{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:3G77PKDSYKCBYUDT2X43G3ZESY","short_pith_number":"pith:3G77PKDS","schema_version":"1.0","canonical_sha256":"d9bff7a872c2841c5073d5f9b36f2496317d599085859f9b5a536ca28b4ef2b1","source":{"kind":"arxiv","id":"2412.03605","version":1},"attestation_state":"computed","paper":{"title":"CBEval: A framework for evaluating and interpreting cognitive biases in LLMs","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.HC"],"primary_cat":"cs.CL","authors_text":"Ammar Shaikh, Raj Abhijit Dandekar, Rajat Dandekar, Sreedath Panat","submitted_at":"2024-12-04T05:53:28Z","abstract_excerpt":"Rapid advancements in Large Language models (LLMs) has significantly enhanced their reasoning capabilities. Despite improved performance on benchmarks, LLMs exhibit notable gaps in their cognitive processes. Additionally, as reflections of human-generated data, these models have the potential to inherit cognitive biases, raising concerns about their reasoning and decision making capabilities. In this paper we present a framework to interpret, understand and provide insights into a host of cognitive biases in LLMs. Conducting our research on frontier language models we're able to elucidate reas"},"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":"2412.03605","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-04T05:53:28Z","cross_cats_sorted":["cs.AI","cs.HC"],"title_canon_sha256":"7553e56264057fdccb7f08469e15c2af447e9593f568db3bd1169f02fbe34262","abstract_canon_sha256":"dd6665af8d464661048138dab9f617e290a0a5438ed584f51377276f7da9dbf5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:44:38.862555Z","signature_b64":"NhT0+Hpop2C5ul56+Sx/Xu5oN8Uzm6XYb1HKEbxqKtiPmW3xTiXKvTJ207JEFy19zckTUOYBYUI2GoX39jyoDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d9bff7a872c2841c5073d5f9b36f2496317d599085859f9b5a536ca28b4ef2b1","last_reissued_at":"2026-07-05T09:44:38.862078Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:44:38.862078Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CBEval: A framework for evaluating and interpreting cognitive biases in LLMs","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.HC"],"primary_cat":"cs.CL","authors_text":"Ammar Shaikh, Raj Abhijit Dandekar, Rajat Dandekar, Sreedath Panat","submitted_at":"2024-12-04T05:53:28Z","abstract_excerpt":"Rapid advancements in Large Language models (LLMs) has significantly enhanced their reasoning capabilities. Despite improved performance on benchmarks, LLMs exhibit notable gaps in their cognitive processes. Additionally, as reflections of human-generated data, these models have the potential to inherit cognitive biases, raising concerns about their reasoning and decision making capabilities. In this paper we present a framework to interpret, understand and provide insights into a host of cognitive biases in LLMs. Conducting our research on frontier language models we're able to elucidate reas"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.03605","kind":"arxiv","version":1},"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/2412.03605/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":"2412.03605","created_at":"2026-07-05T09:44:38.862135+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.03605v1","created_at":"2026-07-05T09:44:38.862135+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.03605","created_at":"2026-07-05T09:44:38.862135+00:00"},{"alias_kind":"pith_short_12","alias_value":"3G77PKDSYKCB","created_at":"2026-07-05T09:44:38.862135+00:00"},{"alias_kind":"pith_short_16","alias_value":"3G77PKDSYKCBYUDT","created_at":"2026-07-05T09:44:38.862135+00:00"},{"alias_kind":"pith_short_8","alias_value":"3G77PKDS","created_at":"2026-07-05T09:44:38.862135+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.22714","citing_title":"AMEL: Accumulated Message Effects on LLM Judgments","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22714","citing_title":"AMEL: Accumulated Message Effects on LLM Judgments","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2506.14092","citing_title":"Fragile Preferences: A Deep Dive Into Order Effects in Large Language Models","ref_index":59,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3G77PKDSYKCBYUDT2X43G3ZESY","json":"https://pith.science/pith/3G77PKDSYKCBYUDT2X43G3ZESY.json","graph_json":"https://pith.science/api/pith-number/3G77PKDSYKCBYUDT2X43G3ZESY/graph.json","events_json":"https://pith.science/api/pith-number/3G77PKDSYKCBYUDT2X43G3ZESY/events.json","paper":"https://pith.science/paper/3G77PKDS"},"agent_actions":{"view_html":"https://pith.science/pith/3G77PKDSYKCBYUDT2X43G3ZESY","download_json":"https://pith.science/pith/3G77PKDSYKCBYUDT2X43G3ZESY.json","view_paper":"https://pith.science/paper/3G77PKDS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.03605&json=true","fetch_graph":"https://pith.science/api/pith-number/3G77PKDSYKCBYUDT2X43G3ZESY/graph.json","fetch_events":"https://pith.science/api/pith-number/3G77PKDSYKCBYUDT2X43G3ZESY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3G77PKDSYKCBYUDT2X43G3ZESY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3G77PKDSYKCBYUDT2X43G3ZESY/action/storage_attestation","attest_author":"https://pith.science/pith/3G77PKDSYKCBYUDT2X43G3ZESY/action/author_attestation","sign_citation":"https://pith.science/pith/3G77PKDSYKCBYUDT2X43G3ZESY/action/citation_signature","submit_replication":"https://pith.science/pith/3G77PKDSYKCBYUDT2X43G3ZESY/action/replication_record"}},"created_at":"2026-07-05T09:44:38.862135+00:00","updated_at":"2026-07-05T09:44:38.862135+00:00"}