{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:FNMRPS4EGIPGFQ7PYFRTUX6WWT","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":"11a36480625262b5d1431f200ff99217c815bf7b047c4af2df20b72268591d2b","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-02T12:48:29Z","title_canon_sha256":"bb02211b26a832765e36bc2d00a4c98f6a50458b3e1052b29dd7ee4b5274104a"},"schema_version":"1.0","source":{"id":"2407.12824","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.12824","created_at":"2026-07-05T08:45:12Z"},{"alias_kind":"arxiv_version","alias_value":"2407.12824v1","created_at":"2026-07-05T08:45:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.12824","created_at":"2026-07-05T08:45:12Z"},{"alias_kind":"pith_short_12","alias_value":"FNMRPS4EGIPG","created_at":"2026-07-05T08:45:12Z"},{"alias_kind":"pith_short_16","alias_value":"FNMRPS4EGIPGFQ7P","created_at":"2026-07-05T08:45:12Z"},{"alias_kind":"pith_short_8","alias_value":"FNMRPS4E","created_at":"2026-07-05T08:45:12Z"}],"graph_snapshots":[{"event_id":"sha256:6d320268cb5425591816fe22efe578b747423799c5ef29bbca788efdfe8e8650","target":"graph","created_at":"2026-07-05T08:45:12Z","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/2407.12824/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"An important issue with Large Language Models (LLMs) is their undesired ability to generate toxic language. In this work, we show that the neurons responsible for toxicity can be determined by their power to discriminate toxic sentences, and that toxic language can be mitigated by reducing their activation levels proportionally to this power. We propose AUROC adaptation (AurA), an intervention that can be applied to any pre-trained LLM to mitigate toxicity. As the intervention is proportional to the ability of each neuron to discriminate toxic content, it is free of any model-dependent hyperpa","authors_text":"Armand Joulin, Katherine Metcalf, Luca Zappella, Nicholas Apostoloff, Pau Rodr\\'iguez, Pieter Delobelle, Xavier Suau","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-02T12:48:29Z","title":"Whispering Experts: Neural Interventions for Toxicity Mitigation in Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.12824","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:c88f41276d6bfddcefaba1bb759159342d649b3667e53ff8ee6a074bed2f0658","target":"record","created_at":"2026-07-05T08:45:12Z","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":"11a36480625262b5d1431f200ff99217c815bf7b047c4af2df20b72268591d2b","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-02T12:48:29Z","title_canon_sha256":"bb02211b26a832765e36bc2d00a4c98f6a50458b3e1052b29dd7ee4b5274104a"},"schema_version":"1.0","source":{"id":"2407.12824","kind":"arxiv","version":1}},"canonical_sha256":"2b5917cb84321e62c3efc1633a5fd6b4e59f277d6856873797980b754a4e8481","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2b5917cb84321e62c3efc1633a5fd6b4e59f277d6856873797980b754a4e8481","first_computed_at":"2026-07-05T08:45:12.201858Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:45:12.201858Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BR8pH3yusd4EMPlfG+2oFURJIKO8sFrFbOn1Nj3O+U0xCcy+d26wh8KohfSP4m5q85sOuMj6h6GBIJiVEKvjBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:45:12.202397Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.12824","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c88f41276d6bfddcefaba1bb759159342d649b3667e53ff8ee6a074bed2f0658","sha256:6d320268cb5425591816fe22efe578b747423799c5ef29bbca788efdfe8e8650"],"state_sha256":"0e4e0190c5821257e219eb186cd1749899687a886b33c5dea266e072d96ee46f"}