{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:UA7NT2YQAUBHKC43YP74DC5W2N","short_pith_number":"pith:UA7NT2YQ","schema_version":"1.0","canonical_sha256":"a03ed9eb100502750b9bc3ffc18bb6d34d34c7c2261f748601e9942cabbd4fe5","source":{"kind":"arxiv","id":"2412.09203","version":1},"attestation_state":"computed","paper":{"title":"CleanComedy: Creating Friendly Humor through Generative Techniques","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Daria Galimzianova, Dmitry Vikhorev, Elizaveta Zhemchuzhina, Ivan P. Yamshchikov, Svetlana Gorovaia","submitted_at":"2024-12-12T11:57:59Z","abstract_excerpt":"Humor generation is a challenging task in natural language processing due to limited resources and the quality of existing datasets. Available humor language resources often suffer from toxicity and duplication, limiting their effectiveness for training robust models. This paper proposes CleanComedy, a specialized, partially annotated toxicity-filtered corpus of English and Russian jokes collected from various sources. We study the effectiveness of our data filtering approach through a survey on humor and toxicity levels in various joke groups. In addition, we study advances in computer humor "},"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":"2412.09203","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-12T11:57:59Z","cross_cats_sorted":[],"title_canon_sha256":"e0e66857c327e3561708e1e330208c73161baa1d64a3cd19b3b93c10a43af660","abstract_canon_sha256":"c05776d38ae609fbbf1259ed4fcd9e943f1c3302a58b774ce37842a71ffb89e4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:48:21.065751Z","signature_b64":"3Xi5gDSEMQ0f6ZlnNAw7GFaB6DprIpykNsLv2MyMMhW7mxI4TZZrr6v6RycpYKKX/1BqEHWM1jVHihRwPBXbBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a03ed9eb100502750b9bc3ffc18bb6d34d34c7c2261f748601e9942cabbd4fe5","last_reissued_at":"2026-07-05T09:48:21.065350Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:48:21.065350Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CleanComedy: Creating Friendly Humor through Generative Techniques","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Daria Galimzianova, Dmitry Vikhorev, Elizaveta Zhemchuzhina, Ivan P. Yamshchikov, Svetlana Gorovaia","submitted_at":"2024-12-12T11:57:59Z","abstract_excerpt":"Humor generation is a challenging task in natural language processing due to limited resources and the quality of existing datasets. Available humor language resources often suffer from toxicity and duplication, limiting their effectiveness for training robust models. This paper proposes CleanComedy, a specialized, partially annotated toxicity-filtered corpus of English and Russian jokes collected from various sources. We study the effectiveness of our data filtering approach through a survey on humor and toxicity levels in various joke groups. In addition, we study advances in computer humor "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.09203","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/2412.09203/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":"2412.09203","created_at":"2026-07-05T09:48:21.065412+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.09203v1","created_at":"2026-07-05T09:48:21.065412+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.09203","created_at":"2026-07-05T09:48:21.065412+00:00"},{"alias_kind":"pith_short_12","alias_value":"UA7NT2YQAUBH","created_at":"2026-07-05T09:48:21.065412+00:00"},{"alias_kind":"pith_short_16","alias_value":"UA7NT2YQAUBHKC43","created_at":"2026-07-05T09:48:21.065412+00:00"},{"alias_kind":"pith_short_8","alias_value":"UA7NT2YQ","created_at":"2026-07-05T09:48:21.065412+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.09629","citing_title":"HumorGen: Cognitive Synergy for Humor Generation in Large Language Models via Persona-Based Distillation","ref_index":26,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UA7NT2YQAUBHKC43YP74DC5W2N","json":"https://pith.science/pith/UA7NT2YQAUBHKC43YP74DC5W2N.json","graph_json":"https://pith.science/api/pith-number/UA7NT2YQAUBHKC43YP74DC5W2N/graph.json","events_json":"https://pith.science/api/pith-number/UA7NT2YQAUBHKC43YP74DC5W2N/events.json","paper":"https://pith.science/paper/UA7NT2YQ"},"agent_actions":{"view_html":"https://pith.science/pith/UA7NT2YQAUBHKC43YP74DC5W2N","download_json":"https://pith.science/pith/UA7NT2YQAUBHKC43YP74DC5W2N.json","view_paper":"https://pith.science/paper/UA7NT2YQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.09203&json=true","fetch_graph":"https://pith.science/api/pith-number/UA7NT2YQAUBHKC43YP74DC5W2N/graph.json","fetch_events":"https://pith.science/api/pith-number/UA7NT2YQAUBHKC43YP74DC5W2N/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UA7NT2YQAUBHKC43YP74DC5W2N/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UA7NT2YQAUBHKC43YP74DC5W2N/action/storage_attestation","attest_author":"https://pith.science/pith/UA7NT2YQAUBHKC43YP74DC5W2N/action/author_attestation","sign_citation":"https://pith.science/pith/UA7NT2YQAUBHKC43YP74DC5W2N/action/citation_signature","submit_replication":"https://pith.science/pith/UA7NT2YQAUBHKC43YP74DC5W2N/action/replication_record"}},"created_at":"2026-07-05T09:48:21.065412+00:00","updated_at":"2026-07-05T09:48:21.065412+00:00"}