{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:MNHGAWTEOR66PY7OGYBPPGDRHA","short_pith_number":"pith:MNHGAWTE","schema_version":"1.0","canonical_sha256":"634e605a64747de7e3ee3602f798713834ff8983ca4fbe51ef707b52d147db9d","source":{"kind":"arxiv","id":"2506.11059","version":1},"attestation_state":"computed","paper":{"title":"CodeMirage: A Multi-Lingual Benchmark for Detecting AI-Generated and Paraphrased Source Code from Production-Level LLMs","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CL","cs.CY","cs.LG"],"primary_cat":"cs.SE","authors_text":"Guangyu Shen, Hanxi Guo, Kaiyuan Zhang, Siyuan Cheng, Xiangyu Zhang","submitted_at":"2025-05-27T03:25:12Z","abstract_excerpt":"Large language models (LLMs) have become integral to modern software development, producing vast amounts of AI-generated source code. While these models boost programming productivity, their misuse introduces critical risks, including code plagiarism, license violations, and the propagation of insecure programs. As a result, robust detection of AI-generated code is essential. To support the development of such detectors, a comprehensive benchmark that reflects real-world conditions is crucial. However, existing benchmarks fall short -- most cover only a limited set of programming languages and"},"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":"2506.11059","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.SE","submitted_at":"2025-05-27T03:25:12Z","cross_cats_sorted":["cs.CL","cs.CY","cs.LG"],"title_canon_sha256":"04080ed9e9e11effda9ea65c0e75a7839b881ad56cb06d942e86fac457b903cd","abstract_canon_sha256":"c43d19af2d797c5241b5a54a3450855e3b623e70c9cf3e17c37636edd0c25403"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:20:58.721859Z","signature_b64":"ADon1PFduJGWFFV+21N7ZzYWYRdgqMQor/TD18s8R8gQ6YH5Vj4IhLhiXdrlml+oLnzUKMj1RsRK/cxrW24dCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"634e605a64747de7e3ee3602f798713834ff8983ca4fbe51ef707b52d147db9d","last_reissued_at":"2026-07-05T11:20:58.721329Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:20:58.721329Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CodeMirage: A Multi-Lingual Benchmark for Detecting AI-Generated and Paraphrased Source Code from Production-Level LLMs","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CL","cs.CY","cs.LG"],"primary_cat":"cs.SE","authors_text":"Guangyu Shen, Hanxi Guo, Kaiyuan Zhang, Siyuan Cheng, Xiangyu Zhang","submitted_at":"2025-05-27T03:25:12Z","abstract_excerpt":"Large language models (LLMs) have become integral to modern software development, producing vast amounts of AI-generated source code. While these models boost programming productivity, their misuse introduces critical risks, including code plagiarism, license violations, and the propagation of insecure programs. As a result, robust detection of AI-generated code is essential. To support the development of such detectors, a comprehensive benchmark that reflects real-world conditions is crucial. However, existing benchmarks fall short -- most cover only a limited set of programming languages and"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.11059","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/2506.11059/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":"2506.11059","created_at":"2026-07-05T11:20:58.721395+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.11059v1","created_at":"2026-07-05T11:20:58.721395+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.11059","created_at":"2026-07-05T11:20:58.721395+00:00"},{"alias_kind":"pith_short_12","alias_value":"MNHGAWTEOR66","created_at":"2026-07-05T11:20:58.721395+00:00"},{"alias_kind":"pith_short_16","alias_value":"MNHGAWTEOR66PY7O","created_at":"2026-07-05T11:20:58.721395+00:00"},{"alias_kind":"pith_short_8","alias_value":"MNHGAWTE","created_at":"2026-07-05T11:20:58.721395+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.17323","citing_title":"I Know Which LLM Wrote Your Code Last Summer: LLM generated Code Stylometry for Authorship Attribution","ref_index":2025,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MNHGAWTEOR66PY7OGYBPPGDRHA","json":"https://pith.science/pith/MNHGAWTEOR66PY7OGYBPPGDRHA.json","graph_json":"https://pith.science/api/pith-number/MNHGAWTEOR66PY7OGYBPPGDRHA/graph.json","events_json":"https://pith.science/api/pith-number/MNHGAWTEOR66PY7OGYBPPGDRHA/events.json","paper":"https://pith.science/paper/MNHGAWTE"},"agent_actions":{"view_html":"https://pith.science/pith/MNHGAWTEOR66PY7OGYBPPGDRHA","download_json":"https://pith.science/pith/MNHGAWTEOR66PY7OGYBPPGDRHA.json","view_paper":"https://pith.science/paper/MNHGAWTE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.11059&json=true","fetch_graph":"https://pith.science/api/pith-number/MNHGAWTEOR66PY7OGYBPPGDRHA/graph.json","fetch_events":"https://pith.science/api/pith-number/MNHGAWTEOR66PY7OGYBPPGDRHA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MNHGAWTEOR66PY7OGYBPPGDRHA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MNHGAWTEOR66PY7OGYBPPGDRHA/action/storage_attestation","attest_author":"https://pith.science/pith/MNHGAWTEOR66PY7OGYBPPGDRHA/action/author_attestation","sign_citation":"https://pith.science/pith/MNHGAWTEOR66PY7OGYBPPGDRHA/action/citation_signature","submit_replication":"https://pith.science/pith/MNHGAWTEOR66PY7OGYBPPGDRHA/action/replication_record"}},"created_at":"2026-07-05T11:20:58.721395+00:00","updated_at":"2026-07-05T11:20:58.721395+00:00"}