{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:WDQDC63AFIQT2MY56A3DW2BGH5","short_pith_number":"pith:WDQDC63A","schema_version":"1.0","canonical_sha256":"b0e0317b602a213d331df0363b68263f551997f562ccbf6cb022c15d0cbee136","source":{"kind":"arxiv","id":"1802.02032","version":1},"attestation_state":"computed","paper":{"title":"Improving Variational Encoder-Decoders in Dialogue Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Hui Su, Shuzi Niu, Vera Demberg, Xiaoyu Shen","submitted_at":"2018-02-06T16:19:05Z","abstract_excerpt":"Variational encoder-decoders (VEDs) have shown promising results in dialogue generation. However, the latent variable distributions are usually approximated by a much simpler model than the powerful RNN structure used for encoding and decoding, yielding the KL-vanishing problem and inconsistent training objective. In this paper, we separate the training step into two phases: The first phase learns to autoencode discrete texts into continuous embeddings, from which the second phase learns to generalize latent representations by reconstructing the encoded embedding. In this case, latent variable"},"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":"1802.02032","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-02-06T16:19:05Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"886abc0b38ecaa9511715c5716b91cd37b66873758fbc6e9240c8e9a42292d4a","abstract_canon_sha256":"1ed47187a8705b7cc57d43003bce45a86f879a6070378093af81b0b22dce3cd0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:24:11.127277Z","signature_b64":"RRvyBijS1JaHjI13NOSMc/FXiUN6fM9AxyOYigJECtHWio8xFKZVgFMVrZ5oNN8bxvB557H7P8ebEHpEY9yWBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b0e0317b602a213d331df0363b68263f551997f562ccbf6cb022c15d0cbee136","last_reissued_at":"2026-05-18T00:24:11.126555Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:24:11.126555Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improving Variational Encoder-Decoders in Dialogue Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Hui Su, Shuzi Niu, Vera Demberg, Xiaoyu Shen","submitted_at":"2018-02-06T16:19:05Z","abstract_excerpt":"Variational encoder-decoders (VEDs) have shown promising results in dialogue generation. However, the latent variable distributions are usually approximated by a much simpler model than the powerful RNN structure used for encoding and decoding, yielding the KL-vanishing problem and inconsistent training objective. In this paper, we separate the training step into two phases: The first phase learns to autoencode discrete texts into continuous embeddings, from which the second phase learns to generalize latent representations by reconstructing the encoded embedding. In this case, latent variable"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.02032","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":""},"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":"1802.02032","created_at":"2026-05-18T00:24:11.126697+00:00"},{"alias_kind":"arxiv_version","alias_value":"1802.02032v1","created_at":"2026-05-18T00:24:11.126697+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.02032","created_at":"2026-05-18T00:24:11.126697+00:00"},{"alias_kind":"pith_short_12","alias_value":"WDQDC63AFIQT","created_at":"2026-05-18T12:32:59.047623+00:00"},{"alias_kind":"pith_short_16","alias_value":"WDQDC63AFIQT2MY5","created_at":"2026-05-18T12:32:59.047623+00:00"},{"alias_kind":"pith_short_8","alias_value":"WDQDC63A","created_at":"2026-05-18T12:32:59.047623+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/WDQDC63AFIQT2MY56A3DW2BGH5","json":"https://pith.science/pith/WDQDC63AFIQT2MY56A3DW2BGH5.json","graph_json":"https://pith.science/api/pith-number/WDQDC63AFIQT2MY56A3DW2BGH5/graph.json","events_json":"https://pith.science/api/pith-number/WDQDC63AFIQT2MY56A3DW2BGH5/events.json","paper":"https://pith.science/paper/WDQDC63A"},"agent_actions":{"view_html":"https://pith.science/pith/WDQDC63AFIQT2MY56A3DW2BGH5","download_json":"https://pith.science/pith/WDQDC63AFIQT2MY56A3DW2BGH5.json","view_paper":"https://pith.science/paper/WDQDC63A","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1802.02032&json=true","fetch_graph":"https://pith.science/api/pith-number/WDQDC63AFIQT2MY56A3DW2BGH5/graph.json","fetch_events":"https://pith.science/api/pith-number/WDQDC63AFIQT2MY56A3DW2BGH5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WDQDC63AFIQT2MY56A3DW2BGH5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WDQDC63AFIQT2MY56A3DW2BGH5/action/storage_attestation","attest_author":"https://pith.science/pith/WDQDC63AFIQT2MY56A3DW2BGH5/action/author_attestation","sign_citation":"https://pith.science/pith/WDQDC63AFIQT2MY56A3DW2BGH5/action/citation_signature","submit_replication":"https://pith.science/pith/WDQDC63AFIQT2MY56A3DW2BGH5/action/replication_record"}},"created_at":"2026-05-18T00:24:11.126697+00:00","updated_at":"2026-05-18T00:24:11.126697+00:00"}