{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:C2OBP3ZJN6ICXGTBYRYPSVZMYI","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":"b3b798154f9310add1a74dc7e47b7ccc50e34e99142c00cbca0294a2b3858134","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-24T18:58:40Z","title_canon_sha256":"c8f87ad12e60940bdeeb77c5a86e75a083d768ce42167a8474997188123920d3"},"schema_version":"1.0","source":{"id":"2501.14723","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.14723","created_at":"2026-07-05T10:08:54Z"},{"alias_kind":"arxiv_version","alias_value":"2501.14723v2","created_at":"2026-07-05T10:08:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.14723","created_at":"2026-07-05T10:08:54Z"},{"alias_kind":"pith_short_12","alias_value":"C2OBP3ZJN6IC","created_at":"2026-07-05T10:08:54Z"},{"alias_kind":"pith_short_16","alias_value":"C2OBP3ZJN6ICXGTB","created_at":"2026-07-05T10:08:54Z"},{"alias_kind":"pith_short_8","alias_value":"C2OBP3ZJ","created_at":"2026-07-05T10:08:54Z"}],"graph_snapshots":[{"event_id":"sha256:9ee8c3727bb50fc82c3b1cf7d454598566ef677cec0f990d756cf42b07e1ac06","target":"graph","created_at":"2026-07-05T10:08:54Z","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/2501.14723/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Scaling test-time compute is a promising axis for improving LLM capabilities. However, test-time compute can be scaled in a variety of ways, and effectively combining different approaches remains an active area of research. Here, we explore this problem in the context of solving real-world GitHub issues from the SWE-bench dataset. Our system, named CodeMonkeys, allows models to iteratively edit a codebase by jointly generating and running a testing script alongside their draft edit. We sample many of these multi-turn trajectories for every issue to generate a collection of candidate edits. Thi","authors_text":"Azalia Mirhoseini, Bradley Brown, Christopher R\\'e, Jordan Juravsky, Ronald Clark, Ryan Ehrlich","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-24T18:58:40Z","title":"CodeMonkeys: Scaling Test-Time Compute for Software Engineering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.14723","kind":"arxiv","version":2},"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":"sha256:5750e378093e42332ea07e21650043ba0a977c42b06cbe530d819b7f5f12f013","target":"record","created_at":"2026-07-05T10:08:54Z","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":"b3b798154f9310add1a74dc7e47b7ccc50e34e99142c00cbca0294a2b3858134","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-24T18:58:40Z","title_canon_sha256":"c8f87ad12e60940bdeeb77c5a86e75a083d768ce42167a8474997188123920d3"},"schema_version":"1.0","source":{"id":"2501.14723","kind":"arxiv","version":2}},"canonical_sha256":"169c17ef296f902b9a61c470f9572cc226c33ef424f7273307e978f6be94ae85","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"169c17ef296f902b9a61c470f9572cc226c33ef424f7273307e978f6be94ae85","first_computed_at":"2026-07-05T10:08:54.510028Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:08:54.510028Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KRqmnYIc8A5LBb+KNgraneEOWlVk/Oad/5AAsyAX6J2kLcr4Ga0+2HZN7m7T3s9zUUWvcBqLRLCEZgrnD++QAA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:08:54.510514Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.14723","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5750e378093e42332ea07e21650043ba0a977c42b06cbe530d819b7f5f12f013","sha256:9ee8c3727bb50fc82c3b1cf7d454598566ef677cec0f990d756cf42b07e1ac06"],"state_sha256":"b059108e5054a5c4fd1596c7f2019775faa10c2006531db236af7bcde1e04e95"}