{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:LKYQ57X3IDT6M2WCTBWVVZEAOM","short_pith_number":"pith:LKYQ57X3","canonical_record":{"source":{"id":"2502.06215","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-02-10T07:33:49Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"a43a38f2008a96b4d26101d539ea513f3351e3d69faf52543d7cddef3dc54016","abstract_canon_sha256":"d6640d7cf270d42259a3b4775c974e32abd298b7376c7df9a712925dc1790a43"},"schema_version":"1.0"},"canonical_sha256":"5ab10efefb40e7e66ac2986d5ae4807334d979050eb71050cb21e2fce5106f90","source":{"kind":"arxiv","id":"2502.06215","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.06215","created_at":"2026-07-05T10:11:49Z"},{"alias_kind":"arxiv_version","alias_value":"2502.06215v1","created_at":"2026-07-05T10:11:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.06215","created_at":"2026-07-05T10:11:49Z"},{"alias_kind":"pith_short_12","alias_value":"LKYQ57X3IDT6","created_at":"2026-07-05T10:11:49Z"},{"alias_kind":"pith_short_16","alias_value":"LKYQ57X3IDT6M2WC","created_at":"2026-07-05T10:11:49Z"},{"alias_kind":"pith_short_8","alias_value":"LKYQ57X3","created_at":"2026-07-05T10:11:49Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:LKYQ57X3IDT6M2WCTBWVVZEAOM","target":"record","payload":{"canonical_record":{"source":{"id":"2502.06215","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-02-10T07:33:49Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"a43a38f2008a96b4d26101d539ea513f3351e3d69faf52543d7cddef3dc54016","abstract_canon_sha256":"d6640d7cf270d42259a3b4775c974e32abd298b7376c7df9a712925dc1790a43"},"schema_version":"1.0"},"canonical_sha256":"5ab10efefb40e7e66ac2986d5ae4807334d979050eb71050cb21e2fce5106f90","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:11:49.122666Z","signature_b64":"Nl7IeNK99Zb5JWvIV8TXBTlzwMJH1EPHteWPI9tuYP6iESyAk3CumDFJOhUSJVTcWNH7Jb9nonqBmqo3jy3lAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5ab10efefb40e7e66ac2986d5ae4807334d979050eb71050cb21e2fce5106f90","last_reissued_at":"2026-07-05T10:11:49.122187Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:11:49.122187Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.06215","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":"2026-07-05T10:11:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Nl44nUGIGEcw47CaKdFkaU3fteYoTtYnP/ndXg0GhwtaalThTmsI2XeHTw+vA6FdY4AZUsipL8Ofnx+jADU9CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T19:12:19.796095Z"},"content_sha256":"27b09dc17dc05c219bd6fcbad7b6f0f22621a60baef413c7caa50e4884a7d74a","schema_version":"1.0","event_id":"sha256:27b09dc17dc05c219bd6fcbad7b6f0f22621a60baef413c7caa50e4884a7d74a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:LKYQ57X3IDT6M2WCTBWVVZEAOM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"LessLeak-Bench: A First Investigation of Data Leakage in LLMs Across 83 Software Engineering Benchmarks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.SE","authors_text":"Beiqi Zhang, Dan Huang, David Lo, Jianming Chang, Junda He, Martin Weyssow, Ratnadira Widyasari, Ting Zhang, Xin Zhou, Yunbo Lyu","submitted_at":"2025-02-10T07:33:49Z","abstract_excerpt":"Large Language Models (LLMs) are widely utilized in software engineering (SE) tasks, such as code generation and automated program repair. However, their reliance on extensive and often undisclosed pre-training datasets raises significant concerns about data leakage, where the evaluation benchmark data is unintentionally ``seen'' by LLMs during the model's construction phase. The data leakage issue could largely undermine the validity of LLM-based research and evaluations. Despite the increasing use of LLMs in the SE community, there is no comprehensive study that assesses the extent of data l"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.06215","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/2502.06215/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":"2026-07-05T10:11:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AfJi7iugIqTFQg3Bxc6wHMChQ6J6VsuNwcv/oPtE37JbIwCtp37bxo5z55KhsOEIFDO8LUzekeNuZmbYIUlCBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T19:12:19.796479Z"},"content_sha256":"4ae43c5d0bd4bd531f4a07b7b8eb8ce7452b698b7c0d91ad2ddd3315472f83d9","schema_version":"1.0","event_id":"sha256:4ae43c5d0bd4bd531f4a07b7b8eb8ce7452b698b7c0d91ad2ddd3315472f83d9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LKYQ57X3IDT6M2WCTBWVVZEAOM/bundle.json","