{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:6OFNLO64CFYZ3XL7JRYIR2HKNL","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":"3ee497a49410fb796df4f96c49ab6bd31fdd6b6223134780e3271ed46059118b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2024-12-02T09:56:18Z","title_canon_sha256":"a19937d2dcea6fc3f89dfdbdddeedddf437c1dc8452305634ecb4666a7644026"},"schema_version":"1.0","source":{"id":"2412.01333","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.01333","created_at":"2026-07-05T09:42:58Z"},{"alias_kind":"arxiv_version","alias_value":"2412.01333v1","created_at":"2026-07-05T09:42:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.01333","created_at":"2026-07-05T09:42:58Z"},{"alias_kind":"pith_short_12","alias_value":"6OFNLO64CFYZ","created_at":"2026-07-05T09:42:58Z"},{"alias_kind":"pith_short_16","alias_value":"6OFNLO64CFYZ3XL7","created_at":"2026-07-05T09:42:58Z"},{"alias_kind":"pith_short_8","alias_value":"6OFNLO64","created_at":"2026-07-05T09:42:58Z"}],"graph_snapshots":[{"event_id":"sha256:9de71b88d8ca6fce13ace12cdad9ec5146d56cceb5856565f9ca8abe2b94bbf0","target":"graph","created_at":"2026-07-05T09:42:58Z","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/2412.01333/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Hongyu Zhang, Philip S. Yu, Wenting Zhao, Xuanhua Shi, Yang Wu, Yao Wan, Ye Liu, Zhaoyang Chu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2024-12-02T09:56:18Z","title":"Can Large Language Models Serve as Evaluators for Code Summarization?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.01333","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:c1f21d98f95e7fcba693a8edf1f59a56ee138d52903c9151e9e2807bbbde6b37","target":"record","created_at":"2026-07-05T09:42:58Z","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":"3ee497a49410fb796df4f96c49ab6bd31fdd6b6223134780e3271ed46059118b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2024-12-02T09:56:18Z","title_canon_sha256":"a19937d2dcea6fc3f89dfdbdddeedddf437c1dc8452305634ecb4666a7644026"},"schema_version":"1.0","source":{"id":"2412.01333","kind":"arxiv","version":1}},"canonical_sha256":"f38ad5bbdc11719ddd7f4c7088e8ea6aea45dc02cf9872fae5fe25618f20ccdf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f38ad5bbdc11719ddd7f4c7088e8ea6aea45dc02cf9872fae5fe25618f20ccdf","first_computed_at":"2026-07-05T09:42:58.261145Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:42:58.261145Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"52sUvm7l2IzNuS3Z9BdEWmVUAN3Mtv/WZpqfzxFcPXNOXBa6Kiw1FSnVYysbOegIKutMAJjH9df1ukwTv4uFCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:42:58.261660Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.01333","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c1f21d98f95e7fcba693a8edf1f59a56ee138d52903c9151e9e2807bbbde6b37","sha256:9de71b88d8ca6fce13ace12cdad9ec5146d56cceb5856565f9ca8abe2b94bbf0"],"state_sha256":"b813ff9ade90f4136977b0eb8ebc856bcba9b701cdd8b32fe80de01be65076cb"}