{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:5TE7NC4PEX72AEHDAYUIFOYPJ7","short_pith_number":"pith:5TE7NC4P","canonical_record":{"source":{"id":"2409.14740","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-23T06:36:57Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"696466fede89e7ecaf0ef1fc27cf779016aa19df736745a291e022c9189b6685","abstract_canon_sha256":"9b817f1056539a7adee4e57a2450fe9943b4835b007ebff393e3933ce1ecd159"},"schema_version":"1.0"},"canonical_sha256":"ecc9f68b8f25ffa010e3062882bb0f4ff84c0a4309d1e3aea6522a13990befa9","source":{"kind":"arxiv","id":"2409.14740","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.14740","created_at":"2026-07-05T10:49:09Z"},{"alias_kind":"arxiv_version","alias_value":"2409.14740v2","created_at":"2026-07-05T10:49:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.14740","created_at":"2026-07-05T10:49:09Z"},{"alias_kind":"pith_short_12","alias_value":"5TE7NC4PEX72","created_at":"2026-07-05T10:49:09Z"},{"alias_kind":"pith_short_16","alias_value":"5TE7NC4PEX72AEHD","created_at":"2026-07-05T10:49:09Z"},{"alias_kind":"pith_short_8","alias_value":"5TE7NC4P","created_at":"2026-07-05T10:49:09Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:5TE7NC4PEX72AEHDAYUIFOYPJ7","target":"record","payload":{"canonical_record":{"source":{"id":"2409.14740","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-23T06:36:57Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"696466fede89e7ecaf0ef1fc27cf779016aa19df736745a291e022c9189b6685","abstract_canon_sha256":"9b817f1056539a7adee4e57a2450fe9943b4835b007ebff393e3933ce1ecd159"},"schema_version":"1.0"},"canonical_sha256":"ecc9f68b8f25ffa010e3062882bb0f4ff84c0a4309d1e3aea6522a13990befa9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:49:09.344535Z","signature_b64":"wmNv6FBsdIMdQhaFb/ajzNh0wmrrK0dQx/Sl3ev1h/08WGlCVkGJhQY8QDUEgLnHfdsSI+ETquYiw9tpM7PIDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ecc9f68b8f25ffa010e3062882bb0f4ff84c0a4309d1e3aea6522a13990befa9","last_reissued_at":"2026-07-05T10:49:09.343334Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:49:09.343334Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2409.14740","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":"2026-07-05T10:49:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VYo7M3n2uQ3vARJJVTfJ2FzRd9S+l5ok0DnoI1oPhPgsLMUt2Y+eNli8rcLvajg+4z7JPbY/vM5W+B6MR88TCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T15:29:35.254814Z"},"content_sha256":"b4d376cb1aa69b31bd76b2f0904f04213e62954c0a74e603976543deee454c29","schema_version":"1.0","event_id":"sha256:b4d376cb1aa69b31bd76b2f0904f04213e62954c0a74e603976543deee454c29"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:5TE7NC4PEX72AEHDAYUIFOYPJ7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ToxiCraft: A Novel Framework for Synthetic Generation of Harmful Information","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, Zhaoxiao Guo, Zheng Hui","submitted_at":"2024-09-23T06:36:57Z","abstract_excerpt":"In different NLP tasks, detecting harmful content is crucial for online environments, especially with the growing influence of social media. However, previous research has two main issues: 1) a lack of data in low-resource settings, and 2) inconsistent definitions and criteria for judging harmful content, requiring classification models to be robust to spurious features and diverse. We propose Toxicraft, a novel framework for synthesizing datasets of harmful information to address these weaknesses. With only a small amount of seed data, our framework can generate a wide variety of synthetic, y"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.14740","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/2409.14740/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":"2026-07-05T10:49:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"G1/mg/gKKCHV41olSU8GZpDjDMD9qQzJiOqtw0z7RCZD4evLCJ0Zkb+NNDhaJhNE7X0n5g7Xr8+Fckb/IL6xCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T15:29:35.255201Z"},"content_sha256":"e47ff2811da28948ce42bdf74bdbad6c69296c1a249c0b5dde2bd2fe26c8740a","schema_version":"1.0","event_id":"sha256:e47ff2811da28948ce42bdf74bdbad6c69296c1a249c0b5dde2bd2fe26c8740a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5TE7NC4PEX72AEHDAYUIFOYPJ7/bundle.json","state_url":"https://pith.science/