{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:24XY472UL7KYCMAYY2RNJIO4QO","short_pith_number":"pith:24XY472U","schema_version":"1.0","canonical_sha256":"d72f8e7f545fd5813018c6a2d4a1dc83a2a510ae0e212f1f4d7f6a17b225a3a8","source":{"kind":"arxiv","id":"2409.11638","version":2},"attestation_state":"computed","paper":{"title":"BanStereoSet: A Dataset to Measure Stereotypical Social Biases in LLMs for Bangla","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Abdullah Al Monsur, Enamul Hassan, Gene Louis Kim, Mahammed Kamruzzaman, Shrabon Das","submitted_at":"2024-09-18T02:02:30Z","abstract_excerpt":"This study presents BanStereoSet, a dataset designed to evaluate stereotypical social biases in multilingual LLMs for the Bangla language. In an effort to extend the focus of bias research beyond English-centric datasets, we have localized the content from the StereoSet, IndiBias, and Kamruzzaman et. al.'s datasets, producing a resource tailored to capture biases prevalent within the Bangla-speaking community. Our BanStereoSet dataset consists of 1,194 sentences spanning 9 categories of bias: race, profession, gender, ageism, beauty, beauty in profession, region, caste, and religion. This data"},"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":"2409.11638","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2024-09-18T02:02:30Z","cross_cats_sorted":[],"title_canon_sha256":"385b5f594cfd60be39eb5b8459daf30c5f502fdeee7f5a3da3ad09090732ce29","abstract_canon_sha256":"ce05bb867b59a827240c27cbd79971bfea5b378ef078c371ac07f9549e4fd76d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:12:20.294742Z","signature_b64":"5yoqGBFNYsdWPASvUlapSPiqpJHS1WKRogImmLylt8UuRnlhWKHjJcBxtn/VIYyVxmbRDi3J7ecF8EX890RIAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d72f8e7f545fd5813018c6a2d4a1dc83a2a510ae0e212f1f4d7f6a17b225a3a8","last_reissued_at":"2026-07-05T11:12:20.294230Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:12:20.294230Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"BanStereoSet: A Dataset to Measure Stereotypical Social Biases in LLMs for Bangla","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Abdullah Al Monsur, Enamul Hassan, Gene Louis Kim, Mahammed Kamruzzaman, Shrabon Das","submitted_at":"2024-09-18T02:02:30Z","abstract_excerpt":"This study presents BanStereoSet, a dataset designed to evaluate stereotypical social biases in multilingual LLMs for the Bangla language. In an effort to extend the focus of bias research beyond English-centric datasets, we have localized the content from the StereoSet, IndiBias, and Kamruzzaman et. al.'s datasets, producing a resource tailored to capture biases prevalent within the Bangla-speaking community. Our BanStereoSet dataset consists of 1,194 sentences spanning 9 categories of bias: race, profession, gender, ageism, beauty, beauty in profession, region, caste, and religion. This data"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.11638","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/2409.11638/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":"2409.11638","created_at":"2026-07-05T11:12:20.294295+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.11638v2","created_at":"2026-07-05T11:12:20.294295+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.11638","created_at":"2026-07-05T11:12:20.294295+00:00"},{"alias_kind":"pith_short_12","alias_value":"24XY472UL7KY","created_at":"2026-07-05T11:12:20.294295+00:00"},{"alias_kind":"pith_short_16","alias_value":"24XY472UL7KYCMAY","created_at":"2026-07-05T11:12:20.294295+00:00"},{"alias_kind":"pith_short_8","alias_value":"24XY472U","created_at":"2026-07-05T11:12:20.294295+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/24XY472UL7KYCMAYY2RNJIO4QO","json":"https://pith.science/pith/24XY472UL7KYCMAYY2RNJIO4QO.json","graph_json":"https://pith.science/api/pith-number/24XY472UL7KYCMAYY2RNJIO4QO/graph.json","events_json":"https://pith.science/api/pith-number/24XY472UL7KYCMAYY2RNJIO4QO/events.json","paper":"https://pith.science/paper/24XY472U"},"agent_actions":{"view_html":"https://pith.science/pith/24XY472UL7KYCMAYY2RNJIO4QO","download_json":"https://pith.science/pith/24XY472UL7KYCMAYY2RNJIO4QO.json","view_paper":"https://pith.science/paper/24XY472U","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.11638&json=true","fetch_graph":"https://pith.science/api/pith-number/24XY472UL7KYCMAYY2RNJIO4QO/graph.json","fetch_events":"https://pith.science/api/pith-number/24XY472UL7KYCMAYY2RNJIO4QO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/24XY472UL7KYCMAYY2RNJIO4QO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/24XY472UL7KYCMAYY2RNJIO4QO/action/storage_attestation","attest_author":"https://pith.science/pith/24XY472UL7KYCMAYY2RNJIO4QO/action/author_attestation","sign_citation":"https://pith.science/pith/24XY472UL7KYCMAYY2RNJIO4QO/action/citation_signature","submit_replication":"https://pith.science/pith/24XY472UL7KYCMAYY2RNJIO4QO/action/replication_record"}},"created_at":"2026-07-05T11:12:20.294295+00:00","updated_at":"2026-07-05T11:12:20.294295+00:00"}