{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:FTZQDMQFLLUZHLEWDZZCTLTVG3","short_pith_number":"pith:FTZQDMQF","schema_version":"1.0","canonical_sha256":"2cf301b2055ae993ac961e7229ae7536dbaf6835607d1e883d88393a361b7522","source":{"kind":"arxiv","id":"2302.05527","version":2},"attestation_state":"computed","paper":{"title":"CodeBERTScore: Evaluating Code Generation with Pretrained Models of Code","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.PL"],"primary_cat":"cs.SE","authors_text":"Graham Neubig, Shuyan Zhou, Sumit Agarwal, Uri Alon","submitted_at":"2023-02-10T22:12:05Z","abstract_excerpt":"Since the rise of neural natural-language-to-code models (NL->Code) that can generate long expressions and statements rather than a single next-token, one of the major problems has been reliably evaluating their generated output. In this paper, we propose CodeBERTScore: an evaluation metric for code generation, which builds on BERTScore (Zhang et al., 2020). Instead of encoding only the generated tokens as in BERTScore, CodeBERTScore also encodes the natural language input preceding the generated code, thus modeling the consistency between the generated code and its given natural language cont"},"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":"2302.05527","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2023-02-10T22:12:05Z","cross_cats_sorted":["cs.LG","cs.PL"],"title_canon_sha256":"7ffc8e002a2cefbacdc25b282261719116ef23b5bed68fada14698c56ef98279","abstract_canon_sha256":"f12ba08ca55c959828f618cb6370686539bc739ab1abc4569270b2086abc7a98"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:07:06.908824Z","signature_b64":"2if1V4Yq2F2hOcArUFY+lXDgoOzJEzQNHRaQ3aQTeO+jh5l4wgYQeyQY/d7Szw6gDZgPlRv//CmEQ6eQK4VjAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2cf301b2055ae993ac961e7229ae7536dbaf6835607d1e883d88393a361b7522","last_reissued_at":"2026-07-05T07:07:06.908309Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:07:06.908309Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CodeBERTScore: Evaluating Code Generation with Pretrained Models of Code","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.PL"],"primary_cat":"cs.SE","authors_text":"Graham Neubig, Shuyan Zhou, Sumit Agarwal, Uri Alon","submitted_at":"2023-02-10T22:12:05Z","abstract_excerpt":"Since the rise of neural natural-language-to-code models (NL->Code) that can generate long expressions and statements rather than a single next-token, one of the major problems has been reliably evaluating their generated output. In this paper, we propose CodeBERTScore: an evaluation metric for code generation, which builds on BERTScore (Zhang et al., 2020). Instead of encoding only the generated tokens as in BERTScore, CodeBERTScore also encodes the natural language input preceding the generated code, thus modeling the consistency between the generated code and its given natural language cont"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.05527","kind":"arxiv","version":2},"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/2302.05527/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":"2302.05527","created_at":"2026-07-05T07:07:06.908379+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.05527v2","created_at":"2026-07-05T07:07:06.908379+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.05527","created_at":"2026-07-05T07:07:06.908379+00:00"},{"alias_kind":"pith_short_12","alias_value":"FTZQDMQFLLUZ","created_at":"2026-07-05T07:07:06.908379+00:00"},{"alias_kind":"pith_short_16","alias_value":"FTZQDMQFLLUZHLEW","created_at":"2026-07-05T07:07:06.908379+00:00"},{"alias_kind":"pith_short_8","alias_value":"FTZQDMQF","created_at":"2026-07-05T07:07:06.908379+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.08553","citing_title":"FusionVul: A Multimodal Feature Fusion Framework for Source Code Vulnerability Detection","ref_index":31,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FTZQDMQFLLUZHLEWDZZCTLTVG3","json":"https://pith.science/pith/FTZQDMQFLLUZHLEWDZZCTLTVG3.json","graph_json":"https://pith.science/api/pith-number/FTZQDMQFLLUZHLEWDZZCTLTVG3/graph.json","events_json":"https://pith.science/api/pith-number/FTZQDMQFLLUZHLEWDZZCTLTVG3/events.json","paper":"https://pith.science/paper/FTZQDMQF"},"agent_actions":{"view_html":"https://pith.science/pith/FTZQDMQFLLUZHLEWDZZCTLTVG3","download_json":"https://pith.science/pith/FTZQDMQFLLUZHLEWDZZCTLTVG3.json","view_paper":"https://pith.science/paper/FTZQDMQF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.05527&json=true","fetch_graph":"https://pith.science/api/pith-number/FTZQDMQFLLUZHLEWDZZCTLTVG3/graph.json","fetch_events":"https://pith.science/api/pith-number/FTZQDMQFLLUZHLEWDZZCTLTVG3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FTZQDMQFLLUZHLEWDZZCTLTVG3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FTZQDMQFLLUZHLEWDZZCTLTVG3/action/storage_attestation","attest_author":"https://pith.science/pith/FTZQDMQFLLUZHLEWDZZCTLTVG3/action/author_attestation","sign_citation":"https://pith.science/pith/FTZQDMQFLLUZHLEWDZZCTLTVG3/action/citation_signature","submit_replication":"https://pith.science/pith/FTZQDMQFLLUZHLEWDZZCTLTVG3/action/replication_record"}},"created_at":"2026-07-05T07:07:06.908379+00:00","updated_at":"2026-07-05T07:07:06.908379+00:00"}