{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:NJI5NNT7QDCEBV7VUVLD7JZMBY","short_pith_number":"pith:NJI5NNT7","canonical_record":{"source":{"id":"2411.10842","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2024-11-16T17:06:21Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"02021f3abffc6aec6e79ace833f8beb8f76f9ab53bc6eb919d648014497fca1f","abstract_canon_sha256":"032eb8c2ce8f370f059c214dff0566863b870aa3e74c0625d04e0b3373633d71"},"schema_version":"1.0"},"canonical_sha256":"6a51d6b67f80c440d7f5a5563fa72c0e3fec122b9dea532d947e3a337550f70a","source":{"kind":"arxiv","id":"2411.10842","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.10842","created_at":"2026-07-05T09:36:23Z"},{"alias_kind":"arxiv_version","alias_value":"2411.10842v1","created_at":"2026-07-05T09:36:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.10842","created_at":"2026-07-05T09:36:23Z"},{"alias_kind":"pith_short_12","alias_value":"NJI5NNT7QDCE","created_at":"2026-07-05T09:36:23Z"},{"alias_kind":"pith_short_16","alias_value":"NJI5NNT7QDCEBV7V","created_at":"2026-07-05T09:36:23Z"},{"alias_kind":"pith_short_8","alias_value":"NJI5NNT7","created_at":"2026-07-05T09:36:23Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:NJI5NNT7QDCEBV7VUVLD7JZMBY","target":"record","payload":{"canonical_record":{"source":{"id":"2411.10842","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2024-11-16T17:06:21Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"02021f3abffc6aec6e79ace833f8beb8f76f9ab53bc6eb919d648014497fca1f","abstract_canon_sha256":"032eb8c2ce8f370f059c214dff0566863b870aa3e74c0625d04e0b3373633d71"},"schema_version":"1.0"},"canonical_sha256":"6a51d6b67f80c440d7f5a5563fa72c0e3fec122b9dea532d947e3a337550f70a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:36:23.373638Z","signature_b64":"u+qofYwZ1d+zUPpoPuGxEjj45IPGFdx54LerLfPM/toBa/eSCmf7LthwhsM20cBDeZXAqdHFR5h3GJ1f4CP0Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6a51d6b67f80c440d7f5a5563fa72c0e3fec122b9dea532d947e3a337550f70a","last_reissued_at":"2026-07-05T09:36:23.373063Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:36:23.373063Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.10842","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:36:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xltXYHrDVSmD+oJ19n8s/+QW9mevb4/FhwMZ1JCYlrvaveubkz2AN8Ue4CiTCS1c1lFajODVHFZZvWw0NZCPAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T17:40:41.368161Z"},"content_sha256":"b64f2e818c842127443805fbc46afbaaca369e790ad7936e7d121457aa475280","schema_version":"1.0","event_id":"sha256:b64f2e818c842127443805fbc46afbaaca369e790ad7936e7d121457aa475280"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:NJI5NNT7QDCEBV7VUVLD7JZMBY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"CODECLEANER: Elevating Standards with A Robust Data Contamination Mitigation Toolkit","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Hau Ching Lo, Jialun Cao, Shing-Chi Cheung, Songqiang Chen, Wuqi Zhang","submitted_at":"2024-11-16T17:06:21Z","abstract_excerpt":"Data contamination presents a critical barrier preventing widespread industrial adoption of advanced software engineering techniques that leverage code language models (CLMs). This phenomenon occurs when evaluation data inadvertently overlaps with the public code repositories used to train CLMs, severely undermining the credibility of performance evaluations. For software companies considering the integration of CLM-based techniques into their development pipeline, this uncertainty about true performance metrics poses an unacceptable business risk. Code refactoring, which comprises code restru"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.10842","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/2411.10842/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:36:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hJUSc6gIwl9k+I/HPdYQbrDfovh386nlZ8zt0VO499CRfKNjUzKkQtKaqyz6YEUqzGfYWlGjqKM5jtpZjzhiAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T17:40:41.369103Z"},"content_sha256":"10217e5eab5f96a59df94a9f89e2d96a03c75d32dee982ac5121521b8219235f","schema_version":"1.0","event_id":"sha256:10217e5eab5f96a59df94a9f89e2d96a03c75d32dee982ac5121521b8219235f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NJI5NNT7QDCEBV7VUVLD7JZMBY/bundle.json","state_url":"https://pith.