{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:NCQKC2GM3DDBKF4ZF7AQBZAJEP","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":"bb4d0369f8370c84a5ff4793ca099be10362b7b34e8f36c7380a339058673d8c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-04-01T16:10:36Z","title_canon_sha256":"40663a4111f064f81332d4ee4beab8ed0f4a8934655abed2851ebecb3fd7ae14"},"schema_version":"1.0","source":{"id":"2304.00350","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.00350","created_at":"2026-07-05T05:57:01Z"},{"alias_kind":"arxiv_version","alias_value":"2304.00350v1","created_at":"2026-07-05T05:57:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.00350","created_at":"2026-07-05T05:57:01Z"},{"alias_kind":"pith_short_12","alias_value":"NCQKC2GM3DDB","created_at":"2026-07-05T05:57:01Z"},{"alias_kind":"pith_short_16","alias_value":"NCQKC2GM3DDBKF4Z","created_at":"2026-07-05T05:57:01Z"},{"alias_kind":"pith_short_8","alias_value":"NCQKC2GM","created_at":"2026-07-05T05:57:01Z"}],"graph_snapshots":[{"event_id":"sha256:4263e0d5a7ad87249a80c9f7dd2e55ab42a550510e0b92acdd1d3d9bd7c8836b","target":"graph","created_at":"2026-07-05T05:57:01Z","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/2304.00350/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Jihwan Kim, Moosung Kim, Nam Soo Kim, Sangah Park, Seoyeon Bae, Sowon Hahn, Won Ik Cho, Yoon Kyung Lee","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-04-01T16:10:36Z","title":"When Crowd Meets Persona: Creating a Large-Scale Open-Domain Persona Dialogue Corpus"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.00350","kind":"arxiv","version":1},"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":"sha256:7fffba5974665654ecce1985690f86c16f03cedb611c0f01d91e5408bb8f8621","target":"record","created_at":"2026-07-05T05:57:01Z","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":"bb4d0369f8370c84a5ff4793ca099be10362b7b34e8f36c7380a339058673d8c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-04-01T16:10:36Z","title_canon_sha256":"40663a4111f064f81332d4ee4beab8ed0f4a8934655abed2851ebecb3fd7ae14"},"schema_version":"1.0","source":{"id":"2304.00350","kind":"arxiv","version":1}},"canonical_sha256":"68a0a168ccd8c61517992fc100e40923fea18b4d9f800006033847fbd3a8a004","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"68a0a168ccd8c61517992fc100e40923fea18b4d9f800006033847fbd3a8a004","first_computed_at":"2026-07-05T05:57:01.434908Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:57:01.434908Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"H8nwFdIt/R9JOTRbmdrWk1KQSjp6LMOGQ3CVzGK2yAL7WkOySrAeJEjlJ6fejOUSbGmICYMe5TFgay70enEUAw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:57:01.435254Z","signed_message":"canonical_sha256_bytes"},"source_id":"2304.00350","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7fffba5974665654ecce1985690f86c16f03cedb611c0f01d91e5408bb8f8621","sha256:4263e0d5a7ad87249a80c9f7dd2e55ab42a550510e0b92acdd1d3d9bd7c8836b"],"state_sha256":"f475ca1c1c49bde4491ed8777b6c79690e494a99ebc3e44dd6679d5a2fd7cb6a"}