{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:RQBOVM7JBLAJAZQ3FQUJGLF44B","short_pith_number":"pith:RQBOVM7J","canonical_record":{"source":{"id":"2310.16253","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2023-10-25T00:06:02Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"33f19cba9fb6c9a8775ba5aff2d48d388cc29f90c870b5b152c03531f83eefce","abstract_canon_sha256":"c7cbca36e539a86efc1a7d3b56a636417256af87252509578756937d8949b1c4"},"schema_version":"1.0"},"canonical_sha256":"8c02eab3e90ac090661b2c28932cbce056d979c7b303b09d50e872b37350c9a0","source":{"kind":"arxiv","id":"2310.16253","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.16253","created_at":"2026-07-05T07:04:54Z"},{"alias_kind":"arxiv_version","alias_value":"2310.16253v1","created_at":"2026-07-05T07:04:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.16253","created_at":"2026-07-05T07:04:54Z"},{"alias_kind":"pith_short_12","alias_value":"RQBOVM7JBLAJ","created_at":"2026-07-05T07:04:54Z"},{"alias_kind":"pith_short_16","alias_value":"RQBOVM7JBLAJAZQ3","created_at":"2026-07-05T07:04:54Z"},{"alias_kind":"pith_short_8","alias_value":"RQBOVM7J","created_at":"2026-07-05T07:04:54Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:RQBOVM7JBLAJAZQ3FQUJGLF44B","target":"record","payload":{"canonical_record":{"source":{"id":"2310.16253","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2023-10-25T00:06:02Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"33f19cba9fb6c9a8775ba5aff2d48d388cc29f90c870b5b152c03531f83eefce","abstract_canon_sha256":"c7cbca36e539a86efc1a7d3b56a636417256af87252509578756937d8949b1c4"},"schema_version":"1.0"},"canonical_sha256":"8c02eab3e90ac090661b2c28932cbce056d979c7b303b09d50e872b37350c9a0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:04:54.486706Z","signature_b64":"GzKZHhWW+N8qmh9UDqOCDGedLtJgez69LU9EpFxj32kODteajOAmkHP0ZZEmMjwknl/d120+9EZreFGO2dz7AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8c02eab3e90ac090661b2c28932cbce056d979c7b303b09d50e872b37350c9a0","last_reissued_at":"2026-07-05T07:04:54.486243Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:04:54.486243Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.16253","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":"2026-07-05T07:04:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"f/CfdmvIyOuzpdz16ZhqcYA0V4PJjnYMF1YdGSXUBiZvI7ePmimaJZGcPB8u3aFKyJ+EzWKmINUZ1mtiaF4BAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T18:03:21.369353Z"},"content_sha256":"b7cf774c57b2058fbc3387daeec6f0c2001c1e3e7e2cda2076f3483b1d7baf32","schema_version":"1.0","event_id":"sha256:b7cf774c57b2058fbc3387daeec6f0c2001c1e3e7e2cda2076f3483b1d7baf32"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:RQBOVM7JBLAJAZQ3FQUJGLF44B","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ConDefects: A New Dataset to Address the Data Leakage Concern for LLM-based Fault Localization and Program Repair","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Jie M. Zhang, Yonghao Wu, Yong Liu, Zheng Li","submitted_at":"2023-10-25T00:06:02Z","abstract_excerpt":"With the growing interest on Large Language Models (LLMs) for fault localization and program repair, ensuring the integrity and generalizability of the LLM-based methods becomes paramount. The code in existing widely-adopted benchmarks for these tasks was written before the the bloom of LLMs and may be included in the training data of existing popular LLMs, thereby suffering from the threat of data leakage, leading to misleadingly optimistic performance metrics. To address this issue, we introduce \"ConDefects\", a novel dataset of real faults meticulously curated to eliminate such overlap. ConD"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.16253","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/2310.16253/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":"2026-07-05T07:04:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Q7i9BpFQCimH7rzzzUSJrZ+7jQpnCGTvnK6e/VwWxHqoCUy3mlTwZJXB/9bo7mIWYAmDqH4Da06Olu94ZaqLDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T18:03:21.370508Z"},"content_sha256":"33223b58c603743e61ffb59abedf71746e8a6c60df3c7e7fe5b9e9780bc3eabb","schema_version":"1.0","event_id":"sha256:33223b58c603743e61ffb59abedf71746e8a6c60df3c7e7fe5b9e9780bc3eabb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RQBOVM7JBLAJAZQ3FQUJGLF44B/bundle.json","state_url":"https://