{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:CH5V77TW4BFNHBEX7ACUJVQKY4","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":"bbae0302de87646da20dceb2d7ce21d7d84e15dbedb1bf446984145ce89be050","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-03-19T13:12:53Z","title_canon_sha256":"a70fe9a889fc1b56c29469a1aecb5c4cec6f569778a619b78ca907d659a852eb"},"schema_version":"1.0","source":{"id":"2604.09629","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.09629","created_at":"2026-05-29T01:05:09Z"},{"alias_kind":"arxiv_version","alias_value":"2604.09629v2","created_at":"2026-05-29T01:05:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.09629","created_at":"2026-05-29T01:05:09Z"},{"alias_kind":"pith_short_12","alias_value":"CH5V77TW4BFN","created_at":"2026-05-29T01:05:09Z"},{"alias_kind":"pith_short_16","alias_value":"CH5V77TW4BFNHBEX","created_at":"2026-05-29T01:05:09Z"},{"alias_kind":"pith_short_8","alias_value":"CH5V77TW","created_at":"2026-05-29T01:05:09Z"}],"graph_snapshots":[{"event_id":"sha256:a11c930a08bc40c3ab1dd65e25b15b23354a44d65f2d9258ad16bb4c87c782f9","target":"graph","created_at":"2026-05-29T01:05:09Z","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 7B model significantly outperforms larger instruction-tuned baselines and achieves performance competitive with state-of-the-art proprietary models. We find that cognitive-driven data curation is far more critical than alignment algorithms or model scale for humor generation."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The humor data synthesized using the six cognitive personas through the Mixture-of-Thought approach provides a high-quality, diverse training signal that effectively improves the model's humor generation capabilities beyond what standard methods achieve."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"A 7B LLM fine-tuned on humor data generated via six cognitive personas and Mixture-of-Thought outperforms larger instruction-tuned baselines and competes with proprietary models."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Cognitive personas synthesizing humor data let a 7B model match or beat much larger LLMs at comedy."}],"snapshot_sha256":"f44079b6296e81c9b17ad67431e10819f748eb4d75dee7f3f6fb3bcc5bf04a7a"},"formal_canon":{"evidence_count":1,"snapshot_sha256":"19a1d8a4f38ade4a25b145f7d88b6dbb2a1bb7dc3d663fa3c258fd7bf72dd01a"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2604.09629/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Humor generation poses a significant challenge for Large Language Models (LLMs), because their standard training objective (next-token prediction) inherently conflicts with the surprise and incongruity required for comedy. To bridge this gap, we introduce the Cognitive Synergy Framework, a methodology for generating highquality humor data inspired by psychological theories of humor. Utilizing a Mixtureof-Thought (MoT) approach, we deploy six cognitive personas (e.g., The Absurdist, The Cynic) to synthesize diverse comedic perspectives for a given prompt. This framework produces a theory-ground","authors_text":"Edward Ajayi, Prasenjit Mitra","cross_cats":[],"headline":"Cognitive personas synthesizing humor data let a 7B model match or beat much larger LLMs at comedy.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-03-19T13:12:53Z","title":"HumorGen: Cognitive Synergy for Humor Generation in Large Language Models via Persona-Based Distillation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2604.09629","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-15T08:38:56.673007Z","id":"3a2418ce-7faa-4f0b-bd9d-4399329aa1b1","model_set":{"reader":"grok-4.3"},"one_line_summary":"A 7B LLM fine-tuned on humor data generated via six cognitive personas and Mixture-of-Thought outperforms larger instruction-tuned baselines and competes with proprietary models.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Cognitive personas synthesizing humor data let a 7B model match or beat much larger LLMs at comedy.","strongest_claim":"our 7B model significantly outperforms larger instruction-tuned baselines and achieves performance competitive with state-of-the-art proprietary models. We find that cognitive-driven data curation is far more critical than alignment algorithms or model scale for humor generation.","weakest_assumption":"The humor data synthesized using the six cognitive personas through the Mixture-of-Thought approach provides a high-quality, diverse training signal that effectively improves the model's humor generation capabilities beyond what standard methods achieve."}},"verdict_id":"3a2418ce-7faa-4f0b-bd9d-4399329aa1b1"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:a1fdcee45ef64b599fb6c594dcd0c408c9174109df04c33051de78fe43820db3","target":"record","created_at":"2026-05-29T01:05:09Z","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":"bbae0302de87646da20dceb2d7ce21d7d84e15dbedb1bf446984145ce89be050","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-03-19T13:12:53Z","title_canon_sha256":"a70fe9a889fc1b56c29469a1aecb5c4cec6f569778a619b78ca907d659a852eb"},"schema_version":"1.0","source":{"id":"2604.09629","kind":"arxiv","version":2}},"canonical_sha256":"11fb5ffe76e04ad38497f80544d60ac73f0b103bce0d44165748bf69ec58a0f3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"11fb5ffe76e04ad38497f80544d60ac73f0b103bce0d44165748bf69ec58a0f3","first_computed_at":"2026-05-29T01:05:09.218698Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-29T01:05:09.218698Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TvgWh0OVfLkl0eguBniR5ZLIhIOY+hMPIG0j3KIKFDDZEP8yj3J8Luzjc2H3eMLfa4lJ/IWsuvakubeCkiTPBg==","signature_status":"signed_v1","signed_at":"2026-05-29T01:05:09.219277Z","signed_message":"canonical_sha256_bytes"},"source_id":"2604.09629","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a1fdcee45ef64b599fb6c594dcd0c408c9174109df04c33051de78fe43820db3","sha256:a11c930a08bc40c3ab1dd65e25b15b23354a44d65f2d9258ad16bb4c87c782f9"],"state_sha256":"e5fb53a4b774dcd611df4d98d4a87e5c62e66bec9b7d5b0764ed5a970ce02e4e"}