{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:DXVGJA63DVQMSOTWYU4W2STUAB","short_pith_number":"pith:DXVGJA63","schema_version":"1.0","canonical_sha256":"1dea6483db1d60c93a76c5396d4a74005c2d9d527409c95c722f491bd15ad11d","source":{"kind":"arxiv","id":"2505.19392","version":1},"attestation_state":"computed","paper":{"title":"Simple and Effective Baselines for Code Summarisation Evaluation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.SE"],"primary_cat":"cs.CL","authors_text":"Jade Robinson, Jonathan K. Kummerfeld","submitted_at":"2025-05-26T01:16:41Z","abstract_excerpt":"Code documentation is useful, but writing it is time-consuming. Different techniques for generating code summaries have emerged, but comparing them is difficult because human evaluation is expensive and automatic metrics are unreliable. In this paper, we introduce a simple new baseline in which we ask an LLM to give an overall score to a summary. Unlike n-gram and embedding-based baselines, our approach is able to consider the code when giving a score. This allows us to also make a variant that does not consider the reference summary at all, which could be used for other tasks, e.g., to evalua"},"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":"2505.19392","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-26T01:16:41Z","cross_cats_sorted":["cs.AI","cs.SE"],"title_canon_sha256":"8dcdd70dba24c4e6675df92e0ccfa0d21e61ac79b894e4ab3a313cd928d0ae64","abstract_canon_sha256":"b16879c9ed025bbcba864dc0f2d17349072f3d5dd97903b3b211e4f38db74e76"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:09:29.511084Z","signature_b64":"YXc7nINhO0/7fSarSLp/kYhpGOBsIuqgXmSecDJaHdALexHMZxRtF+rqEi/BpSDflr6Y6Sf00kBkE6/lFdR/Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1dea6483db1d60c93a76c5396d4a74005c2d9d527409c95c722f491bd15ad11d","last_reissued_at":"2026-07-05T11:09:29.510688Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:09:29.510688Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Simple and Effective Baselines for Code Summarisation Evaluation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.SE"],"primary_cat":"cs.CL","authors_text":"Jade Robinson, Jonathan K. Kummerfeld","submitted_at":"2025-05-26T01:16:41Z","abstract_excerpt":"Code documentation is useful, but writing it is time-consuming. Different techniques for generating code summaries have emerged, but comparing them is difficult because human evaluation is expensive and automatic metrics are unreliable. In this paper, we introduce a simple new baseline in which we ask an LLM to give an overall score to a summary. Unlike n-gram and embedding-based baselines, our approach is able to consider the code when giving a score. This allows us to also make a variant that does not consider the reference summary at all, which could be used for other tasks, e.g., to evalua"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.19392","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/2505.19392/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":"2505.19392","created_at":"2026-07-05T11:09:29.510745+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.19392v1","created_at":"2026-07-05T11:09:29.510745+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.19392","created_at":"2026-07-05T11:09:29.510745+00:00"},{"alias_kind":"pith_short_12","alias_value":"DXVGJA63DVQM","created_at":"2026-07-05T11:09:29.510745+00:00"},{"alias_kind":"pith_short_16","alias_value":"DXVGJA63DVQMSOTW","created_at":"2026-07-05T11:09:29.510745+00:00"},{"alias_kind":"pith_short_8","alias_value":"DXVGJA63","created_at":"2026-07-05T11:09:29.510745+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DXVGJA63DVQMSOTWYU4W2STUAB","json":"https://pith.science/pith/DXVGJA63DVQMSOTWYU4W2STUAB.json","graph_json":"https://pith.science/api/pith-number/DXVGJA63DVQMSOTWYU4W2STUAB/graph.json","events_json":"https://pith.science/api/pith-number/DXVGJA63DVQMSOTWYU4W2STUAB/events.json","paper":"https://pith.science/paper/DXVGJA63"},"agent_actions":{"view_html":"https://pith.science/pith/DXVGJA63DVQMSOTWYU4W2STUAB","download_json":"https://pith.science/pith/DXVGJA63DVQMSOTWYU4W2STUAB.json","view_paper":"https://pith.science/paper/DXVGJA63","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.19392&json=true","fetch_graph":"https://pith.science/api/pith-number/DXVGJA63DVQMSOTWYU4W2STUAB/graph.json","fetch_events":"https://pith.science/api/pith-number/DXVGJA63DVQMSOTWYU4W2STUAB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DXVGJA63DVQMSOTWYU4W2STUAB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DXVGJA63DVQMSOTWYU4W2STUAB/action/storage_attestation","attest_author":"https://pith.science/pith/DXVGJA63DVQMSOTWYU4W2STUAB/action/author_attestation","sign_citation":"https://pith.science/pith/DXVGJA63DVQMSOTWYU4W2STUAB/action/citation_signature","submit_replication":"https://pith.science/pith/DXVGJA63DVQMSOTWYU4W2STUAB/action/replication_record"}},"created_at":"2026-07-05T11:09:29.510745+00:00","updated_at":"2026-07-05T11:09:29.510745+00:00"}