{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:O6G5TR5LUXRNCZJ6UUXH3FBMOT","short_pith_number":"pith:O6G5TR5L","canonical_record":{"source":{"id":"2310.13229","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2023-10-20T02:37:44Z","cross_cats_sorted":[],"title_canon_sha256":"580fb7c262f4ec87505f5261de13d8f8ebd2365787c0ba59d4174bee8206d124","abstract_canon_sha256":"12d88416da96520763055bbdc4c7821d595428a9970bde6d23048603ec5e5d42"},"schema_version":"1.0"},"canonical_sha256":"778dd9c7aba5e2d1653ea52e7d942c74ebf8c11d7c8a5bb7cbf2db543717faeb","source":{"kind":"arxiv","id":"2310.13229","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.13229","created_at":"2026-07-05T07:08:13Z"},{"alias_kind":"arxiv_version","alias_value":"2310.13229v2","created_at":"2026-07-05T07:08:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.13229","created_at":"2026-07-05T07:08:13Z"},{"alias_kind":"pith_short_12","alias_value":"O6G5TR5LUXRN","created_at":"2026-07-05T07:08:13Z"},{"alias_kind":"pith_short_16","alias_value":"O6G5TR5LUXRNCZJ6","created_at":"2026-07-05T07:08:13Z"},{"alias_kind":"pith_short_8","alias_value":"O6G5TR5L","created_at":"2026-07-05T07:08:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:O6G5TR5LUXRNCZJ6UUXH3FBMOT","target":"record","payload":{"canonical_record":{"source":{"id":"2310.13229","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2023-10-20T02:37:44Z","cross_cats_sorted":[],"title_canon_sha256":"580fb7c262f4ec87505f5261de13d8f8ebd2365787c0ba59d4174bee8206d124","abstract_canon_sha256":"12d88416da96520763055bbdc4c7821d595428a9970bde6d23048603ec5e5d42"},"schema_version":"1.0"},"canonical_sha256":"778dd9c7aba5e2d1653ea52e7d942c74ebf8c11d7c8a5bb7cbf2db543717faeb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:08:13.360976Z","signature_b64":"Ltf1Seq8lTKdId6aFKWy5FXEawJ5uu9N+rf/Dp/46BfHIEag9eYL2Nmy2/haeJ3GFSlHypDUHUbUxEzJ2ElsAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"778dd9c7aba5e2d1653ea52e7d942c74ebf8c11d7c8a5bb7cbf2db543717faeb","last_reissued_at":"2026-07-05T07:08:13.360428Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:08:13.360428Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.13229","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":"2026-07-05T07:08:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CgAMZDUwvjzpAELylPAKGIsGTWjBQa9YGAbUH86+FMJVNMA0XC5//HG0YnRr6bMwFpStGlNWmE+1UYUANw+qAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T20:37:58.144993Z"},"content_sha256":"90026f020df37462692b3a1262c83f89d40eea592904d1189a7fd8fcd1cdd974","schema_version":"1.0","event_id":"sha256:90026f020df37462692b3a1262c83f89d40eea592904d1189a7fd8fcd1cdd974"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:O6G5TR5LUXRNCZJ6UUXH3FBMOT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"The GitHub Recent Bugs Dataset for Evaluating LLM-based Debugging Applications","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Jae Yong Lee, Juyeon Yoon, Shin Yoo, Sungmin Kang","submitted_at":"2023-10-20T02:37:44Z","abstract_excerpt":"Large Language Models (LLMs) have demonstrated strong natural language processing and code synthesis capabilities, which has led to their rapid adoption in software engineering applications. However, details about LLM training data are often not made public, which has caused concern as to whether existing bug benchmarks are included. In lieu of the training data for the popular GPT models, we examine the training data of the open-source LLM StarCoder, and find it likely that data from the widely used Defects4J benchmark was included, raising the possibility of its inclusion in GPT training dat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.13229","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/2310.13229/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":"2026-07-05T07:08:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"O7N1uDeVpLBRp5wqA3TEUxsmDih3ebA3yjllrD+nc8zmXSj3nZtgu1LAG898/CABRP9oV7yKZTjzPdkT9HVPBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T20:37:58.145517Z"},"content_sha256":"566a91e3052c3e5a8e50a9e1c5b52c97d875eeec4de3e72527e2860df74d781d","schema_version":"1.0","event_id":"sha256:566a91e3052c3e5a8e50a9e1c5b52c97d875eeec4de3e72527e2860df74d781d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/O6G5TR5LUXRNCZJ6UUXH3FBMOT/bundle.json","state_url":"https