{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:IG5SHB7AUGQ24LGXX4ICLBE5UE","short_pith_number":"pith:IG5SHB7A","schema_version":"1.0","canonical_sha256":"41bb2387e0a1a1ae2cd7bf1025849da134aef00d4e00c2643ba4bf5ecb24256c","source":{"kind":"arxiv","id":"2004.09456","version":1},"attestation_state":"computed","paper":{"title":"StereoSet: Measuring stereotypical bias in pretrained language models","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CY"],"primary_cat":"cs.CL","authors_text":"Anna Bethke, Moin Nadeem, Siva Reddy","submitted_at":"2020-04-20T17:14:33Z","abstract_excerpt":"A stereotype is an over-generalized belief about a particular group of people, e.g., Asians are good at math or Asians are bad drivers. Such beliefs (biases) are known to hurt target groups. Since pretrained language models are trained on large real world data, they are known to capture stereotypical biases. In order to assess the adverse effects of these models, it is important to quantify the bias captured in them. Existing literature on quantifying bias evaluates pretrained language models on a small set of artificially constructed bias-assessing sentences. We present StereoSet, a large-sca"},"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":"2004.09456","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2020-04-20T17:14:33Z","cross_cats_sorted":["cs.AI","cs.CY"],"title_canon_sha256":"4b80ecdcf16cce32ef317270fd4c0319148166e893af73b579559c06e1ab3de3","abstract_canon_sha256":"79fae9d6a0b37ac5e1b5c8a8f21065bcfc619fb6c033c0e6d6b5e95fbf0c3ca6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:56:15.999560Z","signature_b64":"482cpyb19IGusc6u6+vnjwnUxTWEse+JBTDY1UUexrI8/xDCPM+uNDetiodmbIbItN5cQ7iZDsEN+aWFhXl2DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"41bb2387e0a1a1ae2cd7bf1025849da134aef00d4e00c2643ba4bf5ecb24256c","last_reissued_at":"2026-07-05T00:56:15.999110Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:56:15.999110Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"StereoSet: Measuring stereotypical bias in pretrained language models","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CY"],"primary_cat":"cs.CL","authors_text":"Anna Bethke, Moin Nadeem, Siva Reddy","submitted_at":"2020-04-20T17:14:33Z","abstract_excerpt":"A stereotype is an over-generalized belief about a particular group of people, e.g., Asians are good at math or Asians are bad drivers. Such beliefs (biases) are known to hurt target groups. Since pretrained language models are trained on large real world data, they are known to capture stereotypical biases. In order to assess the adverse effects of these models, it is important to quantify the bias captured in them. Existing literature on quantifying bias evaluates pretrained language models on a small set of artificially constructed bias-assessing sentences. We present StereoSet, a large-sca"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.09456","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/2004.09456/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":"2004.09456","created_at":"2026-07-05T00:56:15.999177+00:00"},{"alias_kind":"arxiv_version","alias_value":"2004.09456v1","created_at":"2026-07-05T00:56:15.999177+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.09456","created_at":"2026-07-05T00:56:15.999177+00:00"},{"alias_kind":"pith_short_12","alias_value":"IG5SHB7AUGQ2","created_at":"2026-07-05T00:56:15.999177+00:00"},{"alias_kind":"pith_short_16","alias_value":"IG5SHB7AUGQ24LGX","created_at":"2026-07-05T00:56:15.999177+00:00"},{"alias_kind":"pith_short_8","alias_value":"IG5SHB7A","created_at":"2026-07-05T00:56:15.999177+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":15,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.16723","citing_title":"AgentFairBench: Do LLM Agents Discriminate When They Act?","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2606.12234","citing_title":"On The Effectiveness-Fluency Trade-Off In LLM Conditioning: A Systematic Study","ref_index":85,"is_internal_anchor":false},{"citing_arxiv_id":"2606.05874","citing_title":"Evaluating Stochastic Collapse and Implicit Bias in Multimodal Large Language Models","ref_index":67,"is_internal_anchor":false},{"citing_arxiv_id":"2606.09881","citing_title":"Toward Calibrated, Fair, and accurate Deepfake Detection","ref_index":126,"is_internal_anchor":false},{"citing_arxiv_id":"2305.09620","citing_title":"AI-Augmented Surveys: Leveraging Large Language Models and Surveys for Opinion Prediction","ref_index":77,"is_internal_anchor":false},{"citing_arxiv_id":"2406.14194","citing_title":"VLBiasBench: A Comprehensive Benchmark for Evaluating Bias in Large Vision-Language Model","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17187","citing_title":"PluRule: A Benchmark for Moderating Pluralistic Communities on Social Media","ref_index":243,"is_internal_anchor":false},{"citing_arxiv_id":"2507.00439","citing_title":"Improving the Distributional Alignment of LLMs using Supervision","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2110.08193","citing_title":"BBQ: A Hand-Built Bias Benchmark for Question Answering","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12299","citing_title":"GKnow: Measuring the Entanglement of Gender Bias and Factual Gender","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10639","citing_title":"Navigating the Sea of LLM Evaluation: Investigating Bias in Toxicity Benchmarks","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2112.04359","citing_title":"Ethical and social risks of harm from Language Models","ref_index":200,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00382","citing_title":"Social Bias in LLM-Generated Code: Benchmark and Mitigation","ref_index":144,"is_internal_anchor":false},{"citing_arxiv_id":"2005.14165","citing_title":"Language Models are Few-Shot Learners","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17008","citing_title":"BIASEDTALES-ML: A Multilingual Dataset for Analyzing Narrative Attribute Distributions in LLM-Generated Stories","ref_index":18,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IG5SHB7AUGQ24LGXX4ICLBE5UE","json":"https://pith.science/pith/IG5SHB7AUGQ24LGXX4ICLBE5UE.json","graph_json":"https://pith.science/api/pith-number/IG5SHB7AUGQ24LGXX4ICLBE5UE/graph.json","events_json":"https://pith.science/api/pith-number/IG5SHB7AUGQ24LGXX4ICLBE5UE/events.json","paper":"https://pith.science/paper/IG5SHB7A"},"agent_actions":{"view_html":"https://pith.science/pith/IG5SHB7AUGQ24LGXX4ICLBE5UE","download_json":"https://pith.science/pith/IG5SHB7AUGQ24LGXX4ICLBE5UE.json","view_paper":"https://pith.science/paper/IG5SHB7A","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2004.09456&json=true","fetch_graph":"https://pith.science/api/pith-number/IG5SHB7AUGQ24LGXX4ICLBE5UE/graph.json","fetch_events":"https://pith.science/api/pith-number/IG5SHB7AUGQ24LGXX4ICLBE5UE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IG5SHB7AUGQ24LGXX4ICLBE5UE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IG5SHB7AUGQ24LGXX4ICLBE5UE/action/storage_attestation","attest_author":"https://pith.science/pith/IG5SHB7AUGQ24LGXX4ICLBE5UE/action/author_attestation","sign_citation":"https://pith.science/pith/IG5SHB7AUGQ24LGXX4ICLBE5UE/action/citation_signature","submit_replication":"https://pith.science/pith/IG5SHB7AUGQ24LGXX4ICLBE5UE/action/replication_record"}},"created_at":"2026-07-05T00:56:15.999177+00:00","updated_at":"2026-07-05T00:56:15.999177+00:00"}