{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:36ZKSXT45C6ISDY7TYKGQLZ26T","short_pith_number":"pith:36ZKSXT4","schema_version":"1.0","canonical_sha256":"dfb2a95e7ce8bc890f1f9e14682f3af4c563e7fcc7d109a099b9e00fee0b340f","source":{"kind":"arxiv","id":"2507.20774","version":1},"attestation_state":"computed","paper":{"title":"evalSmarT: An LLM-Based Framework for Evaluating Smart Contract Generated Comments","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Fatou Ndiaye Mbodji","submitted_at":"2025-07-28T12:37:43Z","abstract_excerpt":"Smart contract comment generation has gained traction as a means to improve code comprehension and maintainability in blockchain systems. However, evaluating the quality of generated comments remains a challenge. Traditional metrics such as BLEU and ROUGE fail to capture domain-specific nuances, while human evaluation is costly and unscalable. In this paper, we present \\texttt{evalSmarT}, a modular and extensible framework that leverages large language models (LLMs) as evaluators. The system supports over 400 evaluator configurations by combining approximately 40 LLMs with 10 prompting strateg"},"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":"2507.20774","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-07-28T12:37:43Z","cross_cats_sorted":[],"title_canon_sha256":"20bbea47fe130c04d48782ecd835affb470991a382d20888775700fc6eccc31c","abstract_canon_sha256":"45e198e1f1f690947c1007d4cd62e9a9c2f44de2e6ca6d9cd7795633ba2b02fd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:44:25.636282Z","signature_b64":"LAJAchXhxPNy3L1JwxsGvFZJuALI0Z/SqLc7NLiRy3b/asmGkLnu5UCiBs6y2mWRVMEYa1eo4F4vSSOtg/pIBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dfb2a95e7ce8bc890f1f9e14682f3af4c563e7fcc7d109a099b9e00fee0b340f","last_reissued_at":"2026-07-05T11:44:25.635819Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:44:25.635819Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"evalSmarT: An LLM-Based Framework for Evaluating Smart Contract Generated Comments","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Fatou Ndiaye Mbodji","submitted_at":"2025-07-28T12:37:43Z","abstract_excerpt":"Smart contract comment generation has gained traction as a means to improve code comprehension and maintainability in blockchain systems. However, evaluating the quality of generated comments remains a challenge. Traditional metrics such as BLEU and ROUGE fail to capture domain-specific nuances, while human evaluation is costly and unscalable. In this paper, we present \\texttt{evalSmarT}, a modular and extensible framework that leverages large language models (LLMs) as evaluators. The system supports over 400 evaluator configurations by combining approximately 40 LLMs with 10 prompting strateg"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.20774","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/2507.20774/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":"2507.20774","created_at":"2026-07-05T11:44:25.635883+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.20774v1","created_at":"2026-07-05T11:44:25.635883+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.20774","created_at":"2026-07-05T11:44:25.635883+00:00"},{"alias_kind":"pith_short_12","alias_value":"36ZKSXT45C6I","created_at":"2026-07-05T11:44:25.635883+00:00"},{"alias_kind":"pith_short_16","alias_value":"36ZKSXT45C6ISDY7","created_at":"2026-07-05T11:44:25.635883+00:00"},{"alias_kind":"pith_short_8","alias_value":"36ZKSXT4","created_at":"2026-07-05T11:44:25.635883+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/36ZKSXT45C6ISDY7TYKGQLZ26T","json":"https://pith.science/pith/36ZKSXT45C6ISDY7TYKGQLZ26T.json","graph_json":"https://pith.science/api/pith-number/36ZKSXT45C6ISDY7TYKGQLZ26T/graph.json","events_json":"https://pith.science/api/pith-number/36ZKSXT45C6ISDY7TYKGQLZ26T/events.json","paper":"https://pith.science/paper/36ZKSXT4"},"agent_actions":{"view_html":"https://pith.science/pith/36ZKSXT45C6ISDY7TYKGQLZ26T","download_json":"https://pith.science/pith/36ZKSXT45C6ISDY7TYKGQLZ26T.json","view_paper":"https://pith.science/paper/36ZKSXT4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.20774&json=true","fetch_graph":"https://pith.science/api/pith-number/36ZKSXT45C6ISDY7TYKGQLZ26T/graph.json","fetch_events":"https://pith.science/api/pith-number/36ZKSXT45C6ISDY7TYKGQLZ26T/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/36ZKSXT45C6ISDY7TYKGQLZ26T/action/timestamp_anchor","attest_storage":"https://pith.science/pith/36ZKSXT45C6ISDY7TYKGQLZ26T/action/storage_attestation","attest_author":"https://pith.science/pith/36ZKSXT45C6ISDY7TYKGQLZ26T/action/author_attestation","sign_citation":"https://pith.science/pith/36ZKSXT45C6ISDY7TYKGQLZ26T/action/citation_signature","submit_replication":"https://pith.science/pith/36ZKSXT45C6ISDY7TYKGQLZ26T/action/replication_record"}},"created_at":"2026-07-05T11:44:25.635883+00:00","updated_at":"2026-07-05T11:44:25.635883+00:00"}