{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:LOPND6QUAZA343MTP6KHOU3HH2","short_pith_number":"pith:LOPND6QU","schema_version":"1.0","canonical_sha256":"5b9ed1fa140641be6d937f947753673e94d510d614d1f0a95bbc740bd74e6efb","source":{"kind":"arxiv","id":"2311.09090","version":4},"attestation_state":"computed","paper":{"title":"Social Bias Probing: Fairness Benchmarking for Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Isabelle Augenstein, Karolina Sta\\'nczak, Marta Marchiori Manerba, Riccardo Guidotti","submitted_at":"2023-11-15T16:35:59Z","abstract_excerpt":"While the impact of social biases in language models has been recognized, prior methods for bias evaluation have been limited to binary association tests on small datasets, limiting our understanding of bias complexities. This paper proposes a novel framework for probing language models for social biases by assessing disparate treatment, which involves treating individuals differently according to their affiliation with a sensitive demographic group. We curate SoFa, a large-scale benchmark designed to address the limitations of existing fairness collections. SoFa expands the analysis beyond th"},"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":"2311.09090","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-11-15T16:35:59Z","cross_cats_sorted":[],"title_canon_sha256":"2d35809f08fc0e43542a6f6e9d7419dfb697024163af09fddaeaacb67c25ac49","abstract_canon_sha256":"e07fc5cab78283c30585981d88483263c46050075cd8ae5fe08a3de6fb2b8b36"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:09:41.602882Z","signature_b64":"xkc3hwm+UpO3F+KkLRBChuxlWWjnxFKbe6yRG1Ymb/12iSiHRWQVSovRU7VhaiEMpDrF84p0GlHjYNU3iI0ABg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5b9ed1fa140641be6d937f947753673e94d510d614d1f0a95bbc740bd74e6efb","last_reissued_at":"2026-07-05T11:09:41.602367Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:09:41.602367Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Social Bias Probing: Fairness Benchmarking for Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Isabelle Augenstein, Karolina Sta\\'nczak, Marta Marchiori Manerba, Riccardo Guidotti","submitted_at":"2023-11-15T16:35:59Z","abstract_excerpt":"While the impact of social biases in language models has been recognized, prior methods for bias evaluation have been limited to binary association tests on small datasets, limiting our understanding of bias complexities. This paper proposes a novel framework for probing language models for social biases by assessing disparate treatment, which involves treating individuals differently according to their affiliation with a sensitive demographic group. We curate SoFa, a large-scale benchmark designed to address the limitations of existing fairness collections. SoFa expands the analysis beyond th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.09090","kind":"arxiv","version":4},"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/2311.09090/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":"2311.09090","created_at":"2026-07-05T11:09:41.602429+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.09090v4","created_at":"2026-07-05T11:09:41.602429+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.09090","created_at":"2026-07-05T11:09:41.602429+00:00"},{"alias_kind":"pith_short_12","alias_value":"LOPND6QUAZA3","created_at":"2026-07-05T11:09:41.602429+00:00"},{"alias_kind":"pith_short_16","alias_value":"LOPND6QUAZA343MT","created_at":"2026-07-05T11:09:41.602429+00:00"},{"alias_kind":"pith_short_8","alias_value":"LOPND6QU","created_at":"2026-07-05T11:09:41.602429+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.16128","citing_title":"Veracity Bias and Beyond: Uncovering LLMs' Hidden Beliefs in Problem-Solving Reasoning","ref_index":26,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LOPND6QUAZA343MTP6KHOU3HH2","json":"https://pith.science/pith/LOPND6QUAZA343MTP6KHOU3HH2.json","graph_json":"https://pith.science/api/pith-number/LOPND6QUAZA343MTP6KHOU3HH2/graph.json","events_json":"https://pith.science/api/pith-number/LOPND6QUAZA343MTP6KHOU3HH2/events.json","paper":"https://pith.science/paper/LOPND6QU"},"agent_actions":{"view_html":"https://pith.science/pith/LOPND6QUAZA343MTP6KHOU3HH2","download_json":"https://pith.science/pith/LOPND6QUAZA343MTP6KHOU3HH2.json","view_paper":"https://pith.science/paper/LOPND6QU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.09090&json=true","fetch_graph":"https://pith.science/api/pith-number/LOPND6QUAZA343MTP6KHOU3HH2/graph.json","fetch_events":"https://pith.science/api/pith-number/LOPND6QUAZA343MTP6KHOU3HH2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LOPND6QUAZA343MTP6KHOU3HH2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LOPND6QUAZA343MTP6KHOU3HH2/action/storage_attestation","attest_author":"https://pith.science/pith/LOPND6QUAZA343MTP6KHOU3HH2/action/author_attestation","sign_citation":"https://pith.science/pith/LOPND6QUAZA343MTP6KHOU3HH2/action/citation_signature","submit_replication":"https://pith.science/pith/LOPND6QUAZA343MTP6KHOU3HH2/action/replication_record"}},"created_at":"2026-07-05T11:09:41.602429+00:00","updated_at":"2026-07-05T11:09:41.602429+00:00"}