{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:NES7RRTT2432IARPKLSUJFQNJC","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":"2b1a1d9a9b1777565bac3d4fc13ffbd8d087abd903139f2c6da27e3ac9329245","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-16T09:52:21Z","title_canon_sha256":"00c27485c2d7ee51a5e62479295f0f300ed4cbab6547fa6017d809eb7bdba034"},"schema_version":"1.0","source":{"id":"2405.09948","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.09948","created_at":"2026-07-05T11:10:45Z"},{"alias_kind":"arxiv_version","alias_value":"2405.09948v3","created_at":"2026-07-05T11:10:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.09948","created_at":"2026-07-05T11:10:45Z"},{"alias_kind":"pith_short_12","alias_value":"NES7RRTT2432","created_at":"2026-07-05T11:10:45Z"},{"alias_kind":"pith_short_16","alias_value":"NES7RRTT2432IARP","created_at":"2026-07-05T11:10:45Z"},{"alias_kind":"pith_short_8","alias_value":"NES7RRTT","created_at":"2026-07-05T11:10:45Z"}],"graph_snapshots":[{"event_id":"sha256:20430757022d965d1ea0bae3f5073a14e208b53f2d1bb63bc6044a21acda9189","target":"graph","created_at":"2026-07-05T11:10:45Z","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/2405.09948/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Toxicity mitigation consists in rephrasing text in order to remove offensive or harmful meaning. Neural natural language processing (NLP) models have been widely used to target and mitigate textual toxicity. However, existing methods fail to detoxify text while preserving the initial non-toxic meaning at the same time. In this work, we propose to apply counterfactual generation methods from the eXplainable AI (XAI) field to target and mitigate textual toxicity. In particular, we perform text detoxification by applying local feature importance and counterfactual generation methods to a toxicity","authors_text":"Annabelle Blangero, Jean-Noel Vittaut, Juliette Murris, Marie-Jeanne Lesot, Milan Bhan, Nicolas Chesneau, Nina Achache, Victor Legrand","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-16T09:52:21Z","title":"Mitigating Text Toxicity with Counterfactual Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.09948","kind":"arxiv","version":3},"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":"sha256:993168629fe886e90e21a2e237388d4ecebd35f09130bcec0253d69fe14876db","target":"record","created_at":"2026-07-05T11:10:45Z","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":"2b1a1d9a9b1777565bac3d4fc13ffbd8d087abd903139f2c6da27e3ac9329245","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-16T09:52:21Z","title_canon_sha256":"00c27485c2d7ee51a5e62479295f0f300ed4cbab6547fa6017d809eb7bdba034"},"schema_version":"1.0","source":{"id":"2405.09948","kind":"arxiv","version":3}},"canonical_sha256":"6925f8c673d737a4022f52e544960d48a41651640462d132091f628c62928736","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6925f8c673d737a4022f52e544960d48a41651640462d132091f628c62928736","first_computed_at":"2026-07-05T11:10:45.660519Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:10:45.660519Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YYJ7baceW+BflhgTTyR1NB3uPVsw6hCgt0ZyIPCptc0lK13Do4Cav1f4SCH9ApvEzj8nbMV9NXAZDxqqFTbrBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:10:45.661175Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.09948","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:993168629fe886e90e21a2e237388d4ecebd35f09130bcec0253d69fe14876db","sha256:20430757022d965d1ea0bae3f5073a14e208b53f2d1bb63bc6044a21acda9189"],"state_sha256":"84ec3261f508d12946d9efa46d68303a47c09b4a0dbe7c416bdde3c29e28c885"}