{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:WYSLEUMB2WOCMFI45A2ZPY6TXI","short_pith_number":"pith:WYSLEUMB","schema_version":"1.0","canonical_sha256":"b624b25181d59c26151ce83597e3d3ba2124ac1d47b20fac352b99793a7c839f","source":{"kind":"arxiv","id":"2608.00227","version":1},"attestation_state":"computed","paper":{"title":"Source Code Authorship Attribution Does Not Generalize from Competitions to Classrooms","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Marek Horv\\'ath, Serhii Yemets","submitted_at":"2026-07-31T19:15:43Z","abstract_excerpt":"Source code authorship attribution aims to identify the author of a program fragment from its writing style. We fine-tune the pre-trained transformer CodeBERT on three sources of data: publicly available Google Code Jam (GCJ) submissions from an open Kaggle repository, a curated GCJ archive, and institutional coursework datasets collected at a technical university. On multi-round GCJ data, CodeBERT reaches 92.6% Top-1 accuracy for 10 authors and retains 70.7% Top-1 (88.2% Top-10) for 1000 authors. On the examined coursework datasets, the same pipeline performs at or below the corresponding cha"},"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":"2608.00227","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2026-07-31T19:15:43Z","cross_cats_sorted":[],"title_canon_sha256":"6aebca729217d12d864bffa0a9ec4b194ac76575c06de104f889704ab87e5738","abstract_canon_sha256":"7ee5ea168fc28afabdd0712a2544ad37e10d60f2d10326d830c0baca54f53543"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-04T00:34:26.537661Z","signature_b64":"d/ZDqgjVnw4JYH2z4Fl8HqjN40htNGiJIel/Yij34XOxsXza1Z6s3b1+0G/m00S5pWP/wQL2hmlNPHayEq2ZCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b624b25181d59c26151ce83597e3d3ba2124ac1d47b20fac352b99793a7c839f","last_reissued_at":"2026-08-04T00:34:26.535790Z","signature_status":"signed_v1","first_computed_at":"2026-08-04T00:34:26.535790Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Source Code Authorship Attribution Does Not Generalize from Competitions to Classrooms","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Marek Horv\\'ath, Serhii Yemets","submitted_at":"2026-07-31T19:15:43Z","abstract_excerpt":"Source code authorship attribution aims to identify the author of a program fragment from its writing style. We fine-tune the pre-trained transformer CodeBERT on three sources of data: publicly available Google Code Jam (GCJ) submissions from an open Kaggle repository, a curated GCJ archive, and institutional coursework datasets collected at a technical university. On multi-round GCJ data, CodeBERT reaches 92.6% Top-1 accuracy for 10 authors and retains 70.7% Top-1 (88.2% Top-10) for 1000 authors. On the examined coursework datasets, the same pipeline performs at or below the corresponding cha"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.00227","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/2608.00227/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":"2608.00227","created_at":"2026-08-04T00:34:26.537088+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.00227v1","created_at":"2026-08-04T00:34:26.537088+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.00227","created_at":"2026-08-04T00:34:26.537088+00:00"},{"alias_kind":"pith_short_12","alias_value":"WYSLEUMB2WOC","created_at":"2026-08-04T00:34:26.537088+00:00"},{"alias_kind":"pith_short_16","alias_value":"WYSLEUMB2WOCMFI4","created_at":"2026-08-04T00:34:26.537088+00:00"},{"alias_kind":"pith_short_8","alias_value":"WYSLEUMB","created_at":"2026-08-04T00:34:26.537088+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/WYSLEUMB2WOCMFI45A2ZPY6TXI","json":"https://pith.science/pith/WYSLEUMB2WOCMFI45A2ZPY6TXI.json","graph_json":"https://pith.science/api/pith-number/WYSLEUMB2WOCMFI45A2ZPY6TXI/graph.json","events_json":"https://pith.science/api/pith-number/WYSLEUMB2WOCMFI45A2ZPY6TXI/events.json","paper":"https://pith.science/paper/WYSLEUMB"},"agent_actions":{"view_html":"https://pith.science/pith/WYSLEUMB2WOCMFI45A2ZPY6TXI","download_json":"https://pith.science/pith/WYSLEUMB2WOCMFI45A2ZPY6TXI.json","view_paper":"https://pith.science/paper/WYSLEUMB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.00227&json=true","fetch_graph":"https://pith.science/api/pith-number/WYSLEUMB2WOCMFI45A2ZPY6TXI/graph.json","fetch_events":"https://pith.science/api/pith-number/WYSLEUMB2WOCMFI45A2ZPY6TXI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WYSLEUMB2WOCMFI45A2ZPY6TXI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WYSLEUMB2WOCMFI45A2ZPY6TXI/action/storage_attestation","attest_author":"https://pith.science/pith/WYSLEUMB2WOCMFI45A2ZPY6TXI/action/author_attestation","sign_citation":"https://pith.science/pith/WYSLEUMB2WOCMFI45A2ZPY6TXI/action/citation_signature","submit_replication":"https://pith.science/pith/WYSLEUMB2WOCMFI45A2ZPY6TXI/action/replication_record"}},"created_at":"2026-08-04T00:34:26.537088+00:00","updated_at":"2026-08-04T00:34:26.537088+00:00"}