://pith.science/pith/O6G5TR5LUXRNCZJ6UUXH3FBMOT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/O6G5TR5LUXRNCZJ6UUXH3FBMOT/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":"2026-08-18T20:37:58Z","links":{"resolver":"https://pith.science/pith/O6G5TR5LUXRNCZJ6UUXH3FBMOT","bundle":"https://pith.science/pith/O6G5TR5LUXRNCZJ6UUXH3FBMOT/bundle.json","state":"https://pith.science/pith/O6G5TR5LUXRNCZJ6UUXH3FBMOT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/O6G5TR5LUXRNCZJ6UUXH3FBMOT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:O6G5TR5LUXRNCZJ6UUXH3FBMOT","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":"12d88416da96520763055bbdc4c7821d595428a9970bde6d23048603ec5e5d42","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2023-10-20T02:37:44Z","title_canon_sha256":"580fb7c262f4ec87505f5261de13d8f8ebd2365787c0ba59d4174bee8206d124"},"schema_version":"1.0","source":{"id":"2310.13229","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.13229","created_at":"2026-07-05T07:08:13Z"},{"alias_kind":"arxiv_version","alias_value":"2310.13229v2","created_at":"2026-07-05T07:08:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.13229","created_at":"2026-07-05T07:08:13Z"},{"alias_kind":"pith_short_12","alias_value":"O6G5TR5LUXRN","created_at":"2026-07-05T07:08:13Z"},{"alias_kind":"pith_short_16","alias_value":"O6G5TR5LUXRNCZJ6","created_at":"2026-07-05T07:08:13Z"},{"alias_kind":"pith_short_8","alias_value":"O6G5TR5L","created_at":"2026-07-05T07:08:13Z"}],"graph_snapshots":[{"event_id":"sha256:566a91e3052c3e5a8e50a9e1c5b52c97d875eeec4de3e72527e2860df74d781d","target":"graph","created_at":"2026-07-05T07:08:13Z","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/2310.13229/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) have demonstrated strong natural language processing and code synthesis capabilities, which has led to their rapid adoption in software engineering applications. However, details about LLM training data are often not made public, which has caused concern as to whether existing bug benchmarks are included. In lieu of the training data for the popular GPT models, we examine the training data of the open-source LLM StarCoder, and find it likely that data from the widely used Defects4J benchmark was included, raising the possibility of its inclusion in GPT training dat","authors_text":"Jae Yong Lee, Juyeon Yoon, Shin Yoo, Sungmin Kang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2023-10-20T02:37:44Z","title":"The GitHub Recent Bugs Dataset for Evaluating LLM-based Debugging Applications"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.13229","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":"sha256:90026f020df37462692b3a1262c83f89d40eea592904d1189a7fd8fcd1cdd974","target":"record","created_at":"2026-07-05T07:08:13Z","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":"12d88416da96520763055bbdc4c7821d595428a9970bde6d23048603ec5e5d42","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2023-10-20T02:37:44Z","title_canon_sha256":"580fb7c262f4ec87505f5261de13d8f8ebd2365787c0ba59d4174bee8206d124"},"schema_version":"1.0","source":{"id":"2310.13229","kind":"arxiv","version":2}},"canonical_sha256":"778dd9c7aba5e2d1653ea52e7d942c74ebf8c11d7c8a5bb7cbf2db543717faeb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"778dd9c7aba5e2d1653ea52e7d942c74ebf8c11d7c8a5bb7cbf2db543717faeb","first_computed_at":"2026-07-05T07:08:13.360428Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:08:13.360428Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Ltf1Seq8lTKdId6aFKWy5FXEawJ5uu9N+rf/Dp/46BfHIEag9eYL2Nmy2/haeJ3GFSlHypDUHUbUxEzJ2ElsAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:08:13.360976Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.13229","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:90026f020df37462692b3a1262c83f89d40eea592904d1189a7fd8fcd1cdd974","sha256:566a91e3052c3e5a8e50a9e1c5b52c97d875eeec4de3e72527e2860df74d781d"],"state_sha256":"41c631e34fa41773ad0272b162aa2d1b4ceda6dfbbc7ff88db0ac3c0126f3263"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fXDX+0rrvtuTqiS4uR1RQxcvGr6F4lSOaW7pWAgR8ob1eliG1ukcYN273vVUAbPMXzyy9XHyLfqJV/y2jUilBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T20:37:58.149846Z","bundle_sha256":"bf9e2b55fe5388a45ed00bcfea9823f6dd186de0e2130a065d8125a27aa0fb7f"}}