{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:GXS5HKIMRFSPO5REKBF4VSX6XD","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":"fa8813ae84a46debb0174bfd6cb41ab98e0f5f4337ccb9919f040764e5a16037","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-27T05:41:19Z","title_canon_sha256":"6615bca6deba3c7520e0fc344e9041035d60b8066b7f9009d4c26bf1e3b9dfc1"},"schema_version":"1.0","source":{"id":"2605.27997","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.27997","created_at":"2026-05-28T01:04:55Z"},{"alias_kind":"arxiv_version","alias_value":"2605.27997v1","created_at":"2026-05-28T01:04:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.27997","created_at":"2026-05-28T01:04:55Z"},{"alias_kind":"pith_short_12","alias_value":"GXS5HKIMRFSP","created_at":"2026-05-28T01:04:55Z"},{"alias_kind":"pith_short_16","alias_value":"GXS5HKIMRFSPO5RE","created_at":"2026-05-28T01:04:55Z"},{"alias_kind":"pith_short_8","alias_value":"GXS5HKIM","created_at":"2026-05-28T01:04:55Z"}],"graph_snapshots":[{"event_id":"sha256:cd6161a9225cb2713afe87f3220a865513142db16f8fed5965546fbf719a286e","target":"graph","created_at":"2026-05-28T01:04:55Z","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/2605.27997/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models frequently generate toxic, hateful, or harmful content, yet existing mitigation methods rely on costly retraining or output-level filtering with no mechanistic insight into where toxicity originates internally. We introduce Meow2X and TRNE, two complementary retraining-free frameworks that localize toxicity to specific layers and neurons by analyzing activation differentials between toxic and neutral prompts, then suppress them via inference-time scaling or minimal rank-one weight edits -- without any gradient descent. Evaluations across five LMs, two benchmarks, and 90 c","authors_text":"Himanshu Beniwal, Mayank Singh","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-27T05:41:19Z","title":"Where Does Toxicity Live? Mechanistic Localization and Targeted Suppression in Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.27997","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":"sha256:943c76a4d11fb790eabe2d80e1efa5e0492de9e73342727600eb234e45874376","target":"record","created_at":"2026-05-28T01:04:55Z","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":"fa8813ae84a46debb0174bfd6cb41ab98e0f5f4337ccb9919f040764e5a16037","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-27T05:41:19Z","title_canon_sha256":"6615bca6deba3c7520e0fc344e9041035d60b8066b7f9009d4c26bf1e3b9dfc1"},"schema_version":"1.0","source":{"id":"2605.27997","kind":"arxiv","version":1}},"canonical_sha256":"35e5d3a90c8964f77624504bcacafeb8f510f31af9606570bdffde66123cede0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"35e5d3a90c8964f77624504bcacafeb8f510f31af9606570bdffde66123cede0","first_computed_at":"2026-05-28T01:04:55.602542Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-28T01:04:55.602542Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Hbv61XK14lDnOcZECyztCd1MiBjSLEPc8R+dHdI4WL1O798DNYxSUq9FyJVGkfKShIoNf7x6JBZQ6ywhwPhfBw==","signature_status":"signed_v1","signed_at":"2026-05-28T01:04:55.602959Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.27997","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:943c76a4d11fb790eabe2d80e1efa5e0492de9e73342727600eb234e45874376","sha256:cd6161a9225cb2713afe87f3220a865513142db16f8fed5965546fbf719a286e"],"state_sha256":"3e03626b53f1871be2d4d568054d73ff817da079cf11dd6bf068d1cca75a373c"}