{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:YKFWNTUW7F6J7VR5GT2SKRCUZC","short_pith_number":"pith:YKFWNTUW","schema_version":"1.0","canonical_sha256":"c28b66ce96f97c9fd63d34f5254454c8b0c2dd01c50963911aeb8605c265fbd1","source":{"kind":"arxiv","id":"2602.23866","version":2},"attestation_state":"computed","paper":{"title":"SWE-rebench V2: Language-Agnostic SWE Task Collection at Scale","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.SE","authors_text":"Alexander Golubev, Anton Shevtsov, Ibragim Badertdinov, Maksim Nekrashevich","submitted_at":"2026-02-27T10:06:10Z","abstract_excerpt":"Software engineering agents (SWE) are improving rapidly, with recent gains largely driven by reinforcement learning (RL). However, RL training is constrained by the scarcity of large-scale task collections with reproducible execution environments and reliable test suites. Although a growing number of benchmarks have emerged, datasets suitable for training remain limited in scale and diversity or often target a limited set of high-resource language ecosystems. We introduce SWE-rebench V2, a language-agnostic automated pipeline for harvesting executable real-world SWE tasks and constructing RL t"},"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":"2602.23866","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-02-27T10:06:10Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"9aacf000c6d7a2255d2a30da3551fc85ba23093f9533dc5f0131edd7663966e3","abstract_canon_sha256":"3859fd7155ef47c8bf1b0129144338193ee4ee94b494e14a567505c027f2e422"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T03:04:39.396991Z","signature_b64":"Bh6gyXKbexN7JITj317QoF0+KSlIC3MgQzqBNhiF8qSYp+4UaGVG3Q73fTmk3v89HuV+T83C0QEVMbUkFpe3Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c28b66ce96f97c9fd63d34f5254454c8b0c2dd01c50963911aeb8605c265fbd1","last_reissued_at":"2026-06-02T03:04:39.396532Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T03:04:39.396532Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SWE-rebench V2: Language-Agnostic SWE Task Collection at Scale","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.SE","authors_text":"Alexander Golubev, Anton Shevtsov, Ibragim Badertdinov, Maksim Nekrashevich","submitted_at":"2026-02-27T10:06:10Z","abstract_excerpt":"Software engineering agents (SWE) are improving rapidly, with recent gains largely driven by reinforcement learning (RL). However, RL training is constrained by the scarcity of large-scale task collections with reproducible execution environments and reliable test suites. Although a growing number of benchmarks have emerged, datasets suitable for training remain limited in scale and diversity or often target a limited set of high-resource language ecosystems. We introduce SWE-rebench V2, a language-agnostic automated pipeline for harvesting executable real-world SWE tasks and constructing RL t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.23866","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/2602.23866/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":"2602.23866","created_at":"2026-06-02T03:04:39.396626+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.23866v2","created_at":"2026-06-02T03:04:39.396626+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.23866","created_at":"2026-06-02T03:04:39.396626+00:00"},{"alias_kind":"pith_short_12","alias_value":"YKFWNTUW7F6J","created_at":"2026-06-02T03:04:39.396626+00:00"},{"alias_kind":"pith_short_16","alias_value":"YKFWNTUW7F6J7VR5","created_at":"2026-06-02T03:04:39.396626+00:00"},{"alias_kind":"pith_short_8","alias_value":"YKFWNTUW","created_at":"2026-06-02T03:04:39.396626+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.20456","citing_title":"Agentic Agile-V: From Vibe Coding to Verified Engineering in Software and Hardware Development","ref_index":18,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YKFWNTUW7F6J7VR5GT2SKRCUZC","json":"https://pith.science/pith/YKFWNTUW7F6J7VR5GT2SKRCUZC.json","graph_json":"https://pith.science/api/pith-number/YKFWNTUW7F6J7VR5GT2SKRCUZC/graph.json","events_json":"https://pith.science/api/pith-number/YKFWNTUW7F6J7VR5GT2SKRCUZC/events.json","paper":"https://pith.science/paper/YKFWNTUW"},"agent_actions":{"view_html":"https://pith.science/pith/YKFWNTUW7F6J7VR5GT2SKRCUZC","download_json":"https://pith.science/pith/YKFWNTUW7F6J7VR5GT2SKRCUZC.json","view_paper":"https://pith.science/paper/YKFWNTUW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.23866&json=true","fetch_graph":"https://pith.science/api/pith-number/YKFWNTUW7F6J7VR5GT2SKRCUZC/graph.json","fetch_events":"https://pith.science/api/pith-number/YKFWNTUW7F6J7VR5GT2SKRCUZC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YKFWNTUW7F6J7VR5GT2SKRCUZC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YKFWNTUW7F6J7VR5GT2SKRCUZC/action/storage_attestation","attest_author":"https://pith.science/pith/YKFWNTUW7F6J7VR5GT2SKRCUZC/action/author_attestation","sign_citation":"https://pith.science/pith/YKFWNTUW7F6J7VR5GT2SKRCUZC/action/citation_signature","submit_replication":"https://pith.science/pith/YKFWNTUW7F6J7VR5GT2SKRCUZC/action/replication_record"}},"created_at":"2026-06-02T03:04:39.396626+00:00","updated_at":"2026-06-02T03:04:39.396626+00:00"}