{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:K4HTHSEGA5FIACXAAG3SG5BPGD","short_pith_number":"pith:K4HTHSEG","schema_version":"1.0","canonical_sha256":"570f33c886074a800ae001b723742f30f4e3a0181c9eea80977223d7bbb2d2d6","source":{"kind":"arxiv","id":"2310.18342","version":1},"attestation_state":"computed","paper":{"title":"MIRACLE: Towards Personalized Dialogue Generation with Latent-Space Multiple Personal Attribute Control","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Dangyang Chen, Jixiong Chen, Wei Wei, Xianling Mao, Xiaoye Qu, Zhenyi Lu","submitted_at":"2023-10-22T08:44:26Z","abstract_excerpt":"Personalized dialogue systems aim to endow the chatbot agent with more anthropomorphic traits for human-like interactions. Previous approaches have explored explicitly user profile modeling using text descriptions, implicit derivation of user embeddings, or utilizing handicraft prompts for ChatGPT-like models. However, textual personas are limited in describing multi-faceted attributes (\\emph{e.g.}, \\emph{language style, inner character nuances}), implicit embedding suffers from personality sparsity, and handicraft prompts lack fine-grained and stable controllability. Hence, these approaches m"},"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":"2310.18342","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-22T08:44:26Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b4315ad3a2de7c3e904685cce95a70ebf00d7c0517c5cc0e709b977a270cca12","abstract_canon_sha256":"399521863a4e9195f00d508d845322948f3d3488e6e82e443b817d5b38f55f57"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:06:06.895887Z","signature_b64":"CY3kSNh4PCIzW39JoqsH8rBWcg4kNogTLZN1QY22XFc2EF7Gg4cPcxrAcpKsPcsT9xz5kMHvQjTl2mVJ/l+EDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"570f33c886074a800ae001b723742f30f4e3a0181c9eea80977223d7bbb2d2d6","last_reissued_at":"2026-07-05T07:06:06.895377Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:06:06.895377Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MIRACLE: Towards Personalized Dialogue Generation with Latent-Space Multiple Personal Attribute Control","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Dangyang Chen, Jixiong Chen, Wei Wei, Xianling Mao, Xiaoye Qu, Zhenyi Lu","submitted_at":"2023-10-22T08:44:26Z","abstract_excerpt":"Personalized dialogue systems aim to endow the chatbot agent with more anthropomorphic traits for human-like interactions. Previous approaches have explored explicitly user profile modeling using text descriptions, implicit derivation of user embeddings, or utilizing handicraft prompts for ChatGPT-like models. However, textual personas are limited in describing multi-faceted attributes (\\emph{e.g.}, \\emph{language style, inner character nuances}), implicit embedding suffers from personality sparsity, and handicraft prompts lack fine-grained and stable controllability. Hence, these approaches m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.18342","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/2310.18342/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":"2310.18342","created_at":"2026-07-05T07:06:06.895441+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.18342v1","created_at":"2026-07-05T07:06:06.895441+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.18342","created_at":"2026-07-05T07:06:06.895441+00:00"},{"alias_kind":"pith_short_12","alias_value":"K4HTHSEGA5FI","created_at":"2026-07-05T07:06:06.895441+00:00"},{"alias_kind":"pith_short_16","alias_value":"K4HTHSEGA5FIACXA","created_at":"2026-07-05T07:06:06.895441+00:00"},{"alias_kind":"pith_short_8","alias_value":"K4HTHSEG","created_at":"2026-07-05T07:06:06.895441+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.24647","citing_title":"Know You Before You Speak: User-State Modeling for LLM Personalization in Multi-Turn Conversation","ref_index":19,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/K4HTHSEGA5FIACXAAG3SG5BPGD","json":"https://pith.science/pith/K4HTHSEGA5FIACXAAG3SG5BPGD.json","graph_json":"https://pith.science/api/pith-number/K4HTHSEGA5FIACXAAG3SG5BPGD/graph.json","events_json":"https://pith.science/api/pith-number/K4HTHSEGA5FIACXAAG3SG5BPGD/events.json","paper":"https://pith.science/paper/K4HTHSEG"},"agent_actions":{"view_html":"https://pith.science/pith/K4HTHSEGA5FIACXAAG3SG5BPGD","download_json":"https://pith.science/pith/K4HTHSEGA5FIACXAAG3SG5BPGD.json","view_paper":"https://pith.science/paper/K4HTHSEG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.18342&json=true","fetch_graph":"https://pith.science/api/pith-number/K4HTHSEGA5FIACXAAG3SG5BPGD/graph.json","fetch_events":"https://pith.science/api/pith-number/K4HTHSEGA5FIACXAAG3SG5BPGD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/K4HTHSEGA5FIACXAAG3SG5BPGD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/K4HTHSEGA5FIACXAAG3SG5BPGD/action/storage_attestation","attest_author":"https://pith.science/pith/K4HTHSEGA5FIACXAAG3SG5BPGD/action/author_attestation","sign_citation":"https://pith.science/pith/K4HTHSEGA5FIACXAAG3SG5BPGD/action/citation_signature","submit_replication":"https://pith.science/pith/K4HTHSEGA5FIACXAAG3SG5BPGD/action/replication_record"}},"created_at":"2026-07-05T07:06:06.895441+00:00","updated_at":"2026-07-05T07:06:06.895441+00:00"}