{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:UDXBQE4S2PABACFJDJ6NVYHWI6","short_pith_number":"pith:UDXBQE4S","canonical_record":{"source":{"id":"2503.08532","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2025-03-11T15:23:13Z","cross_cats_sorted":[],"title_canon_sha256":"23d461e5de359196f6c1b23590b88d1411ced4dad21cff37fe55ae7850db261b","abstract_canon_sha256":"29f96d7ec72c6563d313fe73d2e7b1d8f1d1048e30af1d23b67e6af42f7a8b48"},"schema_version":"1.0"},"canonical_sha256":"a0ee181392d3c01008a91a7cdae0f647a0808da99d355c5bcbbfa05cd089eeeb","source":{"kind":"arxiv","id":"2503.08532","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.08532","created_at":"2026-07-05T10:29:01Z"},{"alias_kind":"arxiv_version","alias_value":"2503.08532v1","created_at":"2026-07-05T10:29:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.08532","created_at":"2026-07-05T10:29:01Z"},{"alias_kind":"pith_short_12","alias_value":"UDXBQE4S2PAB","created_at":"2026-07-05T10:29:01Z"},{"alias_kind":"pith_short_16","alias_value":"UDXBQE4S2PABACFJ","created_at":"2026-07-05T10:29:01Z"},{"alias_kind":"pith_short_8","alias_value":"UDXBQE4S","created_at":"2026-07-05T10:29:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:UDXBQE4S2PABACFJDJ6NVYHWI6","target":"record","payload":{"canonical_record":{"source":{"id":"2503.08532","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2025-03-11T15:23:13Z","cross_cats_sorted":[],"title_canon_sha256":"23d461e5de359196f6c1b23590b88d1411ced4dad21cff37fe55ae7850db261b","abstract_canon_sha256":"29f96d7ec72c6563d313fe73d2e7b1d8f1d1048e30af1d23b67e6af42f7a8b48"},"schema_version":"1.0"},"canonical_sha256":"a0ee181392d3c01008a91a7cdae0f647a0808da99d355c5bcbbfa05cd089eeeb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:29:01.573491Z","signature_b64":"lfyoAZnSC5rbWIRgr3KCF4tlJtXCA3pwjB+TFXYUl/x0HncdjkBDE8ozr5DqVoCeZ0h+38Nkv3GOfIBhJ9WYBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a0ee181392d3c01008a91a7cdae0f647a0808da99d355c5bcbbfa05cd089eeeb","last_reissued_at":"2026-07-05T10:29:01.572896Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:29:01.572896Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2503.08532","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":"2026-07-05T10:29:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PmMKN8rdJ5nJDGz3ubBf0ZbQohE1UHCCr4YZQXESkMopRKQ242L9f6B4PwhzeRiehzRj1Ubcti3NYmGPU4dLCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T15:44:23.603295Z"},"content_sha256":"f251f75c3b0188fbf8543a549cb85b3c01653f32f9cd37b3ceb7785b90705bcc","schema_version":"1.0","event_id":"sha256:f251f75c3b0188fbf8543a549cb85b3c01653f32f9cd37b3ceb7785b90705bcc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:UDXBQE4S2PABACFJDJ6NVYHWI6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Bogus Bugs, Duplicates, and Revealing Comments: Data Quality Issues in NPR","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Julian Aron Prenner, Romain Robbes","submitted_at":"2025-03-11T15:23:13Z","abstract_excerpt":"The performance of a machine learning system is not only determined by the model but also, to a substantial degree, by the data it is trained on. With the increasing use of machine learning, issues related to data quality have become a concern also in automated program repair research. In this position paper, we report some of the data-related issues we have come across when working with several large APR datasets and benchmarks, including, for instance, duplicates or \"bogus bugs\". We briefly discuss the potential impact of these problems on repair performance and propose possible remedies. We"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.08532","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/2503.08532/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":"2026-07-05T10:29:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8YZDtSPSXLH5WEmPRydoNSNfZ0zrG7Jsw8JKfcnadguv2HlLsA5pEnkfk10ZOHpOppUplffAgCjPuUIz+SoMDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T15:44:23.603786Z"},"content_sha256":"10385f55037a48cc2738e2e6d6695cf60a6c51b3e58e669c9da711ab8278ce03","schema_version":"1.0","event_id":"sha256:10385f55037a48cc2738e2e6d6695cf60a6c51b3e58e669c9da711ab8278ce03"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UDXBQE4S2PABACFJDJ6NVYHWI6/bundle.json","state_url":"https://pith.