{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:J33L7ABFSXLPLYSICON4C2XC7B","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"7b702477d588ef08385e9c4e26054025de9e91c66708d87f06a2b3f245c34348","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-12T17:34:38Z","title_canon_sha256":"93d07e77f8681845c80b46fd87e32d27ac2081d167fee39fef46082a8264efb9"},"schema_version":"1.0","source":{"id":"2506.10922","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.10922","created_at":"2026-07-05T11:20:40Z"},{"alias_kind":"arxiv_version","alias_value":"2506.10922v1","created_at":"2026-07-05T11:20:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.10922","created_at":"2026-07-05T11:20:40Z"},{"alias_kind":"pith_short_12","alias_value":"J33L7ABFSXLP","created_at":"2026-07-05T11:20:40Z"},{"alias_kind":"pith_short_16","alias_value":"J33L7ABFSXLPLYSI","created_at":"2026-07-05T11:20:40Z"},{"alias_kind":"pith_short_8","alias_value":"J33L7ABF","created_at":"2026-07-05T11:20:40Z"}],"graph_snapshots":[{"event_id":"sha256:14e92de1cf398680284762c7abad02a665ef1c7632dfb6c716bb1c8046dbac29","target":"graph","created_at":"2026-07-05T11:20:40Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2506.10922/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) are increasingly deployed in high-stakes hiring applications, making decisions that directly impact people's careers and livelihoods. While prior studies suggest simple anti-bias prompts can eliminate demographic biases in controlled evaluations, we find these mitigations fail when realistic contextual details are introduced. We address these failures through internal bias mitigation: by identifying and neutralizing sensitive attribute directions within model activations, we achieve robust bias reduction across all tested scenarios. Across leading commercial (GPT-4","authors_text":"Adam Karvonen, Samuel Marks","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-12T17:34:38Z","title":"Robustly Improving LLM Fairness in Realistic Settings via Interpretability"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.10922","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:f87fbbab4e2f39adf3a655da102ae5fc260436e0c498fa0ebc6059458f05a2cf","target":"record","created_at":"2026-07-05T11:20:40Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"7b702477d588ef08385e9c4e26054025de9e91c66708d87f06a2b3f245c34348","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-12T17:34:38Z","title_canon_sha256":"93d07e77f8681845c80b46fd87e32d27ac2081d167fee39fef46082a8264efb9"},"schema_version":"1.0","source":{"id":"2506.10922","kind":"arxiv","version":1}},"canonical_sha256":"4ef6bf802595d6f5e248139bc16ae2f8611f1a8e1900e9c2d4308ea4fcbfe547","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4ef6bf802595d6f5e248139bc16ae2f8611f1a8e1900e9c2d4308ea4fcbfe547","first_computed_at":"2026-07-05T11:20:40.399833Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:20:40.399833Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ay1L2+sCGiz6P3HR7rpUpaPsWcosMkAutx85e7KZm5AM+P/PrNhWSu/DT3OK6fM74hgU+SYsD6FP7+RYG0qDAg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:20:40.400348Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.10922","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f87fbbab4e2f39adf3a655da102ae5fc260436e0c498fa0ebc6059458f05a2cf","sha256:14e92de1cf398680284762c7abad02a665ef1c7632dfb6c716bb1c8046dbac29"],"state_sha256":"b8abd9f05bf610bde1a1326bf88eff7b4a6552f4ab6b7d3f457a5561cdb346d6"}