{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:N4PH2NW2GFACYWHU6G5RQN4NS6","short_pith_number":"pith:N4PH2NW2","schema_version":"1.0","canonical_sha256":"6f1e7d36da31402c58f4f1bb18378d97b108ad7229bf47d6459b5b0a230c141b","source":{"kind":"arxiv","id":"2412.18291","version":2},"attestation_state":"computed","paper":{"title":"DeepCRCEval: Revisiting the Evaluation of Code Review Comment Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.SE","authors_text":"Chun Zuo, Fengjun Zhang, Junyi Lu, Lei Yu, Li Yang, Shiqi Cheng, Xiaojia Li, Zihan Hua","submitted_at":"2024-12-24T08:53:54Z","abstract_excerpt":"Code review is a vital but demanding aspect of software development, generating significant interest in automating review comments. Traditional evaluation methods for these comments, primarily based on text similarity, face two major challenges: inconsistent reliability of human-authored comments in open-source projects and the weak correlation of text similarity with objectives like enhancing code quality and detecting defects.\n  This study empirically analyzes benchmark comments using a novel set of criteria informed by prior research and developer interviews. We then similarly revisit the e"},"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":"2412.18291","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2024-12-24T08:53:54Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"910e3a98b5b0de4f6c15127037393f38ea096e2d0af2a06772c440e2cee29526","abstract_canon_sha256":"24b00c60021fb7d94a0afeaf4a2c0cfa3960c3148122761ff50440475f8b1d3f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:05:15.712300Z","signature_b64":"ico1CDCWxXyB5BKi0B5mgZDWOQWtZrE2m71MmQfa+I5aAvmmZVt1iFifoapceYsjC0X34B3825w8btdf8kcCCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6f1e7d36da31402c58f4f1bb18378d97b108ad7229bf47d6459b5b0a230c141b","last_reissued_at":"2026-07-05T10:05:15.711775Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:05:15.711775Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DeepCRCEval: Revisiting the Evaluation of Code Review Comment Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.SE","authors_text":"Chun Zuo, Fengjun Zhang, Junyi Lu, Lei Yu, Li Yang, Shiqi Cheng, Xiaojia Li, Zihan Hua","submitted_at":"2024-12-24T08:53:54Z","abstract_excerpt":"Code review is a vital but demanding aspect of software development, generating significant interest in automating review comments. Traditional evaluation methods for these comments, primarily based on text similarity, face two major challenges: inconsistent reliability of human-authored comments in open-source projects and the weak correlation of text similarity with objectives like enhancing code quality and detecting defects.\n  This study empirically analyzes benchmark comments using a novel set of criteria informed by prior research and developer interviews. We then similarly revisit the e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.18291","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/2412.18291/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":"2412.18291","created_at":"2026-07-05T10:05:15.711840+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.18291v2","created_at":"2026-07-05T10:05:15.711840+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.18291","created_at":"2026-07-05T10:05:15.711840+00:00"},{"alias_kind":"pith_short_12","alias_value":"N4PH2NW2GFAC","created_at":"2026-07-05T10:05:15.711840+00:00"},{"alias_kind":"pith_short_16","alias_value":"N4PH2NW2GFACYWHU","created_at":"2026-07-05T10:05:15.711840+00:00"},{"alias_kind":"pith_short_8","alias_value":"N4PH2NW2","created_at":"2026-07-05T10:05:15.711840+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.11340","citing_title":"DecompileBench: A Comprehensive Benchmark for Evaluating Decompilers in Real-World Scenarios","ref_index":31,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/N4PH2NW2GFACYWHU6G5RQN4NS6","json":"https://pith.science/pith/N4PH2NW2GFACYWHU6G5RQN4NS6.json","graph_json":"https://pith.science/api/pith-number/N4PH2NW2GFACYWHU6G5RQN4NS6/graph.json","events_json":"https://pith.science/api/pith-number/N4PH2NW2GFACYWHU6G5RQN4NS6/events.json","paper":"https://pith.science/paper/N4PH2NW2"},"agent_actions":{"view_html":"https://pith.science/pith/N4PH2NW2GFACYWHU6G5RQN4NS6","download_json":"https://pith.science/pith/N4PH2NW2GFACYWHU6G5RQN4NS6.json","view_paper":"https://pith.science/paper/N4PH2NW2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.18291&json=true","fetch_graph":"https://pith.science/api/pith-number/N4PH2NW2GFACYWHU6G5RQN4NS6/graph.json","fetch_events":"https://pith.science/api/pith-number/N4PH2NW2GFACYWHU6G5RQN4NS6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/N4PH2NW2GFACYWHU6G5RQN4NS6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/N4PH2NW2GFACYWHU6G5RQN4NS6/action/storage_attestation","attest_author":"https://pith.science/pith/N4PH2NW2GFACYWHU6G5RQN4NS6/action/author_attestation","sign_citation":"https://pith.science/pith/N4PH2NW2GFACYWHU6G5RQN4NS6/action/citation_signature","submit_replication":"https://pith.science/pith/N4PH2NW2GFACYWHU6G5RQN4NS6/action/replication_record"}},"created_at":"2026-07-05T10:05:15.711840+00:00","updated_at":"2026-07-05T10:05:15.711840+00:00"}