{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:CUNN5RFATBNFN3DRIQWI6I57FT","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":"c094dab21eb737f0a8b46a79bf35492b235c0e4c24b66a53b30a47c32620b013","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-05-26T04:29:14Z","title_canon_sha256":"6acf9d702e2810f8f1cc2a98be32c4894b27ec8e5fd8d118001cd87cf70efaf4"},"schema_version":"1.0","source":{"id":"2505.19502","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.19502","created_at":"2026-07-05T11:09:31Z"},{"alias_kind":"arxiv_version","alias_value":"2505.19502v1","created_at":"2026-07-05T11:09:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.19502","created_at":"2026-07-05T11:09:31Z"},{"alias_kind":"pith_short_12","alias_value":"CUNN5RFATBNF","created_at":"2026-07-05T11:09:31Z"},{"alias_kind":"pith_short_16","alias_value":"CUNN5RFATBNFN3DR","created_at":"2026-07-05T11:09:31Z"},{"alias_kind":"pith_short_8","alias_value":"CUNN5RFA","created_at":"2026-07-05T11:09:31Z"}],"graph_snapshots":[{"event_id":"sha256:0712506bf3d3c072936078e326525ee5f054ac0dabe24d14326c284c4b07960b","target":"graph","created_at":"2026-07-05T11:09:31Z","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/2505.19502/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Trustworthy evaluation methods for code snippets play a crucial role in neural code generation. Traditional methods, which either rely on reference solutions or require executable test cases, have inherent limitation in flexibility and scalability. The recent LLM-as-Judge methodology offers a promising alternative by directly evaluating functional consistency between the problem description and the generated code. To systematically understand the landscape of these LLM-as-Judge methods, we conduct a comprehensive empirical study across three diverse datasets. Our investigation reveals the pros","authors_text":"David Lo, Guang Yang, Taolue Chen, Wei Zheng, Xiang Chen, Xing Hu, Xin Zhou, Yu Zhou","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-05-26T04:29:14Z","title":"CODE-DITING: A Reasoning-Based Metric for Functional Alignment in Code Evaluation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.19502","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:f94a3d2e352c118614ab50dd5b6dbb9cbc758606253fb328f14d5ca2c5f80338","target":"record","created_at":"2026-07-05T11:09:31Z","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":"c094dab21eb737f0a8b46a79bf35492b235c0e4c24b66a53b30a47c32620b013","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-05-26T04:29:14Z","title_canon_sha256":"6acf9d702e2810f8f1cc2a98be32c4894b27ec8e5fd8d118001cd87cf70efaf4"},"schema_version":"1.0","source":{"id":"2505.19502","kind":"arxiv","version":1}},"canonical_sha256":"151adec4a0985a56ec71442c8f23bf2cfc3021d37f02a188212bce60dce812d3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"151adec4a0985a56ec71442c8f23bf2cfc3021d37f02a188212bce60dce812d3","first_computed_at":"2026-07-05T11:09:31.340498Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:09:31.340498Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rbdMKt+jMFlLeI7DRbd2KlC4NHo7rDbO3iDzxebYTe8jercuMcnICcDtzcIlMhV/zpSOOd6qUda3csGB4D25Dg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:09:31.340997Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.19502","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f94a3d2e352c118614ab50dd5b6dbb9cbc758606253fb328f14d5ca2c5f80338","sha256:0712506bf3d3c072936078e326525ee5f054ac0dabe24d14326c284c4b07960b"],"state_sha256":"2f4c6f895186f6807fe5cee2b138e52ad8dc9cf33974b429039d1b89d05cdca4"}