{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:2J6365YO7ONFABOU7WGW7QOLOU","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":"b0e05323ce9d6eb80d8abb629bf90e46c013d168207eb98903b3acd8bceb50d6","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-02-18T02:55:48Z","title_canon_sha256":"5427eb9c6693adb461e729b4e881182c29caa215e2cd73bc5d2a7401fee5ee26"},"schema_version":"1.0","source":{"id":"2502.12468","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.12468","created_at":"2026-05-28T01:04:26Z"},{"alias_kind":"arxiv_version","alias_value":"2502.12468v2","created_at":"2026-05-28T01:04:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.12468","created_at":"2026-05-28T01:04:26Z"},{"alias_kind":"pith_short_12","alias_value":"2J6365YO7ONF","created_at":"2026-05-28T01:04:26Z"},{"alias_kind":"pith_short_16","alias_value":"2J6365YO7ONFABOU","created_at":"2026-05-28T01:04:26Z"},{"alias_kind":"pith_short_8","alias_value":"2J6365YO","created_at":"2026-05-28T01:04:26Z"}],"graph_snapshots":[{"event_id":"sha256:33de5793fedfe100783cc7183540e073fa0797f4a3ab0fa0e5360f6b8551a25a","target":"graph","created_at":"2026-05-28T01:04:26Z","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/2502.12468/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The LLM-as-a-Judge paradigm shows promise for evaluating generative content but lacks reliability in reasoning-intensive scenarios, such as programming. Inspired by recent advances in reasoning models and shifts in scaling laws, we pioneer bringing test-time computation into LLM-as-a-Judge, proposing MCTS-Judge, a resource-efficient, System-2 thinking framework for code correctness evaluation. MCTS-Judge leverages Monte Carlo Tree Search (MCTS) to decompose problems into simpler, multi-perspective evaluations. Through a node-selection strategy that combines self-assessment based on historical ","authors_text":"Chaoqun Yang, Guillaume Sartoretti, Jiaoyang Li, Kaixin Li, Ming Hu, Pengliang Ji, Yutong Wang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-02-18T02:55:48Z","title":"MCTS-Judge: Test-Time Scaling in LLM-as-a-Judge for Code Correctness Evaluation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.12468","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":"sha256:9d63356e3e2ca5f2f9e317313635cbb1741877bcf15d5aad02f609cfcaf84a65","target":"record","created_at":"2026-05-28T01:04:26Z","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":"b0e05323ce9d6eb80d8abb629bf90e46c013d168207eb98903b3acd8bceb50d6","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-02-18T02:55:48Z","title_canon_sha256":"5427eb9c6693adb461e729b4e881182c29caa215e2cd73bc5d2a7401fee5ee26"},"schema_version":"1.0","source":{"id":"2502.12468","kind":"arxiv","version":2}},"canonical_sha256":"d27dbf770efb9a5005d4fd8d6fc1cb750533b86356b59f8c278305882741a9c4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d27dbf770efb9a5005d4fd8d6fc1cb750533b86356b59f8c278305882741a9c4","first_computed_at":"2026-05-28T01:04:26.762842Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-28T01:04:26.762842Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+oLclM0vzqnslyBWDU1pOVEcQvkZ2jTo94Uy8107F/leRgOR1Ysvi5LqYtm8FuzEdH+IwdtTxEKoisLsGjTNBQ==","signature_status":"signed_v1","signed_at":"2026-05-28T01:04:26.763364Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.12468","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9d63356e3e2ca5f2f9e317313635cbb1741877bcf15d5aad02f609cfcaf84a65","sha256:33de5793fedfe100783cc7183540e073fa0797f4a3ab0fa0e5360f6b8551a25a"],"state_sha256":"19431dbe9685520dc1a7fcb67b6a206be19102a5d46979babebf14b32a3e8da4"}