{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:F4VD3EWQUJ6YRPE3HI3H3RNLBQ","short_pith_number":"pith:F4VD3EWQ","schema_version":"1.0","canonical_sha256":"2f2a3d92d0a27d88bc9b3a367dc5ab0c075d2fc2e7fe9bcf7b865896c772d123","source":{"kind":"arxiv","id":"2607.03014","version":1},"attestation_state":"computed","paper":{"title":"Detection of LLM-assisted Code Plagiarism Using k-gram Software Birthmarks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Akito Monden, Haruaki Tamada, Hiroki Inayoshi, Masateru Tsunoda, Nikolay Fedorov","submitted_at":"2026-07-03T06:49:26Z","abstract_excerpt":"Large language models (LLMs) have significantly lowered the technical barrier to software plagiarism. By transforming existing source code while preserving its functionality, modern LLMs can generate semantically identical program that may evade traditional plagiarism detection techniques.\n  Among such attacks, code paraphrasing modifies the syntax and structure of a program while preserving its behavior. This paper investigates whether software birthmarks can detect such LLM-assisted plagiarism. As a starting point, we employ k-gram software birthmarks based on unique k-grams of Java opcodes,"},"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":"2607.03014","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-07-03T06:49:26Z","cross_cats_sorted":[],"title_canon_sha256":"4a53d091d8c5ed223fa8f3aa553742e44258772efc9069af1c7fa3d0da364e04","abstract_canon_sha256":"241e83664bd4565d207c87e716d943875b920394ea8feec4ab2d8b68407b78fd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-07T01:16:39.767443Z","signature_b64":"wagbGlk0C+yBnacqmgTzcM8rqQzeB0UFQjck+GIZvLIqeg8K5TFD9D1G/CnCi6/R6jfiXBVUDZBMMe+tfrqvDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2f2a3d92d0a27d88bc9b3a367dc5ab0c075d2fc2e7fe9bcf7b865896c772d123","last_reissued_at":"2026-07-07T01:16:39.767018Z","signature_status":"signed_v1","first_computed_at":"2026-07-07T01:16:39.767018Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Detection of LLM-assisted Code Plagiarism Using k-gram Software Birthmarks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Akito Monden, Haruaki Tamada, Hiroki Inayoshi, Masateru Tsunoda, Nikolay Fedorov","submitted_at":"2026-07-03T06:49:26Z","abstract_excerpt":"Large language models (LLMs) have significantly lowered the technical barrier to software plagiarism. By transforming existing source code while preserving its functionality, modern LLMs can generate semantically identical program that may evade traditional plagiarism detection techniques.\n  Among such attacks, code paraphrasing modifies the syntax and structure of a program while preserving its behavior. This paper investigates whether software birthmarks can detect such LLM-assisted plagiarism. As a starting point, we employ k-gram software birthmarks based on unique k-grams of Java opcodes,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.03014","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/2607.03014/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":"2607.03014","created_at":"2026-07-07T01:16:39.767083+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.03014v1","created_at":"2026-07-07T01:16:39.767083+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.03014","created_at":"2026-07-07T01:16:39.767083+00:00"},{"alias_kind":"pith_short_12","alias_value":"F4VD3EWQUJ6Y","created_at":"2026-07-07T01:16:39.767083+00:00"},{"alias_kind":"pith_short_16","alias_value":"F4VD3EWQUJ6YRPE3","created_at":"2026-07-07T01:16:39.767083+00:00"},{"alias_kind":"pith_short_8","alias_value":"F4VD3EWQ","created_at":"2026-07-07T01:16:39.767083+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/F4VD3EWQUJ6YRPE3HI3H3RNLBQ","json":"https://pith.science/pith/F4VD3EWQUJ6YRPE3HI3H3RNLBQ.json","graph_json":"https://pith.science/api/pith-number/F4VD3EWQUJ6YRPE3HI3H3RNLBQ/graph.json","events_json":"https://pith.science/api/pith-number/F4VD3EWQUJ6YRPE3HI3H3RNLBQ/events.json","paper":"https://pith.science/paper/F4VD3EWQ"},"agent_actions":{"view_html":"https://pith.science/pith/F4VD3EWQUJ6YRPE3HI3H3RNLBQ","download_json":"https://pith.science/pith/F4VD3EWQUJ6YRPE3HI3H3RNLBQ.json","view_paper":"https://pith.science/paper/F4VD3EWQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.03014&json=true","fetch_graph":"https://pith.science/api/pith-number/F4VD3EWQUJ6YRPE3HI3H3RNLBQ/graph.json","fetch_events":"https://pith.science/api/pith-number/F4VD3EWQUJ6YRPE3HI3H3RNLBQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/F4VD3EWQUJ6YRPE3HI3H3RNLBQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/F4VD3EWQUJ6YRPE3HI3H3RNLBQ/action/storage_attestation","attest_author":"https://pith.science/pith/F4VD3EWQUJ6YRPE3HI3H3RNLBQ/action/author_attestation","sign_citation":"https://pith.science/pith/F4VD3EWQUJ6YRPE3HI3H3RNLBQ/action/citation_signature","submit_replication":"https://pith.science/pith/F4VD3EWQUJ6YRPE3HI3H3RNLBQ/action/replication_record"}},"created_at":"2026-07-07T01:16:39.767083+00:00","updated_at":"2026-07-07T01:16:39.767083+00:00"}