{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:CH5V77TW4BFNHBEX7ACUJVQKY4","short_pith_number":"pith:CH5V77TW","schema_version":"1.0","canonical_sha256":"11fb5ffe76e04ad38497f80544d60ac73f0b103bce0d44165748bf69ec58a0f3","source":{"kind":"arxiv","id":"2604.09629","version":2},"attestation_state":"computed","paper":{"title":"HumorGen: Cognitive Synergy for Humor Generation in Large Language Models via Persona-Based Distillation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Cognitive personas synthesizing humor data let a 7B model match or beat much larger LLMs at comedy.","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Edward Ajayi, Prasenjit Mitra","submitted_at":"2026-03-19T13:12:53Z","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"},"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":"2604.09629","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-03-19T13:12:53Z","cross_cats_sorted":[],"title_canon_sha256":"a70fe9a889fc1b56c29469a1aecb5c4cec6f569778a619b78ca907d659a852eb","abstract_canon_sha256":"bbae0302de87646da20dceb2d7ce21d7d84e15dbedb1bf446984145ce89be050"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-29T01:05:09.219277Z","signature_b64":"TvgWh0OVfLkl0eguBniR5ZLIhIOY+hMPIG0j3KIKFDDZEP8yj3J8Luzjc2H3eMLfa4lJ/IWsuvakubeCkiTPBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"11fb5ffe76e04ad38497f80544d60ac73f0b103bce0d44165748bf69ec58a0f3","last_reissued_at":"2026-05-29T01:05:09.218698Z","signature_status":"signed_v1","first_computed_at":"2026-05-29T01:05:09.218698Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HumorGen: Cognitive Synergy for Humor Generation in Large Language Models via Persona-Based Distillation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Cognitive personas synthesizing humor data let a 7B model match or beat much larger LLMs at comedy.","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Edward Ajayi, Prasenjit Mitra","submitted_at":"2026-03-19T13:12:53Z","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"},"claims":{"count":4,"items":[{"kind":"strongest_claim","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.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","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.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","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.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Cognitive personas synthesizing humor data let a 7B model match or beat much larger LLMs at comedy.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"f44079b6296e81c9b17ad67431e10819f748eb4d75dee7f3f6fb3bcc5bf04a7a"},"source":{"id":"2604.09629","kind":"arxiv","version":2},"verdict":{"id":"3a2418ce-7faa-4f0b-bd9d-4399329aa1b1","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T08:38:56.673007Z","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.","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","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.","pith_extraction_headline":"Cognitive personas synthesizing humor data let a 7B model match or beat much larger LLMs at comedy."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2604.09629/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":"19a1d8a4f38ade4a25b145f7d88b6dbb2a1bb7dc3d663fa3c258fd7bf72dd01a"},"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":"2604.09629","created_at":"2026-05-29T01:05:09.218770+00:00"},{"alias_kind":"arxiv_version","alias_value":"2604.09629v2","created_at":"2026-05-29T01:05:09.218770+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.09629","created_at":"2026-05-29T01:05:09.218770+00:00"},{"alias_kind":"pith_short_12","alias_value":"CH5V77TW4BFN","created_at":"2026-05-29T01:05:09.218770+00:00"},{"alias_kind":"pith_short_16","alias_value":"CH5V77TW4BFNHBEX","created_at":"2026-05-29T01:05:09.218770+00:00"},{"alias_kind":"pith_short_8","alias_value":"CH5V77TW","created_at":"2026-05-29T01:05:09.218770+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/CH5V77TW4BFNHBEX7ACUJVQKY4","json":"https://pith.science/pith/CH5V77TW4BFNHBEX7ACUJVQKY4.json","graph_json":"https://pith.science/api/pith-number/CH5V77TW4BFNHBEX7ACUJVQKY4/graph.json","events_json":"https://pith.science/api/pith-number/CH5V77TW4BFNHBEX7ACUJVQKY4/events.json","paper":"https://pith.science/paper/CH5V77TW"},"agent_actions":{"view_html":"https://pith.science/pith/CH5V77TW4BFNHBEX7ACUJVQKY4","download_json":"https://pith.science/pith/CH5V77TW4BFNHBEX7ACUJVQKY4.json","view_paper":"https://pith.science/paper/CH5V77TW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2604.09629&json=true","fetch_graph":"https://pith.science/api/pith-number/CH5V77TW4BFNHBEX7ACUJVQKY4/graph.json","fetch_events":"https://pith.science/api/pith-number/CH5V77TW4BFNHBEX7ACUJVQKY4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CH5V77TW4BFNHBEX7ACUJVQKY4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CH5V77TW4BFNHBEX7ACUJVQKY4/action/storage_attestation","attest_author":"https://pith.science/pith/CH5V77TW4BFNHBEX7ACUJVQKY4/action/author_attestation","sign_citation":"https://pith.science/pith/CH5V77TW4BFNHBEX7ACUJVQKY4/action/citation_signature","submit_replication":"https://pith.science/pith/CH5V77TW4BFNHBEX7ACUJVQKY4/action/replication_record"}},"created_at":"2026-05-29T01:05:09.218770+00:00","updated_at":"2026-05-29T01:05:09.218770+00:00"}