science/pith/UDXBQE4S2PABACFJDJ6NVYHWI6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UDXBQE4S2PABACFJDJ6NVYHWI6/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":"2026-08-22T15:44:23Z","links":{"resolver":"https://pith.science/pith/UDXBQE4S2PABACFJDJ6NVYHWI6","bundle":"https://pith.science/pith/UDXBQE4S2PABACFJDJ6NVYHWI6/bundle.json","state":"https://pith.science/pith/UDXBQE4S2PABACFJDJ6NVYHWI6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UDXBQE4S2PABACFJDJ6NVYHWI6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:UDXBQE4S2PABACFJDJ6NVYHWI6","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":"29f96d7ec72c6563d313fe73d2e7b1d8f1d1048e30af1d23b67e6af42f7a8b48","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2025-03-11T15:23:13Z","title_canon_sha256":"23d461e5de359196f6c1b23590b88d1411ced4dad21cff37fe55ae7850db261b"},"schema_version":"1.0","source":{"id":"2503.08532","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.08532","created_at":"2026-07-05T10:29:01Z"},{"alias_kind":"arxiv_version","alias_value":"2503.08532v1","created_at":"2026-07-05T10:29:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.08532","created_at":"2026-07-05T10:29:01Z"},{"alias_kind":"pith_short_12","alias_value":"UDXBQE4S2PAB","created_at":"2026-07-05T10:29:01Z"},{"alias_kind":"pith_short_16","alias_value":"UDXBQE4S2PABACFJ","created_at":"2026-07-05T10:29:01Z"},{"alias_kind":"pith_short_8","alias_value":"UDXBQE4S","created_at":"2026-07-05T10:29:01Z"}],"graph_snapshots":[{"event_id":"sha256:10385f55037a48cc2738e2e6d6695cf60a6c51b3e58e669c9da711ab8278ce03","target":"graph","created_at":"2026-07-05T10:29:01Z","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/2503.08532/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The performance of a machine learning system is not only determined by the model but also, to a substantial degree, by the data it is trained on. With the increasing use of machine learning, issues related to data quality have become a concern also in automated program repair research. In this position paper, we report some of the data-related issues we have come across when working with several large APR datasets and benchmarks, including, for instance, duplicates or \"bogus bugs\". We briefly discuss the potential impact of these problems on repair performance and propose possible remedies. We","authors_text":"Julian Aron Prenner, Romain Robbes","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2025-03-11T15:23:13Z","title":"Bogus Bugs, Duplicates, and Revealing Comments: Data Quality Issues in NPR"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.08532","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:f251f75c3b0188fbf8543a549cb85b3c01653f32f9cd37b3ceb7785b90705bcc","target":"record","created_at":"2026-07-05T10:29:01Z","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":"29f96d7ec72c6563d313fe73d2e7b1d8f1d1048e30af1d23b67e6af42f7a8b48","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2025-03-11T15:23:13Z","title_canon_sha256":"23d461e5de359196f6c1b23590b88d1411ced4dad21cff37fe55ae7850db261b"},"schema_version":"1.0","source":{"id":"2503.08532","kind":"arxiv","version":1}},"canonical_sha256":"a0ee181392d3c01008a91a7cdae0f647a0808da99d355c5bcbbfa05cd089eeeb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a0ee181392d3c01008a91a7cdae0f647a0808da99d355c5bcbbfa05cd089eeeb","first_computed_at":"2026-07-05T10:29:01.572896Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:29:01.572896Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lfyoAZnSC5rbWIRgr3KCF4tlJtXCA3pwjB+TFXYUl/x0HncdjkBDE8ozr5DqVoCeZ0h+38Nkv3GOfIBhJ9WYBg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:29:01.573491Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.08532","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f251f75c3b0188fbf8543a549cb85b3c01653f32f9cd37b3ceb7785b90705bcc","sha256:10385f55037a48cc2738e2e6d6695cf60a6c51b3e58e669c9da711ab8278ce03"],"state_sha256":"370e2939b540e1b10b82b95b5836bc4aa8de81596b54f436501ac28c143b3213"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zshuHtq98VMYwq+vwqNwvLDEc4+CaKcM5jLtlCkeJsEuIs0dJdvBqp6Y4eeyOsiOJDXeYA22w2/mFuLJVvkBDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-22T15:44:23.608327Z","bundle_sha256":"27a801c429e4b5a42e4a33abce7ba1416fe3fce806fc479e2102da841fb67d41"}}