{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:GGWDUS34DU5B4U2UBBIBZDKIPG","short_pith_number":"pith:GGWDUS34","schema_version":"1.0","canonical_sha256":"31ac3a4b7c1d3a1e535408501c8d4879b288a7762b13f6a11e890b2dc29178cd","source":{"kind":"arxiv","id":"2203.09095","version":2},"attestation_state":"computed","paper":{"title":"Automating Code Review Activities by Large-Scale Pre-training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Alexey Svyatkovskiy, Daya Guo, Deep Majumder, Grant Jenks, Jared Green, Nan Duan, Neel Sundaresan, Shailesh Jannu, Shengyu Fu, Shuai Lu, Zhiyu Li","submitted_at":"2022-03-17T05:40:13Z","abstract_excerpt":"Code review is an essential part to software development lifecycle since it aims at guaranteeing the quality of codes. Modern code review activities necessitate developers viewing, understanding and even running the programs to assess logic, functionality, latency, style and other factors. It turns out that developers have to spend far too much time reviewing the code of their peers. Accordingly, it is in significant demand to automate the code review process. In this research, we focus on utilizing pre-training techniques for the tasks in the code review scenario. We collect a large-scale dat"},"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":"2203.09095","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2022-03-17T05:40:13Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"09a51715a93e030c388d81358d54b6ea69f9b5576eafcf3a0d95f3c2b1476464","abstract_canon_sha256":"dba888cdae0c0998c7114eef3d32864348fe361096c002459c50d430845ec2c2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:05:03.700989Z","signature_b64":"Gm/H2WCelWelMyKTSZfD4s8SzC4yq2jN3jOthgO+SO1c+6Wjdlbrskcw7epbJePMHpNM7ZdAo0bjkAnc2ffbDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"31ac3a4b7c1d3a1e535408501c8d4879b288a7762b13f6a11e890b2dc29178cd","last_reissued_at":"2026-07-05T05:05:03.700533Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:05:03.700533Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Automating Code Review Activities by Large-Scale Pre-training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Alexey Svyatkovskiy, Daya Guo, Deep Majumder, Grant Jenks, Jared Green, Nan Duan, Neel Sundaresan, Shailesh Jannu, Shengyu Fu, Shuai Lu, Zhiyu Li","submitted_at":"2022-03-17T05:40:13Z","abstract_excerpt":"Code review is an essential part to software development lifecycle since it aims at guaranteeing the quality of codes. Modern code review activities necessitate developers viewing, understanding and even running the programs to assess logic, functionality, latency, style and other factors. It turns out that developers have to spend far too much time reviewing the code of their peers. Accordingly, it is in significant demand to automate the code review process. In this research, we focus on utilizing pre-training techniques for the tasks in the code review scenario. We collect a large-scale dat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.09095","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/2203.09095/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":"2203.09095","created_at":"2026-07-05T05:05:03.700595+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.09095v2","created_at":"2026-07-05T05:05:03.700595+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.09095","created_at":"2026-07-05T05:05:03.700595+00:00"},{"alias_kind":"pith_short_12","alias_value":"GGWDUS34DU5B","created_at":"2026-07-05T05:05:03.700595+00:00"},{"alias_kind":"pith_short_16","alias_value":"GGWDUS34DU5B4U2U","created_at":"2026-07-05T05:05:03.700595+00:00"},{"alias_kind":"pith_short_8","alias_value":"GGWDUS34","created_at":"2026-07-05T05:05:03.700595+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06065","citing_title":"SWE-Review: Closing the Loop on Issue Resolution with Agentic Code Review","ref_index":17,"is_internal_anchor":true},{"citing_arxiv_id":"2601.16456","citing_title":"RubberDuckBench: A Benchmark for AI Coding Assistants","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2604.24525","citing_title":"Understanding the Limits of Automated Evaluation for Code Review Bots in Practice","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2604.24450","citing_title":"On the Footprints of Reviewer Bots Feedback on Agentic Pull Requests in OSS GitHub Repositories","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GGWDUS34DU5B4U2UBBIBZDKIPG","json":"https://pith.science/pith/GGWDUS34DU5B4U2UBBIBZDKIPG.json","graph_json":"https://pith.science/api/pith-number/GGWDUS34DU5B4U2UBBIBZDKIPG/graph.json","events_json":"https://pith.science/api/pith-number/GGWDUS34DU5B4U2UBBIBZDKIPG/events.json","paper":"https://pith.science/paper/GGWDUS34"},"agent_actions":{"view_html":"https://pith.science/pith/GGWDUS34DU5B4U2UBBIBZDKIPG","download_json":"https://pith.science/pith/GGWDUS34DU5B4U2UBBIBZDKIPG.json","view_paper":"https://pith.science/paper/GGWDUS34","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.09095&json=true","fetch_graph":"https://pith.science/api/pith-number/GGWDUS34DU5B4U2UBBIBZDKIPG/graph.json","fetch_events":"https://pith.science/api/pith-number/GGWDUS34DU5B4U2UBBIBZDKIPG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GGWDUS34DU5B4U2UBBIBZDKIPG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GGWDUS34DU5B4U2UBBIBZDKIPG/action/storage_attestation","attest_author":"https://pith.science/pith/GGWDUS34DU5B4U2UBBIBZDKIPG/action/author_attestation","sign_citation":"https://pith.science/pith/GGWDUS34DU5B4U2UBBIBZDKIPG/action/citation_signature","submit_replication":"https://pith.science/pith/GGWDUS34DU5B4U2UBBIBZDKIPG/action/replication_record"}},"created_at":"2026-07-05T05:05:03.700595+00:00","updated_at":"2026-07-05T05:05:03.700595+00:00"}