{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:H5JCURQPCN6THLVMKLL7FSYTQZ","short_pith_number":"pith:H5JCURQP","schema_version":"1.0","canonical_sha256":"3f522a460f137d33aeac52d7f2cb138653a4ad4f963d254bb8fc677d526c9e47","source":{"kind":"arxiv","id":"2604.19786","version":2},"attestation_state":"computed","paper":{"title":"HumorRank: A Tournament-Based Leaderboard for Evaluating Humor Generation in Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"HumorRank ranks language models on humor generation through automated joke tournaments that reveal skill in comedic mechanisms over model size.","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Edward Ajayi, Prasenjit Mitra","submitted_at":"2026-03-31T18:54:15Z","abstract_excerpt":"Humor remains difficult to evaluate in large language models (LLMs) because what makes a response funny is subjective, comparative, and shaped by interacting comedic mechanisms rather than a single scalar property. Existing humor evaluation protocols therefore tend to produce isolated scores or task-specific judgments that are difficult to compare across models. We introduce HumorRank, a tournament-based framework for ranking textual humor generation through theory-grounded pairwise preference judgments. Across SemEval-2026 MWAHAHA and Humor Transfer Bench, HumorRank evaluates nine proprietary"},"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":true},"canonical_record":{"source":{"id":"2604.19786","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-03-31T18:54:15Z","cross_cats_sorted":[],"title_canon_sha256":"c9c2eba53722e23fb8feb709c29a73958260cad53c9a87dda7f9312e22a8f42d","abstract_canon_sha256":"f6a0fe4da1e16526bb91e27ce13aede5f5248decc991f96788bf7f214ece6597"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T03:04:41.391444Z","signature_b64":"nEovIP2eIz5zxar15Q82XmImDLDH7qYoL6WdAegvXQLTT2oW0xV0qz9NERZmD4RGm6FIgZaF/1LTxFkCmbKSCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3f522a460f137d33aeac52d7f2cb138653a4ad4f963d254bb8fc677d526c9e47","last_reissued_at":"2026-06-02T03:04:41.390955Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T03:04:41.390955Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HumorRank: A Tournament-Based Leaderboard for Evaluating Humor Generation in Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"HumorRank ranks language models on humor generation through automated joke tournaments that reveal skill in comedic mechanisms over model size.","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Edward Ajayi, Prasenjit Mitra","submitted_at":"2026-03-31T18:54:15Z","abstract_excerpt":"Humor remains difficult to evaluate in large language models (LLMs) because what makes a response funny is subjective, comparative, and shaped by interacting comedic mechanisms rather than a single scalar property. Existing humor evaluation protocols therefore tend to produce isolated scores or task-specific judgments that are difficult to compare across models. We introduce HumorRank, a tournament-based framework for ranking textual humor generation through theory-grounded pairwise preference judgments. Across SemEval-2026 MWAHAHA and Humor Transfer Bench, HumorRank evaluates nine proprietary"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Our results demonstrate that HumorRank yields statistically grounded model stratifications, showing that humor quality is driven by mastery of comedic mechanisms rather than model scale alone.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"Automated pairwise judgments grounded in the General Theory of Verbal Humor accurately reflect true humor quality without systematic bias or the need for human validation.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"HumorRank ranks nine LLMs on textual humor using GTVH-grounded pairwise tournaments and Adaptive Swiss aggregation on the SemEval-2026 MWAHAHA dataset, finding that comedic mechanism mastery matters more than scale.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"HumorRank ranks language models on humor generation through automated joke tournaments that reveal skill in comedic mechanisms over model size.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"7811f44e58e8d0fb363945807edb4bb5d173d04a533c0200ac2c42c0aae3cfaa"},"source":{"id":"2604.19786","kind":"arxiv","version":2},"verdict":{"id":"eb99c771-efe4-47b5-943c-7dfc64a517eb","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-13T23:01:25.712854Z","strongest_claim":"Our results demonstrate that HumorRank yields statistically grounded model stratifications, showing that humor quality is driven by mastery of comedic mechanisms rather than model scale alone.","one_line_summary":"HumorRank ranks nine LLMs on textual humor using GTVH-grounded pairwise tournaments and Adaptive Swiss aggregation on the SemEval-2026 MWAHAHA dataset, finding that comedic mechanism mastery matters more than scale.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"Automated pairwise judgments grounded in the General Theory of Verbal Humor accurately reflect true humor quality without systematic bias or the need for human validation.","pith_extraction_headline":"HumorRank ranks language models on humor generation through automated joke tournaments that reveal skill in comedic mechanisms over model size."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2604.19786/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":1,"snapshot_sha256":"ecec7f28dec845e7b315f057f3711c9c72b24384fc91583ca2b874ddfbd2cfe1"},"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":"2604.19786","created_at":"2026-06-02T03:04:41.391010+00:00"},{"alias_kind":"arxiv_version","alias_value":"2604.19786v2","created_at":"2026-06-02T03:04:41.391010+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.19786","created_at":"2026-06-02T03:04:41.391010+00:00"},{"alias_kind":"pith_short_12","alias_value":"H5JCURQPCN6T","created_at":"2026-06-02T03:04:41.391010+00:00"},{"alias_kind":"pith_short_16","alias_value":"H5JCURQPCN6THLVM","created_at":"2026-06-02T03:04:41.391010+00:00"},{"alias_kind":"pith_short_8","alias_value":"H5JCURQP","created_at":"2026-06-02T03:04:41.391010+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":1,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/H5JCURQPCN6THLVMKLL7FSYTQZ","json":"https://pith.science/pith/H5JCURQPCN6THLVMKLL7FSYTQZ.json","graph_json":"https://pith.science/api/pith-number/H5JCURQPCN6THLVMKLL7FSYTQZ/graph.json","events_json":"https://pith.science/api/pith-number/H5JCURQPCN6THLVMKLL7FSYTQZ/events.json","paper":"https://pith.science/paper/H5JCURQP"},"agent_actions":{"view_html":"https://pith.science/pith/H5JCURQPCN6THLVMKLL7FSYTQZ","download_json":"https://pith.science/pith/H5JCURQPCN6THLVMKLL7FSYTQZ.json","view_paper":"https://pith.science/paper/H5JCURQP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2604.19786&json=true","fetch_graph":"https://pith.science/api/pith-number/H5JCURQPCN6THLVMKLL7FSYTQZ/graph.json","fetch_events":"https://pith.science/api/pith-number/H5JCURQPCN6THLVMKLL7FSYTQZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/H5JCURQPCN6THLVMKLL7FSYTQZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/H5JCURQPCN6THLVMKLL7FSYTQZ/action/storage_attestation","attest_author":"https://pith.science/pith/H5JCURQPCN6THLVMKLL7FSYTQZ/action/author_attestation","sign_citation":"https://pith.science/pith/H5JCURQPCN6THLVMKLL7FSYTQZ/action/citation_signature","submit_replication":"https://pith.science/pith/H5JCURQPCN6THLVMKLL7FSYTQZ/action/replication_record"}},"created_at":"2026-06-02T03:04:41.391010+00:00","updated_at":"2026-06-02T03:04:41.391010+00:00"}