{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:RTWPACCWCBKXN2QXF5OSDG77MP","short_pith_number":"pith:RTWPACCW","schema_version":"1.0","canonical_sha256":"8cecf00856105576ea172f5d219bff63f0e0e47bf7573e6c0c2b7be2e7f025b7","source":{"kind":"arxiv","id":"2211.06869","version":4},"attestation_state":"computed","paper":{"title":"Large Language Models Meet Harry Potter: A Bilingual Dataset for Aligning Dialogue Agents with Characters","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Deng Cai, Haiyun Jiang, Jia Li, Longyue Wang, Nuo Chen, Yan Wang, Yuhan Li, Ziyang Chen","submitted_at":"2022-11-13T10:16:39Z","abstract_excerpt":"In recent years, Dialogue-style Large Language Models (LLMs) such as ChatGPT and GPT4 have demonstrated immense potential in constructing open-domain dialogue agents. However, aligning these agents with specific characters or individuals remains a considerable challenge due to the complexities of character representation and the lack of comprehensive annotations. In this paper, we introduce the Harry Potter Dialogue (HPD) dataset, designed to advance the study of dialogue agents and character alignment. The dataset encompasses all dialogue sessions (in both English and Chinese) from the Harry "},"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":"2211.06869","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-11-13T10:16:39Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"02978ff494bf054df5c21c9ce22d031ed1faf9ab4cd80a23827ef1771153d865","abstract_canon_sha256":"647362bde87b5afb870c74b7083d84b11701d930cc6cfc8da806481577638eed"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:58:36.680602Z","signature_b64":"nm+3QGI/HM7m7CA59CuK5rqlFAKs7w1Hbl/Ja3gg0oyA/afx+LVdWPPV7A6aMXtgCG0cXE4yIyeYc1qTq3teCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8cecf00856105576ea172f5d219bff63f0e0e47bf7573e6c0c2b7be2e7f025b7","last_reissued_at":"2026-07-05T06:58:36.680092Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:58:36.680092Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Large Language Models Meet Harry Potter: A Bilingual Dataset for Aligning Dialogue Agents with Characters","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Deng Cai, Haiyun Jiang, Jia Li, Longyue Wang, Nuo Chen, Yan Wang, Yuhan Li, Ziyang Chen","submitted_at":"2022-11-13T10:16:39Z","abstract_excerpt":"In recent years, Dialogue-style Large Language Models (LLMs) such as ChatGPT and GPT4 have demonstrated immense potential in constructing open-domain dialogue agents. However, aligning these agents with specific characters or individuals remains a considerable challenge due to the complexities of character representation and the lack of comprehensive annotations. In this paper, we introduce the Harry Potter Dialogue (HPD) dataset, designed to advance the study of dialogue agents and character alignment. The dataset encompasses all dialogue sessions (in both English and Chinese) from the Harry "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.06869","kind":"arxiv","version":4},"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/2211.06869/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":"2211.06869","created_at":"2026-07-05T06:58:36.680154+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.06869v4","created_at":"2026-07-05T06:58:36.680154+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.06869","created_at":"2026-07-05T06:58:36.680154+00:00"},{"alias_kind":"pith_short_12","alias_value":"RTWPACCWCBKX","created_at":"2026-07-05T06:58:36.680154+00:00"},{"alias_kind":"pith_short_16","alias_value":"RTWPACCWCBKXN2QX","created_at":"2026-07-05T06:58:36.680154+00:00"},{"alias_kind":"pith_short_8","alias_value":"RTWPACCW","created_at":"2026-07-05T06:58:36.680154+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.11103","citing_title":"ActorMind: Emulating Human Actor Reasoning for Speech Role-Playing","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RTWPACCWCBKXN2QXF5OSDG77MP","json":"https://pith.science/pith/RTWPACCWCBKXN2QXF5OSDG77MP.json","graph_json":"https://pith.science/api/pith-number/RTWPACCWCBKXN2QXF5OSDG77MP/graph.json","events_json":"https://pith.science/api/pith-number/RTWPACCWCBKXN2QXF5OSDG77MP/events.json","paper":"https://pith.science/paper/RTWPACCW"},"agent_actions":{"view_html":"https://pith.science/pith/RTWPACCWCBKXN2QXF5OSDG77MP","download_json":"https://pith.science/pith/RTWPACCWCBKXN2QXF5OSDG77MP.json","view_paper":"https://pith.science/paper/RTWPACCW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.06869&json=true","fetch_graph":"https://pith.science/api/pith-number/RTWPACCWCBKXN2QXF5OSDG77MP/graph.json","fetch_events":"https://pith.science/api/pith-number/RTWPACCWCBKXN2QXF5OSDG77MP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RTWPACCWCBKXN2QXF5OSDG77MP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RTWPACCWCBKXN2QXF5OSDG77MP/action/storage_attestation","attest_author":"https://pith.science/pith/RTWPACCWCBKXN2QXF5OSDG77MP/action/author_attestation","sign_citation":"https://pith.science/pith/RTWPACCWCBKXN2QXF5OSDG77MP/action/citation_signature","submit_replication":"https://pith.science/pith/RTWPACCWCBKXN2QXF5OSDG77MP/action/replication_record"}},"created_at":"2026-07-05T06:58:36.680154+00:00","updated_at":"2026-07-05T06:58:36.680154+00:00"}