{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:MSVELTBFLBEXRFK7EATFETDCCY","short_pith_number":"pith:MSVELTBF","schema_version":"1.0","canonical_sha256":"64aa45cc25584978955f2026524c621601a67d66eadce2e0a1c58ebd4e5c6f59","source":{"kind":"arxiv","id":"2108.01764","version":1},"attestation_state":"computed","paper":{"title":"Q-Pain: A Question Answering Dataset to Measure Social Bias in Pain Management","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Adriel Saporta, Andrew Y. Ng, C\\'ecile Log\\'e, David Yaw Amoah Dadey, Emily Ross, Pranav Rajpurkar, Saahil Jain","submitted_at":"2021-08-03T21:55:28Z","abstract_excerpt":"Recent advances in Natural Language Processing (NLP), and specifically automated Question Answering (QA) systems, have demonstrated both impressive linguistic fluency and a pernicious tendency to reflect social biases. In this study, we introduce Q-Pain, a dataset for assessing bias in medical QA in the context of pain management, one of the most challenging forms of clinical decision-making. Along with the dataset, we propose a new, rigorous framework, including a sample experimental design, to measure the potential biases present when making treatment decisions. We demonstrate its use by ass"},"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":"2108.01764","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-08-03T21:55:28Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8b21ee33b5cf4af06c38de97cbecdda2c035fd19809e8bfdf4b0aedb13538dd6","abstract_canon_sha256":"005ee8f43ee46bec81d9ae93072ce0760bc23df136b1aec743cb1d1cb34d2a5a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:03:10.382362Z","signature_b64":"Wq1SvRag89C8Lzb9v0lVKWzZyhofdl/zcIk9Y1AGwlLL5mthL+R108kRxC/e9IXYzO2uzsH4SZ7ws0B/HzqfBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"64aa45cc25584978955f2026524c621601a67d66eadce2e0a1c58ebd4e5c6f59","last_reissued_at":"2026-07-05T03:03:10.381887Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:03:10.381887Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Q-Pain: A Question Answering Dataset to Measure Social Bias in Pain Management","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Adriel Saporta, Andrew Y. Ng, C\\'ecile Log\\'e, David Yaw Amoah Dadey, Emily Ross, Pranav Rajpurkar, Saahil Jain","submitted_at":"2021-08-03T21:55:28Z","abstract_excerpt":"Recent advances in Natural Language Processing (NLP), and specifically automated Question Answering (QA) systems, have demonstrated both impressive linguistic fluency and a pernicious tendency to reflect social biases. In this study, we introduce Q-Pain, a dataset for assessing bias in medical QA in the context of pain management, one of the most challenging forms of clinical decision-making. Along with the dataset, we propose a new, rigorous framework, including a sample experimental design, to measure the potential biases present when making treatment decisions. We demonstrate its use by ass"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.01764","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/2108.01764/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":"2108.01764","created_at":"2026-07-05T03:03:10.381946+00:00"},{"alias_kind":"arxiv_version","alias_value":"2108.01764v1","created_at":"2026-07-05T03:03:10.381946+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.01764","created_at":"2026-07-05T03:03:10.381946+00:00"},{"alias_kind":"pith_short_12","alias_value":"MSVELTBFLBEX","created_at":"2026-07-05T03:03:10.381946+00:00"},{"alias_kind":"pith_short_16","alias_value":"MSVELTBFLBEXRFK7","created_at":"2026-07-05T03:03:10.381946+00:00"},{"alias_kind":"pith_short_8","alias_value":"MSVELTBF","created_at":"2026-07-05T03:03:10.381946+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.01048","citing_title":"Compared to What? Baselines and Metrics for Counterfactual Prompting","ref_index":166,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01048","citing_title":"Compared to What? Baselines and Metrics for Counterfactual Prompting","ref_index":2,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MSVELTBFLBEXRFK7EATFETDCCY","json":"https://pith.science/pith/MSVELTBFLBEXRFK7EATFETDCCY.json","graph_json":"https://pith.science/api/pith-number/MSVELTBFLBEXRFK7EATFETDCCY/graph.json","events_json":"https://pith.science/api/pith-number/MSVELTBFLBEXRFK7EATFETDCCY/events.json","paper":"https://pith.science/paper/MSVELTBF"},"agent_actions":{"view_html":"https://pith.science/pith/MSVELTBFLBEXRFK7EATFETDCCY","download_json":"https://pith.science/pith/MSVELTBFLBEXRFK7EATFETDCCY.json","view_paper":"https://pith.science/paper/MSVELTBF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2108.01764&json=true","fetch_graph":"https://pith.science/api/pith-number/MSVELTBFLBEXRFK7EATFETDCCY/graph.json","fetch_events":"https://pith.science/api/pith-number/MSVELTBFLBEXRFK7EATFETDCCY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MSVELTBFLBEXRFK7EATFETDCCY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MSVELTBFLBEXRFK7EATFETDCCY/action/storage_attestation","attest_author":"https://pith.science/pith/MSVELTBFLBEXRFK7EATFETDCCY/action/author_attestation","sign_citation":"https://pith.science/pith/MSVELTBFLBEXRFK7EATFETDCCY/action/citation_signature","submit_replication":"https://pith.science/pith/MSVELTBFLBEXRFK7EATFETDCCY/action/replication_record"}},"created_at":"2026-07-05T03:03:10.381946+00:00","updated_at":"2026-07-05T03:03:10.381946+00:00"}