{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:XZCZ7GL33J5DTVIDLURLAKVZLJ","short_pith_number":"pith:XZCZ7GL3","schema_version":"1.0","canonical_sha256":"be459f997bda7a39d5035d22b02ab95a40e969c036b2bfc1fcd265e7acbd56f6","source":{"kind":"arxiv","id":"2312.06315","version":1},"attestation_state":"computed","paper":{"title":"GPTBIAS: A Comprehensive Framework for Evaluating Bias in Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CY","cs.LG"],"primary_cat":"cs.CL","authors_text":"Jiaxu Zhao, Meng Fang, Mykola Pechenizkiy, Shirui Pan, Wenpeng Yin","submitted_at":"2023-12-11T12:02:14Z","abstract_excerpt":"Warning: This paper contains content that may be offensive or upsetting. There has been a significant increase in the usage of large language models (LLMs) in various applications, both in their original form and through fine-tuned adaptations. As a result, LLMs have gained popularity and are being widely adopted by a large user community. However, one of the concerns with LLMs is the potential generation of socially biased content. The existing evaluation methods have many constraints, and their results exhibit a limited degree of interpretability. In this work, we propose a bias evaluation f"},"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":"2312.06315","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-12-11T12:02:14Z","cross_cats_sorted":["cs.CY","cs.LG"],"title_canon_sha256":"63cd0b6416423168e800fcb8d452331bac8310f33c6bed1f6783132a9e768019","abstract_canon_sha256":"ba21bb26d106f8ad3a9d5f19b401907d8b6a2df479ffb2f154db1e5b8c16dfdd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:22:42.608657Z","signature_b64":"g7jJpxGSWE/3Vsfpyig1Ta7m+MQXoj6gdhYMoTy2Lej/dVqqBBFugfiFWaZTWN/qT2dqPK2WIWdfmBxilaqjDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"be459f997bda7a39d5035d22b02ab95a40e969c036b2bfc1fcd265e7acbd56f6","last_reissued_at":"2026-07-05T07:22:42.608124Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:22:42.608124Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GPTBIAS: A Comprehensive Framework for Evaluating Bias in Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CY","cs.LG"],"primary_cat":"cs.CL","authors_text":"Jiaxu Zhao, Meng Fang, Mykola Pechenizkiy, Shirui Pan, Wenpeng Yin","submitted_at":"2023-12-11T12:02:14Z","abstract_excerpt":"Warning: This paper contains content that may be offensive or upsetting. There has been a significant increase in the usage of large language models (LLMs) in various applications, both in their original form and through fine-tuned adaptations. As a result, LLMs have gained popularity and are being widely adopted by a large user community. However, one of the concerns with LLMs is the potential generation of socially biased content. The existing evaluation methods have many constraints, and their results exhibit a limited degree of interpretability. In this work, we propose a bias evaluation f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.06315","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/2312.06315/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":"2312.06315","created_at":"2026-07-05T07:22:42.608186+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.06315v1","created_at":"2026-07-05T07:22:42.608186+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.06315","created_at":"2026-07-05T07:22:42.608186+00:00"},{"alias_kind":"pith_short_12","alias_value":"XZCZ7GL33J5D","created_at":"2026-07-05T07:22:42.608186+00:00"},{"alias_kind":"pith_short_16","alias_value":"XZCZ7GL33J5DTVID","created_at":"2026-07-05T07:22:42.608186+00:00"},{"alias_kind":"pith_short_8","alias_value":"XZCZ7GL3","created_at":"2026-07-05T07:22:42.608186+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.00382","citing_title":"Social Bias in LLM-Generated Code: Benchmark and Mitigation","ref_index":148,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05483","citing_title":"Can We Trust a Black-box LLM? LLM Untrustworthy Boundary Detection via Bias-Diffusion and Multi-Agent Reinforcement Learning","ref_index":44,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XZCZ7GL33J5DTVIDLURLAKVZLJ","json":"https://pith.science/pith/XZCZ7GL33J5DTVIDLURLAKVZLJ.json","graph_json":"https://pith.science/api/pith-number/XZCZ7GL33J5DTVIDLURLAKVZLJ/graph.json","events_json":"https://pith.science/api/pith-number/XZCZ7GL33J5DTVIDLURLAKVZLJ/events.json","paper":"https://pith.science/paper/XZCZ7GL3"},"agent_actions":{"view_html":"https://pith.science/pith/XZCZ7GL33J5DTVIDLURLAKVZLJ","download_json":"https://pith.science/pith/XZCZ7GL33J5DTVIDLURLAKVZLJ.json","view_paper":"https://pith.science/paper/XZCZ7GL3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.06315&json=true","fetch_graph":"https://pith.science/api/pith-number/XZCZ7GL33J5DTVIDLURLAKVZLJ/graph.json","fetch_events":"https://pith.science/api/pith-number/XZCZ7GL33J5DTVIDLURLAKVZLJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XZCZ7GL33J5DTVIDLURLAKVZLJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XZCZ7GL33J5DTVIDLURLAKVZLJ/action/storage_attestation","attest_author":"https://pith.science/pith/XZCZ7GL33J5DTVIDLURLAKVZLJ/action/author_attestation","sign_citation":"https://pith.science/pith/XZCZ7GL33J5DTVIDLURLAKVZLJ/action/citation_signature","submit_replication":"https://pith.science/pith/XZCZ7GL33J5DTVIDLURLAKVZLJ/action/replication_record"}},"created_at":"2026-07-05T07:22:42.608186+00:00","updated_at":"2026-07-05T07:22:42.608186+00:00"}