{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:HCXV2QJ7DMG6E5HFRBDWSPBGRF","short_pith_number":"pith:HCXV2QJ7","schema_version":"1.0","canonical_sha256":"38af5d413f1b0de274e58847693c268946b24296a8c05bfeab5dc35ca32ee20b","source":{"kind":"arxiv","id":"2507.02799","version":1},"attestation_state":"computed","paper":{"title":"Is Reasoning All You Need? Probing Bias in the Age of Reasoning Language Models","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alessio Orsino, Domenico Talia, Nicola Gabriele, Riccardo Cantini","submitted_at":"2025-07-03T17:01:53Z","abstract_excerpt":"Reasoning Language Models (RLMs) have gained traction for their ability to perform complex, multi-step reasoning tasks through mechanisms such as Chain-of-Thought (CoT) prompting or fine-tuned reasoning traces. While these capabilities promise improved reliability, their impact on robustness to social biases remains unclear. In this work, we leverage the CLEAR-Bias benchmark, originally designed for Large Language Models (LLMs), to investigate the adversarial robustness of RLMs to bias elicitation. We systematically evaluate state-of-the-art RLMs across diverse sociocultural dimensions, using "},"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":"2507.02799","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-03T17:01:53Z","cross_cats_sorted":[],"title_canon_sha256":"ab838f542b0b1779a625f8d2ab98b37c50c91ce11034553f7d970cae9a7ba2aa","abstract_canon_sha256":"d4431551bc7924684d8bd1a8d2ddead728545773f38701d7f684ba27ca292f4a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:31:34.762968Z","signature_b64":"04UkaEDNQSTgIXPzEa4+Yrc9e0ib4tkY7mOt7cLp5Fl6nrN8M3Uw25+m2ApHbvK56/ieOds29hDTqbx+oAg0DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"38af5d413f1b0de274e58847693c268946b24296a8c05bfeab5dc35ca32ee20b","last_reissued_at":"2026-07-05T11:31:34.762490Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:31:34.762490Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Is Reasoning All You Need? Probing Bias in the Age of Reasoning Language Models","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alessio Orsino, Domenico Talia, Nicola Gabriele, Riccardo Cantini","submitted_at":"2025-07-03T17:01:53Z","abstract_excerpt":"Reasoning Language Models (RLMs) have gained traction for their ability to perform complex, multi-step reasoning tasks through mechanisms such as Chain-of-Thought (CoT) prompting or fine-tuned reasoning traces. While these capabilities promise improved reliability, their impact on robustness to social biases remains unclear. In this work, we leverage the CLEAR-Bias benchmark, originally designed for Large Language Models (LLMs), to investigate the adversarial robustness of RLMs to bias elicitation. We systematically evaluate state-of-the-art RLMs across diverse sociocultural dimensions, using "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.02799","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/2507.02799/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":"2507.02799","created_at":"2026-07-05T11:31:34.762548+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.02799v1","created_at":"2026-07-05T11:31:34.762548+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.02799","created_at":"2026-07-05T11:31:34.762548+00:00"},{"alias_kind":"pith_short_12","alias_value":"HCXV2QJ7DMG6","created_at":"2026-07-05T11:31:34.762548+00:00"},{"alias_kind":"pith_short_16","alias_value":"HCXV2QJ7DMG6E5HF","created_at":"2026-07-05T11:31:34.762548+00:00"},{"alias_kind":"pith_short_8","alias_value":"HCXV2QJ7","created_at":"2026-07-05T11:31:34.762548+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.21296","citing_title":"Discriminatory Compliance: How LLMs Answer Queries from Protected Groups","ref_index":89,"is_internal_anchor":false},{"citing_arxiv_id":"2510.17062","citing_title":"Investigating Thinking Behaviours of Reasoning-Based Language Models for Social Bias Mitigation","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17316","citing_title":"Calibrated? Not for Everyone: How Sexual Orientation and Religious Markers Distort LLM Accuracy and Confidence in Medical QA","ref_index":1,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HCXV2QJ7DMG6E5HFRBDWSPBGRF","json":"https://pith.science/pith/HCXV2QJ7DMG6E5HFRBDWSPBGRF.json","graph_json":"https://pith.science/api/pith-number/HCXV2QJ7DMG6E5HFRBDWSPBGRF/graph.json","events_json":"https://pith.science/api/pith-number/HCXV2QJ7DMG6E5HFRBDWSPBGRF/events.json","paper":"https://pith.science/paper/HCXV2QJ7"},"agent_actions":{"view_html":"https://pith.science/pith/HCXV2QJ7DMG6E5HFRBDWSPBGRF","download_json":"https://pith.science/pith/HCXV2QJ7DMG6E5HFRBDWSPBGRF.json","view_paper":"https://pith.science/paper/HCXV2QJ7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.02799&json=true","fetch_graph":"https://pith.science/api/pith-number/HCXV2QJ7DMG6E5HFRBDWSPBGRF/graph.json","fetch_events":"https://pith.science/api/pith-number/HCXV2QJ7DMG6E5HFRBDWSPBGRF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HCXV2QJ7DMG6E5HFRBDWSPBGRF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HCXV2QJ7DMG6E5HFRBDWSPBGRF/action/storage_attestation","attest_author":"https://pith.science/pith/HCXV2QJ7DMG6E5HFRBDWSPBGRF/action/author_attestation","sign_citation":"https://pith.science/pith/HCXV2QJ7DMG6E5HFRBDWSPBGRF/action/citation_signature","submit_replication":"https://pith.science/pith/HCXV2QJ7DMG6E5HFRBDWSPBGRF/action/replication_record"}},"created_at":"2026-07-05T11:31:34.762548+00:00","updated_at":"2026-07-05T11:31:34.762548+00:00"}