{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:H2LO5NIAUSNJZ3QICWN7RVTN3X","short_pith_number":"pith:H2LO5NIA","schema_version":"1.0","canonical_sha256":"3e96eeb500a49a9cee08159bf8d66dddc50ae601bed430c979e59216fabf2791","source":{"kind":"arxiv","id":"2507.03373","version":2},"attestation_state":"computed","paper":{"title":"WETBench: A Benchmark for Detecting Task-Specific Machine-Generated Text on Wikipedia","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Denny Vrande\\v{c}i\\'c, Elena Simperl, Elizabeth Black, Gerrit Quaremba","submitted_at":"2025-07-04T08:13:10Z","abstract_excerpt":"Given Wikipedia's role as a trusted source of high-quality, reliable content, concerns are growing about the proliferation of low-quality machine-generated text (MGT) produced by large language models (LLMs) on its platform. Reliable detection of MGT is therefore essential. However, existing work primarily evaluates MGT detectors on generic generation tasks rather than on tasks more commonly performed by Wikipedia editors. This misalignment can lead to poor generalisability when applied in real-world Wikipedia contexts. We introduce WETBench, a multilingual, multi-generator, and task-specific "},"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":"2507.03373","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-04T08:13:10Z","cross_cats_sorted":[],"title_canon_sha256":"7207cdd6a252f96c7df5df4953f6464cf126f9b57a7bc0aa866a5872da0f7ebd","abstract_canon_sha256":"8f4c5477f1f702fde1780f51fbb9240f94149570ee80a8cf33eeeaa6defaad79"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-04T01:08:30.157071Z","signature_b64":"FF066cttnnkj0xJ/2GEfdnaZtrsKTYP7EdnJEZ1YyDuzfmE5dql7HZdgmz4LUZhY6ySSgstBlSekedMr03NoAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3e96eeb500a49a9cee08159bf8d66dddc50ae601bed430c979e59216fabf2791","last_reissued_at":"2026-06-04T01:08:30.156485Z","signature_status":"signed_v1","first_computed_at":"2026-06-04T01:08:30.156485Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"WETBench: A Benchmark for Detecting Task-Specific Machine-Generated Text on Wikipedia","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Denny Vrande\\v{c}i\\'c, Elena Simperl, Elizabeth Black, Gerrit Quaremba","submitted_at":"2025-07-04T08:13:10Z","abstract_excerpt":"Given Wikipedia's role as a trusted source of high-quality, reliable content, concerns are growing about the proliferation of low-quality machine-generated text (MGT) produced by large language models (LLMs) on its platform. Reliable detection of MGT is therefore essential. However, existing work primarily evaluates MGT detectors on generic generation tasks rather than on tasks more commonly performed by Wikipedia editors. This misalignment can lead to poor generalisability when applied in real-world Wikipedia contexts. We introduce WETBench, a multilingual, multi-generator, and task-specific "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.03373","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/2507.03373/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":"2507.03373","created_at":"2026-06-04T01:08:30.156552+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.03373v2","created_at":"2026-06-04T01:08:30.156552+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.03373","created_at":"2026-06-04T01:08:30.156552+00:00"},{"alias_kind":"pith_short_12","alias_value":"H2LO5NIAUSNJ","created_at":"2026-06-04T01:08:30.156552+00:00"},{"alias_kind":"pith_short_16","alias_value":"H2LO5NIAUSNJZ3QI","created_at":"2026-06-04T01:08:30.156552+00:00"},{"alias_kind":"pith_short_8","alias_value":"H2LO5NIA","created_at":"2026-06-04T01:08:30.156552+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/H2LO5NIAUSNJZ3QICWN7RVTN3X","json":"https://pith.science/pith/H2LO5NIAUSNJZ3QICWN7RVTN3X.json","graph_json":"https://pith.science/api/pith-number/H2LO5NIAUSNJZ3QICWN7RVTN3X/graph.json","events_json":"https://pith.science/api/pith-number/H2LO5NIAUSNJZ3QICWN7RVTN3X/events.json","paper":"https://pith.science/paper/H2LO5NIA"},"agent_actions":{"view_html":"https://pith.science/pith/H2LO5NIAUSNJZ3QICWN7RVTN3X","download_json":"https://pith.science/pith/H2LO5NIAUSNJZ3QICWN7RVTN3X.json","view_paper":"https://pith.science/paper/H2LO5NIA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.03373&json=true","fetch_graph":"https://pith.science/api/pith-number/H2LO5NIAUSNJZ3QICWN7RVTN3X/graph.json","fetch_events":"https://pith.science/api/pith-number/H2LO5NIAUSNJZ3QICWN7RVTN3X/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/H2LO5NIAUSNJZ3QICWN7RVTN3X/action/timestamp_anchor","attest_storage":"https://pith.science/pith/H2LO5NIAUSNJZ3QICWN7RVTN3X/action/storage_attestation","attest_author":"https://pith.science/pith/H2LO5NIAUSNJZ3QICWN7RVTN3X/action/author_attestation","sign_citation":"https://pith.science/pith/H2LO5NIAUSNJZ3QICWN7RVTN3X/action/citation_signature","submit_replication":"https://pith.science/pith/H2LO5NIAUSNJZ3QICWN7RVTN3X/action/replication_record"}},"created_at":"2026-06-04T01:08:30.156552+00:00","updated_at":"2026-06-04T01:08:30.156552+00:00"}