{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:LE4UJQK4ISUDM6OMSQIOFMFNEW","short_pith_number":"pith:LE4UJQK4","schema_version":"1.0","canonical_sha256":"593944c15c44a83679cc9410e2b0ad259fe7c98eadbc6f205539ec524e14e9c0","source":{"kind":"arxiv","id":"2507.10852","version":2},"attestation_state":"computed","paper":{"title":"LLMs on Trial: Evaluating Judicial Fairness for Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Charles L.A. Clarke, Haitao Li, Ning Zheng, Qingjing Chen, Qingyao Ai, Shaochun Wang, Siyuan Zheng, Weixing Shen, Xihan Zhang, Yiqun Liu, Yiran Hu, Yun Liu, Zongyue Xue","submitted_at":"2025-07-14T22:56:58Z","abstract_excerpt":"Large Language Models (LLMs) are increasingly used in high-stakes fields where their decisions impact rights and equity. However, LLMs' judicial fairness and implications for social justice remain underexplored. When LLMs act as judges, the ability to fairly resolve judicial issues is a prerequisite to ensure their trustworthiness. Based on theories of judicial fairness, we construct a comprehensive framework to measure LLM fairness, leading to a selection of 65 labels and 161 corresponding values. Applying this framework to the judicial system, we compile an extensive dataset, JudiFair, compr"},"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":"2507.10852","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-14T22:56:58Z","cross_cats_sorted":[],"title_canon_sha256":"eb17b90fa00fe3b584849231c47ddbd8e72f9ffb28d017e4b15b55e8521cf886","abstract_canon_sha256":"b0092ea77fada0860b988a47584b134c3bd77bec6c05cb8181482b5b1b225a24"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:47:26.037403Z","signature_b64":"Kv26Lf/r4CTWOBcJiwHwOzWvhigJyshL7QKKFF/oJ6ToOmpzZeBgKm/TNTD/HGlPEGyyM8O4JIblvB2XWt2RDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"593944c15c44a83679cc9410e2b0ad259fe7c98eadbc6f205539ec524e14e9c0","last_reissued_at":"2026-07-05T11:47:26.036891Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:47:26.036891Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LLMs on Trial: Evaluating Judicial Fairness for Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Charles L.A. Clarke, Haitao Li, Ning Zheng, Qingjing Chen, Qingyao Ai, Shaochun Wang, Siyuan Zheng, Weixing Shen, Xihan Zhang, Yiqun Liu, Yiran Hu, Yun Liu, Zongyue Xue","submitted_at":"2025-07-14T22:56:58Z","abstract_excerpt":"Large Language Models (LLMs) are increasingly used in high-stakes fields where their decisions impact rights and equity. However, LLMs' judicial fairness and implications for social justice remain underexplored. When LLMs act as judges, the ability to fairly resolve judicial issues is a prerequisite to ensure their trustworthiness. Based on theories of judicial fairness, we construct a comprehensive framework to measure LLM fairness, leading to a selection of 65 labels and 161 corresponding values. Applying this framework to the judicial system, we compile an extensive dataset, JudiFair, compr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.10852","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/2507.10852/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":"2507.10852","created_at":"2026-07-05T11:47:26.036950+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.10852v2","created_at":"2026-07-05T11:47:26.036950+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.10852","created_at":"2026-07-05T11:47:26.036950+00:00"},{"alias_kind":"pith_short_12","alias_value":"LE4UJQK4ISUD","created_at":"2026-07-05T11:47:26.036950+00:00"},{"alias_kind":"pith_short_16","alias_value":"LE4UJQK4ISUDM6OM","created_at":"2026-07-05T11:47:26.036950+00:00"},{"alias_kind":"pith_short_8","alias_value":"LE4UJQK4","created_at":"2026-07-05T11:47:26.036950+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LE4UJQK4ISUDM6OMSQIOFMFNEW","json":"https://pith.science/pith/LE4UJQK4ISUDM6OMSQIOFMFNEW.json","graph_json":"https://pith.science/api/pith-number/LE4UJQK4ISUDM6OMSQIOFMFNEW/graph.json","events_json":"https://pith.science/api/pith-number/LE4UJQK4ISUDM6OMSQIOFMFNEW/events.json","paper":"https://pith.science/paper/LE4UJQK4"},"agent_actions":{"view_html":"https://pith.science/pith/LE4UJQK4ISUDM6OMSQIOFMFNEW","download_json":"https://pith.science/pith/LE4UJQK4ISUDM6OMSQIOFMFNEW.json","view_paper":"https://pith.science/paper/LE4UJQK4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.10852&json=true","fetch_graph":"https://pith.science/api/pith-number/LE4UJQK4ISUDM6OMSQIOFMFNEW/graph.json","fetch_events":"https://pith.science/api/pith-number/LE4UJQK4ISUDM6OMSQIOFMFNEW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LE4UJQK4ISUDM6OMSQIOFMFNEW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LE4UJQK4ISUDM6OMSQIOFMFNEW/action/storage_attestation","attest_author":"https://pith.science/pith/LE4UJQK4ISUDM6OMSQIOFMFNEW/action/author_attestation","sign_citation":"https://pith.science/pith/LE4UJQK4ISUDM6OMSQIOFMFNEW/action/citation_signature","submit_replication":"https://pith.science/pith/LE4UJQK4ISUDM6OMSQIOFMFNEW/action/replication_record"}},"created_at":"2026-07-05T11:47:26.036950+00:00","updated_at":"2026-07-05T11:47:26.036950+00:00"}