{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:W6HRQ625ZMM6ASYXM2UBQOQEXH","short_pith_number":"pith:W6HRQ625","schema_version":"1.0","canonical_sha256":"b78f187b5dcb19e04b1766a8183a04b9e578e70f1ce2b79024cac24911d569f4","source":{"kind":"arxiv","id":"2410.14677","version":3},"attestation_state":"computed","paper":{"title":"Are AI Detectors Good Enough? A Survey on Quality of Datasets With Machine-Generated Texts","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Anastasia Voznyuk, Andrey Grabovoy, German Gritsai, Yury Chekhovich","submitted_at":"2024-10-18T17:59:57Z","abstract_excerpt":"The rapid development of autoregressive Large Language Models (LLMs) has significantly improved the quality of generated texts, necessitating reliable machine-generated text detectors. A huge number of detectors and collections with AI fragments have emerged, and several detection methods even showed recognition quality up to 99.9% according to the target metrics in such collections. However, the quality of such detectors tends to drop dramatically in the wild, posing a question: Are detectors actually highly trustworthy or do their high benchmark scores come from the poor quality of evaluatio"},"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":"2410.14677","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-18T17:59:57Z","cross_cats_sorted":[],"title_canon_sha256":"87ce3357417287228d15f31ef4bc79871c47025cb22a60bd000204b3c53f9056","abstract_canon_sha256":"353ddb6e3896312e1f6b5c8b1a819a15b0676e894e31c3e77b969abf90f9c404"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:26:09.154184Z","signature_b64":"VOb1C6aiNzgslN7XWG4UXGTQ6wM+ORttr8KkhQz0OgE+L9/R46UfG2BsDbqiGzmiiHUQr0pZQMMeBhFj4gnYDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b78f187b5dcb19e04b1766a8183a04b9e578e70f1ce2b79024cac24911d569f4","last_reissued_at":"2026-07-05T10:26:09.153560Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:26:09.153560Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Are AI Detectors Good Enough? A Survey on Quality of Datasets With Machine-Generated Texts","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Anastasia Voznyuk, Andrey Grabovoy, German Gritsai, Yury Chekhovich","submitted_at":"2024-10-18T17:59:57Z","abstract_excerpt":"The rapid development of autoregressive Large Language Models (LLMs) has significantly improved the quality of generated texts, necessitating reliable machine-generated text detectors. A huge number of detectors and collections with AI fragments have emerged, and several detection methods even showed recognition quality up to 99.9% according to the target metrics in such collections. However, the quality of such detectors tends to drop dramatically in the wild, posing a question: Are detectors actually highly trustworthy or do their high benchmark scores come from the poor quality of evaluatio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.14677","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/2410.14677/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":"2410.14677","created_at":"2026-07-05T10:26:09.153643+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.14677v3","created_at":"2026-07-05T10:26:09.153643+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.14677","created_at":"2026-07-05T10:26:09.153643+00:00"},{"alias_kind":"pith_short_12","alias_value":"W6HRQ625ZMM6","created_at":"2026-07-05T10:26:09.153643+00:00"},{"alias_kind":"pith_short_16","alias_value":"W6HRQ625ZMM6ASYX","created_at":"2026-07-05T10:26:09.153643+00:00"},{"alias_kind":"pith_short_8","alias_value":"W6HRQ625","created_at":"2026-07-05T10:26:09.153643+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2509.22055","citing_title":"RedNote-Vibe: A Dataset for Capturing Temporal Dynamics of AI-Generated Text in Lifestyle Social Media","ref_index":5,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/W6HRQ625ZMM6ASYXM2UBQOQEXH","json":"https://pith.science/pith/W6HRQ625ZMM6ASYXM2UBQOQEXH.json","graph_json":"https://pith.science/api/pith-number/W6HRQ625ZMM6ASYXM2UBQOQEXH/graph.json","events_json":"https://pith.science/api/pith-number/W6HRQ625ZMM6ASYXM2UBQOQEXH/events.json","paper":"https://pith.science/paper/W6HRQ625"},"agent_actions":{"view_html":"https://pith.science/pith/W6HRQ625ZMM6ASYXM2UBQOQEXH","download_json":"https://pith.science/pith/W6HRQ625ZMM6ASYXM2UBQOQEXH.json","view_paper":"https://pith.science/paper/W6HRQ625","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.14677&json=true","fetch_graph":"https://pith.science/api/pith-number/W6HRQ625ZMM6ASYXM2UBQOQEXH/graph.json","fetch_events":"https://pith.science/api/pith-number/W6HRQ625ZMM6ASYXM2UBQOQEXH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/W6HRQ625ZMM6ASYXM2UBQOQEXH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/W6HRQ625ZMM6ASYXM2UBQOQEXH/action/storage_attestation","attest_author":"https://pith.science/pith/W6HRQ625ZMM6ASYXM2UBQOQEXH/action/author_attestation","sign_citation":"https://pith.science/pith/W6HRQ625ZMM6ASYXM2UBQOQEXH/action/citation_signature","submit_replication":"https://pith.science/pith/W6HRQ625ZMM6ASYXM2UBQOQEXH/action/replication_record"}},"created_at":"2026-07-05T10:26:09.153643+00:00","updated_at":"2026-07-05T10:26:09.153643+00:00"}