{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:NUGTPK2TCMB5N7H3P6EKPIF2I2","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"01a350614ed194466446937f20dff84e1b479c9d4d71f56115db62b4f8381b27","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.SE","submitted_at":"2025-04-11T17:08:02Z","title_canon_sha256":"25901ce855a2f087f2d13ad181942356c829e000916cad249a4ba9be83093498"},"schema_version":"1.0","source":{"id":"2504.08703","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.08703","created_at":"2026-07-05T10:53:16Z"},{"alias_kind":"arxiv_version","alias_value":"2504.08703v3","created_at":"2026-07-05T10:53:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.08703","created_at":"2026-07-05T10:53:16Z"},{"alias_kind":"pith_short_12","alias_value":"NUGTPK2TCMB5","created_at":"2026-07-05T10:53:16Z"},{"alias_kind":"pith_short_16","alias_value":"NUGTPK2TCMB5N7H3","created_at":"2026-07-05T10:53:16Z"},{"alias_kind":"pith_short_8","alias_value":"NUGTPK2T","created_at":"2026-07-05T10:53:16Z"}],"graph_snapshots":[{"event_id":"sha256:b6fc8e215b3c49b614fc7a20cf375a84acf58ce9a93ae90aab1c5b6be3b38fff","target":"graph","created_at":"2026-07-05T10:53:16Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2504.08703/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","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","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.SE","submitted_at":"2025-04-11T17:08:02Z","title":"SWE-PolyBench: A multi-language benchmark for repository level evaluation of coding agents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.08703","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:c963e7d54fe69938730829100d795dd8f72ef3e0fa99dbe5798ccb771015596b","target":"record","created_at":"2026-07-05T10:53:16Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"01a350614ed194466446937f20dff84e1b479c9d4d71f56115db62b4f8381b27","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.SE","submitted_at":"2025-04-11T17:08:02Z","title_canon_sha256":"25901ce855a2f087f2d13ad181942356c829e000916cad249a4ba9be83093498"},"schema_version":"1.0","source":{"id":"2504.08703","kind":"arxiv","version":3}},"canonical_sha256":"6d0d37ab531303d6fcfb7f88a7a0ba469ebfac7ed005fcb65c886b570715c40a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6d0d37ab531303d6fcfb7f88a7a0ba469ebfac7ed005fcb65c886b570715c40a","first_computed_at":"2026-07-05T10:53:16.997495Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:53:16.997495Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"op3qZowBrBsVm8waUQK92T/Pe8KWmG6j+JmAxHxQ9PgYGQoiCWlT4sx87oAUeH/1+LMfqV5a8wNC9+wc33+QBg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:53:16.998078Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.08703","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c963e7d54fe69938730829100d795dd8f72ef3e0fa99dbe5798ccb771015596b","sha256:b6fc8e215b3c49b614fc7a20cf375a84acf58ce9a93ae90aab1c5b6be3b38fff"],"state_sha256":"6bc0581cfbc355ce77f9afcd852330efaaf92a0fe530220e817385f0e6d76baf"}