{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:GTGGIJXGKVOURUDBHHNCN4VETH","short_pith_number":"pith:GTGGIJXG","canonical_record":{"source":{"id":"2411.15175","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-18T00:21:14Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c48cd38cc91411bfbb573717615b5b62539d19615c09d51ba461a25bfa330be5","abstract_canon_sha256":"7607fd81bbfb79a1691356eef6e943080c32ac8c1ada9b60b4b1964b11229c6d"},"schema_version":"1.0"},"canonical_sha256":"34cc6426e6555d48d06139da26f2a499f214187e75a530814d63ae2b35fc6f8a","source":{"kind":"arxiv","id":"2411.15175","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.15175","created_at":"2026-07-05T10:18:11Z"},{"alias_kind":"arxiv_version","alias_value":"2411.15175v4","created_at":"2026-07-05T10:18:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.15175","created_at":"2026-07-05T10:18:11Z"},{"alias_kind":"pith_short_12","alias_value":"GTGGIJXGKVOU","created_at":"2026-07-05T10:18:11Z"},{"alias_kind":"pith_short_16","alias_value":"GTGGIJXGKVOURUDB","created_at":"2026-07-05T10:18:11Z"},{"alias_kind":"pith_short_8","alias_value":"GTGGIJXG","created_at":"2026-07-05T10:18:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:GTGGIJXGKVOURUDBHHNCN4VETH","target":"record","payload":{"canonical_record":{"source":{"id":"2411.15175","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-18T00:21:14Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c48cd38cc91411bfbb573717615b5b62539d19615c09d51ba461a25bfa330be5","abstract_canon_sha256":"7607fd81bbfb79a1691356eef6e943080c32ac8c1ada9b60b4b1964b11229c6d"},"schema_version":"1.0"},"canonical_sha256":"34cc6426e6555d48d06139da26f2a499f214187e75a530814d63ae2b35fc6f8a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:18:11.195411Z","signature_b64":"/UhOE43nxvkSWN3NvvXieoY9ZqsNvi+Ju5v7sfpDOvTQH7Lgbe9vCqUxpIjalwf/DQYlWxqxmHkskf+UFFL/CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"34cc6426e6555d48d06139da26f2a499f214187e75a530814d63ae2b35fc6f8a","last_reissued_at":"2026-07-05T10:18:11.194904Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:18:11.194904Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.15175","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:18:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WXKTXEkfZGIamPWC5g56M9S9vowdLYsXhWlFuO/Nl6jRMFT8AP3FaWc0nYoHHQCYwi8Mbr43vfydzrgxk0uPBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-26T05:38:55.337755Z"},"content_sha256":"144892f43ae1972dd763905bfcb7da51c70d275cbd89f94d3299b612bf011c87","schema_version":"1.0","event_id":"sha256:144892f43ae1972dd763905bfcb7da51c70d275cbd89f94d3299b612bf011c87"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:GTGGIJXGKVOURUDBHHNCN4VETH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ToxiLab: How Well Do Open-Source LLMs Generate Synthetic Toxicity Data?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Congrui Huang, Hang Zhao, Juanyong Duan, Julia Hirschberg, Lin Ai, Yinheng Li, Zhaoxiao Guo, Zheng Hui","submitted_at":"2024-11-18T00:21:14Z","abstract_excerpt":"Effective toxic content detection relies heavily on high-quality and diverse data, which serve as the foundation for robust content moderation models. Synthetic data has become a common approach for training models across various NLP tasks. However, its effectiveness remains uncertain for highly subjective tasks like hate speech detection, with previous research yielding mixed results. This study explores the potential of open-source LLMs for harmful data synthesis, utilizing controlled prompting and supervised fine-tuning techniques to enhance data quality and diversity. We systematically eva"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.15175","kind":"arxiv","version":4},"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/2411.15175/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":"2026-07-05T10:18:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hXrim+JQbvSdogm+uE+lRp6c1x0ygVMZEBsRJN4k6KG03dCJFbcykbloh1DA1ZUVb0eRl5bQ7rl2EMUwcIA2AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-26T05:38:55.338148Z"},"content_sha256":"cde5b353f4b1ce45be5a6328da1f018f62883a0e43cba40cb6fe7540db258790","schema_version":"1.0","event_id":"sha256:cde5b353f4b1ce45be5a6328da1f018f62883a0e43cba40cb6fe7540db258790"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GTGGIJXGKVOURUDBHHNCN4VETH/bundle.json","state_url":"https://pith.science