{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:O4ICOBPRM7LVXI4J4AQP2GXNN4","short_pith_number":"pith:O4ICOBPR","schema_version":"1.0","canonical_sha256":"77102705f167d75ba389e020fd1aed6f053df88f5d7b801138ca3c4ba08659c1","source":{"kind":"arxiv","id":"2506.04482","version":1},"attestation_state":"computed","paper":{"title":"Understanding and Meeting Practitioner Needs When Measuring Representational Harms Caused by LLM-Based Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CY","authors_text":"Alexandra Chouldechova, Alexandra Olteanu, Emily Sheng, Emma Harvey, Hanna Wallach, Jean Garcia-Gathright, Su Lin Blodgett","submitted_at":"2025-06-04T22:01:31Z","abstract_excerpt":"The NLP research community has made publicly available numerous instruments for measuring representational harms caused by large language model (LLM)-based systems. These instruments have taken the form of datasets, metrics, tools, and more. In this paper, we examine the extent to which such instruments meet the needs of practitioners tasked with evaluating LLM-based systems. Via semi-structured interviews with 12 such practitioners, we find that practitioners are often unable to use publicly available instruments for measuring representational harms. We identify two types of challenges. In so"},"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":"2506.04482","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CY","submitted_at":"2025-06-04T22:01:31Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"a382cfdd1af029114d34bbdd7343d98125caaf5201743bc251509f5f88d6f6fe","abstract_canon_sha256":"255bcba8b0dd76681c9666cca0469152f2f730c0f41d5c583b038ca570246d68"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:16:15.339449Z","signature_b64":"wSqzYsEwr/YVYR0MlVFrc+xbiIU9vNLS8pXLTN6S3L8wyLT24CajZBbvrdsPT16fFwATtAKknYjDSk0zt8rGAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"77102705f167d75ba389e020fd1aed6f053df88f5d7b801138ca3c4ba08659c1","last_reissued_at":"2026-07-05T11:16:15.338932Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:16:15.338932Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Understanding and Meeting Practitioner Needs When Measuring Representational Harms Caused by LLM-Based Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CY","authors_text":"Alexandra Chouldechova, Alexandra Olteanu, Emily Sheng, Emma Harvey, Hanna Wallach, Jean Garcia-Gathright, Su Lin Blodgett","submitted_at":"2025-06-04T22:01:31Z","abstract_excerpt":"The NLP research community has made publicly available numerous instruments for measuring representational harms caused by large language model (LLM)-based systems. These instruments have taken the form of datasets, metrics, tools, and more. In this paper, we examine the extent to which such instruments meet the needs of practitioners tasked with evaluating LLM-based systems. Via semi-structured interviews with 12 such practitioners, we find that practitioners are often unable to use publicly available instruments for measuring representational harms. We identify two types of challenges. In so"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.04482","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/2506.04482/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":"2506.04482","created_at":"2026-07-05T11:16:15.338985+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.04482v1","created_at":"2026-07-05T11:16:15.338985+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.04482","created_at":"2026-07-05T11:16:15.338985+00:00"},{"alias_kind":"pith_short_12","alias_value":"O4ICOBPRM7LV","created_at":"2026-07-05T11:16:15.338985+00:00"},{"alias_kind":"pith_short_16","alias_value":"O4ICOBPRM7LVXI4J","created_at":"2026-07-05T11:16:15.338985+00:00"},{"alias_kind":"pith_short_8","alias_value":"O4ICOBPR","created_at":"2026-07-05T11:16:15.338985+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.02406","citing_title":"Evaluating AI-Generated Images of Cultural Artifacts with Community-Informed Rubrics","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2604.02406","citing_title":"Evaluating AI-Generated Images of Cultural Artifacts with Community-Informed Rubrics","ref_index":51,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/O4ICOBPRM7LVXI4J4AQP2GXNN4","json":"https://pith.science/pith/O4ICOBPRM7LVXI4J4AQP2GXNN4.json","graph_json":"https://pith.science/api/pith-number/O4ICOBPRM7LVXI4J4AQP2GXNN4/graph.json","events_json":"https://pith.science/api/pith-number/O4ICOBPRM7LVXI4J4AQP2GXNN4/events.json","paper":"https://pith.science/paper/O4ICOBPR"},"agent_actions":{"view_html":"https://pith.science/pith/O4ICOBPRM7LVXI4J4AQP2GXNN4","download_json":"https://pith.science/pith/O4ICOBPRM7LVXI4J4AQP2GXNN4.json","view_paper":"https://pith.science/paper/O4ICOBPR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.04482&json=true","fetch_graph":"https://pith.science/api/pith-number/O4ICOBPRM7LVXI4J4AQP2GXNN4/graph.json","fetch_events":"https://pith.science/api/pith-number/O4ICOBPRM7LVXI4J4AQP2GXNN4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/O4ICOBPRM7LVXI4J4AQP2GXNN4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/O4ICOBPRM7LVXI4J4AQP2GXNN4/action/storage_attestation","attest_author":"https://pith.science/pith/O4ICOBPRM7LVXI4J4AQP2GXNN4/action/author_attestation","sign_citation":"https://pith.science/pith/O4ICOBPRM7LVXI4J4AQP2GXNN4/action/citation_signature","submit_replication":"https://pith.science/pith/O4ICOBPRM7LVXI4J4AQP2GXNN4/action/replication_record"}},"created_at":"2026-07-05T11:16:15.338985+00:00","updated_at":"2026-07-05T11:16:15.338985+00:00"}