science/pith/NJI5NNT7QDCEBV7VUVLD7JZMBY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NJI5NNT7QDCEBV7VUVLD7JZMBY/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-13T17:40:41Z","links":{"resolver":"https://pith.science/pith/NJI5NNT7QDCEBV7VUVLD7JZMBY","bundle":"https://pith.science/pith/NJI5NNT7QDCEBV7VUVLD7JZMBY/bundle.json","state":"https://pith.science/pith/NJI5NNT7QDCEBV7VUVLD7JZMBY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NJI5NNT7QDCEBV7VUVLD7JZMBY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:NJI5NNT7QDCEBV7VUVLD7JZMBY","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"032eb8c2ce8f370f059c214dff0566863b870aa3e74c0625d04e0b3373633d71","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2024-11-16T17:06:21Z","title_canon_sha256":"02021f3abffc6aec6e79ace833f8beb8f76f9ab53bc6eb919d648014497fca1f"},"schema_version":"1.0","source":{"id":"2411.10842","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.10842","created_at":"2026-07-05T09:36:23Z"},{"alias_kind":"arxiv_version","alias_value":"2411.10842v1","created_at":"2026-07-05T09:36:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.10842","created_at":"2026-07-05T09:36:23Z"},{"alias_kind":"pith_short_12","alias_value":"NJI5NNT7QDCE","created_at":"2026-07-05T09:36:23Z"},{"alias_kind":"pith_short_16","alias_value":"NJI5NNT7QDCEBV7V","created_at":"2026-07-05T09:36:23Z"},{"alias_kind":"pith_short_8","alias_value":"NJI5NNT7","created_at":"2026-07-05T09:36:23Z"}],"graph_snapshots":[{"event_id":"sha256:10217e5eab5f96a59df94a9f89e2d96a03c75d32dee982ac5121521b8219235f","target":"graph","created_at":"2026-07-05T09:36:23Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2411.10842/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Data contamination presents a critical barrier preventing widespread industrial adoption of advanced software engineering techniques that leverage code language models (CLMs). This phenomenon occurs when evaluation data inadvertently overlaps with the public code repositories used to train CLMs, severely undermining the credibility of performance evaluations. For software companies considering the integration of CLM-based techniques into their development pipeline, this uncertainty about true performance metrics poses an unacceptable business risk. Code refactoring, which comprises code restru","authors_text":"Hau Ching Lo, Jialun Cao, Shing-Chi Cheung, Songqiang Chen, Wuqi Zhang","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2024-11-16T17:06:21Z","title":"CODECLEANER: Elevating Standards with A Robust Data Contamination Mitigation Toolkit"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.10842","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:b64f2e818c842127443805fbc46afbaaca369e790ad7936e7d121457aa475280","target":"record","created_at":"2026-07-05T09:36:23Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"032eb8c2ce8f370f059c214dff0566863b870aa3e74c0625d04e0b3373633d71","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2024-11-16T17:06:21Z","title_canon_sha256":"02021f3abffc6aec6e79ace833f8beb8f76f9ab53bc6eb919d648014497fca1f"},"schema_version":"1.0","source":{"id":"2411.10842","kind":"arxiv","version":1}},"canonical_sha256":"6a51d6b67f80c440d7f5a5563fa72c0e3fec122b9dea532d947e3a337550f70a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6a51d6b67f80c440d7f5a5563fa72c0e3fec122b9dea532d947e3a337550f70a","first_computed_at":"2026-07-05T09:36:23.373063Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:36:23.373063Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"u+qofYwZ1d+zUPpoPuGxEjj45IPGFdx54LerLfPM/toBa/eSCmf7LthwhsM20cBDeZXAqdHFR5h3GJ1f4CP0Dw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:36:23.373638Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.10842","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b64f2e818c842127443805fbc46afbaaca369e790ad7936e7d121457aa475280","sha256:10217e5eab5f96a59df94a9f89e2d96a03c75d32dee982ac5121521b8219235f"],"state_sha256":"fd9a21de43fd76b00168e5a89b5539b4d3f22710b593d248576d67b827b63d3b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"p/tTbPrboYveMdz9LphtS/PeMDmLpwFbhLDebqYiuAEaYO4PJ3Y+dkRBMGiXWR+O6MU1/oCihjH2tv6Qzp+hBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-13T17:40:41.381567Z","bundle_sha256":"dc2d46844566610a16c980c49927f0de6026bbfb8e5ca2b23a80d807d433d34b"}}