{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:XI2U5GOUUO4OW7TJ6T2IUMEZN5","short_pith_number":"pith:XI2U5GOU","schema_version":"1.0","canonical_sha256":"ba354e99d4a3b8eb7e69f4f48a30996f70ea2d3ef8c844fd504cc54efc927709","source":{"kind":"arxiv","id":"2412.06593","version":2},"attestation_state":"computed","paper":{"title":"Anchoring Bias in Large Language Models: An Experimental Study","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jiaxu Lou, Yifan Sun","submitted_at":"2024-12-09T15:45:03Z","abstract_excerpt":"Large Language Models (LLMs) like GPT-4 and Gemini have significantly advanced artificial intelligence by enabling machines to generate and comprehend human-like text. Despite their impressive capabilities, LLMs are not immune to limitations, including various biases. While much research has explored demographic biases, the cognitive biases in LLMs have not been equally scrutinized. This study delves into anchoring bias, a cognitive bias where initial information disproportionately influences judgment. Utilizing an experimental dataset, we examine how anchoring bias manifests in LLMs and verif"},"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":"2412.06593","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-09T15:45:03Z","cross_cats_sorted":[],"title_canon_sha256":"b56cd5c9b9dc64b3582e44e63cfad21ad793ae6322a3279652f18a1fc1eac8c3","abstract_canon_sha256":"aa45a4d7d5fdadba8c45f10c33fb64b12b00472225144cc7c0f6c97cfdf434f3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:50:55.037194Z","signature_b64":"ZJQUy39ixhWryWvGcOZULcoXdcJ10ybJKJpLSuiG9vMt+fYZb3HmrjoWWHesU/qtezo4olxhVKIgG5/i79p3AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ba354e99d4a3b8eb7e69f4f48a30996f70ea2d3ef8c844fd504cc54efc927709","last_reissued_at":"2026-07-05T09:50:55.036703Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:50:55.036703Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Anchoring Bias in Large Language Models: An Experimental Study","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jiaxu Lou, Yifan Sun","submitted_at":"2024-12-09T15:45:03Z","abstract_excerpt":"Large Language Models (LLMs) like GPT-4 and Gemini have significantly advanced artificial intelligence by enabling machines to generate and comprehend human-like text. Despite their impressive capabilities, LLMs are not immune to limitations, including various biases. While much research has explored demographic biases, the cognitive biases in LLMs have not been equally scrutinized. This study delves into anchoring bias, a cognitive bias where initial information disproportionately influences judgment. Utilizing an experimental dataset, we examine how anchoring bias manifests in LLMs and verif"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.06593","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/2412.06593/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":"2412.06593","created_at":"2026-07-05T09:50:55.036760+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.06593v2","created_at":"2026-07-05T09:50:55.036760+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.06593","created_at":"2026-07-05T09:50:55.036760+00:00"},{"alias_kind":"pith_short_12","alias_value":"XI2U5GOUUO4O","created_at":"2026-07-05T09:50:55.036760+00:00"},{"alias_kind":"pith_short_16","alias_value":"XI2U5GOUUO4OW7TJ","created_at":"2026-07-05T09:50:55.036760+00:00"},{"alias_kind":"pith_short_8","alias_value":"XI2U5GOU","created_at":"2026-07-05T09:50:55.036760+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.12818","citing_title":"Localizing Anchoring Pathways in Language Models","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22714","citing_title":"AMEL: Accumulated Message Effects on LLM Judgments","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2605.27485","citing_title":"Automating Formal Verification with Agent-Guided Tree Search","ref_index":112,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22714","citing_title":"AMEL: Accumulated Message Effects on LLM Judgments","ref_index":15,"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":38,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11789","citing_title":"Beyond Inefficiency: Systemic Costs of Incivility in Multi-Agent Monte Carlo Simulations","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11218","citing_title":"Don't Look at the Numbers: Visual Anchoring Bias and Layer-wise Representation in VLMs","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XI2U5GOUUO4OW7TJ6T2IUMEZN5","json":"https://pith.science/pith/XI2U5GOUUO4OW7TJ6T2IUMEZN5.json","graph_json":"https://pith.science/api/pith-number/XI2U5GOUUO4OW7TJ6T2IUMEZN5/graph.json","events_json":"https://pith.science/api/pith-number/XI2U5GOUUO4OW7TJ6T2IUMEZN5/events.json","paper":"https://pith.science/paper/XI2U5GOU"},"agent_actions":{"view_html":"https://pith.science/pith/XI2U5GOUUO4OW7TJ6T2IUMEZN5","download_json":"https://pith.science/pith/XI2U5GOUUO4OW7TJ6T2IUMEZN5.json","view_paper":"https://pith.science/paper/XI2U5GOU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.06593&json=true","fetch_graph":"https://pith.science/api/pith-number/XI2U5GOUUO4OW7TJ6T2IUMEZN5/graph.json","fetch_events":"https://pith.science/api/pith-number/XI2U5GOUUO4OW7TJ6T2IUMEZN5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XI2U5GOUUO4OW7TJ6T2IUMEZN5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XI2U5GOUUO4OW7TJ6T2IUMEZN5/action/storage_attestation","attest_author":"https://pith.science/pith/XI2U5GOUUO4OW7TJ6T2IUMEZN5/action/author_attestation","sign_citation":"https://pith.science/pith/XI2U5GOUUO4OW7TJ6T2IUMEZN5/action/citation_signature","submit_replication":"https://pith.science/pith/XI2U5GOUUO4OW7TJ6T2IUMEZN5/action/replication_record"}},"created_at":"2026-07-05T09:50:55.036760+00:00","updated_at":"2026-07-05T09:50:55.036760+00:00"}