state_url":"https://pith.science/pith/LKYQ57X3IDT6M2WCTBWVVZEAOM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LKYQ57X3IDT6M2WCTBWVVZEAOM/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":"2026-07-08T19:12:19Z","links":{"resolver":"https://pith.science/pith/LKYQ57X3IDT6M2WCTBWVVZEAOM","bundle":"https://pith.science/pith/LKYQ57X3IDT6M2WCTBWVVZEAOM/bundle.json","state":"https://pith.science/pith/LKYQ57X3IDT6M2WCTBWVVZEAOM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LKYQ57X3IDT6M2WCTBWVVZEAOM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:LKYQ57X3IDT6M2WCTBWVVZEAOM","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":"d6640d7cf270d42259a3b4775c974e32abd298b7376c7df9a712925dc1790a43","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-02-10T07:33:49Z","title_canon_sha256":"a43a38f2008a96b4d26101d539ea513f3351e3d69faf52543d7cddef3dc54016"},"schema_version":"1.0","source":{"id":"2502.06215","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.06215","created_at":"2026-07-05T10:11:49Z"},{"alias_kind":"arxiv_version","alias_value":"2502.06215v1","created_at":"2026-07-05T10:11:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.06215","created_at":"2026-07-05T10:11:49Z"},{"alias_kind":"pith_short_12","alias_value":"LKYQ57X3IDT6","created_at":"2026-07-05T10:11:49Z"},{"alias_kind":"pith_short_16","alias_value":"LKYQ57X3IDT6M2WC","created_at":"2026-07-05T10:11:49Z"},{"alias_kind":"pith_short_8","alias_value":"LKYQ57X3","created_at":"2026-07-05T10:11:49Z"}],"graph_snapshots":[{"event_id":"sha256:4ae43c5d0bd4bd531f4a07b7b8eb8ce7452b698b7c0d91ad2ddd3315472f83d9","target":"graph","created_at":"2026-07-05T10:11:49Z","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/2502.06215/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) are widely utilized in software engineering (SE) tasks, such as code generation and automated program repair. However, their reliance on extensive and often undisclosed pre-training datasets raises significant concerns about data leakage, where the evaluation benchmark data is unintentionally ``seen'' by LLMs during the model's construction phase. The data leakage issue could largely undermine the validity of LLM-based research and evaluations. Despite the increasing use of LLMs in the SE community, there is no comprehensive study that assesses the extent of data l","authors_text":"Beiqi Zhang, Dan Huang, David Lo, Jianming Chang, Junda He, Martin Weyssow, Ratnadira Widyasari, Ting Zhang, Xin Zhou, Yunbo Lyu","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-02-10T07:33:49Z","title":"LessLeak-Bench: A First Investigation of Data Leakage in LLMs Across 83 Software Engineering Benchmarks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.06215","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":"sha256:27b09dc17dc05c219bd6fcbad7b6f0f22621a60baef413c7caa50e4884a7d74a","target":"record","created_at":"2026-07-05T10:11:49Z","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":"d6640d7cf270d42259a3b4775c974e32abd298b7376c7df9a712925dc1790a43","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-02-10T07:33:49Z","title_canon_sha256":"a43a38f2008a96b4d26101d539ea513f3351e3d69faf52543d7cddef3dc54016"},"schema_version":"1.0","source":{"id":"2502.06215","kind":"arxiv","version":1}},"canonical_sha256":"5ab10efefb40e7e66ac2986d5ae4807334d979050eb71050cb21e2fce5106f90","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5ab10efefb40e7e66ac2986d5ae4807334d979050eb71050cb21e2fce5106f90","first_computed_at":"2026-07-05T10:11:49.122187Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:11:49.122187Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Nl7IeNK99Zb5JWvIV8TXBTlzwMJH1EPHteWPI9tuYP6iESyAk3CumDFJOhUSJVTcWNH7Jb9nonqBmqo3jy3lAg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:11:49.122666Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.06215","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:27b09dc17dc05c219bd6fcbad7b6f0f22621a60baef413c7caa50e4884a7d74a","sha256:4ae43c5d0bd4bd531f4a07b7b8eb8ce7452b698b7c0d91ad2ddd3315472f83d9"],"state_sha256":"d8ec5eb8afd006825daace0f388a85d23e714ed94d73946d58cfd449a706235d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GDpHt6EdikkG7U8DN+zB17im/VQZWITie0UZFlHtBf0ZEZoF1VKjK5lUHZrvSYl9x+mYwW9Nw+xWkYoOk10gBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-08T19:12:19.798504Z","bundle_sha256":"814ae2f177a699cf47192fe7d572ca812c1b5b3eb507d2f97f384df5930a2749"}}