{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:JX6E2YY5F5TI5QUOVVCHIZ3RTQ","short_pith_number":"pith:JX6E2YY5","schema_version":"1.0","canonical_sha256":"4dfc4d631d2f668ec28ead447467719c0325eea2653b4e76deb9a146355e0b51","source":{"kind":"arxiv","id":"2411.04032","version":3},"attestation_state":"computed","paper":{"title":"Beemo: Benchmark of Expert-edited Machine-generated Outputs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Adaku Uchendu, Ekaterina Artemova, Jason Lucas, Jooyoung Lee, Saranya Venkatraman, Sergei Tilga, Vladislav Mikhailov","submitted_at":"2024-11-06T16:31:28Z","abstract_excerpt":"The rapid proliferation of large language models (LLMs) has increased the volume of machine-generated texts (MGTs) and blurred text authorship in various domains. However, most existing MGT benchmarks include single-author texts (human-written and machine-generated). This conventional design fails to capture more practical multi-author scenarios, where the user refines the LLM response for natural flow, coherence, and factual correctness. Our paper introduces the Benchmark of Expert-edited Machine-generated Outputs (Beemo), which includes 6.5k texts written by humans, generated by ten instruct"},"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":"2411.04032","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-06T16:31:28Z","cross_cats_sorted":[],"title_canon_sha256":"a19857ba66747e3b35e21152197eba5064648ef8e50118d0bafdf77260d908ed","abstract_canon_sha256":"8c1d2358a1680c0fad9ed69d5b5124fae8a83b8c4f9b5b0054f47f2e4adc4c3d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:32:33.301458Z","signature_b64":"sZNURH0duqEzj959BMZd7GyOttv0BpQMtje2n3nFw2/GUBPND3dDJ8MHC2GR2aTtlIIh8imdZwX8c/4Wgm5DCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4dfc4d631d2f668ec28ead447467719c0325eea2653b4e76deb9a146355e0b51","last_reissued_at":"2026-07-05T10:32:33.300734Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:32:33.300734Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Beemo: Benchmark of Expert-edited Machine-generated Outputs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Adaku Uchendu, Ekaterina Artemova, Jason Lucas, Jooyoung Lee, Saranya Venkatraman, Sergei Tilga, Vladislav Mikhailov","submitted_at":"2024-11-06T16:31:28Z","abstract_excerpt":"The rapid proliferation of large language models (LLMs) has increased the volume of machine-generated texts (MGTs) and blurred text authorship in various domains. However, most existing MGT benchmarks include single-author texts (human-written and machine-generated). This conventional design fails to capture more practical multi-author scenarios, where the user refines the LLM response for natural flow, coherence, and factual correctness. Our paper introduces the Benchmark of Expert-edited Machine-generated Outputs (Beemo), which includes 6.5k texts written by humans, generated by ten instruct"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.04032","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/2411.04032/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":"2411.04032","created_at":"2026-07-05T10:32:33.300816+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.04032v3","created_at":"2026-07-05T10:32:33.300816+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.04032","created_at":"2026-07-05T10:32:33.300816+00:00"},{"alias_kind":"pith_short_12","alias_value":"JX6E2YY5F5TI","created_at":"2026-07-05T10:32:33.300816+00:00"},{"alias_kind":"pith_short_16","alias_value":"JX6E2YY5F5TI5QUO","created_at":"2026-07-05T10:32:33.300816+00:00"},{"alias_kind":"pith_short_8","alias_value":"JX6E2YY5","created_at":"2026-07-05T10:32:33.300816+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.12620","citing_title":"HybridCodeAuthorship: A Benchmark Dataset for Line-Level Code Authorship Detection","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JX6E2YY5F5TI5QUOVVCHIZ3RTQ","json":"https://pith.science/pith/JX6E2YY5F5TI5QUOVVCHIZ3RTQ.json","graph_json":"https://pith.science/api/pith-number/JX6E2YY5F5TI5QUOVVCHIZ3RTQ/graph.json","events_json":"https://pith.science/api/pith-number/JX6E2YY5F5TI5QUOVVCHIZ3RTQ/events.json","paper":"https://pith.science/paper/JX6E2YY5"},"agent_actions":{"view_html":"https://pith.science/pith/JX6E2YY5F5TI5QUOVVCHIZ3RTQ","download_json":"https://pith.science/pith/JX6E2YY5F5TI5QUOVVCHIZ3RTQ.json","view_paper":"https://pith.science/paper/JX6E2YY5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.04032&json=true","fetch_graph":"https://pith.science/api/pith-number/JX6E2YY5F5TI5QUOVVCHIZ3RTQ/graph.json","fetch_events":"https://pith.science/api/pith-number/JX6E2YY5F5TI5QUOVVCHIZ3RTQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JX6E2YY5F5TI5QUOVVCHIZ3RTQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JX6E2YY5F5TI5QUOVVCHIZ3RTQ/action/storage_attestation","attest_author":"https://pith.science/pith/JX6E2YY5F5TI5QUOVVCHIZ3RTQ/action/author_attestation","sign_citation":"https://pith.science/pith/JX6E2YY5F5TI5QUOVVCHIZ3RTQ/action/citation_signature","submit_replication":"https://pith.science/pith/JX6E2YY5F5TI5QUOVVCHIZ3RTQ/action/replication_record"}},"created_at":"2026-07-05T10:32:33.300816+00:00","updated_at":"2026-07-05T10:32:33.300816+00:00"}