{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:T3ZH7MLMLV4Q44VICALH5O7L62","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":"294bcbb6cd841dd2cc410cfd316752427c0170b5de2ca9bd127c314c8670a96e","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-04-09T17:55:19Z","title_canon_sha256":"70098fc4624de999c5f149328d433a6d363579285e9b244a7aaf326a47f6c794"},"schema_version":"1.0","source":{"id":"2504.07164","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.07164","created_at":"2026-07-05T10:47:04Z"},{"alias_kind":"arxiv_version","alias_value":"2504.07164v1","created_at":"2026-07-05T10:47:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.07164","created_at":"2026-07-05T10:47:04Z"},{"alias_kind":"pith_short_12","alias_value":"T3ZH7MLMLV4Q","created_at":"2026-07-05T10:47:04Z"},{"alias_kind":"pith_short_16","alias_value":"T3ZH7MLMLV4Q44VI","created_at":"2026-07-05T10:47:04Z"},{"alias_kind":"pith_short_8","alias_value":"T3ZH7MLM","created_at":"2026-07-05T10:47:04Z"}],"graph_snapshots":[{"event_id":"sha256:a2a9b55de1cd3f53e4afc164f031f60a901de6339f3a67dd7391dc366455781d","target":"graph","created_at":"2026-07-05T10:47:04Z","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/2504.07164/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Improving open-source models on real-world SWE tasks (solving GITHUB issues) faces two key challenges: 1) scalable curation of execution environments to train these models, and, 2) optimal scaling of test-time compute. We introduce AgentGym, the largest procedurally-curated executable gym environment for training real-world SWE-agents, consisting of more than 8.7K tasks. AgentGym is powered by two main contributions: 1) SYNGEN: a synthetic data curation recipe that enables scalable curation of executable environments using test-generation and back-translation directly from commits, thereby red","authors_text":"Ion Stoica, Jaskirat Singh, Koushik Sen, Liang Zheng, Manish Shetty, Naman Jain","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-04-09T17:55:19Z","title":"R2E-Gym: Procedural Environments and Hybrid Verifiers for Scaling Open-Weights SWE Agents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.07164","kind":"arxiv","version":1},"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":"sha256:3b6acd13ed1e2f64decd7321692019a8c24305994a2cb465697967b4499ab19d","target":"record","created_at":"2026-07-05T10:47:04Z","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":"294bcbb6cd841dd2cc410cfd316752427c0170b5de2ca9bd127c314c8670a96e","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-04-09T17:55:19Z","title_canon_sha256":"70098fc4624de999c5f149328d433a6d363579285e9b244a7aaf326a47f6c794"},"schema_version":"1.0","source":{"id":"2504.07164","kind":"arxiv","version":1}},"canonical_sha256":"9ef27fb16c5d790e72a810167ebbebf691be5ec383e4a458e0a2f5245efe7d0b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9ef27fb16c5d790e72a810167ebbebf691be5ec383e4a458e0a2f5245efe7d0b","first_computed_at":"2026-07-05T10:47:04.458615Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:47:04.458615Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"aadlz3kd6xq6e78NJqMTYfZQP5npNvacIWEEp6QT1NmwLAeou1/Oa2cJfawyHjVa0vIc5K0dLe1q6hWWvmiiBw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:47:04.459080Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.07164","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3b6acd13ed1e2f64decd7321692019a8c24305994a2cb465697967b4499ab19d","sha256:a2a9b55de1cd3f53e4afc164f031f60a901de6339f3a67dd7391dc366455781d"],"state_sha256":"67c83c5e6ed9e57583ce8e802f2ad3d126caa80b8905398a5069e30b7d1d6619"}