{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:WOXFKTPS5JBHESJJYE76SBUE6D","short_pith_number":"pith:WOXFKTPS","schema_version":"1.0","canonical_sha256":"b3ae554df2ea42724929c13fe90684f0fd36b227a9785d4487a39cc859b2fdca","source":{"kind":"arxiv","id":"2306.01153","version":2},"attestation_state":"computed","paper":{"title":"Diverse and Faithful Knowledge-Grounded Dialogue Generation via Sequential Posterior Inference","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bo Pang, Dehong Xu, Deqian Kong, Pascale Fung, Yan Xu, Ying Nian Wu, Ziwei Ji","submitted_at":"2023-06-01T21:23:13Z","abstract_excerpt":"The capability to generate responses with diversity and faithfulness using factual knowledge is paramount for creating a human-like, trustworthy dialogue system. Common strategies either adopt a two-step paradigm, which optimizes knowledge selection and response generation separately, and may overlook the inherent correlation between these two tasks, or leverage conditional variational method to jointly optimize knowledge selection and response generation by employing an inference network. In this paper, we present an end-to-end learning framework, termed Sequential Posterior Inference (SPI), "},"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":"2306.01153","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-01T21:23:13Z","cross_cats_sorted":[],"title_canon_sha256":"0e291dd3a388d6164d285eebf380bf723230edae1f4477f5c36e5ae77828c3fd","abstract_canon_sha256":"31c276c1bc7041ea75b5541f342e827f372dd89aa0053222dacd1330502fad58"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:38:00.661678Z","signature_b64":"zS2ZvuhOKYyYZBXhvt3n3WMIZjx9FQrpyAtvmBwa+N8An6L9WXtSyZd3lZniYedZ5aeTllm0quqFkuE0yBjFCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b3ae554df2ea42724929c13fe90684f0fd36b227a9785d4487a39cc859b2fdca","last_reissued_at":"2026-07-05T06:38:00.661171Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:38:00.661171Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Diverse and Faithful Knowledge-Grounded Dialogue Generation via Sequential Posterior Inference","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bo Pang, Dehong Xu, Deqian Kong, Pascale Fung, Yan Xu, Ying Nian Wu, Ziwei Ji","submitted_at":"2023-06-01T21:23:13Z","abstract_excerpt":"The capability to generate responses with diversity and faithfulness using factual knowledge is paramount for creating a human-like, trustworthy dialogue system. Common strategies either adopt a two-step paradigm, which optimizes knowledge selection and response generation separately, and may overlook the inherent correlation between these two tasks, or leverage conditional variational method to jointly optimize knowledge selection and response generation by employing an inference network. In this paper, we present an end-to-end learning framework, termed Sequential Posterior Inference (SPI), "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.01153","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/2306.01153/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":"2306.01153","created_at":"2026-07-05T06:38:00.661233+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.01153v2","created_at":"2026-07-05T06:38:00.661233+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.01153","created_at":"2026-07-05T06:38:00.661233+00:00"},{"alias_kind":"pith_short_12","alias_value":"WOXFKTPS5JBH","created_at":"2026-07-05T06:38:00.661233+00:00"},{"alias_kind":"pith_short_16","alias_value":"WOXFKTPS5JBHESJJ","created_at":"2026-07-05T06:38:00.661233+00:00"},{"alias_kind":"pith_short_8","alias_value":"WOXFKTPS","created_at":"2026-07-05T06:38:00.661233+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.01567","citing_title":"Latent Thought Models with Variational Bayes Inference-Time Computation","ref_index":28,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WOXFKTPS5JBHESJJYE76SBUE6D","json":"https://pith.science/pith/WOXFKTPS5JBHESJJYE76SBUE6D.json","graph_json":"https://pith.science/api/pith-number/WOXFKTPS5JBHESJJYE76SBUE6D/graph.json","events_json":"https://pith.science/api/pith-number/WOXFKTPS5JBHESJJYE76SBUE6D/events.json","paper":"https://pith.science/paper/WOXFKTPS"},"agent_actions":{"view_html":"https://pith.science/pith/WOXFKTPS5JBHESJJYE76SBUE6D","download_json":"https://pith.science/pith/WOXFKTPS5JBHESJJYE76SBUE6D.json","view_paper":"https://pith.science/paper/WOXFKTPS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.01153&json=true","fetch_graph":"https://pith.science/api/pith-number/WOXFKTPS5JBHESJJYE76SBUE6D/graph.json","fetch_events":"https://pith.science/api/pith-number/WOXFKTPS5JBHESJJYE76SBUE6D/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WOXFKTPS5JBHESJJYE76SBUE6D/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WOXFKTPS5JBHESJJYE76SBUE6D/action/storage_attestation","attest_author":"https://pith.science/pith/WOXFKTPS5JBHESJJYE76SBUE6D/action/author_attestation","sign_citation":"https://pith.science/pith/WOXFKTPS5JBHESJJYE76SBUE6D/action/citation_signature","submit_replication":"https://pith.science/pith/WOXFKTPS5JBHESJJYE76SBUE6D/action/replication_record"}},"created_at":"2026-07-05T06:38:00.661233+00:00","updated_at":"2026-07-05T06:38:00.661233+00:00"}