{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ZSKGLUENOJXIRCATTTCOV2CGYT","short_pith_number":"pith:ZSKGLUEN","schema_version":"1.0","canonical_sha256":"cc9465d08d726e8888139cc4eae846c4ff54199a35422793f54b9255bad3c1b6","source":{"kind":"arxiv","id":"2503.07832","version":1},"attestation_state":"computed","paper":{"title":"RefactorBench: Evaluating Stateful Reasoning in Language Agents Through Code","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.LG","cs.SE"],"primary_cat":"cs.AI","authors_text":"Dhruv Gautam, Jinu Jang, Neel Sundaresan, Roshanak Zilouchian Moghaddam, Spandan Garg","submitted_at":"2025-03-10T20:23:24Z","abstract_excerpt":"Recent advances in language model (LM) agents and function calling have enabled autonomous, feedback-driven systems to solve problems across various digital domains. To better understand the unique limitations of LM agents, we introduce RefactorBench, a benchmark consisting of 100 large handcrafted multi-file refactoring tasks in popular open-source repositories. Solving tasks within RefactorBench requires thorough exploration of dependencies across multiple files and strong adherence to relevant instructions. Every task is defined by 3 natural language instructions of varying specificity and "},"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":"2503.07832","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-03-10T20:23:24Z","cross_cats_sorted":["cs.CL","cs.LG","cs.SE"],"title_canon_sha256":"dbab28fb36c2a2c17e4a9e946c70d283906c1bacd03d025557e55c1cefc8de56","abstract_canon_sha256":"d45cd72c75b596bd43ff2b4c2a7c2136d616647a2d645ffe86875a21d196b799"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:28:44.801469Z","signature_b64":"gEnLJwSK6p5UqYnbBEiZORsj8pgCB4KXoHm4Ps104ZHXiRRuk6HBYoj7do/INHhF0vrqpd1HfMfYQFFEhggsDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cc9465d08d726e8888139cc4eae846c4ff54199a35422793f54b9255bad3c1b6","last_reissued_at":"2026-07-05T10:28:44.800968Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:28:44.800968Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RefactorBench: Evaluating Stateful Reasoning in Language Agents Through Code","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.LG","cs.SE"],"primary_cat":"cs.AI","authors_text":"Dhruv Gautam, Jinu Jang, Neel Sundaresan, Roshanak Zilouchian Moghaddam, Spandan Garg","submitted_at":"2025-03-10T20:23:24Z","abstract_excerpt":"Recent advances in language model (LM) agents and function calling have enabled autonomous, feedback-driven systems to solve problems across various digital domains. To better understand the unique limitations of LM agents, we introduce RefactorBench, a benchmark consisting of 100 large handcrafted multi-file refactoring tasks in popular open-source repositories. Solving tasks within RefactorBench requires thorough exploration of dependencies across multiple files and strong adherence to relevant instructions. Every task is defined by 3 natural language instructions of varying specificity and "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.07832","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/2503.07832/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":"2503.07832","created_at":"2026-07-05T10:28:44.801026+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.07832v1","created_at":"2026-07-05T10:28:44.801026+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.07832","created_at":"2026-07-05T10:28:44.801026+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZSKGLUENOJXI","created_at":"2026-07-05T10:28:44.801026+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZSKGLUENOJXIRCAT","created_at":"2026-07-05T10:28:44.801026+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZSKGLUEN","created_at":"2026-07-05T10:28:44.801026+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.05574","citing_title":"SmellBench: Towards Fine-Grained Evaluation of Code Agents on Refactoring Tasks","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20244","citing_title":"Lean Refactor: Multi-Objective Controllable Proof Optimization via Agentic Strategy Search","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2512.14917","citing_title":"Evaluating Code Reasoning Abilities of Large Language Models Under Real-World Settings","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2504.19678","citing_title":"From LLM Reasoning to Autonomous AI Agents: A Comprehensive Review","ref_index":116,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07001","citing_title":"SmellBench: Evaluating LLM Agents on Architectural Code Smell Repair","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08468","citing_title":"PYTHALAB-MERA: Validation-Grounded Memory, Retrieval, and Acceptance Control for Frozen-LLM Coding Agents","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08366","citing_title":"SWE Atlas: Benchmarking Coding Agents Beyond Issue Resolution","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07001","citing_title":"SmellBench: Evaluating LLM Agents on Architectural Code Smell Repair","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZSKGLUENOJXIRCATTTCOV2CGYT","json":"https://pith.science/pith/ZSKGLUENOJXIRCATTTCOV2CGYT.json","graph_json":"https://pith.science/api/pith-number/ZSKGLUENOJXIRCATTTCOV2CGYT/graph.json","events_json":"https://pith.science/api/pith-number/ZSKGLUENOJXIRCATTTCOV2CGYT/events.json","paper":"https://pith.science/paper/ZSKGLUEN"},"agent_actions":{"view_html":"https://pith.science/pith/ZSKGLUENOJXIRCATTTCOV2CGYT","download_json":"https://pith.science/pith/ZSKGLUENOJXIRCATTTCOV2CGYT.json","view_paper":"https://pith.science/paper/ZSKGLUEN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.07832&json=true","fetch_graph":"https://pith.science/api/pith-number/ZSKGLUENOJXIRCATTTCOV2CGYT/graph.json","fetch_events":"https://pith.science/api/pith-number/ZSKGLUENOJXIRCATTTCOV2CGYT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZSKGLUENOJXIRCATTTCOV2CGYT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZSKGLUENOJXIRCATTTCOV2CGYT/action/storage_attestation","attest_author":"https://pith.science/pith/ZSKGLUENOJXIRCATTTCOV2CGYT/action/author_attestation","sign_citation":"https://pith.science/pith/ZSKGLUENOJXIRCATTTCOV2CGYT/action/citation_signature","submit_replication":"https://pith.science/pith/ZSKGLUENOJXIRCATTTCOV2CGYT/action/replication_record"}},"created_at":"2026-07-05T10:28:44.801026+00:00","updated_at":"2026-07-05T10:28:44.801026+00:00"}