pith/5TE7NC4PEX72AEHDAYUIFOYPJ7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5TE7NC4PEX72AEHDAYUIFOYPJ7/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":"2026-08-03T15:29:35Z","links":{"resolver":"https://pith.science/pith/5TE7NC4PEX72AEHDAYUIFOYPJ7","bundle":"https://pith.science/pith/5TE7NC4PEX72AEHDAYUIFOYPJ7/bundle.json","state":"https://pith.science/pith/5TE7NC4PEX72AEHDAYUIFOYPJ7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5TE7NC4PEX72AEHDAYUIFOYPJ7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:5TE7NC4PEX72AEHDAYUIFOYPJ7","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":"9b817f1056539a7adee4e57a2450fe9943b4835b007ebff393e3933ce1ecd159","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-23T06:36:57Z","title_canon_sha256":"696466fede89e7ecaf0ef1fc27cf779016aa19df736745a291e022c9189b6685"},"schema_version":"1.0","source":{"id":"2409.14740","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.14740","created_at":"2026-07-05T10:49:09Z"},{"alias_kind":"arxiv_version","alias_value":"2409.14740v2","created_at":"2026-07-05T10:49:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.14740","created_at":"2026-07-05T10:49:09Z"},{"alias_kind":"pith_short_12","alias_value":"5TE7NC4PEX72","created_at":"2026-07-05T10:49:09Z"},{"alias_kind":"pith_short_16","alias_value":"5TE7NC4PEX72AEHD","created_at":"2026-07-05T10:49:09Z"},{"alias_kind":"pith_short_8","alias_value":"5TE7NC4P","created_at":"2026-07-05T10:49:09Z"}],"graph_snapshots":[{"event_id":"sha256:e47ff2811da28948ce42bdf74bdbad6c69296c1a249c0b5dde2bd2fe26c8740a","target":"graph","created_at":"2026-07-05T10:49:09Z","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/2409.14740/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In different NLP tasks, detecting harmful content is crucial for online environments, especially with the growing influence of social media. However, previous research has two main issues: 1) a lack of data in low-resource settings, and 2) inconsistent definitions and criteria for judging harmful content, requiring classification models to be robust to spurious features and diverse. We propose Toxicraft, a novel framework for synthesizing datasets of harmful information to address these weaknesses. With only a small amount of seed data, our framework can generate a wide variety of synthetic, y","authors_text":"Congrui Huang, Hang Zhao, Juanyong Duan, Zhaoxiao Guo, Zheng Hui","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-23T06:36:57Z","title":"ToxiCraft: A Novel Framework for Synthetic Generation of Harmful Information"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.14740","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:b4d376cb1aa69b31bd76b2f0904f04213e62954c0a74e603976543deee454c29","target":"record","created_at":"2026-07-05T10:49:09Z","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":"9b817f1056539a7adee4e57a2450fe9943b4835b007ebff393e3933ce1ecd159","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-23T06:36:57Z","title_canon_sha256":"696466fede89e7ecaf0ef1fc27cf779016aa19df736745a291e022c9189b6685"},"schema_version":"1.0","source":{"id":"2409.14740","kind":"arxiv","version":2}},"canonical_sha256":"ecc9f68b8f25ffa010e3062882bb0f4ff84c0a4309d1e3aea6522a13990befa9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ecc9f68b8f25ffa010e3062882bb0f4ff84c0a4309d1e3aea6522a13990befa9","first_computed_at":"2026-07-05T10:49:09.343334Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:49:09.343334Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wmNv6FBsdIMdQhaFb/ajzNh0wmrrK0dQx/Sl3ev1h/08WGlCVkGJhQY8QDUEgLnHfdsSI+ETquYiw9tpM7PIDw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:49:09.344535Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.14740","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b4d376cb1aa69b31bd76b2f0904f04213e62954c0a74e603976543deee454c29","sha256:e47ff2811da28948ce42bdf74bdbad6c69296c1a249c0b5dde2bd2fe26c8740a"],"state_sha256":"bfc87d8a9e57a852e2963c3a0bd20de27ea28ff9a38a7617c7469ae0c0bae183"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aiqih7yj15Z2Tnhbs+tsGywDCdXmOUPiWHfsYCQyRnERAp4pOxxky60T/QgV7v1CACjdhIUOn8XBa3z10+Y3CA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T15:29:35.259024Z","bundle_sha256":"113440dbe9deb7c73594068d75a45c2e8f4fa1180bda1a1d4fe250049f61af0d"}}