/pith/GTGGIJXGKVOURUDBHHNCN4VETH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GTGGIJXGKVOURUDBHHNCN4VETH/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":"2026-07-26T05:38:55Z","links":{"resolver":"https://pith.science/pith/GTGGIJXGKVOURUDBHHNCN4VETH","bundle":"https://pith.science/pith/GTGGIJXGKVOURUDBHHNCN4VETH/bundle.json","state":"https://pith.science/pith/GTGGIJXGKVOURUDBHHNCN4VETH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GTGGIJXGKVOURUDBHHNCN4VETH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:GTGGIJXGKVOURUDBHHNCN4VETH","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":"7607fd81bbfb79a1691356eef6e943080c32ac8c1ada9b60b4b1964b11229c6d","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-18T00:21:14Z","title_canon_sha256":"c48cd38cc91411bfbb573717615b5b62539d19615c09d51ba461a25bfa330be5"},"schema_version":"1.0","source":{"id":"2411.15175","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.15175","created_at":"2026-07-05T10:18:11Z"},{"alias_kind":"arxiv_version","alias_value":"2411.15175v4","created_at":"2026-07-05T10:18:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.15175","created_at":"2026-07-05T10:18:11Z"},{"alias_kind":"pith_short_12","alias_value":"GTGGIJXGKVOU","created_at":"2026-07-05T10:18:11Z"},{"alias_kind":"pith_short_16","alias_value":"GTGGIJXGKVOURUDB","created_at":"2026-07-05T10:18:11Z"},{"alias_kind":"pith_short_8","alias_value":"GTGGIJXG","created_at":"2026-07-05T10:18:11Z"}],"graph_snapshots":[{"event_id":"sha256:cde5b353f4b1ce45be5a6328da1f018f62883a0e43cba40cb6fe7540db258790","target":"graph","created_at":"2026-07-05T10:18:11Z","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/2411.15175/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Effective toxic content detection relies heavily on high-quality and diverse data, which serve as the foundation for robust content moderation models. Synthetic data has become a common approach for training models across various NLP tasks. However, its effectiveness remains uncertain for highly subjective tasks like hate speech detection, with previous research yielding mixed results. This study explores the potential of open-source LLMs for harmful data synthesis, utilizing controlled prompting and supervised fine-tuning techniques to enhance data quality and diversity. We systematically eva","authors_text":"Congrui Huang, Hang Zhao, Juanyong Duan, Julia Hirschberg, Lin Ai, Yinheng Li, Zhaoxiao Guo, Zheng Hui","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-18T00:21:14Z","title":"ToxiLab: How Well Do Open-Source LLMs Generate Synthetic Toxicity Data?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.15175","kind":"arxiv","version":4},"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":"sha256:144892f43ae1972dd763905bfcb7da51c70d275cbd89f94d3299b612bf011c87","target":"record","created_at":"2026-07-05T10:18:11Z","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":"7607fd81bbfb79a1691356eef6e943080c32ac8c1ada9b60b4b1964b11229c6d","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-18T00:21:14Z","title_canon_sha256":"c48cd38cc91411bfbb573717615b5b62539d19615c09d51ba461a25bfa330be5"},"schema_version":"1.0","source":{"id":"2411.15175","kind":"arxiv","version":4}},"canonical_sha256":"34cc6426e6555d48d06139da26f2a499f214187e75a530814d63ae2b35fc6f8a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"34cc6426e6555d48d06139da26f2a499f214187e75a530814d63ae2b35fc6f8a","first_computed_at":"2026-07-05T10:18:11.194904Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:18:11.194904Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/UhOE43nxvkSWN3NvvXieoY9ZqsNvi+Ju5v7sfpDOvTQH7Lgbe9vCqUxpIjalwf/DQYlWxqxmHkskf+UFFL/CQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:18:11.195411Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.15175","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:144892f43ae1972dd763905bfcb7da51c70d275cbd89f94d3299b612bf011c87","sha256:cde5b353f4b1ce45be5a6328da1f018f62883a0e43cba40cb6fe7540db258790"],"state_sha256":"a635e930f249c8520715bc979ca2a88d7bc5fc4dfcc9081967d114e885820352"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"h6c40CGolt/iY6Gg+Fz7ns2/j1nZaNvPKfzgbxFku7wc1gKty5JFcvhARrtBkKoXJbduH7RMOWJJ4Dtz3+w5DQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-26T05:38:55.340532Z","bundle_sha256":"856745ccdf3e8e113646918ae83114b2fb6dd7ee1a1057820590128264240eac"}}