{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:XWP3ZQ7PMJ7SD2HMQES7UWBT43","short_pith_number":"pith:XWP3ZQ7P","schema_version":"1.0","canonical_sha256":"bd9fbcc3ef627f21e8ec8125fa5833e6d8890ca3bb2149f6c6bd71d5e66542fe","source":{"kind":"arxiv","id":"2504.19445","version":1},"attestation_state":"computed","paper":{"title":"Systematic Bias in Large Language Models: Discrepant Response Patterns in Binary vs. Continuous Judgment Tasks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chunhui Zhang, Wei Wang, Yi-Long Lu","submitted_at":"2025-04-28T03:20:55Z","abstract_excerpt":"Large Language Models (LLMs) are increasingly used in tasks such as psychological text analysis and decision-making in automated workflows. However, their reliability remains a concern due to potential biases inherited from their training process. In this study, we examine how different response format: binary versus continuous, may systematically influence LLMs' judgments. In a value statement judgments task and a text sentiment analysis task, we prompted LLMs to simulate human responses and tested both formats across several models, including both open-source and commercial models. Our findi"},"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":"2504.19445","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-28T03:20:55Z","cross_cats_sorted":[],"title_canon_sha256":"ed62eaea1b18a9ed2bc2d2a5144bc3b44ad7b33ab0c81e9f9add263434177886","abstract_canon_sha256":"8314ce1618de399f772ac8d1261edb0f117f4fcb874f68e0053a3b4177ac8d0b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:54:57.665872Z","signature_b64":"V2xUq9Ero5q++rZtHQ1EDq/g12gIKCR4CyrcmA0EfTx+ha6LtE3yXzP7DhSwlg96lgAxdocMV6JPVd7xeH2XDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bd9fbcc3ef627f21e8ec8125fa5833e6d8890ca3bb2149f6c6bd71d5e66542fe","last_reissued_at":"2026-07-05T10:54:57.665397Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:54:57.665397Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Systematic Bias in Large Language Models: Discrepant Response Patterns in Binary vs. Continuous Judgment Tasks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chunhui Zhang, Wei Wang, Yi-Long Lu","submitted_at":"2025-04-28T03:20:55Z","abstract_excerpt":"Large Language Models (LLMs) are increasingly used in tasks such as psychological text analysis and decision-making in automated workflows. However, their reliability remains a concern due to potential biases inherited from their training process. In this study, we examine how different response format: binary versus continuous, may systematically influence LLMs' judgments. In a value statement judgments task and a text sentiment analysis task, we prompted LLMs to simulate human responses and tested both formats across several models, including both open-source and commercial models. Our findi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.19445","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/2504.19445/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":"2504.19445","created_at":"2026-07-05T10:54:57.665455+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.19445v1","created_at":"2026-07-05T10:54:57.665455+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.19445","created_at":"2026-07-05T10:54:57.665455+00:00"},{"alias_kind":"pith_short_12","alias_value":"XWP3ZQ7PMJ7S","created_at":"2026-07-05T10:54:57.665455+00:00"},{"alias_kind":"pith_short_16","alias_value":"XWP3ZQ7PMJ7SD2HM","created_at":"2026-07-05T10:54:57.665455+00:00"},{"alias_kind":"pith_short_8","alias_value":"XWP3ZQ7P","created_at":"2026-07-05T10:54:57.665455+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.22714","citing_title":"AMEL: Accumulated Message Effects on LLM Judgments","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22714","citing_title":"AMEL: Accumulated Message Effects on LLM Judgments","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14345","citing_title":"PAC-MCTS: Bias-Aware Pruning for Robust LLM-Guided Search and Planning","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14345","citing_title":"PAC-MCTS: Bias-Aware Pruning for Robust LLM-Guided Search and Planning","ref_index":1,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XWP3ZQ7PMJ7SD2HMQES7UWBT43","json":"https://pith.science/pith/XWP3ZQ7PMJ7SD2HMQES7UWBT43.json","graph_json":"https://pith.science/api/pith-number/XWP3ZQ7PMJ7SD2HMQES7UWBT43/graph.json","events_json":"https://pith.science/api/pith-number/XWP3ZQ7PMJ7SD2HMQES7UWBT43/events.json","paper":"https://pith.science/paper/XWP3ZQ7P"},"agent_actions":{"view_html":"https://pith.science/pith/XWP3ZQ7PMJ7SD2HMQES7UWBT43","download_json":"https://pith.science/pith/XWP3ZQ7PMJ7SD2HMQES7UWBT43.json","view_paper":"https://pith.science/paper/XWP3ZQ7P","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.19445&json=true","fetch_graph":"https://pith.science/api/pith-number/XWP3ZQ7PMJ7SD2HMQES7UWBT43/graph.json","fetch_events":"https://pith.science/api/pith-number/XWP3ZQ7PMJ7SD2HMQES7UWBT43/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XWP3ZQ7PMJ7SD2HMQES7UWBT43/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XWP3ZQ7PMJ7SD2HMQES7UWBT43/action/storage_attestation","attest_author":"https://pith.science/pith/XWP3ZQ7PMJ7SD2HMQES7UWBT43/action/author_attestation","sign_citation":"https://pith.science/pith/XWP3ZQ7PMJ7SD2HMQES7UWBT43/action/citation_signature","submit_replication":"https://pith.science/pith/XWP3ZQ7PMJ7SD2HMQES7UWBT43/action/replication_record"}},"created_at":"2026-07-05T10:54:57.665455+00:00","updated_at":"2026-07-05T10:54:57.665455+00:00"}