{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:JRY554RWUBTNZK3IWGY3JGPQID","short_pith_number":"pith:JRY554RW","schema_version":"1.0","canonical_sha256":"4c71def236a066dcab68b1b1b499f040daeebbdb8b9b87adc5e2fead7cd0a60f","source":{"kind":"arxiv","id":"2605.16953","version":1},"attestation_state":"computed","paper":{"title":"How do Humans Process AI-generated Hallucination Contents: a Neuroimaging Study","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Misjudged AI hallucinations fail to activate the brain's standard fact verification pathway, as shown by distinct EEG responses.","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Bangde Du, Qingyao Ai, Shuqi Zhu, Yiqun Liu, Yi Zhong, Yujia Zhou, Ziyi Ye","submitted_at":"2026-05-16T12:08:22Z","abstract_excerpt":"While AI-generated hallucinations pose considerable risks, the underlying cognitive mechanisms by which humans can successfully recognize or be misled by these hallucinations remain unclear. To address this problem, this paper explores humans' neural dynamics to characterize how the brain processes hallucinated content. We record EEG signals from 27 participants while they are performing a verification task to judge the correctness of image descriptions generated by a multi-modal large language model (MLLM). Based on an averaged event-related potential (ERP) study, we reveal that multiple cogn"},"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":true,"formal_links_present":true},"canonical_record":{"source":{"id":"2605.16953","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-16T12:08:22Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"1b53d67b8609919fb5a93647a8f0299001bc393a2f38abfd7f7a0be77c09e844","abstract_canon_sha256":"55cfcc2118f0b98201fbaa79c0a8e687d7c08302585eee91540d07733727119e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:03:32.700366Z","signature_b64":"bnOi7UPxIFtXCFxDgfsTzj59hKjDiVI24NLVym7y2EclkcBbkmyEvM91vPOr2nKv/Jlklc6IUAlDL5fkuaNlBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4c71def236a066dcab68b1b1b499f040daeebbdb8b9b87adc5e2fead7cd0a60f","last_reissued_at":"2026-05-20T00:03:32.699460Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:03:32.699460Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"How do Humans Process AI-generated Hallucination Contents: a Neuroimaging Study","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Misjudged AI hallucinations fail to activate the brain's standard fact verification pathway, as shown by distinct EEG responses.","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Bangde Du, Qingyao Ai, Shuqi Zhu, Yiqun Liu, Yi Zhong, Yujia Zhou, Ziyi Ye","submitted_at":"2026-05-16T12:08:22Z","abstract_excerpt":"While AI-generated hallucinations pose considerable risks, the underlying cognitive mechanisms by which humans can successfully recognize or be misled by these hallucinations remain unclear. To address this problem, this paper explores humans' neural dynamics to characterize how the brain processes hallucinated content. We record EEG signals from 27 participants while they are performing a verification task to judge the correctness of image descriptions generated by a multi-modal large language model (MLLM). Based on an averaged event-related potential (ERP) study, we reveal that multiple cogn"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Notably, neural responses to hallucinations that were misjudged versus correctly judged by human participants showed significant differences. This indicates that misjudged AI-generated hallucinations failed to trigger the standard neurocognitive fact verification pathway.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The observed ERP differences specifically reflect processing of hallucinated content rather than confounding factors such as varying task difficulty, content complexity, or individual participant differences in the verification task.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"EEG study of 27 participants reveals distinct neural patterns for AI-generated hallucinations, with misjudged ones failing to trigger standard fact verification pathways.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Misjudged AI hallucinations fail to activate the brain's standard fact verification pathway, as shown by distinct EEG responses.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"be9d2940ef4bdb392eaaeab7c5dcbe6e4382e6302b5e10f250645ee5c25e8dfd"},"source":{"id":"2605.16953","kind":"arxiv","version":1},"verdict":{"id":"55daaa0f-1833-4d1b-9b5b-c83a361a7e7b","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-19T20:29:32.988803Z","strongest_claim":"Notably, neural responses to hallucinations that were misjudged versus correctly judged by human participants showed significant differences. This indicates that misjudged AI-generated hallucinations failed to trigger the standard neurocognitive fact verification pathway.","one_line_summary":"EEG study of 27 participants reveals distinct neural patterns for AI-generated hallucinations, with misjudged ones failing to trigger standard fact verification pathways.