pith.science/pith/RQBOVM7JBLAJAZQ3FQUJGLF44B/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RQBOVM7JBLAJAZQ3FQUJGLF44B/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":"2026-08-08T18:03:21Z","links":{"resolver":"https://pith.science/pith/RQBOVM7JBLAJAZQ3FQUJGLF44B","bundle":"https://pith.science/pith/RQBOVM7JBLAJAZQ3FQUJGLF44B/bundle.json","state":"https://pith.science/pith/RQBOVM7JBLAJAZQ3FQUJGLF44B/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RQBOVM7JBLAJAZQ3FQUJGLF44B/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:RQBOVM7JBLAJAZQ3FQUJGLF44B","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":"c7cbca36e539a86efc1a7d3b56a636417256af87252509578756937d8949b1c4","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2023-10-25T00:06:02Z","title_canon_sha256":"33f19cba9fb6c9a8775ba5aff2d48d388cc29f90c870b5b152c03531f83eefce"},"schema_version":"1.0","source":{"id":"2310.16253","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.16253","created_at":"2026-07-05T07:04:54Z"},{"alias_kind":"arxiv_version","alias_value":"2310.16253v1","created_at":"2026-07-05T07:04:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.16253","created_at":"2026-07-05T07:04:54Z"},{"alias_kind":"pith_short_12","alias_value":"RQBOVM7JBLAJ","created_at":"2026-07-05T07:04:54Z"},{"alias_kind":"pith_short_16","alias_value":"RQBOVM7JBLAJAZQ3","created_at":"2026-07-05T07:04:54Z"},{"alias_kind":"pith_short_8","alias_value":"RQBOVM7J","created_at":"2026-07-05T07:04:54Z"}],"graph_snapshots":[{"event_id":"sha256:33223b58c603743e61ffb59abedf71746e8a6c60df3c7e7fe5b9e9780bc3eabb","target":"graph","created_at":"2026-07-05T07:04:54Z","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/2310.16253/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"With the growing interest on Large Language Models (LLMs) for fault localization and program repair, ensuring the integrity and generalizability of the LLM-based methods becomes paramount. The code in existing widely-adopted benchmarks for these tasks was written before the the bloom of LLMs and may be included in the training data of existing popular LLMs, thereby suffering from the threat of data leakage, leading to misleadingly optimistic performance metrics. To address this issue, we introduce \"ConDefects\", a novel dataset of real faults meticulously curated to eliminate such overlap. ConD","authors_text":"Jie M. Zhang, Yonghao Wu, Yong Liu, Zheng Li","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2023-10-25T00:06:02Z","title":"ConDefects: A New Dataset to Address the Data Leakage Concern for LLM-based Fault Localization and Program Repair"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.16253","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:b7cf774c57b2058fbc3387daeec6f0c2001c1e3e7e2cda2076f3483b1d7baf32","target":"record","created_at":"2026-07-05T07:04:54Z","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":"c7cbca36e539a86efc1a7d3b56a636417256af87252509578756937d8949b1c4","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2023-10-25T00:06:02Z","title_canon_sha256":"33f19cba9fb6c9a8775ba5aff2d48d388cc29f90c870b5b152c03531f83eefce"},"schema_version":"1.0","source":{"id":"2310.16253","kind":"arxiv","version":1}},"canonical_sha256":"8c02eab3e90ac090661b2c28932cbce056d979c7b303b09d50e872b37350c9a0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8c02eab3e90ac090661b2c28932cbce056d979c7b303b09d50e872b37350c9a0","first_computed_at":"2026-07-05T07:04:54.486243Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:04:54.486243Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GzKZHhWW+N8qmh9UDqOCDGedLtJgez69LU9EpFxj32kODteajOAmkHP0ZZEmMjwknl/d120+9EZreFGO2dz7AA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:04:54.486706Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.16253","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b7cf774c57b2058fbc3387daeec6f0c2001c1e3e7e2cda2076f3483b1d7baf32","sha256:33223b58c603743e61ffb59abedf71746e8a6c60df3c7e7fe5b9e9780bc3eabb"],"state_sha256":"ea09584aa2b8b1a3d6f028be653635f067ba1df487c9d5f5a893388834f0c149"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nSSn0a27GiZaMZhOMnhtAYV2yPygBKdCtqkpkrTOveqMSDPjUeTu0A09pxMA5uU/KaqjYADVcQCCKojDQls7Cg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T18:03:21.379824Z","bundle_sha256":"e5a630758bfddd50a844ab85ed12bf44c98142b22e47db44fefbbc04dfec10d7"}}