{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:FRHV3LX56X5WZTLFX5GAGYOQDE","short_pith_number":"pith:FRHV3LX5","schema_version":"1.0","canonical_sha256":"2c4f5daefdf5fb6ccd65bf4c0361d019154fa0758b3ef9dc636f8762500812e7","source":{"kind":"arxiv","id":"2403.16898","version":2},"attestation_state":"computed","paper":{"title":"Concerned with Data Contamination? Assessing Countermeasures in Code Language Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.SE","authors_text":"Jialun Cao, Shing-Chi Cheung, Wuqi Zhang","submitted_at":"2024-03-25T16:10:25Z","abstract_excerpt":"Various techniques have been proposed to leverage the capabilities of code language models (CLMs) for SE tasks. While these techniques typically evaluate their effectiveness using publicly available datasets, the evaluation can be subject to data contamination threats where the evaluation datasets have already been used to train the concerned CLMs. This can significantly affect the reliability of the evaluation. Different countermeasures have been suggested to mitigate the data contamination threat. Countermeasures include using more recent data, curating new data, and refactoring existing dat"},"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":"2403.16898","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2024-03-25T16:10:25Z","cross_cats_sorted":["cs.CR"],"title_canon_sha256":"52780d1967daf7c51342b22a9a0cf0335a5085f67d9c1d04de96ffdabe2d9131","abstract_canon_sha256":"9565480be517188155838c11fcf950325830bb7aaa45b43dc313f5a9222827a8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:01:56.009195Z","signature_b64":"YIUFYaC6vCk2TzGR8Hqx4+dMFiHIEjVT4/99I38D6LcC1c30nTNGPujrjJWnNLbe74iPNOfNdRh7HmKBzcJ5AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2c4f5daefdf5fb6ccd65bf4c0361d019154fa0758b3ef9dc636f8762500812e7","last_reissued_at":"2026-07-05T08:01:56.008682Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:01:56.008682Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Concerned with Data Contamination? Assessing Countermeasures in Code Language Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.SE","authors_text":"Jialun Cao, Shing-Chi Cheung, Wuqi Zhang","submitted_at":"2024-03-25T16:10:25Z","abstract_excerpt":"Various techniques have been proposed to leverage the capabilities of code language models (CLMs) for SE tasks. While these techniques typically evaluate their effectiveness using publicly available datasets, the evaluation can be subject to data contamination threats where the evaluation datasets have already been used to train the concerned CLMs. This can significantly affect the reliability of the evaluation. Different countermeasures have been suggested to mitigate the data contamination threat. Countermeasures include using more recent data, curating new data, and refactoring existing dat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.16898","kind":"arxiv","version":2},"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/2403.16898/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":"2403.16898","created_at":"2026-07-05T08:01:56.008742+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.16898v2","created_at":"2026-07-05T08:01:56.008742+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.16898","created_at":"2026-07-05T08:01:56.008742+00:00"},{"alias_kind":"pith_short_12","alias_value":"FRHV3LX56X5W","created_at":"2026-07-05T08:01:56.008742+00:00"},{"alias_kind":"pith_short_16","alias_value":"FRHV3LX56X5WZTLF","created_at":"2026-07-05T08:01:56.008742+00:00"},{"alias_kind":"pith_short_8","alias_value":"FRHV3LX5","created_at":"2026-07-05T08:01:56.008742+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2604.19224","citing_title":"iCoRe: An Iterative Correlation-Aware Retriever for Bug Reproduction Test Generation","ref_index":7,"is_internal_anchor":true},{"citing_arxiv_id":"2605.26133","citing_title":"Pretraining Data Exposure in Large Language Models: A Survey of Membership Inference, Data Contamination, and Security Implications","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2408.15815","citing_title":"MR-Adopt: Automatic Deduction of Input Transformation Function for Metamorphic Testing","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2406.04244","citing_title":"Benchmark Data Contamination of Large Language Models: A Survey","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19224","citing_title":"iCoRe: An Iterative Correlation-Aware Retriever for Bug Reproduction Test Generation","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10126","citing_title":"MR-Coupler: Automated Metamorphic Test Generation via Functional Coupling Analysis","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FRHV3LX56X5WZTLFX5GAGYOQDE","json":"https://pith.science/pith/FRHV3LX56X5WZTLFX5GAGYOQDE.json","graph_json":"https://pith.science/api/pith-number/FRHV3LX56X5WZTLFX5GAGYOQDE/graph.json","events_json":"https://pith.science/api/pith-number/FRHV3LX56X5WZTLFX5GAGYOQDE/events.json","paper":"https://pith.science/paper/FRHV3LX5"},"agent_actions":{"view_html":"https://pith.science/pith/FRHV3LX56X5WZTLFX5GAGYOQDE","download_json":"https://pith.science/pith/FRHV3LX56X5WZTLFX5GAGYOQDE.json","view_paper":"https://pith.science/paper/FRHV3LX5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.16898&json=true","fetch_graph":"https://pith.science/api/pith-number/FRHV3LX56X5WZTLFX5GAGYOQDE/graph.json","fetch_events":"https://pith.science/api/pith-number/FRHV3LX56X5WZTLFX5GAGYOQDE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FRHV3LX56X5WZTLFX5GAGYOQDE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FRHV3LX56X5WZTLFX5GAGYOQDE/action/storage_attestation","attest_author":"https://pith.science/pith/FRHV3LX56X5WZTLFX5GAGYOQDE/action/author_attestation","sign_citation":"https://pith.science/pith/FRHV3LX56X5WZTLFX5GAGYOQDE/action/citation_signature","submit_replication":"https://pith.science/pith/FRHV3LX56X5WZTLFX5GAGYOQDE/action/replication_record"}},"created_at":"2026-07-05T08:01:56.008742+00:00","updated_at":"2026-07-05T08:01:56.008742+00:00"}