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The observed ERP differences specifically reflect processing of hallucinated content rather than confounding factors such as varying task difficulty, content complexity, or individual participant differences in the verification task.","pith_extraction_headline":"Misjudged AI hallucinations fail to activate the brain's standard fact verification pathway, as shown by distinct EEG responses."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.16953/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"doi_title_agreement","ran_at":"2026-05-19T21:01:19.095146Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T20:40:51.744617Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"cited_work_retraction","ran_at":"2026-05-19T19:52:00.115591Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"claim_evidence","ran_at":"2026-05-19T18:41:56.236628Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-19T18:33:26.320716Z","status":"skipped","version":"1.0.0","findings_count":0}],"snapshot_sha256":"948042268259f03647902adc392f2ce16af9a8d23a5ea787c766cd51795d8f6d"},"references":{"count":17,"sample":[{"doi":"","year":null,"title":"I think, therefore i hallucinate: Minds, ma- chines, and the art of being wrong.arXiv preprint arXiv:2503.05806,","work_id":"bd44320d-5fef-4d0d-88d1-a7546d468386","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Generated faces in the wild: Quantitative compar- ison of stable diffusion, midjourney and dall-e 2.arXiv preprint arXiv:2210.00586,","work_id":"42d28ba8-0d9d-4c38-8121-507939e5f689","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2025,"title":"Kim, S. S., Vaughan, J. W., Liao, Q. V ., Lombrozo, T., and Russakovsky, O. Fostering appropriate reliance on large language models: The role of explanations, sources, and inconsistencies. InProceedin","work_id":"8d72307d-e0e1-4fcb-b79e-9cf4f84083d7","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2014,"title":"Lin, T.-Y ., Maire, M., Belongie, S., Hays, J., Perona, P., Ra- manan, D., Doll´ar, P., and Zitnick, C. L. Microsoft coco: Common objects in context. InComputer Vision–ECCV 2014: 13th European Confere","work_id":"fd479e58-072e-4422-89cc-54be4808e008","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Models","work_id":"90efebf6-4006-4176-9bf1-21a876571751","ref_index":5,"cited_arxiv_id":"2303.08896","is_internal_anchor":true}],"resolved_work":17,"snapshot_sha256":"64f89f9790dd0ebaa3f88de78999230ecb1506a8468c7ba302ad2d222d513267","internal_anchors":8},"formal_canon":{"evidence_count":2,"snapshot_sha256":"06959eee32aecd3d8be5c9b680fcc31e3bfb45c92b6816eea51908d6c2a27ebc"},"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":"2605.16953","created_at":"2026-05-20T00:03:32.699627+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.16953v1","created_at":"2026-05-20T00:03:32.699627+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.16953","created_at":"2026-05-20T00:03:32.699627+00:00"},{"alias_kind":"pith_short_12","alias_value":"JRY554RWUBTN","created_at":"2026-05-20T00:03:32.699627+00:00"},{"alias_kind":"pith_short_16","alias_value":"JRY554RWUBTNZK3I","created_at":"2026-05-20T00:03:32.699627+00:00"},{"alias_kind":"pith_short_8","alias_value":"JRY554RW","created_at":"2026-05-20T00:03:32.699627+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JRY554RWUBTNZK3IWGY3JGPQID","json":"https://pith.science/pith/JRY554RWUBTNZK3IWGY3JGPQID.json","graph_json":"https://pith.science/api/pith-number/JRY554RWUBTNZK3IWGY3JGPQID/graph.json","events_json":"https://pith.science/api/pith-number/JRY554RWUBTNZK3IWGY3JGPQID/events.json","paper":"https://pith.science/paper/JRY554RW"},"agent_actions":{"view_html":"https://pith.science/pith/JRY554RWUBTNZK3IWGY3JGPQID","download_json":"https://pith.science/pith/JRY554RWUBTNZK3IWGY3JGPQID.json","view_paper":"https://pith.science/paper/JRY554RW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.16953&json=true","fetch_graph":"https://pith.science/api/pith-number/JRY554RWUBTNZK3IWGY3JGPQID/graph.json","fetch_events":"https://pith.science/api/pith-number/JRY554RWUBTNZK3IWGY3JGPQID/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JRY554RWUBTNZK3IWGY3JGPQID/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JRY554RWUBTNZK3IWGY3JGPQID/action/storage_attestation","attest_author":"https://pith.science/pith/JRY554RWUBTNZK3IWGY3JGPQID/action/author_attestation","sign_citation":"https://pith.science/pith/JRY554RWUBTNZK3IWGY3JGPQID/action/citation_signature","submit_replication":"https://pith.science/pith/JRY554RWUBTNZK3IWGY3JGPQID/action/replication_record"}},"created_at":"2026-05-20T00:03:32.699627+00:00","updated_at":"2026-05-20T00:03:32.699627+00:00"}