{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:FRHV3LX56X5WZTLFX5GAGYOQDE","short_pith_number":"pith:FRHV3LX5","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"},"canonical_sha256":"2c4f5daefdf5fb6ccd65bf4c0361d019154fa0758b3ef9dc636f8762500812e7","source":{"kind":"arxiv","id":"2403.16898","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.16898","created_at":"2026-07-05T08:01:56Z"},{"alias_kind":"arxiv_version","alias_value":"2403.16898v2","created_at":"2026-07-05T08:01:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.16898","created_at":"2026-07-05T08:01:56Z"},{"alias_kind":"pith_short_12","alias_value":"FRHV3LX56X5W","created_at":"2026-07-05T08:01:56Z"},{"alias_kind":"pith_short_16","alias_value":"FRHV3LX56X5WZTLF","created_at":"2026-07-05T08:01:56Z"},{"alias_kind":"pith_short_8","alias_value":"FRHV3LX5","created_at":"2026-07-05T08:01:56Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:FRHV3LX56X5WZTLFX5GAGYOQDE","target":"record","payload":{"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"},"canonical_sha256":"2c4f5daefdf5fb6ccd65bf4c0361d019154fa0758b3ef9dc636f8762500812e7","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"},"source_kind":"arxiv","source_id":"2403.16898","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:01:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"X6DNVxpCzNy7nnes9M68kHRFzsETfTy7tKcLtY5sdGLbp2u43jkAGhIzTrKWCQOxVM4uNfr+8HYpHMamZ2RRAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T20:34:43.432197Z"},"content_sha256":"881d59ba8b802e72204b8c270b4703d80440e808aba30cd578c86dba4d4f9a98","schema_version":"1.0","event_id":"sha256:881d59ba8b802e72204b8c270b4703d80440e808aba30cd578c86dba4d4f9a98"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:FRHV3LX56X5WZTLFX5GAGYOQDE","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:01:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sUDf/GobGjFwBmXNRds3tDpvm0/qvTNrEfToWz5npyoyRzj4bP6oxzuRq9SIgrpu1eG+ssy7whEi7rIGam37Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T20:34:43.432882Z"},"content_sha256":"bd78c6322806e8ba12306133e29aba82f140a70622dfa91b3a6c8a0e813098da","schema_version":"1.0","event_id":"sha256:bd78c6322806e8ba12306133e29aba82f140a70622dfa91b3a6c8a0e813098da"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FRHV3LX56X5WZTLFX5GAGYOQDE/bundle.json","state_url":"https://pith.science/pith/FRHV3LX56X5WZTLFX5GAGYOQDE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FRHV3LX56X5WZTLFX5GAGYOQDE/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":"2026-08-10T20:34:43Z","links":{"resolver":"https://pith.science/pith/FRHV3LX56X5WZTLFX5GAGYOQDE","bundle":"https://pith.science/pith/FRHV3LX56X5WZTLFX5GAGYOQDE/bundle.json","state":"https://pith.science/pith/FRHV3LX56X5WZTLFX5GAGYOQDE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FRHV3LX56X5WZTLFX5GAGYOQDE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:FRHV3LX56X5WZTLFX5GAGYOQDE","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":"9565480be517188155838c11fcf950325830bb7aaa45b43dc313f5a9222827a8","cross_cats_sorted":["cs.CR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2024-03-25T16:10:25Z","title_canon_sha256":"52780d1967daf7c51342b22a9a0cf0335a5085f67d9c1d04de96ffdabe2d9131"},"schema_version":"1.0","source":{"id":"2403.16898","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.16898","created_at":"2026-07-05T08:01:56Z"},{"alias_kind":"arxiv_version","alias_value":"2403.16898v2","created_at":"2026-07-05T08:01:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.16898","created_at":"2026-07-05T08:01:56Z"},{"alias_kind":"pith_short_12","alias_value":"FRHV3LX56X5W","created_at":"2026-07-05T08:01:56Z"},{"alias_kind":"pith_short_16","alias_value":"FRHV3LX56X5WZTLF","created_at":"2026-07-05T08:01:56Z"},{"alias_kind":"pith_short_8","alias_value":"FRHV3LX5","created_at":"2026-07-05T08:01:56Z"}],"graph_snapshots":[{"event_id":"sha256:bd78c6322806e8ba12306133e29aba82f140a70622dfa91b3a6c8a0e813098da","target":"graph","created_at":"2026-07-05T08:01:56Z","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/2403.16898/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Jialun Cao, Shing-Chi Cheung, Wuqi Zhang","cross_cats":["cs.CR"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2024-03-25T16:10:25Z","title":"Concerned with Data Contamination? Assessing Countermeasures in Code Language Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.16898","kind":"arxiv","version":2},"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":"sha256:881d59ba8b802e72204b8c270b4703d80440e808aba30cd578c86dba4d4f9a98","target":"record","created_at":"2026-07-05T08:01:56Z","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":"9565480be517188155838c11fcf950325830bb7aaa45b43dc313f5a9222827a8","cross_cats_sorted":["cs.CR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2024-03-25T16:10:25Z","title_canon_sha256":"52780d1967daf7c51342b22a9a0cf0335a5085f67d9c1d04de96ffdabe2d9131"},"schema_version":"1.0","source":{"id":"2403.16898","kind":"arxiv","version":2}},"canonical_sha256":"2c4f5daefdf5fb6ccd65bf4c0361d019154fa0758b3ef9dc636f8762500812e7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2c4f5daefdf5fb6ccd65bf4c0361d019154fa0758b3ef9dc636f8762500812e7","first_computed_at":"2026-07-05T08:01:56.008682Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:01:56.008682Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YIUFYaC6vCk2TzGR8Hqx4+dMFiHIEjVT4/99I38D6LcC1c30nTNGPujrjJWnNLbe74iPNOfNdRh7HmKBzcJ5AA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:01:56.009195Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.16898","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:881d59ba8b802e72204b8c270b4703d80440e808aba30cd578c86dba4d4f9a98","sha256:bd78c6322806e8ba12306133e29aba82f140a70622dfa91b3a6c8a0e813098da"],"state_sha256":"373cebbd5138e86e4b79b918a223a6ea5e936dcef10f27f823be6de0937dfb0d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8iBf8HPOkzDTFILUrMvEFa+ZG2S2JEXjBG5icA5WvVzbYD+ZeUeN800DLk8rGD7pzucHyvCWhIxOfBT6zMD7Cw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T20:34:43.436993Z","bundle_sha256":"ce17d3c314a599a818bf80b11778b3a2e29ac4c62d55046166836a971be43034"}}