{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:TVOB3BCZYMLJWR3W5B6WQ52MMA","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":"b33bfca04197a985789bd26384ab3aa2b6da4a7a023b19323b7ceb1d2a820dd3","cross_cats_sorted":["cs.CY"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-03T05:55:00Z","title_canon_sha256":"2ef56be54bbb5714c76770fb1cf31921624db556df7a9770379a8ee77bdbed52"},"schema_version":"1.0","source":{"id":"2605.01727","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.01727","created_at":"2026-06-12T01:09:28Z"},{"alias_kind":"arxiv_version","alias_value":"2605.01727v1","created_at":"2026-06-12T01:09:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.01727","created_at":"2026-06-12T01:09:28Z"},{"alias_kind":"pith_short_12","alias_value":"TVOB3BCZYMLJ","created_at":"2026-06-12T01:09:28Z"},{"alias_kind":"pith_short_16","alias_value":"TVOB3BCZYMLJWR3W","created_at":"2026-06-12T01:09:28Z"},{"alias_kind":"pith_short_8","alias_value":"TVOB3BCZ","created_at":"2026-06-12T01:09:28Z"}],"graph_snapshots":[{"event_id":"sha256:afd022cd3e29207c534fb562098aa320703b921f879cbbf5b792ec37eccafb78","target":"graph","created_at":"2026-06-12T01:09:28Z","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":"Across four frontier models, we find a clear but model-specific genre asymmetry: DeepSeek-V3.2 and GPT-5.2 show false-positive-rate gaps of 10.1 and 8.8 percentage points, respectively (both p < .001), whereas Claude Opus 4.6 and Gemini 3 Flash show no comparable difference."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That the within-dataset design on GossipCop sufficiently isolates genre effects from confounding differences in topic, source, or unverifiability of private-life claims between entertainment and hard news."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Certain frontier LLMs exhibit higher false-positive rates on legitimate entertainment news than hard news, with model-specific patterns not explained by style alone."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Some large language models misclassify legitimate entertainment news as fake at higher rates than hard news."}],"snapshot_sha256":"d190bb12ac227399c2561ea8a717a0fcde89b67c9f70c9a162f7b92cd88cfc60"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-20T17:37:31.901475Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_title_agreement","ran_at":"2026-05-20T05:01:23.130086Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_compliance","ran_at":"2026-05-19T17:00:50.742878Z","status":"completed","version":"1.0.0"}],"endpoint":"/pith/2605.01727/integrity.json","findings":[],"snapshot_sha256":"c2fa63669aab41d6eb1405d8cf085a4721477d2099b2874aa40e76a38d58131a","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) are increasingly used for automated news credibility assessment, yet it remains unclear whether they apply even-handed standards across journalistic genres. We examine whether zero-shot LLMs are more likely to misclassify legitimate entertainment news as fake than legitimate hard news, using a within-dataset design on GossipCop from FakeNewsNet. Across four frontier models, we find a clear but model-specific genre asymmetry: DeepSeek-V3.2 and GPT-5.2 show false-positive-rate gaps of 10.1 and 8.8 percentage points, respectively (both $p < .001$), whereas Claude Opus","authors_text":"Huiqian Lai","cross_cats":["cs.CY"],"headline":"Some large language models misclassify legitimate entertainment news as fake at higher rates than hard news.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-03T05:55:00Z","title":"Are LLMs More Skeptical of Entertainment News?"},"references":{"count":13,"internal_anchors":0,"resolved_work":13,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"SoK: Machine Learning for Misinformation Detec- tion.arXiv preprint arXiv:2308.12215. Horne, B.; and Adali, S. 2017. This Just In: Fake News Packs A Lot In Title, Uses Simpler, Repetitive Content in T","work_id":"b9dfe36b-8928-403f-94fb-c14ccb029d09","year":2017},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"A Survey on the Use of Large Language Models (LLMs) in Fake News.Future Internet, 16(8). Pelrine, K.; Mosber, A.; Zheng, J.; Yang, J.-Y .; Peng, A.; Rabbany, R.; and Cheung, J. C. K. 2023. Towards Re-","work_id":"981f6e87-a0bf-410b-8d41-49962f61c18c","year":2023},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"P´erez-Rosas, V .; Kleinberg, B.; Lefevre, A.; and Mihalcea, R","work_id":"2311371a-907b-4de1-aa69-d3b324fb2fe6","year":2018},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"In Palmer, M.; Hwa, R.; and Riedel, S., eds.,Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, 2931–2937","work_id":"ccf60c23-b01a-4517-820e-0aa8ea16f097","year":2017},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Hard and Soft News: A Review of Concepts, Oper- ationalizations and Key Findings.Journalism, 13(2): 221– 239. Roberts, S. T. 2019.Behind the screen : content modera- tion in the shadows of social medi","work_id":"7b1e133e-83d7-424b-9f5a-18db4bb4005b","year":2019}],"snapshot_sha256":"5d9333e09d13e8d2e0b73b8ca026ab4d5144537e2be1f42d59bb0bc76c9458ad"},"source":{"id":"2605.01727","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-10T16:24:57.696423Z","id":"cd3e19a2-ad21-4442-bd5a-43952fb8a946","model_set":{"reader":"grok-4.3"},"one_line_summary":"Certain frontier LLMs exhibit higher false-positive rates on legitimate entertainment news than hard news, with model-specific patterns not explained by style alone.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Some large language models misclassify legitimate entertainment news as fake at higher rates than hard news.","strongest_claim":"Across four frontier models, we find a clear but model-specific genre asymmetry: DeepSeek-V3.2 and GPT-5.2 show false-positive-rate gaps of 10.1 and 8.8 percentage points, respectively (both p < .001), whereas Claude Opus 4.6 and Gemini 3 Flash show no comparable difference.","weakest_assumption":"That the within-dataset design on GossipCop sufficiently isolates genre effects from confounding differences in topic, source, or unverifiability of private-life claims between entertainment and hard news."}},"verdict_id":"cd3e19a2-ad21-4442-bd5a-43952fb8a946"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:a14de44bd8c4784d31b614b0145b1f53c0e6236c7eb18585120986d146932244","target":"record","created_at":"2026-06-12T01:09:28Z","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":"b33bfca04197a985789bd26384ab3aa2b6da4a7a023b19323b7ceb1d2a820dd3","cross_cats_sorted":["cs.CY"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-03T05:55:00Z","title_canon_sha256":"2ef56be54bbb5714c76770fb1cf31921624db556df7a9770379a8ee77bdbed52"},"schema_version":"1.0","source":{"id":"2605.01727","kind":"arxiv","version":1}},"canonical_sha256":"9d5c1d8459c3169b4776e87d68774c6030de5400f389f7a90d79e8a487ed94f3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9d5c1d8459c3169b4776e87d68774c6030de5400f389f7a90d79e8a487ed94f3","first_computed_at":"2026-06-12T01:09:28.441944Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-12T01:09:28.441944Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CYgzPmSAWAHUHg/6BkTbEgUNzrsCkgrNxFV23O2fg28YxUdaxoYWS9GUpQ3VKKRZ9nZoRor3fXHJN1/1gDERBw==","signature_status":"signed_v1","signed_at":"2026-06-12T01:09:28.442357Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.01727","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a14de44bd8c4784d31b614b0145b1f53c0e6236c7eb18585120986d146932244","sha256:afd022cd3e29207c534fb562098aa320703b921f879cbbf5b792ec37eccafb78"],"state_sha256":"b9b0673ddd3fb32a9d71e56a4be4574afec676bae2c424a908e9c07bdd27a4ad"}