{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:DXQKDWRYA4QF4OTDLGDNMR2BFR","short_pith_number":"pith:DXQKDWRY","schema_version":"1.0","canonical_sha256":"1de0a1da3807205e3a635986d647412c40e57654c81723fc1dc09de3aec53924","source":{"kind":"arxiv","id":"2502.15740","version":1},"attestation_state":"computed","paper":{"title":"Detection of LLM-Generated Java Code Using Discretized Nested Bigrams","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.SE","authors_text":"Chilukuri Mohan, Timothy Paek","submitted_at":"2025-02-07T14:32:20Z","abstract_excerpt":"Large Language Models (LLMs) are currently used extensively to generate code by professionals and students, motivating the development of tools to detect LLM-generated code for applications such as academic integrity and cybersecurity. We address this authorship attribution problem as a binary classification task along with feature identification and extraction. We propose new Discretized Nested Bigram Frequency features on source code groups of various sizes. Compared to prior work, improvements are obtained by representing sparse information in dense membership bins. Experimental evaluation "},"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":"2502.15740","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2025-02-07T14:32:20Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"8d69ae3cfd09a146bc905d927d0494840a382c8cab1a6f618ab64da62415ef18","abstract_canon_sha256":"4a89d41ba14ea078a83c0a8d8d1084d6aa79afdd4bd2c797225ea91815e296f9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:18:15.814382Z","signature_b64":"I7r8gtiO0NtguGR8fmLet9mFM33GUhJoVGhr1inuPhaNMD8U9gMGskm163hb3rs80P4RIsTyu7vfQtAmPaIrAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1de0a1da3807205e3a635986d647412c40e57654c81723fc1dc09de3aec53924","last_reissued_at":"2026-07-05T10:18:15.813953Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:18:15.813953Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Detection of LLM-Generated Java Code Using Discretized Nested Bigrams","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.SE","authors_text":"Chilukuri Mohan, Timothy Paek","submitted_at":"2025-02-07T14:32:20Z","abstract_excerpt":"Large Language Models (LLMs) are currently used extensively to generate code by professionals and students, motivating the development of tools to detect LLM-generated code for applications such as academic integrity and cybersecurity. We address this authorship attribution problem as a binary classification task along with feature identification and extraction. We propose new Discretized Nested Bigram Frequency features on source code groups of various sizes. Compared to prior work, improvements are obtained by representing sparse information in dense membership bins. Experimental evaluation "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.15740","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/2502.15740/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":"2502.15740","created_at":"2026-07-05T10:18:15.814008+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.15740v1","created_at":"2026-07-05T10:18:15.814008+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.15740","created_at":"2026-07-05T10:18:15.814008+00:00"},{"alias_kind":"pith_short_12","alias_value":"DXQKDWRYA4QF","created_at":"2026-07-05T10:18:15.814008+00:00"},{"alias_kind":"pith_short_16","alias_value":"DXQKDWRYA4QF4OTD","created_at":"2026-07-05T10:18:15.814008+00:00"},{"alias_kind":"pith_short_8","alias_value":"DXQKDWRY","created_at":"2026-07-05T10:18:15.814008+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":45,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DXQKDWRYA4QF4OTDLGDNMR2BFR","json":"https://pith.science/pith/DXQKDWRYA4QF4OTDLGDNMR2BFR.json","graph_json":"https://pith.science/api/pith-number/DXQKDWRYA4QF4OTDLGDNMR2BFR/graph.json","events_json":"https://pith.science/api/pith-number/DXQKDWRYA4QF4OTDLGDNMR2BFR/events.json","paper":"https://pith.science/paper/DXQKDWRY"},"agent_actions":{"view_html":"https://pith.science/pith/DXQKDWRYA4QF4OTDLGDNMR2BFR","download_json":"https://pith.science/pith/DXQKDWRYA4QF4OTDLGDNMR2BFR.json","view_paper":"https://pith.science/paper/DXQKDWRY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.15740&json=true","fetch_graph":"https://pith.science/api/pith-number/DXQKDWRYA4QF4OTDLGDNMR2BFR/graph.json","fetch_events":"https://pith.science/api/pith-number/DXQKDWRYA4QF4OTDLGDNMR2BFR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DXQKDWRYA4QF4OTDLGDNMR2BFR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DXQKDWRYA4QF4OTDLGDNMR2BFR/action/storage_attestation","attest_author":"https://pith.science/pith/DXQKDWRYA4QF4OTDLGDNMR2BFR/action/author_attestation","sign_citation":"https://pith.science/pith/DXQKDWRYA4QF4OTDLGDNMR2BFR/action/citation_signature","submit_replication":"https://pith.science/pith/DXQKDWRYA4QF4OTDLGDNMR2BFR/action/replication_record"}},"created_at":"2026-07-05T10:18:15.814008+00:00","updated_at":"2026-07-05T10:18:15.814008+00:00"}