{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:CW2DEUUYLH3H422UDQ7MT2QP2B","short_pith_number":"pith:CW2DEUUY","schema_version":"1.0","canonical_sha256":"15b432529859f67e6b541c3ec9ea0fd0785a178b944e4e3d9f011a1e8e6c6f2a","source":{"kind":"arxiv","id":"2605.31113","version":1},"attestation_state":"computed","paper":{"title":"TSM-Bench: Detecting LLM-Generated Text in Real-World Wikipedia Editing Practices","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":"2026-05-29T10:25:32Z","abstract_excerpt":"Automatically detecting machine-generated text (MGT) is critical to maintaining the knowledge integrity of user-generated content (UGC) platforms such as Wikipedia. Existing detection benchmarks primarily focus on \\textit{generic} text generation tasks (e.g., ``Write an article about machine learning.''). However, editors frequently employ LLMs for specific writing tasks (e.g., summarisation). These \\textit{task-specific} MGT instances tend to resemble human-written text more closely due to their constrained task formulation and contextual conditioning. In this work, we show that a range of SO"},"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":"2605.31113","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-29T10:25:32Z","cross_cats_sorted":[],"title_canon_sha256":"cfad387fc16aaddc6d1d685c11d084ce5047fb06a907555c3bc6e57019805793","abstract_canon_sha256":"3b11dbe41f32c776c359476e9a253bee03027d537fa698f3deb0e329c67bc07d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-01T01:03:58.627092Z","signature_b64":"Viux/jIeSEkSJj9vrBVHHnM41mc5NWy0TtTzKZHJ+FmGgsx9WpkUh2NSE407Od4hFdbpq9B5Uit0HIPq8xSfBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"15b432529859f67e6b541c3ec9ea0fd0785a178b944e4e3d9f011a1e8e6c6f2a","last_reissued_at":"2026-06-01T01:03:58.626219Z","signature_status":"signed_v1","first_computed_at":"2026-06-01T01:03:58.626219Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TSM-Bench: Detecting LLM-Generated Text in Real-World Wikipedia Editing Practices","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":"2026-05-29T10:25:32Z","abstract_excerpt":"Automatically detecting machine-generated text (MGT) is critical to maintaining the knowledge integrity of user-generated content (UGC) platforms such as Wikipedia. Existing detection benchmarks primarily focus on \\textit{generic} text generation tasks (e.g., ``Write an article about machine learning.''). However, editors frequently employ LLMs for specific writing tasks (e.g., summarisation). These \\textit{task-specific} MGT instances tend to resemble human-written text more closely due to their constrained task formulation and contextual conditioning. In this work, we show that a range of SO"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.31113","kind":"arxiv","version":1},"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/2605.31113/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":"2605.31113","created_at":"2026-06-01T01:03:58.626391+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.31113v1","created_at":"2026-06-01T01:03:58.626391+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.31113","created_at":"2026-06-01T01:03:58.626391+00:00"},{"alias_kind":"pith_short_12","alias_value":"CW2DEUUYLH3H","created_at":"2026-06-01T01:03:58.626391+00:00"},{"alias_kind":"pith_short_16","alias_value":"CW2DEUUYLH3H422U","created_at":"2026-06-01T01:03:58.626391+00:00"},{"alias_kind":"pith_short_8","alias_value":"CW2DEUUY","created_at":"2026-06-01T01:03:58.626391+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/CW2DEUUYLH3H422UDQ7MT2QP2B","json":"https://pith.science/pith/CW2DEUUYLH3H422UDQ7MT2QP2B.json","graph_json":"https://pith.science/api/pith-number/CW2DEUUYLH3H422UDQ7MT2QP2B/graph.json","events_json":"https://pith.science/api/pith-number/CW2DEUUYLH3H422UDQ7MT2QP2B/events.json","paper":"https://pith.science/paper/CW2DEUUY"},"agent_actions":{"view_html":"https://pith.science/pith/CW2DEUUYLH3H422UDQ7MT2QP2B","download_json":"https://pith.science/pith/CW2DEUUYLH3H422UDQ7MT2QP2B.json","view_paper":"https://pith.science/paper/CW2DEUUY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.31113&json=true","fetch_graph":"https://pith.science/api/pith-number/CW2DEUUYLH3H422UDQ7MT2QP2B/graph.json","fetch_events":"https://pith.science/api/pith-number/CW2DEUUYLH3H422UDQ7MT2QP2B/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CW2DEUUYLH3H422UDQ7MT2QP2B/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CW2DEUUYLH3H422UDQ7MT2QP2B/action/storage_attestation","attest_author":"https://pith.science/pith/CW2DEUUYLH3H422UDQ7MT2QP2B/action/author_attestation","sign_citation":"https://pith.science/pith/CW2DEUUYLH3H422UDQ7MT2QP2B/action/citation_signature","submit_replication":"https://pith.science/pith/CW2DEUUYLH3H422UDQ7MT2QP2B/action/replication_record"}},"created_at":"2026-06-01T01:03:58.626391+00:00","updated_at":"2026-06-01T01:03:58.626391+00:00"}