{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:2IXFANAX7NAQC2QOWC6Y2WLZBN","short_pith_number":"pith:2IXFANAX","schema_version":"1.0","canonical_sha256":"d22e503417fb41016a0eb0bd8d59790b54495dd5b9b5d3937dc25a1924a1f00a","source":{"kind":"arxiv","id":"2409.16022","version":2},"attestation_state":"computed","paper":{"title":"AI Can Be Cognitively Biased: An Exploratory Study on Threshold Priming in LLM-Based Batch Relevance Assessment","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Jiqun Liu, Nuo Chen, Qijiong Liu, Tetsuya Sakai, Xiao-Ming Wu, Xiaoyu Dong","submitted_at":"2024-09-24T12:23:15Z","abstract_excerpt":"Cognitive biases are systematic deviations in thinking that lead to irrational judgments and problematic decision-making, extensively studied across various fields. Recently, large language models (LLMs) have shown advanced understanding capabilities but may inherit human biases from their training data. While social biases in LLMs have been well-studied, cognitive biases have received less attention, with existing research focusing on specific scenarios. The broader impact of cognitive biases on LLMs in various decision-making contexts remains underexplored. We investigated whether LLMs are i"},"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":false},"canonical_record":{"source":{"id":"2409.16022","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-24T12:23:15Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"4d8384c4e310faabf4f1bf35fa2cccf29ae1ed7c75b43099630246f3b3c5841d","abstract_canon_sha256":"c6778fac2ddbfbfc834e3c500e78f64d65c847adb4c026564b437ae4767494e2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:17:48.943397Z","signature_b64":"VEV74KbTaDIAollYAOtkjX8//LSB9vWm0/BSiDkSuQKyKnv/K3crM2z0f098wTF1mkk0LSnX3npI/eeZ4ckxAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d22e503417fb41016a0eb0bd8d59790b54495dd5b9b5d3937dc25a1924a1f00a","last_reissued_at":"2026-07-05T09:17:48.942945Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:17:48.942945Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AI Can Be Cognitively Biased: An Exploratory Study on Threshold Priming in LLM-Based Batch Relevance Assessment","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Jiqun Liu, Nuo Chen, Qijiong Liu, Tetsuya Sakai, Xiao-Ming Wu, Xiaoyu Dong","submitted_at":"2024-09-24T12:23:15Z","abstract_excerpt":"Cognitive biases are systematic deviations in thinking that lead to irrational judgments and problematic decision-making, extensively studied across various fields. Recently, large language models (LLMs) have shown advanced understanding capabilities but may inherit human biases from their training data. While social biases in LLMs have been well-studied, cognitive biases have received less attention, with existing research focusing on specific scenarios. The broader impact of cognitive biases on LLMs in various decision-making contexts remains underexplored. We investigated whether LLMs are i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.16022","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2409.16022/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":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"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":"2409.16022","created_at":"2026-07-05T09:17:48.943003+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.16022v2","created_at":"2026-07-05T09:17:48.943003+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.16022","created_at":"2026-07-05T09:17:48.943003+00:00"},{"alias_kind":"pith_short_12","alias_value":"2IXFANAX7NAQ","created_at":"2026-07-05T09:17:48.943003+00:00"},{"alias_kind":"pith_short_16","alias_value":"2IXFANAX7NAQC2QO","created_at":"2026-07-05T09:17:48.943003+00:00"},{"alias_kind":"pith_short_8","alias_value":"2IXFANAX","created_at":"2026-07-05T09:17:48.943003+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.06593","citing_title":"Anchoring Bias in Large Language Models: An Experimental Study","ref_index":16,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2IXFANAX7NAQC2QOWC6Y2WLZBN","json":"https://pith.science/pith/2IXFANAX7NAQC2QOWC6Y2WLZBN.json","graph_json":"https://pith.science/api/pith-number/2IXFANAX7NAQC2QOWC6Y2WLZBN/graph.json","events_json":"https://pith.science/api/pith-number/2IXFANAX7NAQC2QOWC6Y2WLZBN/events.json","paper":"https://pith.science/paper/2IXFANAX"},"agent_actions":{"view_html":"https://pith.science/pith/2IXFANAX7NAQC2QOWC6Y2WLZBN","download_json":"https://pith.science/pith/2IXFANAX7NAQC2QOWC6Y2WLZBN.json","view_paper":"https://pith.science/paper/2IXFANAX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.16022&json=true","fetch_graph":"https://pith.science/api/pith-number/2IXFANAX7NAQC2QOWC6Y2WLZBN/graph.json","fetch_events":"https://pith.science/api/pith-number/2IXFANAX7NAQC2QOWC6Y2WLZBN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2IXFANAX7NAQC2QOWC6Y2WLZBN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2IXFANAX7NAQC2QOWC6Y2WLZBN/action/storage_attestation","attest_author":"https://pith.science/pith/2IXFANAX7NAQC2QOWC6Y2WLZBN/action/author_attestation","sign_citation":"https://pith.science/pith/2IXFANAX7NAQC2QOWC6Y2WLZBN/action/citation_signature","submit_replication":"https://pith.science/pith/2IXFANAX7NAQC2QOWC6Y2WLZBN/action/replication_record"}},"created_at":"2026-07-05T09:17:48.943003+00:00","updated_at":"2026-07-05T09:17:48.943003+00:00"}