{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:CUNN5RFATBNFN3DRIQWI6I57FT","short_pith_number":"pith:CUNN5RFA","schema_version":"1.0","canonical_sha256":"151adec4a0985a56ec71442c8f23bf2cfc3021d37f02a188212bce60dce812d3","source":{"kind":"arxiv","id":"2505.19502","version":1},"attestation_state":"computed","paper":{"title":"CODE-DITING: A Reasoning-Based Metric for Functional Alignment in Code Evaluation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"David Lo, Guang Yang, Taolue Chen, Wei Zheng, Xiang Chen, Xing Hu, Xin Zhou, Yu Zhou","submitted_at":"2025-05-26T04:29:14Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2505.19502","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-05-26T04:29:14Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"6acf9d702e2810f8f1cc2a98be32c4894b27ec8e5fd8d118001cd87cf70efaf4","abstract_canon_sha256":"c094dab21eb737f0a8b46a79bf35492b235c0e4c24b66a53b30a47c32620b013"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:09:31.340997Z","signature_b64":"rbdMKt+jMFlLeI7DRbd2KlC4NHo7rDbO3iDzxebYTe8jercuMcnICcDtzcIlMhV/zpSOOd6qUda3csGB4D25Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"151adec4a0985a56ec71442c8f23bf2cfc3021d37f02a188212bce60dce812d3","last_reissued_at":"2026-07-05T11:09:31.340498Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:09:31.340498Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CODE-DITING: A Reasoning-Based Metric for Functional Alignment in Code Evaluation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"David Lo, Guang Yang, Taolue Chen, Wei Zheng, Xiang Chen, Xing Hu, Xin Zhou, Yu Zhou","submitted_at":"2025-05-26T04:29:14Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.19502","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2505.19502/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2505.19502","created_at":"2026-07-05T11:09:31.340555+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.19502v1","created_at":"2026-07-05T11:09:31.340555+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.19502","created_at":"2026-07-05T11:09:31.340555+00:00"},{"alias_kind":"pith_short_12","alias_value":"CUNN5RFATBNF","created_at":"2026-07-05T11:09:31.340555+00:00"},{"alias_kind":"pith_short_16","alias_value":"CUNN5RFATBNFN3DR","created_at":"2026-07-05T11:09:31.340555+00:00"},{"alias_kind":"pith_short_8","alias_value":"CUNN5RFA","created_at":"2026-07-05T11:09:31.340555+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.10535","citing_title":"CodeJudgeBench: Benchmarking LLM-as-a-Judge for Coding Tasks","ref_index":50,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CUNN5RFATBNFN3DRIQWI6I57FT","json":"https://pith.science/pith/CUNN5RFATBNFN3DRIQWI6I57FT.json","graph_json":"https://pith.science/api/pith-number/CUNN5RFATBNFN3DRIQWI6I57FT/graph.json","events_json":"https://pith.science/api/pith-number/CUNN5RFATBNFN3DRIQWI6I57FT/events.json","paper":"https://pith.science/paper/CUNN5RFA"},"agent_actions":{"view_html":"https://pith.science/pith/CUNN5RFATBNFN3DRIQWI6I57FT","download_json":"https://pith.science/pith/CUNN5RFATBNFN3DRIQWI6I57FT.json","view_paper":"https://pith.science/paper/CUNN5RFA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.19502&json=true","fetch_graph":"https://pith.science/api/pith-number/CUNN5RFATBNFN3DRIQWI6I57FT/graph.json","fetch_events":"https://pith.science/api/pith-number/CUNN5RFATBNFN3DRIQWI6I57FT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CUNN5RFATBNFN3DRIQWI6I57FT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CUNN5RFATBNFN3DRIQWI6I57FT/action/storage_attestation","attest_author":"https://pith.science/pith/CUNN5RFATBNFN3DRIQWI6I57FT/action/author_attestation","sign_citation":"https://pith.science/pith/CUNN5RFATBNFN3DRIQWI6I57FT/action/citation_signature","submit_replication":"https://pith.science/pith/CUNN5RFATBNFN3DRIQWI6I57FT/action/replication_record"}},"created_at":"2026-07-05T11:09:31.340555+00:00","updated_at":"2026-07-05T11:09:31.340555+00:00"}