{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:BBGEHE54XDDZYZPT6BK5WHHZVK","short_pith_number":"pith:BBGEHE54","schema_version":"1.0","canonical_sha256":"084c4393bcb8c79c65f3f055db1cf9aa898f53188cf6b34baa74b678f7b13463","source":{"kind":"arxiv","id":"2412.20340","version":2},"attestation_state":"computed","paper":{"title":"Distilling Desired Comments for Enhanced Code Review with Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Dong Shao, Guohao Shi, Guoping Rong, Haifeng Shen, Haoxiang Yan, Jiahao Zhang, Lei Zhang, Qiushi Wang, Ruiqi Pan, Yongda Yu, Yuan Li, Zhao Tian","submitted_at":"2024-12-29T03:49:13Z","abstract_excerpt":"There has been a growing interest in using Large Language Models (LLMs) for code review thanks to their proven proficiency in code comprehension. The primary objective of most review scenarios is to generate desired review comments (DRCs) that explicitly identify issues to trigger code fixes. However, existing LLM-based solutions are not so effective in generating DRCs for various reasons such as hallucination. To enhance their code review ability, they need to be fine-tuned with a customized dataset that is ideally full of DRCs. Nevertheless, such a dataset is not yet available, while manual "},"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":"2412.20340","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2024-12-29T03:49:13Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"10ca8eaefcbfb4ad52eae5b5586139090f13fe84dd7dd1fc84b6ef48a2fa8fd8","abstract_canon_sha256":"e78381ffaea29782d48d2cbe55394137ad7319c7c638bcc50e078db041ef57f3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:56:58.662120Z","signature_b64":"bhKkwbBOqohidtZJCDRpqu4YgjlRs2XccR0Bbzwo1nLnXTZegTP1ngslid/LQUQDXtogw1BSfkWa8jSn8TvKDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"084c4393bcb8c79c65f3f055db1cf9aa898f53188cf6b34baa74b678f7b13463","last_reissued_at":"2026-07-05T09:56:58.661644Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:56:58.661644Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Distilling Desired Comments for Enhanced Code Review with Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Dong Shao, Guohao Shi, Guoping Rong, Haifeng Shen, Haoxiang Yan, Jiahao Zhang, Lei Zhang, Qiushi Wang, Ruiqi Pan, Yongda Yu, Yuan Li, Zhao Tian","submitted_at":"2024-12-29T03:49:13Z","abstract_excerpt":"There has been a growing interest in using Large Language Models (LLMs) for code review thanks to their proven proficiency in code comprehension. The primary objective of most review scenarios is to generate desired review comments (DRCs) that explicitly identify issues to trigger code fixes. However, existing LLM-based solutions are not so effective in generating DRCs for various reasons such as hallucination. To enhance their code review ability, they need to be fine-tuned with a customized dataset that is ideally full of DRCs. Nevertheless, such a dataset is not yet available, while manual "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.20340","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/2412.20340/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":"2412.20340","created_at":"2026-07-05T09:56:58.661702+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.20340v2","created_at":"2026-07-05T09:56:58.661702+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.20340","created_at":"2026-07-05T09:56:58.661702+00:00"},{"alias_kind":"pith_short_12","alias_value":"BBGEHE54XDDZ","created_at":"2026-07-05T09:56:58.661702+00:00"},{"alias_kind":"pith_short_16","alias_value":"BBGEHE54XDDZYZPT","created_at":"2026-07-05T09:56:58.661702+00:00"},{"alias_kind":"pith_short_8","alias_value":"BBGEHE54","created_at":"2026-07-05T09:56:58.661702+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BBGEHE54XDDZYZPT6BK5WHHZVK","json":"https://pith.science/pith/BBGEHE54XDDZYZPT6BK5WHHZVK.json","graph_json":"https://pith.science/api/pith-number/BBGEHE54XDDZYZPT6BK5WHHZVK/graph.json","events_json":"https://pith.science/api/pith-number/BBGEHE54XDDZYZPT6BK5WHHZVK/events.json","paper":"https://pith.science/paper/BBGEHE54"},"agent_actions":{"view_html":"https://pith.science/pith/BBGEHE54XDDZYZPT6BK5WHHZVK","download_json":"https://pith.science/pith/BBGEHE54XDDZYZPT6BK5WHHZVK.json","view_paper":"https://pith.science/paper/BBGEHE54","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.20340&json=true","fetch_graph":"https://pith.science/api/pith-number/BBGEHE54XDDZYZPT6BK5WHHZVK/graph.json","fetch_events":"https://pith.science/api/pith-number/BBGEHE54XDDZYZPT6BK5WHHZVK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BBGEHE54XDDZYZPT6BK5WHHZVK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BBGEHE54XDDZYZPT6BK5WHHZVK/action/storage_attestation","attest_author":"https://pith.science/pith/BBGEHE54XDDZYZPT6BK5WHHZVK/action/author_attestation","sign_citation":"https://pith.science/pith/BBGEHE54XDDZYZPT6BK5WHHZVK/action/citation_signature","submit_replication":"https://pith.science/pith/BBGEHE54XDDZYZPT6BK5WHHZVK/action/replication_record"}},"created_at":"2026-07-05T09:56:58.661702+00:00","updated_at":"2026-07-05T09:56:58.661702+00:00"}