{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:2XXHJWWQE2NKY2XQP4TOLPP4RO","short_pith_number":"pith:2XXHJWWQ","schema_version":"1.0","canonical_sha256":"d5ee74dad0269aac6af07f26e5bdfc8bbbaec0f152f2e432f98e86f7617735bc","source":{"kind":"arxiv","id":"2305.11482","version":1},"attestation_state":"computed","paper":{"title":"Enhancing Personalized Dialogue Generation with Contrastive Latent Variables: Combining Sparse and Dense Persona","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bo Wang, Dongming Zhao, Kun Huang, Miao Fang, Ruifang He, Yihong Tang, Yuexian Hou","submitted_at":"2023-05-19T07:24:27Z","abstract_excerpt":"The personalized dialogue explores the consistent relationship between dialogue generation and personality. Existing personalized dialogue agents model persona profiles from three resources: sparse or dense persona descriptions and dialogue histories. However, sparse structured persona attributes are explicit but uninformative, dense persona texts contain rich persona descriptions with much noise, and dialogue history query is both noisy and uninformative for persona modeling. In this work, we combine the advantages of the three resources to obtain a richer and more accurate persona. We design"},"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":"2305.11482","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-19T07:24:27Z","cross_cats_sorted":[],"title_canon_sha256":"810b021812f7c7e3c55ed9be141ae695470c30cab72ced21b3f85011a15e867a","abstract_canon_sha256":"aad9a9e2afb1cdcbd2bcdfbe430c6b0a6f9b761a732ffa9526e73bd2d015dd32"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:11:47.549173Z","signature_b64":"wXu8pen5noCdD1Gsr1UMivbf3lIfz7ojd9Sqe+qrJvwtuMboKoJILWyC4bL8DxQ2FX0oDNl6PwDfjXH4zAT7AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d5ee74dad0269aac6af07f26e5bdfc8bbbaec0f152f2e432f98e86f7617735bc","last_reissued_at":"2026-07-05T06:11:47.548774Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:11:47.548774Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Enhancing Personalized Dialogue Generation with Contrastive Latent Variables: Combining Sparse and Dense Persona","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bo Wang, Dongming Zhao, Kun Huang, Miao Fang, Ruifang He, Yihong Tang, Yuexian Hou","submitted_at":"2023-05-19T07:24:27Z","abstract_excerpt":"The personalized dialogue explores the consistent relationship between dialogue generation and personality. Existing personalized dialogue agents model persona profiles from three resources: sparse or dense persona descriptions and dialogue histories. However, sparse structured persona attributes are explicit but uninformative, dense persona texts contain rich persona descriptions with much noise, and dialogue history query is both noisy and uninformative for persona modeling. In this work, we combine the advantages of the three resources to obtain a richer and more accurate persona. We design"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.11482","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/2305.11482/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":"2305.11482","created_at":"2026-07-05T06:11:47.548833+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.11482v1","created_at":"2026-07-05T06:11:47.548833+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.11482","created_at":"2026-07-05T06:11:47.548833+00:00"},{"alias_kind":"pith_short_12","alias_value":"2XXHJWWQE2NK","created_at":"2026-07-05T06:11:47.548833+00:00"},{"alias_kind":"pith_short_16","alias_value":"2XXHJWWQE2NKY2XQ","created_at":"2026-07-05T06:11:47.548833+00:00"},{"alias_kind":"pith_short_8","alias_value":"2XXHJWWQ","created_at":"2026-07-05T06:11:47.548833+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.08841","citing_title":"ZIPP:Zero-shot Image Personalization from Personas","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2605.24647","citing_title":"Know You Before You Speak: User-State Modeling for LLM Personalization in Multi-Turn Conversation","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10339","citing_title":"An Annotation Scheme and Classifier for Personal Facts in Dialogue","ref_index":31,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2XXHJWWQE2NKY2XQP4TOLPP4RO","json":"https://pith.science/pith/2XXHJWWQE2NKY2XQP4TOLPP4RO.json","graph_json":"https://pith.science/api/pith-number/2XXHJWWQE2NKY2XQP4TOLPP4RO/graph.json","events_json":"https://pith.science/api/pith-number/2XXHJWWQE2NKY2XQP4TOLPP4RO/events.json","paper":"https://pith.science/paper/2XXHJWWQ"},"agent_actions":{"view_html":"https://pith.science/pith/2XXHJWWQE2NKY2XQP4TOLPP4RO","download_json":"https://pith.science/pith/2XXHJWWQE2NKY2XQP4TOLPP4RO.json","view_paper":"https://pith.science/paper/2XXHJWWQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.11482&json=true","fetch_graph":"https://pith.science/api/pith-number/2XXHJWWQE2NKY2XQP4TOLPP4RO/graph.json","fetch_events":"https://pith.science/api/pith-number/2XXHJWWQE2NKY2XQP4TOLPP4RO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2XXHJWWQE2NKY2XQP4TOLPP4RO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2XXHJWWQE2NKY2XQP4TOLPP4RO/action/storage_attestation","attest_author":"https://pith.science/pith/2XXHJWWQE2NKY2XQP4TOLPP4RO/action/author_attestation","sign_citation":"https://pith.science/pith/2XXHJWWQE2NKY2XQP4TOLPP4RO/action/citation_signature","submit_replication":"https://pith.science/pith/2XXHJWWQE2NKY2XQP4TOLPP4RO/action/replication_record"}},"created_at":"2026-07-05T06:11:47.548833+00:00","updated_at":"2026-07-05T06:11:47.548833+00:00"}