{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:6OFNLO64CFYZ3XL7JRYIR2HKNL","short_pith_number":"pith:6OFNLO64","schema_version":"1.0","canonical_sha256":"f38ad5bbdc11719ddd7f4c7088e8ea6aea45dc02cf9872fae5fe25618f20ccdf","source":{"kind":"arxiv","id":"2412.01333","version":1},"attestation_state":"computed","paper":{"title":"Can Large Language Models Serve as Evaluators for Code Summarization?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Hongyu Zhang, Philip S. Yu, Wenting Zhao, Xuanhua Shi, Yang Wu, Yao Wan, Ye Liu, Zhaoyang Chu","submitted_at":"2024-12-02T09:56:18Z","abstract_excerpt":"Code summarization facilitates program comprehension and software maintenance by converting code snippets into natural-language descriptions. Over the years, numerous methods have been developed for this task, but a key challenge remains: effectively evaluating the quality of generated summaries. While human evaluation is effective for assessing code summary quality, it is labor-intensive and difficult to scale. Commonly used automatic metrics, such as BLEU, ROUGE-L, METEOR, and BERTScore, often fail to align closely with human judgments. In this paper, we explore the potential of Large Langua"},"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":"2412.01333","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2024-12-02T09:56:18Z","cross_cats_sorted":[],"title_canon_sha256":"a19937d2dcea6fc3f89dfdbdddeedddf437c1dc8452305634ecb4666a7644026","abstract_canon_sha256":"3ee497a49410fb796df4f96c49ab6bd31fdd6b6223134780e3271ed46059118b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:42:58.261660Z","signature_b64":"52sUvm7l2IzNuS3Z9BdEWmVUAN3Mtv/WZpqfzxFcPXNOXBa6Kiw1FSnVYysbOegIKutMAJjH9df1ukwTv4uFCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f38ad5bbdc11719ddd7f4c7088e8ea6aea45dc02cf9872fae5fe25618f20ccdf","last_reissued_at":"2026-07-05T09:42:58.261145Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:42:58.261145Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Can Large Language Models Serve as Evaluators for Code Summarization?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Hongyu Zhang, Philip S. Yu, Wenting Zhao, Xuanhua Shi, Yang Wu, Yao Wan, Ye Liu, Zhaoyang Chu","submitted_at":"2024-12-02T09:56:18Z","abstract_excerpt":"Code summarization facilitates program comprehension and software maintenance by converting code snippets into natural-language descriptions. Over the years, numerous methods have been developed for this task, but a key challenge remains: effectively evaluating the quality of generated summaries. While human evaluation is effective for assessing code summary quality, it is labor-intensive and difficult to scale. Commonly used automatic metrics, such as BLEU, ROUGE-L, METEOR, and BERTScore, often fail to align closely with human judgments. In this paper, we explore the potential of Large Langua"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.01333","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/2412.01333/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":"2412.01333","created_at":"2026-07-05T09:42:58.261211+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.01333v1","created_at":"2026-07-05T09:42:58.261211+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.01333","created_at":"2026-07-05T09:42:58.261211+00:00"},{"alias_kind":"pith_short_12","alias_value":"6OFNLO64CFYZ","created_at":"2026-07-05T09:42:58.261211+00:00"},{"alias_kind":"pith_short_16","alias_value":"6OFNLO64CFYZ3XL7","created_at":"2026-07-05T09:42:58.261211+00:00"},{"alias_kind":"pith_short_8","alias_value":"6OFNLO64","created_at":"2026-07-05T09:42:58.261211+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2512.00380","citing_title":"Knowledge-Graph-Driven Data Synthesis for Low-Resource Software Development: A HarmonyOS Case Study","ref_index":67,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6OFNLO64CFYZ3XL7JRYIR2HKNL","json":"https://pith.science/pith/6OFNLO64CFYZ3XL7JRYIR2HKNL.json","graph_json":"https://pith.science/api/pith-number/6OFNLO64CFYZ3XL7JRYIR2HKNL/graph.json","events_json":"https://pith.science/api/pith-number/6OFNLO64CFYZ3XL7JRYIR2HKNL/events.json","paper":"https://pith.science/paper/6OFNLO64"},"agent_actions":{"view_html":"https://pith.science/pith/6OFNLO64CFYZ3XL7JRYIR2HKNL","download_json":"https://pith.science/pith/6OFNLO64CFYZ3XL7JRYIR2HKNL.json","view_paper":"https://pith.science/paper/6OFNLO64","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.01333&json=true","fetch_graph":"https://pith.science/api/pith-number/6OFNLO64CFYZ3XL7JRYIR2HKNL/graph.json","fetch_events":"https://pith.science/api/pith-number/6OFNLO64CFYZ3XL7JRYIR2HKNL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6OFNLO64CFYZ3XL7JRYIR2HKNL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6OFNLO64CFYZ3XL7JRYIR2HKNL/action/storage_attestation","attest_author":"https://pith.science/pith/6OFNLO64CFYZ3XL7JRYIR2HKNL/action/author_attestation","sign_citation":"https://pith.science/pith/6OFNLO64CFYZ3XL7JRYIR2HKNL/action/citation_signature","submit_replication":"https://pith.science/pith/6OFNLO64CFYZ3XL7JRYIR2HKNL/action/replication_record"}},"created_at":"2026-07-05T09:42:58.261211+00:00","updated_at":"2026-07-05T09:42:58.261211+00:00"}