{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:STZVQG5BHD5DLTIDIBBSUMM7CY","short_pith_number":"pith:STZVQG5B","schema_version":"1.0","canonical_sha256":"94f3581ba138fa35cd0340432a319f1601c813577e37a93d987fde848329c3a2","source":{"kind":"arxiv","id":"2412.09034","version":2},"attestation_state":"computed","paper":{"title":"Dialogue Language Model with Large-Scale Persona Data Engineering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.HC"],"primary_cat":"cs.CL","authors_text":"Chaotao Chen, Chen Jason Zhang, Di Jiang, Mengze Hong, Rongzhong Lian","submitted_at":"2024-12-12T07:49:06Z","abstract_excerpt":"Maintaining persona consistency is paramount in the application of open-domain dialogue systems, as exemplified by models like ChatGPT. Despite significant advancements, the limited scale and diversity of current persona dialogue datasets remain challenges to achieving robust persona-consistent dialogue models. In this study, drawing inspiration from the success of large-scale pre-training, we introduce PPDS, an open-domain persona dialogue system that employs extensive generative pre-training on a persona dialogue dataset to enhance persona consistency. Specifically, we present a persona extr"},"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":"2412.09034","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-12T07:49:06Z","cross_cats_sorted":["cs.HC"],"title_canon_sha256":"0f5823cab9d7f949731c089073683e531f0a212adf986f2fc65ce2b82a576c2c","abstract_canon_sha256":"d9f172812110b253ac028d215234e904b56f49f94cc9a27c3e8eef40d8239cba"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:16:59.503785Z","signature_b64":"RuWznJaY96kMdaeWyvQq3gvU+zETkLHkPL37qtyOw0xCEkCMpnw+bGphy2GnR7GeTQdg1rc5JpdeOLQhvUH+Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"94f3581ba138fa35cd0340432a319f1601c813577e37a93d987fde848329c3a2","last_reissued_at":"2026-07-05T10:16:59.503304Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:16:59.503304Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dialogue Language Model with Large-Scale Persona Data Engineering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.HC"],"primary_cat":"cs.CL","authors_text":"Chaotao Chen, Chen Jason Zhang, Di Jiang, Mengze Hong, Rongzhong Lian","submitted_at":"2024-12-12T07:49:06Z","abstract_excerpt":"Maintaining persona consistency is paramount in the application of open-domain dialogue systems, as exemplified by models like ChatGPT. Despite significant advancements, the limited scale and diversity of current persona dialogue datasets remain challenges to achieving robust persona-consistent dialogue models. In this study, drawing inspiration from the success of large-scale pre-training, we introduce PPDS, an open-domain persona dialogue system that employs extensive generative pre-training on a persona dialogue dataset to enhance persona consistency. Specifically, we present a persona extr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.09034","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/2412.09034/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":"2412.09034","created_at":"2026-07-05T10:16:59.503362+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.09034v2","created_at":"2026-07-05T10:16:59.503362+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.09034","created_at":"2026-07-05T10:16:59.503362+00:00"},{"alias_kind":"pith_short_12","alias_value":"STZVQG5BHD5D","created_at":"2026-07-05T10:16:59.503362+00:00"},{"alias_kind":"pith_short_16","alias_value":"STZVQG5BHD5DLTID","created_at":"2026-07-05T10:16:59.503362+00:00"},{"alias_kind":"pith_short_8","alias_value":"STZVQG5B","created_at":"2026-07-05T10:16:59.503362+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.08498","citing_title":"Semantic-Augmented Latent Topic Modeling with LLM-in-the-Loop","ref_index":11,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/STZVQG5BHD5DLTIDIBBSUMM7CY","json":"https://pith.science/pith/STZVQG5BHD5DLTIDIBBSUMM7CY.json","graph_json":"https://pith.science/api/pith-number/STZVQG5BHD5DLTIDIBBSUMM7CY/graph.json","events_json":"https://pith.science/api/pith-number/STZVQG5BHD5DLTIDIBBSUMM7CY/events.json","paper":"https://pith.science/paper/STZVQG5B"},"agent_actions":{"view_html":"https://pith.science/pith/STZVQG5BHD5DLTIDIBBSUMM7CY","download_json":"https://pith.science/pith/STZVQG5BHD5DLTIDIBBSUMM7CY.json","view_paper":"https://pith.science/paper/STZVQG5B","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.09034&json=true","fetch_graph":"https://pith.science/api/pith-number/STZVQG5BHD5DLTIDIBBSUMM7CY/graph.json","fetch_events":"https://pith.science/api/pith-number/STZVQG5BHD5DLTIDIBBSUMM7CY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/STZVQG5BHD5DLTIDIBBSUMM7CY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/STZVQG5BHD5DLTIDIBBSUMM7CY/action/storage_attestation","attest_author":"https://pith.science/pith/STZVQG5BHD5DLTIDIBBSUMM7CY/action/author_attestation","sign_citation":"https://pith.science/pith/STZVQG5BHD5DLTIDIBBSUMM7CY/action/citation_signature","submit_replication":"https://pith.science/pith/STZVQG5BHD5DLTIDIBBSUMM7CY/action/replication_record"}},"created_at":"2026-07-05T10:16:59.503362+00:00","updated_at":"2026-07-05T10:16:59.503362+00:00"}