{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:XI2ULD5AVL5AT3AVIGWQIIOG65","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":"faa5eee88df4601ce191b5e95527cd735fb755f672eb50287d6f4bd64b6226dc","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-06-20T00:14:38Z","title_canon_sha256":"4937f5bc5dbabc252e9165c6bf26dac9d172a53e8c968b247b9dd926fa838b45"},"schema_version":"1.0","source":{"id":"2606.21811","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.21811","created_at":"2026-06-23T01:13:23Z"},{"alias_kind":"arxiv_version","alias_value":"2606.21811v1","created_at":"2026-06-23T01:13:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.21811","created_at":"2026-06-23T01:13:23Z"},{"alias_kind":"pith_short_12","alias_value":"XI2ULD5AVL5A","created_at":"2026-06-23T01:13:23Z"},{"alias_kind":"pith_short_16","alias_value":"XI2ULD5AVL5AT3AV","created_at":"2026-06-23T01:13:23Z"},{"alias_kind":"pith_short_8","alias_value":"XI2ULD5A","created_at":"2026-06-23T01:13:23Z"}],"graph_snapshots":[{"event_id":"sha256:b33b211cbc3499bed7c748ef76fa3d8e82d9dbfabcfd324474220b4b4cdf51cc","target":"graph","created_at":"2026-06-23T01:13:23Z","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/2606.21811/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"End-to-end code agent training is resource-intensive and plateaus on the strategy-level reasoning needed to resolve code issues, since jointly optimizing code-level execution and strategy-level reasoning leaves the latter underdeveloped. Instead, we freeze the agent and add a critic model to supply that signal. Prior code critics are post-hoc, scoring completed trajectories rather than steering the agent; we instead train a small critic that provides intra-trajectory feedback via Supervised Fine-Tuning. On SWE-bench Verified, a critic trained on CWM-32B trajectories transfers to two unseen age","authors_text":"Atharva Naik, Carolyn Rose, Ruichen Zhu, Shubham Gandhi, Yiqing Xie","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-06-20T00:14:38Z","title":"Steer, Don't Solve: Training Small Critic Models for Large Code Agents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.21811","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:fd5b073e71cdb35ad9ee44767c789708cdad3aa6b426c8a4c6760fe49b58a308","target":"record","created_at":"2026-06-23T01:13:23Z","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":"faa5eee88df4601ce191b5e95527cd735fb755f672eb50287d6f4bd64b6226dc","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-06-20T00:14:38Z","title_canon_sha256":"4937f5bc5dbabc252e9165c6bf26dac9d172a53e8c968b247b9dd926fa838b45"},"schema_version":"1.0","source":{"id":"2606.21811","kind":"arxiv","version":1}},"canonical_sha256":"ba35458fa0aafa09ec1541ad0421c6f74da072d4209fccd4b01bdb38907cf7e2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ba35458fa0aafa09ec1541ad0421c6f74da072d4209fccd4b01bdb38907cf7e2","first_computed_at":"2026-06-23T01:13:23.429993Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-23T01:13:23.429993Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"b+6YxykQOjqM8YiFz867Y4MSLpA4enr4gYFzsQlu11yd8iIAeoiJYgcZcZa2pfuugmTeZ2Xq3WOzTXwctsYgDw==","signature_status":"signed_v1","signed_at":"2026-06-23T01:13:23.430643Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.21811","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fd5b073e71cdb35ad9ee44767c789708cdad3aa6b426c8a4c6760fe49b58a308","sha256:b33b211cbc3499bed7c748ef76fa3d8e82d9dbfabcfd324474220b4b4cdf51cc"],"state_sha256":"d8b8270ea365d758c94a3851906daeb1a34e2bfdd5aa82e33bba3514be82b08b"}