{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:5TE7NC4PEX72AEHDAYUIFOYPJ7","short_pith_number":"pith:5TE7NC4P","schema_version":"1.0","canonical_sha256":"ecc9f68b8f25ffa010e3062882bb0f4ff84c0a4309d1e3aea6522a13990befa9","source":{"kind":"arxiv","id":"2409.14740","version":2},"attestation_state":"computed","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"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"},"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"},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2409.14740","created_at":"2026-07-05T10:49:09.343399+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.14740v2","created_at":"2026-07-05T10:49:09.343399+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.14740","created_at":"2026-07-05T10:49:09.343399+00:00"},{"alias_kind":"pith_short_12","alias_value":"5TE7NC4PEX72","created_at":"2026-07-05T10:49:09.343399+00:00"},{"alias_kind":"pith_short_16","alias_value":"5TE7NC4PEX72AEHD","created_at":"2026-07-05T10:49:09.343399+00:00"},{"alias_kind":"pith_short_8","alias_value":"5TE7NC4P","created_at":"2026-07-05T10:49:09.343399+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5TE7NC4PEX72AEHDAYUIFOYPJ7","json":"https://pith.science/pith/5TE7NC4PEX72AEHDAYUIFOYPJ7.json","graph_json":"https://pith.science/api/pith-number/5TE7NC4PEX72AEHDAYUIFOYPJ7/graph.json","events_json":"https://pith.science/api/pith-number/5TE7NC4PEX72AEHDAYUIFOYPJ7/events.json","paper":"https://pith.science/paper/5TE7NC4P"},"agent_actions":{"view_html":"https://pith.science/pith/5TE7NC4PEX72AEHDAYUIFOYPJ7","download_json":"https://pith.science/pith/5TE7NC4PEX72AEHDAYUIFOYPJ7.json","view_paper":"https://pith.science/paper/5TE7NC4P","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.14740&json=true","fetch_graph":"https://pith.science/api/pith-number/5TE7NC4PEX72AEHDAYUIFOYPJ7/graph.json","fetch_events":"https://pith.science/api/pith-number/5TE7NC4PEX72AEHDAYUIFOYPJ7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5TE7NC4PEX72AEHDAYUIFOYPJ7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5TE7NC4PEX72AEHDAYUIFOYPJ7/action/storage_attestation","attest_author":"https://pith.science/pith/5TE7NC4PEX72AEHDAYUIFOYPJ7/action/author_attestation","sign_citation":"https://pith.science/pith/5TE7NC4PEX72AEHDAYUIFOYPJ7/action/citation_signature","submit_replication":"https://pith.science/pith/5TE7NC4PEX72AEHDAYUIFOYPJ7/action/replication_record"}},"created_at":"2026-07-05T10:49:09.343399+00:00","updated_at":"2026-07-05T10:49:09.343399+00:00"}