{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:N75JPUYRSEA6E72RKYYPY4SPTK","short_pith_number":"pith:N75JPUYR","schema_version":"1.0","canonical_sha256":"6ffa97d3119101e27f515630fc724f9a9e33d8c9aa6cdc2531e1017ec6b73828","source":{"kind":"arxiv","id":"2509.01494","version":2},"attestation_state":"computed","paper":{"title":"SWR-Bench: Assessing LLM Performance in Real-World Code Review Comment Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Kaicheng Sun, Keke Han, Ruikai Shi, Rui Xie, Shikun Zhang, Wei Ye, Yidong Wang, Yixin Li, Zhengran Zeng, Zhuohao Yu","submitted_at":"2025-09-01T14:13:34Z","abstract_excerpt":"Automated Code Review (ACR) is crucial for software quality, yet existing benchmarks often fail to reflect real-world complexities, hindering the evaluation of modern Large Language Models (LLMs). Current benchmarks frequently focus on fine-grained code units, lack complete project context, and use inadequate evaluation metrics. To address these limitations, we introduce SWRBench , a new benchmark comprising 1000 manually verified Pull Requests (PRs) from GitHub, offering PR-centric review with full project context. SWRBench employs an objective LLM-based evaluation method that aligns strongly"},"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":"2509.01494","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-09-01T14:13:34Z","cross_cats_sorted":[],"title_canon_sha256":"f2db0372e4b3b178e847b818d6d64dd899fc6287b16ab2821a5857a5001a162b","abstract_canon_sha256":"eeeeb21ebc694961cf736d79f8eef058f8647377f624c71e6107c8ebfd6b2f12"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-08T01:03:47.948580Z","signature_b64":"IQ6fPZ4pF8RLuwqWsLJKF2k2s47nuyoF3wuJ0bpzcT7mwvFDOwCCowGuVmf0UBT9+ptkdIbEE8lG/9gEMh3yAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6ffa97d3119101e27f515630fc724f9a9e33d8c9aa6cdc2531e1017ec6b73828","last_reissued_at":"2026-06-08T01:03:47.947761Z","signature_status":"signed_v1","first_computed_at":"2026-06-08T01:03:47.947761Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SWR-Bench: Assessing LLM Performance in Real-World Code Review Comment Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Kaicheng Sun, Keke Han, Ruikai Shi, Rui Xie, Shikun Zhang, Wei Ye, Yidong Wang, Yixin Li, Zhengran Zeng, Zhuohao Yu","submitted_at":"2025-09-01T14:13:34Z","abstract_excerpt":"Automated Code Review (ACR) is crucial for software quality, yet existing benchmarks often fail to reflect real-world complexities, hindering the evaluation of modern Large Language Models (LLMs). Current benchmarks frequently focus on fine-grained code units, lack complete project context, and use inadequate evaluation metrics. To address these limitations, we introduce SWRBench , a new benchmark comprising 1000 manually verified Pull Requests (PRs) from GitHub, offering PR-centric review with full project context. SWRBench employs an objective LLM-based evaluation method that aligns strongly"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.01494","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/2509.01494/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":"2509.01494","created_at":"2026-06-08T01:03:47.947896+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.01494v2","created_at":"2026-06-08T01:03:47.947896+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.01494","created_at":"2026-06-08T01:03:47.947896+00:00"},{"alias_kind":"pith_short_12","alias_value":"N75JPUYRSEA6","created_at":"2026-06-08T01:03:47.947896+00:00"},{"alias_kind":"pith_short_16","alias_value":"N75JPUYRSEA6E72R","created_at":"2026-06-08T01:03:47.947896+00:00"},{"alias_kind":"pith_short_8","alias_value":"N75JPUYR","created_at":"2026-06-08T01:03:47.947896+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":3,"sample":[{"citing_arxiv_id":"2605.17548","citing_title":"Rethinking Code Review in the Age of AI: A Vision for Agentic Code Review","ref_index":136,"is_internal_anchor":true},{"citing_arxiv_id":"2603.23448","citing_title":"Code Review Agent Benchmark","ref_index":28,"is_internal_anchor":true},{"citing_arxiv_id":"2604.24450","citing_title":"On the Footprints of Reviewer Bots Feedback on Agentic Pull Requests in OSS GitHub Repositories","ref_index":27,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/N75JPUYRSEA6E72RKYYPY4SPTK","json":"https://pith.science/pith/N75JPUYRSEA6E72RKYYPY4SPTK.json","graph_json":"https://pith.science/api/pith-number/N75JPUYRSEA6E72RKYYPY4SPTK/graph.json","events_json":"https://pith.science/api/pith-number/N75JPUYRSEA6E72RKYYPY4SPTK/events.json","paper":"https://pith.science/paper/N75JPUYR"},"agent_actions":{"view_html":"https://pith.science/pith/N75JPUYRSEA6E72RKYYPY4SPTK","download_json":"https://pith.science/pith/N75JPUYRSEA6E72RKYYPY4SPTK.json","view_paper":"https://pith.science/paper/N75JPUYR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.01494&json=true","fetch_graph":"https://pith.science/api/pith-number/N75JPUYRSEA6E72RKYYPY4SPTK/graph.json","fetch_events":"https://pith.science/api/pith-number/N75JPUYRSEA6E72RKYYPY4SPTK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/N75JPUYRSEA6E72RKYYPY4SPTK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/N75JPUYRSEA6E72RKYYPY4SPTK/action/storage_attestation","attest_author":"https://pith.science/pith/N75JPUYRSEA6E72RKYYPY4SPTK/action/author_attestation","sign_citation":"https://pith.science/pith/N75JPUYRSEA6E72RKYYPY4SPTK/action/citation_signature","submit_replication":"https://pith.science/pith/N75JPUYRSEA6E72RKYYPY4SPTK/action/replication_record"}},"created_at":"2026-06-08T01:03:47.947896+00:00","updated_at":"2026-06-08T01:03:47.947896+00:00"}