{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:NUGTPK2TCMB5N7H3P6EKPIF2I2","short_pith_number":"pith:NUGTPK2T","schema_version":"1.0","canonical_sha256":"6d0d37ab531303d6fcfb7f88a7a0ba469ebfac7ed005fcb65c886b570715c40a","source":{"kind":"arxiv","id":"2504.08703","version":3},"attestation_state":"computed","paper":{"title":"SWE-PolyBench: A multi-language benchmark for repository level evaluation of coding agents","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Alexander Buchholz, Anoop Deoras, Christian Bock, Giovanni Zappella, Laurent Callot, Luca Franceschi, Martin Wistuba, Muhammad Shihab Rashid, Prabhu Teja Sivaprasad, Simon Valentin, Tim Esler, Woo Jung Kim, Yuan Zhuang","submitted_at":"2025-04-11T17:08:02Z","abstract_excerpt":"Coding agents powered by large language models have shown impressive capabilities in software engineering tasks, but evaluating their performance across diverse programming languages and real-world scenarios remains challenging. We introduce SWE-PolyBench, a new multi-language benchmark for repository-level, execution-based evaluation of coding agents. SWE-PolyBench contains 2110 instances from 21 repositories and includes tasks in Java (165), JavaScript (1017), TypeScript (729) and Python (199), covering bug fixes, feature additions, and code refactoring. We provide a task and repository-stra"},"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":"2504.08703","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.SE","submitted_at":"2025-04-11T17:08:02Z","cross_cats_sorted":[],"title_canon_sha256":"25901ce855a2f087f2d13ad181942356c829e000916cad249a4ba9be83093498","abstract_canon_sha256":"01a350614ed194466446937f20dff84e1b479c9d4d71f56115db62b4f8381b27"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:53:16.998078Z","signature_b64":"op3qZowBrBsVm8waUQK92T/Pe8KWmG6j+JmAxHxQ9PgYGQoiCWlT4sx87oAUeH/1+LMfqV5a8wNC9+wc33+QBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6d0d37ab531303d6fcfb7f88a7a0ba469ebfac7ed005fcb65c886b570715c40a","last_reissued_at":"2026-07-05T10:53:16.997495Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:53:16.997495Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SWE-PolyBench: A multi-language benchmark for repository level evaluation of coding agents","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Alexander Buchholz, Anoop Deoras, Christian Bock, Giovanni Zappella, Laurent Callot, Luca Franceschi, Martin Wistuba, Muhammad Shihab Rashid, Prabhu Teja Sivaprasad, Simon Valentin, Tim Esler, Woo Jung Kim, Yuan Zhuang","submitted_at":"2025-04-11T17:08:02Z","abstract_excerpt":"Coding agents powered by large language models have shown impressive capabilities in software engineering tasks, but evaluating their performance across diverse programming languages and real-world scenarios remains challenging. We introduce SWE-PolyBench, a new multi-language benchmark for repository-level, execution-based evaluation of coding agents. SWE-PolyBench contains 2110 instances from 21 repositories and includes tasks in Java (165), JavaScript (1017), TypeScript (729) and Python (199), covering bug fixes, feature additions, and code refactoring. We provide a task and repository-stra"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.08703","kind":"arxiv","version":3},"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/2504.08703/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":"2504.08703","created_at":"2026-07-05T10:53:16.997560+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.08703v3","created_at":"2026-07-05T10:53:16.997560+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.08703","created_at":"2026-07-05T10:53:16.997560+00:00"},{"alias_kind":"pith_short_12","alias_value":"NUGTPK2TCMB5","created_at":"2026-07-05T10:53:16.997560+00:00"},{"alias_kind":"pith_short_16","alias_value":"NUGTPK2TCMB5N7H3","created_at":"2026-07-05T10:53:16.997560+00:00"},{"alias_kind":"pith_short_8","alias_value":"NUGTPK2T","created_at":"2026-07-05T10:53:16.997560+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":16,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.25514","citing_title":"Unlocking Model Potentials Through Adaptive Multi-Agent Scaffolding for Efficient Issue Resolution","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2606.22504","citing_title":"Lingering Authority: Revocable Resource-and-Effect Capabilities for Coding Agents","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2606.22417","citing_title":"Code Isn't Memory: A Structural Codebase Index Inside a Coding Agent","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2606.08500","citing_title":"Projecting the Emerging Mindset of SWE Agent by Launching a Wild Code Understanding Journey","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2606.05249","citing_title":"SWE-InfraBench: Evaluating Language Models on Cloud Infrastructure Code","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2607.00700","citing_title":"LLVM-Bench: Benchmarking and Advancing Large Language Models for LLVM Compiler Issue Resolution","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2607.00990","citing_title":"SWE-Doctor: Guiding Software Engineering Agents with Runtime Diagnosis from Multi-Faceted Bug Reproduction Tests","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2605.26177","citing_title":"RepoMirage: Probing Repository Context Reasoning in Code Agents with Perturbations","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2605.26100","citing_title":"Beyond Summaries: Structure-Aware Labeling of Code Changes with Large Language Models","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2605.27489","citing_title":"HARP: Measuring Harm Amplification in Multi-Agent LLM Systems","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14859","citing_title":"Do Coding Agents Understand Least-Privilege Authorization?","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08693","citing_title":"SkillMaster: Toward Autonomous Skill Mastery in LLM Agents","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08693","citing_title":"SkillMaster: Toward Autonomous Skill Mastery in LLM Agents","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06445","citing_title":"Constraint Decay: The Fragility of LLM Agents in Backend Code Generation","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04320","citing_title":"Reproduction Test Generation for Java SWE Issues","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04320","citing_title":"Reproduction Test Generation for Java SWE Issues","ref_index":25,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NUGTPK2TCMB5N7H3P6EKPIF2I2","json":"https://pith.science/pith/NUGTPK2TCMB5N7H3P6EKPIF2I2.json","graph_json":"https://pith.science/api/pith-number/NUGTPK2TCMB5N7H3P6EKPIF2I2/graph.json","events_json":"https://pith.science/api/pith-number/NUGTPK2TCMB5N7H3P6EKPIF2I2/events.json","paper":"https://pith.science/paper/NUGTPK2T"},"agent_actions":{"view_html":"https://pith.science/pith/NUGTPK2TCMB5N7H3P6EKPIF2I2","download_json":"https://pith.science/pith/NUGTPK2TCMB5N7H3P6EKPIF2I2.json","view_paper":"https://pith.science/paper/NUGTPK2T","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.08703&json=true","fetch_graph":"https://pith.science/api/pith-number/NUGTPK2TCMB5N7H3P6EKPIF2I2/graph.json","fetch_events":"https://pith.science/api/pith-number/NUGTPK2TCMB5N7H3P6EKPIF2I2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NUGTPK2TCMB5N7H3P6EKPIF2I2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NUGTPK2TCMB5N7H3P6EKPIF2I2/action/storage_attestation","attest_author":"https://pith.science/pith/NUGTPK2TCMB5N7H3P6EKPIF2I2/action/author_attestation","sign_citation":"https://pith.science/pith/NUGTPK2TCMB5N7H3P6EKPIF2I2/action/citation_signature","submit_replication":"https://pith.science/pith/NUGTPK2TCMB5N7H3P6EKPIF2I2/action/replication_record"}},"created_at":"2026-07-05T10:53:16.997560+00:00","updated_at":"2026-07-05T10:53:16.997560+00:00"}