{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:H5JCURQPCN6THLVMKLL7FSYTQZ","short_pith_number":"pith:H5JCURQP","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"},"canonical_sha256":"3f522a460f137d33aeac52d7f2cb138653a4ad4f963d254bb8fc677d526c9e47","source":{"kind":"arxiv","id":"2604.19786","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.19786","created_at":"2026-06-02T03:04:41Z"},{"alias_kind":"arxiv_version","alias_value":"2604.19786v2","created_at":"2026-06-02T03:04:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.19786","created_at":"2026-06-02T03:04:41Z"},{"alias_kind":"pith_short_12","alias_value":"H5JCURQPCN6T","created_at":"2026-06-02T03:04:41Z"},{"alias_kind":"pith_short_16","alias_value":"H5JCURQPCN6THLVM","created_at":"2026-06-02T03:04:41Z"},{"alias_kind":"pith_short_8","alias_value":"H5JCURQP","created_at":"2026-06-02T03:04:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:H5JCURQPCN6THLVMKLL7FSYTQZ","target":"record","payload":{"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"},"canonical_sha256":"3f522a460f137d33aeac52d7f2cb138653a4ad4f963d254bb8fc677d526c9e47","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"},"source_kind":"arxiv","source_id":"2604.19786","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-02T03:04:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WLJfJQccLrQ3uAZ76VnLOBuhvTxivvZ3njps11a+K2iStzhvAlIVFaGDagSUB8i7wjXPpnGve4dgCRWNawEtAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-07T14:08:55.078897Z"},"content_sha256":"6690c67b59ad3fe0c79f94894c144488e6c0b491b7dabbd0f70a7eb7248ae18c","schema_version":"1.0","event_id":"sha256:6690c67b59ad3fe0c79f94894c144488e6c0b491b7dabbd0f70a7eb7248ae18c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:H5JCURQPCN6THLVMKLL7FSYTQZ","target":"graph","payload":{"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"},"verdict_id":"eb99c771-efe4-47b5-943c-7dfc64a517eb"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-02T03:04:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6tBjSdER+PFJxXWu/ma3yc/yGJTHD2G52WTPAuGvcyOLIKI/3vrjXAYhSVonZc4dP3k/hbK/7Y9xOGPJhUNLDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-07T14:08:55.079761Z"},"content_sha256":"a84354f1b15b6591c3b82607d37c708b86002bc18306180658293ea969101f39","schema_version":"1.0","event_id":"sha256:a84354f1b15b6591c3b82607d37c708b86002bc18306180658293ea969101f39"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/H5JCURQPCN6THLVMKLL7FSYTQZ/bundle.json","state_url":"https://pith.science/pith/H5JCURQPCN6THLVMKLL7FSYTQZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/H5JCURQPCN6THLVMKLL7FSYTQZ/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-07T14:08:55Z","links":{"resolver":"https://pith.science/pith/H5JCURQPCN6THLVMKLL7FSYTQZ","bundle":"https://pith.science/pith/H5JCURQPCN6THLVMKLL7FSYTQZ/bundle.json","state":"https://pith.science/pith/H5JCURQPCN6THLVMKLL7FSYTQZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/H5JCURQPCN6THLVMKLL7FSYTQZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:H5JCURQPCN6THLVMKLL7FSYTQZ","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":"f6a0fe4da1e16526bb91e27ce13aede5f5248decc991f96788bf7f214ece6597","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-03-31T18:54:15Z","title_canon_sha256":"c9c2eba53722e23fb8feb709c29a73958260cad53c9a87dda7f9312e22a8f42d"},"schema_version":"1.0","source":{"id":"2604.19786","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.19786","created_at":"2026-06-02T03:04:41Z"},{"alias_kind":"arxiv_version","alias_value":"2604.19786v2","created_at":"2026-06-02T03:04:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.19786","created_at":"2026-06-02T03:04:41Z"},{"alias_kind":"pith_short_12","alias_value":"H5JCURQPCN6T","created_at":"2026-06-02T03:04:41Z"},{"alias_kind":"pith_short_16","alias_value":"H5JCURQPCN6THLVM","created_at":"2026-06-02T03:04:41Z"},{"alias_kind":"pith_short_8","alias_value":"H5JCURQP","created_at":"2026-06-02T03:04:41Z"}],"graph_snapshots":[{"event_id":"sha256:a84354f1b15b6591c3b82607d37c708b86002bc18306180658293ea969101f39","target":"graph","created_at":"2026-06-02T03:04:41Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"HumorRank ranks language models on humor generation through automated joke tournaments that reveal skill in comedic mechanisms over model size."}],"snapshot_sha256":"7811f44e58e8d0fb363945807edb4bb5d173d04a533c0200ac2c42c0aae3cfaa"},"formal_canon":{"evidence_count":1,"snapshot_sha256":"ecec7f28dec845e7b315f057f3711c9c72b24384fc91583ca2b874ddfbd2cfe1"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2604.19786/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Edward Ajayi, Prasenjit Mitra","cross_cats":[],"headline":"HumorRank ranks language models on humor generation through automated joke tournaments that reveal skill in comedic mechanisms over model size.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-03-31T18:54:15Z","title":"HumorRank: A Tournament-Based Leaderboard for Evaluating Humor Generation in Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2604.19786","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-13T23:01:25.712854Z","id":"eb99c771-efe4-47b5-943c-7dfc64a517eb","model_set":{"reader":"grok-4.3"},"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","pith_extraction_headline":"HumorRank ranks language models on humor generation through automated joke tournaments that reveal skill in comedic mechanisms over model size.","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.","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."}},"verdict_id":"eb99c771-efe4-47b5-943c-7dfc64a517eb"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:6690c67b59ad3fe0c79f94894c144488e6c0b491b7dabbd0f70a7eb7248ae18c","target":"record","created_at":"2026-06-02T03:04:41Z","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":"f6a0fe4da1e16526bb91e27ce13aede5f5248decc991f96788bf7f214ece6597","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-03-31T18:54:15Z","title_canon_sha256":"c9c2eba53722e23fb8feb709c29a73958260cad53c9a87dda7f9312e22a8f42d"},"schema_version":"1.0","source":{"id":"2604.19786","kind":"arxiv","version":2}},"canonical_sha256":"3f522a460f137d33aeac52d7f2cb138653a4ad4f963d254bb8fc677d526c9e47","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3f522a460f137d33aeac52d7f2cb138653a4ad4f963d254bb8fc677d526c9e47","first_computed_at":"2026-06-02T03:04:41.390955Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-02T03:04:41.390955Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nEovIP2eIz5zxar15Q82XmImDLDH7qYoL6WdAegvXQLTT2oW0xV0qz9NERZmD4RGm6FIgZaF/1LTxFkCmbKSCw==","signature_status":"signed_v1","signed_at":"2026-06-02T03:04:41.391444Z","signed_message":"canonical_sha256_bytes"},"source_id":"2604.19786","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6690c67b59ad3fe0c79f94894c144488e6c0b491b7dabbd0f70a7eb7248ae18c","sha256:a84354f1b15b6591c3b82607d37c708b86002bc18306180658293ea969101f39"],"state_sha256":"7d8afa0e57b9af8164473448c7c223829eab51b8087fbc865daea6aa9386201d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"N+uqfkrO4D8aQnsuSMEP9O4oFju6g0IDg0z3/DXrQCG2PvWuIAvn9ARRhRcjb2JCzCLgFCrG/cWaD6ZOIXeEAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-07T14:08:55.083869Z","bundle_sha256":"40d660e79d7a49ca9664b526abffa4163b027716dffaa20137fe26517cf07de0"}}