{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:LJS2VB7XDGSZNWDGRTDIWKS7WH","short_pith_number":"pith:LJS2VB7X","schema_version":"1.0","canonical_sha256":"5a65aa87f719a596d8668cc68b2a5fb1f1db9605750dc5a3ca7592152b4ef01f","source":{"kind":"arxiv","id":"2506.09289","version":1},"attestation_state":"computed","paper":{"title":"UTBoost: Rigorous Evaluation of Coding Agents on SWE-Bench","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.SE","authors_text":"Boxi Yu, Daniel Kang, Pinjia He, Yuxuan Zhu","submitted_at":"2025-06-10T22:56:49Z","abstract_excerpt":"The advent of Large Language Models (LLMs) has spurred the development of coding agents for real-world code generation. As a widely used benchmark for evaluating the code generation capabilities of these agents, SWE-Bench uses real-world problems based on GitHub issues and their corresponding pull requests. However, the manually written test cases included in these pull requests are often insufficient, allowing generated patches to pass the tests without resolving the underlying issue. To address this challenge, we introduce UTGenerator, an LLM-driven test case generator that automatically ana"},"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":"2506.09289","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-06-10T22:56:49Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"df0887d63628893f5894a0a7a5c03e4fd5fb4f61d9538752a58baa856ec3de6c","abstract_canon_sha256":"fdb86117f6820c495f8eb62e96a737c3e7d242a9980c9a50b6c34f2c9f5e8cf6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:19:34.237162Z","signature_b64":"gX+oWjxESVZHxMVbDwt3ZQYJy539/LN49yz/fi87Rrv1FhwLZmWqFe1mf0bzqR0AnQ1gWueeZyB27ms8eGxwCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5a65aa87f719a596d8668cc68b2a5fb1f1db9605750dc5a3ca7592152b4ef01f","last_reissued_at":"2026-07-05T11:19:34.236606Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:19:34.236606Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"UTBoost: Rigorous Evaluation of Coding Agents on SWE-Bench","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.SE","authors_text":"Boxi Yu, Daniel Kang, Pinjia He, Yuxuan Zhu","submitted_at":"2025-06-10T22:56:49Z","abstract_excerpt":"The advent of Large Language Models (LLMs) has spurred the development of coding agents for real-world code generation. As a widely used benchmark for evaluating the code generation capabilities of these agents, SWE-Bench uses real-world problems based on GitHub issues and their corresponding pull requests. However, the manually written test cases included in these pull requests are often insufficient, allowing generated patches to pass the tests without resolving the underlying issue. To address this challenge, we introduce UTGenerator, an LLM-driven test case generator that automatically ana"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.09289","kind":"arxiv","version":1},"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/2506.09289/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":"2506.09289","created_at":"2026-07-05T11:19:34.236672+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.09289v1","created_at":"2026-07-05T11:19:34.236672+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.09289","created_at":"2026-07-05T11:19:34.236672+00:00"},{"alias_kind":"pith_short_12","alias_value":"LJS2VB7XDGSZ","created_at":"2026-07-05T11:19:34.236672+00:00"},{"alias_kind":"pith_short_16","alias_value":"LJS2VB7XDGSZNWDG","created_at":"2026-07-05T11:19:34.236672+00:00"},{"alias_kind":"pith_short_8","alias_value":"LJS2VB7X","created_at":"2026-07-05T11:19:34.236672+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.05775","citing_title":"Beyond the Leaderboard: A Synthesis of Tool-Use, Planning, and Reasoning Failures in Large Language Model Agents","ref_index":6,"is_internal_anchor":true},{"citing_arxiv_id":"2605.26321","citing_title":"Anchor: Mitigating Artifact Drift in Agent Benchmark Generation","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12673","citing_title":"Do Androids Dream of Breaking the Game? Systematically Auditing AI Agent Benchmarks with BenchJack","ref_index":62,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13139","citing_title":"SWE-Cycle: Benchmarking Code Agents across the Complete Issue Resolution Cycle","ref_index":39,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LJS2VB7XDGSZNWDGRTDIWKS7WH","json":"https://pith.science/pith/LJS2VB7XDGSZNWDGRTDIWKS7WH.json","graph_json":"https://pith.science/api/pith-number/LJS2VB7XDGSZNWDGRTDIWKS7WH/graph.json","events_json":"https://pith.science/api/pith-number/LJS2VB7XDGSZNWDGRTDIWKS7WH/events.json","paper":"https://pith.science/paper/LJS2VB7X"},"agent_actions":{"view_html":"https://pith.science/pith/LJS2VB7XDGSZNWDGRTDIWKS7WH","download_json":"https://pith.science/pith/LJS2VB7XDGSZNWDGRTDIWKS7WH.json","view_paper":"https://pith.science/paper/LJS2VB7X","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.09289&json=true","fetch_graph":"https://pith.science/api/pith-number/LJS2VB7XDGSZNWDGRTDIWKS7WH/graph.json","fetch_events":"https://pith.science/api/pith-number/LJS2VB7XDGSZNWDGRTDIWKS7WH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LJS2VB7XDGSZNWDGRTDIWKS7WH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LJS2VB7XDGSZNWDGRTDIWKS7WH/action/storage_attestation","attest_author":"https://pith.science/pith/LJS2VB7XDGSZNWDGRTDIWKS7WH/action/author_attestation","sign_citation":"https://pith.science/pith/LJS2VB7XDGSZNWDGRTDIWKS7WH/action/citation_signature","submit_replication":"https://pith.science/pith/LJS2VB7XDGSZNWDGRTDIWKS7WH/action/replication_record"}},"created_at":"2026-07-05T11:19:34.236672+00:00","updated_at":"2026-07-05T11:19:34.236672+00:00"}