{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:ODZVNJM6STBYUSCXEX2UJTEAP7","short_pith_number":"pith:ODZVNJM6","schema_version":"1.0","canonical_sha256":"70f356a59e94c38a485725f544cc807fd99c5ce353e176a09dda667950869b5c","source":{"kind":"arxiv","id":"2607.05679","version":1},"attestation_state":"computed","paper":{"title":"RPAM: A Principled Metric for Evaluating Associations in Language Models with High Predictive Validity in Downstream Outputs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Aylin Caliskan, Damian Hodel, Jevin West","submitted_at":"2026-07-06T22:48:13Z","abstract_excerpt":"Language models (LMs) exhibit problematic biases, such as stereotypes. Effectively analyzing and mitigating such biases requires accurate and generalizable evaluation methods of the underlying associations. Some existing approaches focus on downstream metrics that analyze associations in generated text. Since generated text content can vary drastically across LMs, such metrics often require specialized evaluation datasets, which limits the generalization of such downstream metrics. In contrast, upstream metrics examine LMs at the fundamental level of embeddings or continuation probabilities, e"},"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":"2607.05679","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-06T22:48:13Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"1f867871b88fe8d3e4ae3fb15ac70cb81bab115e37885523d5ead9dddb4bb075","abstract_canon_sha256":"1df377c5c8eff03de51a4316d64adf70f13820bb890a92da681f4022ca39209c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-08T01:18:41.432476Z","signature_b64":"hhIZpqIOWu7WP45C1Rv6hWNzCV6VaOjWkRI5g4TVL9D3tF7qtnlNA7KU1BLniTSiEWd+tSjxtMREb2WmagQ9DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"70f356a59e94c38a485725f544cc807fd99c5ce353e176a09dda667950869b5c","last_reissued_at":"2026-07-08T01:18:41.432063Z","signature_status":"signed_v1","first_computed_at":"2026-07-08T01:18:41.432063Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RPAM: A Principled Metric for Evaluating Associations in Language Models with High Predictive Validity in Downstream Outputs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Aylin Caliskan, Damian Hodel, Jevin West","submitted_at":"2026-07-06T22:48:13Z","abstract_excerpt":"Language models (LMs) exhibit problematic biases, such as stereotypes. Effectively analyzing and mitigating such biases requires accurate and generalizable evaluation methods of the underlying associations. Some existing approaches focus on downstream metrics that analyze associations in generated text. Since generated text content can vary drastically across LMs, such metrics often require specialized evaluation datasets, which limits the generalization of such downstream metrics. In contrast, upstream metrics examine LMs at the fundamental level of embeddings or continuation probabilities, e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.05679","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/2607.05679/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":"2607.05679","created_at":"2026-07-08T01:18:41.432116+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.05679v1","created_at":"2026-07-08T01:18:41.432116+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.05679","created_at":"2026-07-08T01:18:41.432116+00:00"},{"alias_kind":"pith_short_12","alias_value":"ODZVNJM6STBY","created_at":"2026-07-08T01:18:41.432116+00:00"},{"alias_kind":"pith_short_16","alias_value":"ODZVNJM6STBYUSCX","created_at":"2026-07-08T01:18:41.432116+00:00"},{"alias_kind":"pith_short_8","alias_value":"ODZVNJM6","created_at":"2026-07-08T01:18:41.432116+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/ODZVNJM6STBYUSCXEX2UJTEAP7","json":"https://pith.science/pith/ODZVNJM6STBYUSCXEX2UJTEAP7.json","graph_json":"https://pith.science/api/pith-number/ODZVNJM6STBYUSCXEX2UJTEAP7/graph.json","events_json":"https://pith.science/api/pith-number/ODZVNJM6STBYUSCXEX2UJTEAP7/events.json","paper":"https://pith.science/paper/ODZVNJM6"},"agent_actions":{"view_html":"https://pith.science/pith/ODZVNJM6STBYUSCXEX2UJTEAP7","download_json":"https://pith.science/pith/ODZVNJM6STBYUSCXEX2UJTEAP7.json","view_paper":"https://pith.science/paper/ODZVNJM6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.05679&json=true","fetch_graph":"https://pith.science/api/pith-number/ODZVNJM6STBYUSCXEX2UJTEAP7/graph.json","fetch_events":"https://pith.science/api/pith-number/ODZVNJM6STBYUSCXEX2UJTEAP7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ODZVNJM6STBYUSCXEX2UJTEAP7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ODZVNJM6STBYUSCXEX2UJTEAP7/action/storage_attestation","attest_author":"https://pith.science/pith/ODZVNJM6STBYUSCXEX2UJTEAP7/action/author_attestation","sign_citation":"https://pith.science/pith/ODZVNJM6STBYUSCXEX2UJTEAP7/action/citation_signature","submit_replication":"https://pith.science/pith/ODZVNJM6STBYUSCXEX2UJTEAP7/action/replication_record"}},"created_at":"2026-07-08T01:18:41.432116+00:00","updated_at":"2026-07-08T01:18:41.432116+00:00"}