{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:WVHOSZIWI6QSUTJPVHOJNGCDKZ","short_pith_number":"pith:WVHOSZIW","schema_version":"1.0","canonical_sha256":"b54ee9651647a12a4d2fa9dc9698435652a695db2f8966d101653cb0686fb8c3","source":{"kind":"arxiv","id":"1911.08816","version":2},"attestation_state":"computed","paper":{"title":"Can We Benchmark Code Review Studies? A Systematic Mapping Study of Methodology, Dataset, and Metric","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Dong Wang, Kenichi Matsumoto, Raula Gaikovina Kula, Takashi Ishio, Yuki Ueda","submitted_at":"2019-11-20T10:50:29Z","abstract_excerpt":"Code Review (CR) is the cornerstone for software quality assurance and a crucial practice for software development. As CR research matures, it can be difficult to keep track of the best practices and state-of-the-art in methodology, dataset, and metric. This paper investigates the potential of benchmarking by collecting methodology, dataset, and metric of CR studies. A systematic mapping study was conducted. A total of 112 studies from 19,847 papers published in high-impact venues between the years 2011 and 2019 were selected and analyzed. First, we find that empirical evaluation is the most c"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1911.08816","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2019-11-20T10:50:29Z","cross_cats_sorted":[],"title_canon_sha256":"2111a0de8ac45e806a34e4cf9bda9331b08c0c1a1ae411b89c68649dee546778","abstract_canon_sha256":"81f5a58e57e8874ad0136fb7729e30b59bc48195056a49a659c726dcea6d7120"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:31:16.961131Z","signature_b64":"AhhfgvgGIHv/mpudmZi07Xo3rjTmbllYXJiwDZToTEjcx4Kmq6TNLfZkYA2bY5MtZq/Okp+68uQHiQWGjPk0Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b54ee9651647a12a4d2fa9dc9698435652a695db2f8966d101653cb0686fb8c3","last_reissued_at":"2026-07-05T02:31:16.960549Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:31:16.960549Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Can We Benchmark Code Review Studies? A Systematic Mapping Study of Methodology, Dataset, and Metric","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Dong Wang, Kenichi Matsumoto, Raula Gaikovina Kula, Takashi Ishio, Yuki Ueda","submitted_at":"2019-11-20T10:50:29Z","abstract_excerpt":"Code Review (CR) is the cornerstone for software quality assurance and a crucial practice for software development. As CR research matures, it can be difficult to keep track of the best practices and state-of-the-art in methodology, dataset, and metric. This paper investigates the potential of benchmarking by collecting methodology, dataset, and metric of CR studies. A systematic mapping study was conducted. A total of 112 studies from 19,847 papers published in high-impact venues between the years 2011 and 2019 were selected and analyzed. First, we find that empirical evaluation is the most c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1911.08816","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/1911.08816/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1911.08816","created_at":"2026-07-05T02:31:16.960613+00:00"},{"alias_kind":"arxiv_version","alias_value":"1911.08816v2","created_at":"2026-07-05T02:31:16.960613+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1911.08816","created_at":"2026-07-05T02:31:16.960613+00:00"},{"alias_kind":"pith_short_12","alias_value":"WVHOSZIWI6QS","created_at":"2026-07-05T02:31:16.960613+00:00"},{"alias_kind":"pith_short_16","alias_value":"WVHOSZIWI6QSUTJP","created_at":"2026-07-05T02:31:16.960613+00:00"},{"alias_kind":"pith_short_8","alias_value":"WVHOSZIW","created_at":"2026-07-05T02:31:16.960613+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.22534","citing_title":"Why Are Agentic Pull Requests Merged or Rejected? An Empirical Study","ref_index":18,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WVHOSZIWI6QSUTJPVHOJNGCDKZ","json":"https://pith.science/pith/WVHOSZIWI6QSUTJPVHOJNGCDKZ.json","graph_json":"https://pith.science/api/pith-number/WVHOSZIWI6QSUTJPVHOJNGCDKZ/graph.json","events_json":"https://pith.science/api/pith-number/WVHOSZIWI6QSUTJPVHOJNGCDKZ/events.json","paper":"https://pith.science/paper/WVHOSZIW"},"agent_actions":{"view_html":"https://pith.science/pith/WVHOSZIWI6QSUTJPVHOJNGCDKZ","download_json":"https://pith.science/pith/WVHOSZIWI6QSUTJPVHOJNGCDKZ.json","view_paper":"https://pith.science/paper/WVHOSZIW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1911.08816&json=true","fetch_graph":"https://pith.science/api/pith-number/WVHOSZIWI6QSUTJPVHOJNGCDKZ/graph.json","fetch_events":"https://pith.science/api/pith-number/WVHOSZIWI6QSUTJPVHOJNGCDKZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WVHOSZIWI6QSUTJPVHOJNGCDKZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WVHOSZIWI6QSUTJPVHOJNGCDKZ/action/storage_attestation","attest_author":"https://pith.science/pith/WVHOSZIWI6QSUTJPVHOJNGCDKZ/action/author_attestation","sign_citation":"https://pith.science/pith/WVHOSZIWI6QSUTJPVHOJNGCDKZ/action/citation_signature","submit_replication":"https://pith.science/pith/WVHOSZIWI6QSUTJPVHOJNGCDKZ/action/replication_record"}},"created_at":"2026-07-05T02:31:16.960613+00:00","updated_at":"2026-07-05T02:31:16.960613+00:00"}