{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:NCQKC2GM3DDBKF4ZF7AQBZAJEP","short_pith_number":"pith:NCQKC2GM","schema_version":"1.0","canonical_sha256":"68a0a168ccd8c61517992fc100e40923fea18b4d9f800006033847fbd3a8a004","source":{"kind":"arxiv","id":"2304.00350","version":1},"attestation_state":"computed","paper":{"title":"When Crowd Meets Persona: Creating a Large-Scale Open-Domain Persona Dialogue Corpus","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jihwan Kim, Moosung Kim, Nam Soo Kim, Sangah Park, Seoyeon Bae, Sowon Hahn, Won Ik Cho, Yoon Kyung Lee","submitted_at":"2023-04-01T16:10:36Z","abstract_excerpt":"Building a natural language dataset requires caution since word semantics is vulnerable to subtle text change or the definition of the annotated concept. Such a tendency can be seen in generative tasks like question-answering and dialogue generation and also in tasks that create a categorization-based corpus, like topic classification or sentiment analysis. Open-domain conversations involve two or more crowdworkers freely conversing about any topic, and collecting such data is particularly difficult for two reasons: 1) the dataset should be ``crafted\" rather than ``obtained\" due to privacy con"},"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":"2304.00350","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-04-01T16:10:36Z","cross_cats_sorted":[],"title_canon_sha256":"40663a4111f064f81332d4ee4beab8ed0f4a8934655abed2851ebecb3fd7ae14","abstract_canon_sha256":"bb4d0369f8370c84a5ff4793ca099be10362b7b34e8f36c7380a339058673d8c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:57:01.435254Z","signature_b64":"H8nwFdIt/R9JOTRbmdrWk1KQSjp6LMOGQ3CVzGK2yAL7WkOySrAeJEjlJ6fejOUSbGmICYMe5TFgay70enEUAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"68a0a168ccd8c61517992fc100e40923fea18b4d9f800006033847fbd3a8a004","last_reissued_at":"2026-07-05T05:57:01.434908Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:57:01.434908Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"When Crowd Meets Persona: Creating a Large-Scale Open-Domain Persona Dialogue Corpus","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jihwan Kim, Moosung Kim, Nam Soo Kim, Sangah Park, Seoyeon Bae, Sowon Hahn, Won Ik Cho, Yoon Kyung Lee","submitted_at":"2023-04-01T16:10:36Z","abstract_excerpt":"Building a natural language dataset requires caution since word semantics is vulnerable to subtle text change or the definition of the annotated concept. Such a tendency can be seen in generative tasks like question-answering and dialogue generation and also in tasks that create a categorization-based corpus, like topic classification or sentiment analysis. Open-domain conversations involve two or more crowdworkers freely conversing about any topic, and collecting such data is particularly difficult for two reasons: 1) the dataset should be ``crafted\" rather than ``obtained\" due to privacy con"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.00350","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/2304.00350/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":"2304.00350","created_at":"2026-07-05T05:57:01.434973+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.00350v1","created_at":"2026-07-05T05:57:01.434973+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.00350","created_at":"2026-07-05T05:57:01.434973+00:00"},{"alias_kind":"pith_short_12","alias_value":"NCQKC2GM3DDB","created_at":"2026-07-05T05:57:01.434973+00:00"},{"alias_kind":"pith_short_16","alias_value":"NCQKC2GM3DDBKF4Z","created_at":"2026-07-05T05:57:01.434973+00:00"},{"alias_kind":"pith_short_8","alias_value":"NCQKC2GM","created_at":"2026-07-05T05:57:01.434973+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NCQKC2GM3DDBKF4ZF7AQBZAJEP","json":"https://pith.science/pith/NCQKC2GM3DDBKF4ZF7AQBZAJEP.json","graph_json":"https://pith.science/api/pith-number/NCQKC2GM3DDBKF4ZF7AQBZAJEP/graph.json","events_json":"https://pith.science/api/pith-number/NCQKC2GM3DDBKF4ZF7AQBZAJEP/events.json","paper":"https://pith.science/paper/NCQKC2GM"},"agent_actions":{"view_html":"https://pith.science/pith/NCQKC2GM3DDBKF4ZF7AQBZAJEP","download_json":"https://pith.science/pith/NCQKC2GM3DDBKF4ZF7AQBZAJEP.json","view_paper":"https://pith.science/paper/NCQKC2GM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.00350&json=true","fetch_graph":"https://pith.science/api/pith-number/NCQKC2GM3DDBKF4ZF7AQBZAJEP/graph.json","fetch_events":"https://pith.science/api/pith-number/NCQKC2GM3DDBKF4ZF7AQBZAJEP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NCQKC2GM3DDBKF4ZF7AQBZAJEP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NCQKC2GM3DDBKF4ZF7AQBZAJEP/action/storage_attestation","attest_author":"https://pith.science/pith/NCQKC2GM3DDBKF4ZF7AQBZAJEP/action/author_attestation","sign_citation":"https://pith.science/pith/NCQKC2GM3DDBKF4ZF7AQBZAJEP/action/citation_signature","submit_replication":"https://pith.science/pith/NCQKC2GM3DDBKF4ZF7AQBZAJEP/action/replication_record"}},"created_at":"2026-07-05T05:57:01.434973+00:00","updated_at":"2026-07-05T05:57:01.434973+00:00"}