{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:53GXPDCAU33QBBA72TMB7RG2BQ","short_pith_number":"pith:53GXPDCA","schema_version":"1.0","canonical_sha256":"eecd778c40a6f700841fd4d81fc4da0c3db73ac99ce99d9b024a0c84073ff879","source":{"kind":"arxiv","id":"2410.23746","version":3},"attestation_state":"computed","paper":{"title":"DetectRL: Benchmarking LLM-Generated Text Detection in Real-World Scenarios","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Derek F. Wong, Junchao Wu, Lidia S. Chao, Runzhe Zhan, Shu Yang, Xinyi Yang, Yulin Yuan","submitted_at":"2024-10-31T09:01:25Z","abstract_excerpt":"Detecting text generated by large language models (LLMs) is of great recent interest. With zero-shot methods like DetectGPT, detection capabilities have reached impressive levels. However, the reliability of existing detectors in real-world applications remains underexplored. In this study, we present a new benchmark, DetectRL, highlighting that even state-of-the-art (SOTA) detection techniques still underperformed in this task. We collected human-written datasets from domains where LLMs are particularly prone to misuse. Using popular LLMs, we generated data that better aligns with real-world "},"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":"2410.23746","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-31T09:01:25Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8600b71279db6453ef53bbe3a021c683590ff6d4762b9b064c4322a64433ce48","abstract_canon_sha256":"6c066f7926e6eed50bfa54a079f267aee20f130be6c515c5948683849926bc61"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:29:25.907453Z","signature_b64":"ogwsow5QviUycywJxJJ1nZ5HFmjh6gvhJkSQ9Y08NfntDoG5pwlEJd4r2l+tOuTrV3Z2BvsxGPTXKiY7ROdOAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eecd778c40a6f700841fd4d81fc4da0c3db73ac99ce99d9b024a0c84073ff879","last_reissued_at":"2026-07-05T10:29:25.907001Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:29:25.907001Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DetectRL: Benchmarking LLM-Generated Text Detection in Real-World Scenarios","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Derek F. Wong, Junchao Wu, Lidia S. Chao, Runzhe Zhan, Shu Yang, Xinyi Yang, Yulin Yuan","submitted_at":"2024-10-31T09:01:25Z","abstract_excerpt":"Detecting text generated by large language models (LLMs) is of great recent interest. With zero-shot methods like DetectGPT, detection capabilities have reached impressive levels. However, the reliability of existing detectors in real-world applications remains underexplored. In this study, we present a new benchmark, DetectRL, highlighting that even state-of-the-art (SOTA) detection techniques still underperformed in this task. We collected human-written datasets from domains where LLMs are particularly prone to misuse. Using popular LLMs, we generated data that better aligns with real-world "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.23746","kind":"arxiv","version":3},"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/2410.23746/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":"2410.23746","created_at":"2026-07-05T10:29:25.907064+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.23746v3","created_at":"2026-07-05T10:29:25.907064+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.23746","created_at":"2026-07-05T10:29:25.907064+00:00"},{"alias_kind":"pith_short_12","alias_value":"53GXPDCAU33Q","created_at":"2026-07-05T10:29:25.907064+00:00"},{"alias_kind":"pith_short_16","alias_value":"53GXPDCAU33QBBA7","created_at":"2026-07-05T10:29:25.907064+00:00"},{"alias_kind":"pith_short_8","alias_value":"53GXPDCA","created_at":"2026-07-05T10:29:25.907064+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.04205","citing_title":"DetectZoo: A Unified Toolkit for AI-Generated Content Detection Across Text, Audio, and Image Modalities","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2605.27921","citing_title":"Show, Don't TELL: Explainable AI-Generated Text Detection","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07313","citing_title":"SV-Detect: AI-generated Text Detection with Steering Vectors","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/53GXPDCAU33QBBA72TMB7RG2BQ","json":"https://pith.science/pith/53GXPDCAU33QBBA72TMB7RG2BQ.json","graph_json":"https://pith.science/api/pith-number/53GXPDCAU33QBBA72TMB7RG2BQ/graph.json","events_json":"https://pith.science/api/pith-number/53GXPDCAU33QBBA72TMB7RG2BQ/events.json","paper":"https://pith.science/paper/53GXPDCA"},"agent_actions":{"view_html":"https://pith.science/pith/53GXPDCAU33QBBA72TMB7RG2BQ","download_json":"https://pith.science/pith/53GXPDCAU33QBBA72TMB7RG2BQ.json","view_paper":"https://pith.science/paper/53GXPDCA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.23746&json=true","fetch_graph":"https://pith.science/api/pith-number/53GXPDCAU33QBBA72TMB7RG2BQ/graph.json","fetch_events":"https://pith.science/api/pith-number/53GXPDCAU33QBBA72TMB7RG2BQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/53GXPDCAU33QBBA72TMB7RG2BQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/53GXPDCAU33QBBA72TMB7RG2BQ/action/storage_attestation","attest_author":"https://pith.science/pith/53GXPDCAU33QBBA72TMB7RG2BQ/action/author_attestation","sign_citation":"https://pith.science/pith/53GXPDCAU33QBBA72TMB7RG2BQ/action/citation_signature","submit_replication":"https://pith.science/pith/53GXPDCAU33QBBA72TMB7RG2BQ/action/replication_record"}},"created_at":"2026-07-05T10:29:25.907064+00:00","updated_at":"2026-07-05T10:29:25.907064+00:00"}