{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:B7GYC7B6TBKNLGFBP3NZONKJ3J","short_pith_number":"pith:B7GYC7B6","schema_version":"1.0","canonical_sha256":"0fcd817c3e9854d598a17edb973549da485247e56891d73027407a73bfb96c91","source":{"kind":"arxiv","id":"2406.06902","version":1},"attestation_state":"computed","paper":{"title":"CodeScore-R: An Automated Robustness Metric for Assessing the FunctionalCorrectness of Code Synthesis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Guang Yang, Xiang Chen, Xiangyu Zhang, Yu Zhou","submitted_at":"2024-06-11T02:51:17Z","abstract_excerpt":"Evaluation metrics are crucial in the field of code synthesis. Commonly used code evaluation metrics canbe classified into three types: match-based, semantic-based, and execution-based. Among them, the execution-basedPass@k metric accurately assesses the functionality of predicted code by executing test cases. However, calculatingthis metric requires a significant amount of overhead, necessitating the design of an automated evaluation metric thatcan assess the functionality of predicted code without the need for test cases. Additionally, a good evaluation metricshould be robust, that is the me"},"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":"2406.06902","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2024-06-11T02:51:17Z","cross_cats_sorted":[],"title_canon_sha256":"f4f97b36e8397bc0040dcef586258fd370c78d6ee3c2e04c34cdd0c37366aeb3","abstract_canon_sha256":"c4a410a7f8a76ace232cdaf2d3c6c5e7d52e7e7573b30504d34f23ae3bd1313a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:30:15.196506Z","signature_b64":"oInKvi2Ca6P7QAtVcS3v4/sfA2Duenqs3EfDE1efkiRAGv2Ab3Ozfe6oPP3L+ID2xTKimudPgJLJI8tVGpdqCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0fcd817c3e9854d598a17edb973549da485247e56891d73027407a73bfb96c91","last_reissued_at":"2026-07-05T08:30:15.195951Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:30:15.195951Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CodeScore-R: An Automated Robustness Metric for Assessing the FunctionalCorrectness of Code Synthesis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Guang Yang, Xiang Chen, Xiangyu Zhang, Yu Zhou","submitted_at":"2024-06-11T02:51:17Z","abstract_excerpt":"Evaluation metrics are crucial in the field of code synthesis. Commonly used code evaluation metrics canbe classified into three types: match-based, semantic-based, and execution-based. Among them, the execution-basedPass@k metric accurately assesses the functionality of predicted code by executing test cases. However, calculatingthis metric requires a significant amount of overhead, necessitating the design of an automated evaluation metric thatcan assess the functionality of predicted code without the need for test cases. Additionally, a good evaluation metricshould be robust, that is the me"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.06902","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/2406.06902/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":"2406.06902","created_at":"2026-07-05T08:30:15.196015+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.06902v1","created_at":"2026-07-05T08:30:15.196015+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.06902","created_at":"2026-07-05T08:30:15.196015+00:00"},{"alias_kind":"pith_short_12","alias_value":"B7GYC7B6TBKN","created_at":"2026-07-05T08:30:15.196015+00:00"},{"alias_kind":"pith_short_16","alias_value":"B7GYC7B6TBKNLGFB","created_at":"2026-07-05T08:30:15.196015+00:00"},{"alias_kind":"pith_short_8","alias_value":"B7GYC7B6","created_at":"2026-07-05T08:30:15.196015+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.19502","citing_title":"CODE-DITING: A Reasoning-Based Metric for Functional Alignment in Code Evaluation","ref_index":31,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/B7GYC7B6TBKNLGFBP3NZONKJ3J","json":"https://pith.science/pith/B7GYC7B6TBKNLGFBP3NZONKJ3J.json","graph_json":"https://pith.science/api/pith-number/B7GYC7B6TBKNLGFBP3NZONKJ3J/graph.json","events_json":"https://pith.science/api/pith-number/B7GYC7B6TBKNLGFBP3NZONKJ3J/events.json","paper":"https://pith.science/paper/B7GYC7B6"},"agent_actions":{"view_html":"https://pith.science/pith/B7GYC7B6TBKNLGFBP3NZONKJ3J","download_json":"https://pith.science/pith/B7GYC7B6TBKNLGFBP3NZONKJ3J.json","view_paper":"https://pith.science/paper/B7GYC7B6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.06902&json=true","fetch_graph":"https://pith.science/api/pith-number/B7GYC7B6TBKNLGFBP3NZONKJ3J/graph.json","fetch_events":"https://pith.science/api/pith-number/B7GYC7B6TBKNLGFBP3NZONKJ3J/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/B7GYC7B6TBKNLGFBP3NZONKJ3J/action/timestamp_anchor","attest_storage":"https://pith.science/pith/B7GYC7B6TBKNLGFBP3NZONKJ3J/action/storage_attestation","attest_author":"https://pith.science/pith/B7GYC7B6TBKNLGFBP3NZONKJ3J/action/author_attestation","sign_citation":"https://pith.science/pith/B7GYC7B6TBKNLGFBP3NZONKJ3J/action/citation_signature","submit_replication":"https://pith.science/pith/B7GYC7B6TBKNLGFBP3NZONKJ3J/action/replication_record"}},"created_at":"2026-07-05T08:30:15.196015+00:00","updated_at":"2026-07-05T08:30:15.196015+00:00"}