{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:STZVQG5BHD5DLTIDIBBSUMM7CY","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"d9f172812110b253ac028d215234e904b56f49f94cc9a27c3e8eef40d8239cba","cross_cats_sorted":["cs.HC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-12T07:49:06Z","title_canon_sha256":"0f5823cab9d7f949731c089073683e531f0a212adf986f2fc65ce2b82a576c2c"},"schema_version":"1.0","source":{"id":"2412.09034","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.09034","created_at":"2026-07-05T10:16:59Z"},{"alias_kind":"arxiv_version","alias_value":"2412.09034v2","created_at":"2026-07-05T10:16:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.09034","created_at":"2026-07-05T10:16:59Z"},{"alias_kind":"pith_short_12","alias_value":"STZVQG5BHD5D","created_at":"2026-07-05T10:16:59Z"},{"alias_kind":"pith_short_16","alias_value":"STZVQG5BHD5DLTID","created_at":"2026-07-05T10:16:59Z"},{"alias_kind":"pith_short_8","alias_value":"STZVQG5B","created_at":"2026-07-05T10:16:59Z"}],"graph_snapshots":[{"event_id":"sha256:d307bc8d4fabfe4d43812fbd16813d4b7d7afdc4ee92e4dddb852e8caf408df6","target":"graph","created_at":"2026-07-05T10:16:59Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2412.09034/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Chaotao Chen, Chen Jason Zhang, Di Jiang, Mengze Hong, Rongzhong Lian","cross_cats":["cs.HC"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-12T07:49:06Z","title":"Dialogue Language Model with Large-Scale Persona Data Engineering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.09034","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:cef98302ebbc2617c0c342b126022545a4b1c3658db5d9669f71afceff754c99","target":"record","created_at":"2026-07-05T10:16:59Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"d9f172812110b253ac028d215234e904b56f49f94cc9a27c3e8eef40d8239cba","cross_cats_sorted":["cs.HC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-12T07:49:06Z","title_canon_sha256":"0f5823cab9d7f949731c089073683e531f0a212adf986f2fc65ce2b82a576c2c"},"schema_version":"1.0","source":{"id":"2412.09034","kind":"arxiv","version":2}},"canonical_sha256":"94f3581ba138fa35cd0340432a319f1601c813577e37a93d987fde848329c3a2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"94f3581ba138fa35cd0340432a319f1601c813577e37a93d987fde848329c3a2","first_computed_at":"2026-07-05T10:16:59.503304Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:16:59.503304Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RuWznJaY96kMdaeWyvQq3gvU+zETkLHkPL37qtyOw0xCEkCMpnw+bGphy2GnR7GeTQdg1rc5JpdeOLQhvUH+Cw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:16:59.503785Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.09034","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cef98302ebbc2617c0c342b126022545a4b1c3658db5d9669f71afceff754c99","sha256:d307bc8d4fabfe4d43812fbd16813d4b7d7afdc4ee92e4dddb852e8caf408df6"],"state_sha256":"3bbe80e681097b1ad3ad024d612c717adae3be93886976e4cd822c4495c7b63e"}