{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:FIDUOC35N6MGGMW45ADB3LTTDB","short_pith_number":"pith:FIDUOC35","schema_version":"1.0","canonical_sha256":"2a07470b7d6f986332dce8061dae731852f1c1b14c5a89093369de4e03ed3ccf","source":{"kind":"arxiv","id":"2409.19801","version":2},"attestation_state":"computed","paper":{"title":"CRScore: Grounding Automated Evaluation of Code Review Comments in Code Claims and Smells","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.SE","authors_text":"Atharva Naik, Carolyn Rose, Daniel Fried, Marcus Alenius","submitted_at":"2024-09-29T21:53:18Z","abstract_excerpt":"The task of automated code review has recently gained a lot of attention from the machine learning community. However, current review comment evaluation metrics rely on comparisons with a human-written reference for a given code change (also called a diff). Furthermore, code review is a one-to-many problem, like generation and summarization, with many \"valid reviews\" for a diff. Thus, we develop CRScore - a reference-free metric to measure dimensions of review quality like conciseness, comprehensiveness, and relevance. We design CRScore to evaluate reviews in a way that is grounded in claims a"},"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":"2409.19801","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2024-09-29T21:53:18Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"ff1f8c1123cdb3f6d999d3e295be57234279eab511f037c6eaec7e1bbe4a1ec4","abstract_canon_sha256":"aaab5667df3f6b48bb8de1e5889fb58dc1af444fb20c017bb0b38cd05844c790"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:31:47.427958Z","signature_b64":"x3IpfBPHVl50skpO93PYxKU4Ps2dpVjkkHSH7nqNMpSg0HA6RfchUoI0B1mQ0h3Swzl6JCK40JhAGDy2ImEEBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2a07470b7d6f986332dce8061dae731852f1c1b14c5a89093369de4e03ed3ccf","last_reissued_at":"2026-07-05T10:31:47.427151Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:31:47.427151Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CRScore: Grounding Automated Evaluation of Code Review Comments in Code Claims and Smells","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.SE","authors_text":"Atharva Naik, Carolyn Rose, Daniel Fried, Marcus Alenius","submitted_at":"2024-09-29T21:53:18Z","abstract_excerpt":"The task of automated code review has recently gained a lot of attention from the machine learning community. However, current review comment evaluation metrics rely on comparisons with a human-written reference for a given code change (also called a diff). Furthermore, code review is a one-to-many problem, like generation and summarization, with many \"valid reviews\" for a diff. Thus, we develop CRScore - a reference-free metric to measure dimensions of review quality like conciseness, comprehensiveness, and relevance. We design CRScore to evaluate reviews in a way that is grounded in claims a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.19801","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/2409.19801/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":"2409.19801","created_at":"2026-07-05T10:31:47.427227+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.19801v2","created_at":"2026-07-05T10:31:47.427227+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.19801","created_at":"2026-07-05T10:31:47.427227+00:00"},{"alias_kind":"pith_short_12","alias_value":"FIDUOC35N6MG","created_at":"2026-07-05T10:31:47.427227+00:00"},{"alias_kind":"pith_short_16","alias_value":"FIDUOC35N6MGGMW4","created_at":"2026-07-05T10:31:47.427227+00:00"},{"alias_kind":"pith_short_8","alias_value":"FIDUOC35","created_at":"2026-07-05T10:31:47.427227+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2507.11687","citing_title":"MetaLint: Easy-to-Hard Generalization for Code Linting","ref_index":28,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FIDUOC35N6MGGMW45ADB3LTTDB","json":"https://pith.science/pith/FIDUOC35N6MGGMW45ADB3LTTDB.json","graph_json":"https://pith.science/api/pith-number/FIDUOC35N6MGGMW45ADB3LTTDB/graph.json","events_json":"https://pith.science/api/pith-number/FIDUOC35N6MGGMW45ADB3LTTDB/events.json","paper":"https://pith.science/paper/FIDUOC35"},"agent_actions":{"view_html":"https://pith.science/pith/FIDUOC35N6MGGMW45ADB3LTTDB","download_json":"https://pith.science/pith/FIDUOC35N6MGGMW45ADB3LTTDB.json","view_paper":"https://pith.science/paper/FIDUOC35","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.19801&json=true","fetch_graph":"https://pith.science/api/pith-number/FIDUOC35N6MGGMW45ADB3LTTDB/graph.json","fetch_events":"https://pith.science/api/pith-number/FIDUOC35N6MGGMW45ADB3LTTDB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FIDUOC35N6MGGMW45ADB3LTTDB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FIDUOC35N6MGGMW45ADB3LTTDB/action/storage_attestation","attest_author":"https://pith.science/pith/FIDUOC35N6MGGMW45ADB3LTTDB/action/author_attestation","sign_citation":"https://pith.science/pith/FIDUOC35N6MGGMW45ADB3LTTDB/action/citation_signature","submit_replication":"https://pith.science/pith/FIDUOC35N6MGGMW45ADB3LTTDB/action/replication_record"}},"created_at":"2026-07-05T10:31:47.427227+00:00","updated_at":"2026-07-05T10:31:47.427227+00:00"}