational intents and generates diverse responses using only greedy decoders. We have further developed a novel varia"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.10960","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1703.10960","created_at":"2026-05-18T00:32:20.695604+00:00"},{"alias_kind":"arxiv_version","alias_value":"1703.10960v3","created_at":"2026-05-18T00:32:20.695604+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.10960","created_at":"2026-05-18T00:32:20.695604+00:00"},{"alias_kind":"pith_short_12","alias_value":"6WR2LY5IVL5J","created_at":"2026-05-18T12:31:03.183658+00:00"},{"alias_kind":"pith_short_16","alias_value":"6WR2LY5IVL5JXUK4","created_at":"2026-05-18T12:31:03.183658+00:00"},{"alias_kind":"pith_short_8","alias_value":"6WR2LY5I","created_at":"2026-05-18T12:31:03.183658+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":18,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6WR2LY5IVL5JXUK4FZD2HRK232","json":"https://pith.science/pith/6WR2LY5IVL5JXUK4FZD2HRK232.json","graph_json":"https://pith.science/api/pith-number/6WR2LY5IVL5JXUK4FZD2HRK232/graph.json","events_json":"https://pith.science/api/pith-number/6WR2LY5IVL5JXUK4FZD2HRK232/events.json","paper":"https://pith.science/paper/6WR2LY5I"},"agent_actions":{"view_html":"https://pith.science/pith/6WR2LY5IVL5JXUK4FZD2HRK232","download_json":"https://pith.science/pith/6WR2LY5IVL5JXUK4FZD2HRK232.json","view_paper":"https://pith.science/paper/6WR2LY5I","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1703.10960&json=true","fetch_graph":"https://pith.science/api/pith-number/6WR2LY5IVL5JXUK4FZD2HRK232/graph.json","fetch_events":"https://pith.science/api/pith-number/6WR2LY5IVL5JXUK4FZD2HRK232/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6WR2LY5IVL5JXUK4FZD2HRK232/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6WR2LY5IVL5JXUK4FZD2HRK232/action/storage_attestation","attest_author":"https://pith.science/pith/6WR2LY5IVL5JXUK4FZD2HRK232/action/author_attestation","sign_citation":"https://pith.science/pith/6WR2LY5IVL5JXUK4FZD2HRK232/action/citation_signature","submit_replication":"https://pith.science/pith/6WR2LY5IVL5JXUK4FZD2HRK232/action/replication_record"}},"created_at":"2026-05-18T00:32:20.695604+00:00","updated_at":"2026-05-18T00:32:20.695604+00:00"}