{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:PKJJ5XOU5PMORR2U6CB3FOO7NZ","short_pith_number":"pith:PKJJ5XOU","schema_version":"1.0","canonical_sha256":"7a929eddd4ebd8e8c754f083b2b9df6e7d461ddb1060c292a6db109af827fe08","source":{"kind":"arxiv","id":"2604.11796","version":2},"attestation_state":"computed","paper":{"title":"C-ReD: A Comprehensive Chinese Benchmark for AI-Generated Text Detection Derived from Real-World Prompts","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"The C-ReD benchmark uses real-world prompts to achieve reliable Chinese AI-text detection and generalization to unseen LLMs and external datasets.","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Bin Chen, Chenxi Qing, Hao Wu, Hongyao Yu, Junxi Wu, Shu-Tao Xia, Yixiang Qiu, Zheng Liu","submitted_at":"2026-04-13T17:56:27Z","abstract_excerpt":"Recently, large language models (LLMs) are capable of generating highly fluent textual content. While they offer significant convenience to humans, they also introduce various risks, like phishing and academic dishonesty. Numerous research efforts have been dedicated to developing algorithms for detecting AI-generated text and constructing relevant datasets. However, in the domain of Chinese corpora, challenges remain, including limited model diversity and data homogeneity. To address these issues, we propose C-ReD: a comprehensive Chinese Real-prompt AI-generated Detection benchmark. Experime"},"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":"2604.11796","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-04-13T17:56:27Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"6f3deab8814d16d848b96e87e8d6affe2406ef08a51d30356a38da3d12072bcc","abstract_canon_sha256":"b2ad41cbfd4b3229b3262551d3d22e44e235aadbac4a8c0e79592ffbf80c03cf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T01:05:13.147008Z","signature_b64":"WLx7/2yyO6OHhn3itt1CBPuABObuBGLpcf6uW4CBeAnnvOinxHzEEAtbTnFbxiVfKpiVbRY9RGxAohpqQ6lnAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7a929eddd4ebd8e8c754f083b2b9df6e7d461ddb1060c292a6db109af827fe08","last_reissued_at":"2026-05-20T01:05:13.146534Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T01:05:13.146534Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"C-ReD: A Comprehensive Chinese Benchmark for AI-Generated Text Detection Derived from Real-World Prompts","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"The C-ReD benchmark uses real-world prompts to achieve reliable Chinese AI-text detection and generalization to unseen LLMs and external datasets.","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Bin Chen, Chenxi Qing, Hao Wu, Hongyao Yu, Junxi Wu, Shu-Tao Xia, Yixiang Qiu, Zheng Liu","submitted_at":"2026-04-13T17:56:27Z","abstract_excerpt":"Recently, large language models (LLMs) are capable of generating highly fluent textual content. While they offer significant convenience to humans, they also introduce various risks, like phishing and academic dishonesty. Numerous research efforts have been dedicated to developing algorithms for detecting AI-generated text and constructing relevant datasets. However, in the domain of Chinese corpora, challenges remain, including limited model diversity and data homogeneity. To address these issues, we propose C-ReD: a comprehensive Chinese Real-prompt AI-generated Detection benchmark. Experime"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"C-ReD not only enables reliable in-domain detection but also supports strong generalization to unseen LLMs and external Chinese datasets-addressing critical gaps in model diversity, domain coverage, and prompt realism that have limited prior Chinese detection benchmarks.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the chosen real-world prompts and set of LLMs are sufficiently representative to guarantee generalization to truly unseen models and external datasets.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"C-ReD is a Chinese AI-text detection benchmark built from diverse real-world prompts and multiple LLMs that shows strong in-domain performance and generalization to unseen models and external datasets.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"The C-ReD benchmark uses real-world prompts to achieve reliable Chinese AI-text detection and generalization to unseen LLMs and external datasets.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"0ffcc99deaec9f63e0e5a3091711c671769367c33e5721e74d8fccd18dfdb72a"},"source":{"id":"2604.11796","kind":"arxiv","version":2},"verdict":{"id":"5220bbd9-8b30-4ce2-bcdd-75c16c9a358b","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-10T15:58:23.341729Z","strongest_claim":"C-ReD not only enables reliable in-domain detection but also supports strong generalization to unseen LLMs and external Chinese datasets-addressing critical gaps in model diversity, domain coverage, and prompt realism that have limited prior Chinese detection benchmarks.","one_line_summary":"C-ReD is a Chinese AI-text detection benchmark built from diverse real-world prompts and multiple LLMs that shows strong in-domain performance and generalization to unseen models and external datasets.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the chosen real-world prompts and set of LLMs are sufficiently representative to guarantee generalization to truly unseen models and external datasets.","pith_extraction_headline":"The C-ReD benchmark uses real-world prompts to achieve reliable Chinese AI-text detection and generalization to unseen LLMs and external datasets."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2604.11796/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":"2604.11796","created_at":"2026-05-20T01:05:13.146600+00:00"},{"alias_kind":"arxiv_version","alias_value":"2604.11796v2","created_at":"2026-05-20T01:05:13.146600+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.11796","created_at":"2026-05-20T01:05:13.146600+00:00"},{"alias_kind":"pith_short_12","alias_value":"PKJJ5XOU5PMO","created_at":"2026-05-20T01:05:13.146600+00:00"},{"alias_kind":"pith_short_16","alias_value":"PKJJ5XOU5PMORR2U","created_at":"2026-05-20T01:05:13.146600+00:00"},{"alias_kind":"pith_short_8","alias_value":"PKJJ5XOU","created_at":"2026-05-20T01:05:13.146600+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2604.16923","citing_title":"Alignment Imprint: Zero-Shot AI-Generated Text Detection via Provable Preference Discrepancy","ref_index":8,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PKJJ5XOU5PMORR2U6CB3FOO7NZ","json":"https://pith.science/pith/PKJJ5XOU5PMORR2U6CB3FOO7NZ.json","graph_json":"https://pith.science/api/pith-number/PKJJ5XOU5PMORR2U6CB3FOO7NZ/graph.json","events_json":"https://pith.science/api/pith-number/PKJJ5XOU5PMORR2U6CB3FOO7NZ/events.json","paper":"https://pith.science/paper/PKJJ5XOU"},"agent_actions":{"view_html":"https://pith.science/pith/PKJJ5XOU5PMORR2U6CB3FOO7NZ","download_json":"https://pith.science/pith/PKJJ5XOU5PMORR2U6CB3FOO7NZ.json","view_paper":"https://pith.science/paper/PKJJ5XOU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2604.11796&json=true","fetch_graph":"https://pith.science/api/pith-number/PKJJ5XOU5PMORR2U6CB3FOO7NZ/graph.json","fetch_events":"https://pith.science/api/pith-number/PKJJ5XOU5PMORR2U6CB3FOO7NZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PKJJ5XOU5PMORR2U6CB3FOO7NZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PKJJ5XOU5PMORR2U6CB3FOO7NZ/action/storage_attestation","attest_author":"https://pith.science/pith/PKJJ5XOU5PMORR2U6CB3FOO7NZ/action/author_attestation","sign_citation":"https://pith.science/pith/PKJJ5XOU5PMORR2U6CB3FOO7NZ/action/citation_signature","submit_replication":"https://pith.science/pith/PKJJ5XOU5PMORR2U6CB3FOO7NZ/action/replication_record"}},"created_at":"2026-05-20T01:05:13.146600+00:00","updated_at":"2026-05-20T01:05:13.146600+00:00"}