{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:XEBTXYGO6UZGJEYENOGQXFSTSE","short_pith_number":"pith:XEBTXYGO","schema_version":"1.0","canonical_sha256":"b9033be0cef5326493046b8d0b9653913c913709e575f6967ff6599acdd72534","source":{"kind":"arxiv","id":"2507.21693","version":1},"attestation_state":"computed","paper":{"title":"MultiAIGCD: A Comprehensive dataset for AI Generated Code Detection Covering Multiple Languages, Models,Prompts, and Scenarios","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Basak Demirok, Mucahid Kutlu, Selin Mergen","submitted_at":"2025-07-29T11:16:55Z","abstract_excerpt":"As large language models (LLMs) rapidly advance, their role in code generation has expanded significantly. While this offers streamlined development, it also creates concerns in areas like education and job interviews. Consequently, developing robust systems to detect AI-generated code is imperative to maintain academic integrity and ensure fairness in hiring processes. In this study, we introduce MultiAIGCD, a dataset for AI-generated code detection for Python, Java, and Go. From the CodeNet dataset's problem definitions and human-authored codes, we generate several code samples in Java, Pyth"},"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":"2507.21693","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-07-29T11:16:55Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ba8bafd35122b96bdbffc30e9ec271e832396514049f3f96111e865f6b81c7e0","abstract_canon_sha256":"96b9f37132da6491939f674b5ab20de12053536fd7ec05ae09dfa5d16a897ec7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:45:04.628567Z","signature_b64":"ZrlUIeITfmLKHSI6FAgBg8KyrfHqb+IAdSioRLHsrIiOTolgczbShhYDlhQoyxz0eJxaUh8PPSNC161Gv68ABA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b9033be0cef5326493046b8d0b9653913c913709e575f6967ff6599acdd72534","last_reissued_at":"2026-07-05T11:45:04.628138Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:45:04.628138Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MultiAIGCD: A Comprehensive dataset for AI Generated Code Detection Covering Multiple Languages, Models,Prompts, and Scenarios","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Basak Demirok, Mucahid Kutlu, Selin Mergen","submitted_at":"2025-07-29T11:16:55Z","abstract_excerpt":"As large language models (LLMs) rapidly advance, their role in code generation has expanded significantly. While this offers streamlined development, it also creates concerns in areas like education and job interviews. Consequently, developing robust systems to detect AI-generated code is imperative to maintain academic integrity and ensure fairness in hiring processes. In this study, we introduce MultiAIGCD, a dataset for AI-generated code detection for Python, Java, and Go. From the CodeNet dataset's problem definitions and human-authored codes, we generate several code samples in Java, Pyth"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.21693","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/2507.21693/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":"2507.21693","created_at":"2026-07-05T11:45:04.628195+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.21693v1","created_at":"2026-07-05T11:45:04.628195+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.21693","created_at":"2026-07-05T11:45:04.628195+00:00"},{"alias_kind":"pith_short_12","alias_value":"XEBTXYGO6UZG","created_at":"2026-07-05T11:45:04.628195+00:00"},{"alias_kind":"pith_short_16","alias_value":"XEBTXYGO6UZGJEYE","created_at":"2026-07-05T11:45:04.628195+00:00"},{"alias_kind":"pith_short_8","alias_value":"XEBTXYGO","created_at":"2026-07-05T11:45:04.628195+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":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XEBTXYGO6UZGJEYENOGQXFSTSE","json":"https://pith.science/pith/XEBTXYGO6UZGJEYENOGQXFSTSE.json","graph_json":"https://pith.science/api/pith-number/XEBTXYGO6UZGJEYENOGQXFSTSE/graph.json","events_json":"https://pith.science/api/pith-number/XEBTXYGO6UZGJEYENOGQXFSTSE/events.json","paper":"https://pith.science/paper/XEBTXYGO"},"agent_actions":{"view_html":"https://pith.science/pith/XEBTXYGO6UZGJEYENOGQXFSTSE","download_json":"https://pith.science/pith/XEBTXYGO6UZGJEYENOGQXFSTSE.json","view_paper":"https://pith.science/paper/XEBTXYGO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.21693&json=true","fetch_graph":"https://pith.science/api/pith-number/XEBTXYGO6UZGJEYENOGQXFSTSE/graph.json","fetch_events":"https://pith.science/api/pith-number/XEBTXYGO6UZGJEYENOGQXFSTSE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XEBTXYGO6UZGJEYENOGQXFSTSE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XEBTXYGO6UZGJEYENOGQXFSTSE/action/storage_attestation","attest_author":"https://pith.science/pith/XEBTXYGO6UZGJEYENOGQXFSTSE/action/author_attestation","sign_citation":"https://pith.science/pith/XEBTXYGO6UZGJEYENOGQXFSTSE/action/citation_signature","submit_replication":"https://pith.science/pith/XEBTXYGO6UZGJEYENOGQXFSTSE/action/replication_record"}},"created_at":"2026-07-05T11:45:04.628195+00:00","updated_at":"2026-07-05T11:45:04.628195+00:00"}