{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:PQWVUPPRAYJOJFT5NUQY3F4CQT","short_pith_number":"pith:PQWVUPPR","canonical_record":{"source":{"id":"2507.01050","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-23T05:48:10Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"22d3af0a4a7bb281548d379965e64611725f4d3af96cfdf171b1b109a27fbbe4","abstract_canon_sha256":"5e1fa488b16016dd12744952c11c2a2b7ba17d5523353fb1ab1709f32dfe0a38"},"schema_version":"1.0"},"canonical_sha256":"7c2d5a3df10612e4967d6d218d978284c68c527e2a621dd1865161c3201e96b4","source":{"kind":"arxiv","id":"2507.01050","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.01050","created_at":"2026-07-05T11:32:33Z"},{"alias_kind":"arxiv_version","alias_value":"2507.01050v2","created_at":"2026-07-05T11:32:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.01050","created_at":"2026-07-05T11:32:33Z"},{"alias_kind":"pith_short_12","alias_value":"PQWVUPPRAYJO","created_at":"2026-07-05T11:32:33Z"},{"alias_kind":"pith_short_16","alias_value":"PQWVUPPRAYJOJFT5","created_at":"2026-07-05T11:32:33Z"},{"alias_kind":"pith_short_8","alias_value":"PQWVUPPR","created_at":"2026-07-05T11:32:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:PQWVUPPRAYJOJFT5NUQY3F4CQT","target":"record","payload":{"canonical_record":{"source":{"id":"2507.01050","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-23T05:48:10Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"22d3af0a4a7bb281548d379965e64611725f4d3af96cfdf171b1b109a27fbbe4","abstract_canon_sha256":"5e1fa488b16016dd12744952c11c2a2b7ba17d5523353fb1ab1709f32dfe0a38"},"schema_version":"1.0"},"canonical_sha256":"7c2d5a3df10612e4967d6d218d978284c68c527e2a621dd1865161c3201e96b4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:32:33.107423Z","signature_b64":"rPJ4jBUNApHzuMzgS+OP14+Tji0UFHsaHBdIz+bEWdEwFdpY3BkgRoQwSzLwE9DPsuCVuLUqkYlkj0nbxd3eCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7c2d5a3df10612e4967d6d218d978284c68c527e2a621dd1865161c3201e96b4","last_reissued_at":"2026-07-05T11:32:33.106966Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:32:33.106966Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.01050","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:32:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JTuSOd1JXqmngO8CMZ2zl8gE/HQlFNF3lLyaTXxuhhyaKBha6QkCIwkWL+P1m2xaD4hXfowKFhCtzrxdOpzoBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T05:05:25.619549Z"},"content_sha256":"82ed6cd21566103b8e2e6211960561c2c1ddaabdad83dad8b8e70524a52b7f3b","schema_version":"1.0","event_id":"sha256:82ed6cd21566103b8e2e6211960561c2c1ddaabdad83dad8b8e70524a52b7f3b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:PQWVUPPRAYJOJFT5NUQY3F4CQT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Text Detoxification: Data Efficiency, Semantic Preservation and Model Generalization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Bo Pang, Jiapeng Zhu, Jing Yu, Wenming Shao, Xiang Li, Yibo Zhao, Zhao Zhang","submitted_at":"2025-06-23T05:48:10Z","abstract_excerpt":"The widespread dissemination of toxic content on social media poses a serious threat to both online environments and public discourse, highlighting the urgent need for detoxification methods that effectively remove toxicity while preserving the original semantics. However, existing approaches often struggle to simultaneously achieve strong detoxification performance, semantic preservation, and robustness to out-of-distribution data. Moreover, they typically rely on costly, manually annotated parallel corpora while showing poor data efficiency. To address these challenges, we propose a two-stag"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.01050","kind":"arxiv","version":2},"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/2507.01050/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:32:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"crffnziXFdqMFtpYL6YSXxlZUFYXr65hj1XDWY5nXwstYavRK+jfmQ8HmRUNKtiy4NiTsVNlacfALIgbEKR6CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T05:05:25.620075Z"},"content_sha256":"6280bf8227b969b5fc9fd3760e117c1657cd948ccb379e6b99fa7c69c4e2d5ea","schema_version":"1.0","event_id":"sha256:6280bf8227b969b5fc9fd3760e117c1657cd948ccb379e6b99fa7c69c4e2d5ea"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PQWVUPPRAYJOJFT5NUQY3F4CQT/bundle.json","state_url":"https://pith.science/pith/PQWVUPPRAYJOJFT5NUQY3F4CQT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PQWVUPPRAYJOJFT5NUQY3F4CQT/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-16T05:05:25Z","links":{"resolver":"https://pith.science/pith/PQWVUPPRAYJOJFT5NUQY3F4CQT","bundle":"https://pith.science/pith/PQWVUPPRAYJOJFT5NUQY3F4CQT/bundle.json","state":"https://pith.science/pith/PQWVUPPRAYJOJFT5NUQY3F4CQT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PQWVUPPRAYJOJFT5NUQY3F4CQT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:PQWVUPPRAYJOJFT5NUQY3F4CQT","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":"5e1fa488b16016dd12744952c11c2a2b7ba17d5523353fb1ab1709f32dfe0a38","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-23T05:48:10Z","title_canon_sha256":"22d3af0a4a7bb281548d379965e64611725f4d3af96cfdf171b1b109a27fbbe4"},"schema_version":"1.0","source":{"id":"2507.01050","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.01050","created_at":"2026-07-05T11:32:33Z"},{"alias_kind":"arxiv_version","alias_value":"2507.01050v2","created_at":"2026-07-05T11:32:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.01050","created_at":"2026-07-05T11:32:33Z"},{"alias_kind":"pith_short_12","alias_value":"PQWVUPPRAYJO","created_at":"2026-07-05T11:32:33Z"},{"alias_kind":"pith_short_16","alias_value":"PQWVUPPRAYJOJFT5","created_at":"2026-07-05T11:32:33Z"},{"alias_kind":"pith_short_8","alias_value":"PQWVUPPR","created_at":"2026-07-05T11:32:33Z"}],"graph_snapshots":[{"event_id":"sha256:6280bf8227b969b5fc9fd3760e117c1657cd948ccb379e6b99fa7c69c4e2d5ea","target":"graph","created_at":"2026-07-05T11:32:33Z","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/2507.01050/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The widespread dissemination of toxic content on social media poses a serious threat to both online environments and public discourse, highlighting the urgent need for detoxification methods that effectively remove toxicity while preserving the original semantics. However, existing approaches often struggle to simultaneously achieve strong detoxification performance, semantic preservation, and robustness to out-of-distribution data. Moreover, they typically rely on costly, manually annotated parallel corpora while showing poor data efficiency. To address these challenges, we propose a two-stag","authors_text":"Bo Pang, Jiapeng Zhu, Jing Yu, Wenming Shao, Xiang Li, Yibo Zhao, Zhao Zhang","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-23T05:48:10Z","title":"Text Detoxification: Data Efficiency, Semantic Preservation and Model Generalization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.01050","kind":"arxiv","version":2},"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":"sha256:82ed6cd21566103b8e2e6211960561c2c1ddaabdad83dad8b8e70524a52b7f3b","target":"record","created_at":"2026-07-05T11:32:33Z","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":"5e1fa488b16016dd12744952c11c2a2b7ba17d5523353fb1ab1709f32dfe0a38","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-23T05:48:10Z","title_canon_sha256":"22d3af0a4a7bb281548d379965e64611725f4d3af96cfdf171b1b109a27fbbe4"},"schema_version":"1.0","source":{"id":"2507.01050","kind":"arxiv","version":2}},"canonical_sha256":"7c2d5a3df10612e4967d6d218d978284c68c527e2a621dd1865161c3201e96b4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7c2d5a3df10612e4967d6d218d978284c68c527e2a621dd1865161c3201e96b4","first_computed_at":"2026-07-05T11:32:33.106966Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:32:33.106966Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rPJ4jBUNApHzuMzgS+OP14+Tji0UFHsaHBdIz+bEWdEwFdpY3BkgRoQwSzLwE9DPsuCVuLUqkYlkj0nbxd3eCA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:32:33.107423Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.01050","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:82ed6cd21566103b8e2e6211960561c2c1ddaabdad83dad8b8e70524a52b7f3b","sha256:6280bf8227b969b5fc9fd3760e117c1657cd948ccb379e6b99fa7c69c4e2d5ea"],"state_sha256":"48f8f8d1a820e8aab3bc99acf3337f382607fe903506559cd8c890d64f43bd88"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WDN7F9EC2Q+FqnOJ80JIjBqSpyBtpsHHDFqeIFKaBVsF5afaFzI5jyeBP0pc2SRTTIb3ocJCuxUfJwP2iYuNAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-16T05:05:25.625243Z","bundle_sha256":"6bc129764898c7d6ab06fe6beba3b35689ef43e92b73c4af2dd6bbbf5bd6691c"}}