{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:VIRIXHHNOYWXKE4H4SWPAIW56A","short_pith_number":"pith:VIRIXHHN","schema_version":"1.0","canonical_sha256":"aa228b9ced762d751387e4acf022ddf00d03c72dd532f9a5631ad93dd0e6f5dd","source":{"kind":"arxiv","id":"2503.20417","version":1},"attestation_state":"computed","paper":{"title":"CFunModel: A \"Funny\" Language Model Capable of Chinese Humor Generation and Processing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Xiaojun Wan, Xinyu Hu, Zhenghan Yu","submitted_at":"2025-03-26T10:44:51Z","abstract_excerpt":"Humor plays a significant role in daily language communication. With the rapid development of large language models (LLMs), natural language processing has made significant strides in understanding and generating various genres of texts. However, most LLMs exhibit poor performance in generating and processing Chinese humor. In this study, we introduce a comprehensive Chinese humor-related dataset, the Chinese Fun Set (CFunSet). This dataset aggregates existing Chinese humor datasets and includes over 20,000 jokes collected from Tieba-JokeBar, a Chinese online platform known for joke sharing. T"},"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":"2503.20417","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-03-26T10:44:51Z","cross_cats_sorted":[],"title_canon_sha256":"1503df88fc75329f6b1f10094fbe0ae4c8350e49b21e9887f0866801fb05b35d","abstract_canon_sha256":"2aefa666329e392186b1b293bbd8bb3d80aa5452330e849f489bf34ac5dd258e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:39:37.943982Z","signature_b64":"JkgYQ4L/teEb3wJpUt4iOal5IiiCdudcfAsMVwtmystp1+mAayJmtMWtOFoiYHtDUfXzt+Ubk+B+tjj92GkMAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aa228b9ced762d751387e4acf022ddf00d03c72dd532f9a5631ad93dd0e6f5dd","last_reissued_at":"2026-07-05T10:39:37.943438Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:39:37.943438Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CFunModel: A \"Funny\" Language Model Capable of Chinese Humor Generation and Processing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Xiaojun Wan, Xinyu Hu, Zhenghan Yu","submitted_at":"2025-03-26T10:44:51Z","abstract_excerpt":"Humor plays a significant role in daily language communication. With the rapid development of large language models (LLMs), natural language processing has made significant strides in understanding and generating various genres of texts. However, most LLMs exhibit poor performance in generating and processing Chinese humor. In this study, we introduce a comprehensive Chinese humor-related dataset, the Chinese Fun Set (CFunSet). This dataset aggregates existing Chinese humor datasets and includes over 20,000 jokes collected from Tieba-JokeBar, a Chinese online platform known for joke sharing. T"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.20417","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/2503.20417/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":"2503.20417","created_at":"2026-07-05T10:39:37.943501+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.20417v1","created_at":"2026-07-05T10:39:37.943501+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.20417","created_at":"2026-07-05T10:39:37.943501+00:00"},{"alias_kind":"pith_short_12","alias_value":"VIRIXHHNOYWX","created_at":"2026-07-05T10:39:37.943501+00:00"},{"alias_kind":"pith_short_16","alias_value":"VIRIXHHNOYWXKE4H","created_at":"2026-07-05T10:39:37.943501+00:00"},{"alias_kind":"pith_short_8","alias_value":"VIRIXHHN","created_at":"2026-07-05T10:39:37.943501+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/VIRIXHHNOYWXKE4H4SWPAIW56A","json":"https://pith.science/pith/VIRIXHHNOYWXKE4H4SWPAIW56A.json","graph_json":"https://pith.science/api/pith-number/VIRIXHHNOYWXKE4H4SWPAIW56A/graph.json","events_json":"https://pith.science/api/pith-number/VIRIXHHNOYWXKE4H4SWPAIW56A/events.json","paper":"https://pith.science/paper/VIRIXHHN"},"agent_actions":{"view_html":"https://pith.science/pith/VIRIXHHNOYWXKE4H4SWPAIW56A","download_json":"https://pith.science/pith/VIRIXHHNOYWXKE4H4SWPAIW56A.json","view_paper":"https://pith.science/paper/VIRIXHHN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.20417&json=true","fetch_graph":"https://pith.science/api/pith-number/VIRIXHHNOYWXKE4H4SWPAIW56A/graph.json","fetch_events":"https://pith.science/api/pith-number/VIRIXHHNOYWXKE4H4SWPAIW56A/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VIRIXHHNOYWXKE4H4SWPAIW56A/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VIRIXHHNOYWXKE4H4SWPAIW56A/action/storage_attestation","attest_author":"https://pith.science/pith/VIRIXHHNOYWXKE4H4SWPAIW56A/action/author_attestation","sign_citation":"https://pith.science/pith/VIRIXHHNOYWXKE4H4SWPAIW56A/action/citation_signature","submit_replication":"https://pith.science/pith/VIRIXHHNOYWXKE4H4SWPAIW56A/action/replication_record"}},"created_at":"2026-07-05T10:39:37.943501+00:00","updated_at":"2026-07-05T10:39:37.943501+00:00"}