{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:PFN27RLMWOJBMNTVCZFCT2YUDR","short_pith_number":"pith:PFN27RLM","schema_version":"1.0","canonical_sha256":"795bafc56cb392163675164a29eb141c412ead53c0c79513919260cfe8cd8d56","source":{"kind":"arxiv","id":"2507.05200","version":1},"attestation_state":"computed","paper":{"title":"In-Context Learning as an Effective Estimator of Functional Correctness of LLM-Generated Code","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.SE","authors_text":"Debasis Ganguly, Gul Calikli, Madhusudan Ghosh, Priyanka Swami, Susmita Das","submitted_at":"2025-07-07T17:01:17Z","abstract_excerpt":"When applying LLM-based code generation to software development projects that follow a feature-driven or rapid application development approach, it becomes necessary to estimate the functional correctness of the generated code in the absence of test cases. Just as a user selects a relevant document from a ranked list of retrieved ones, a software generation workflow requires a developer to choose (and potentially refine) a generated solution from a ranked list of alternative solutions, ordered by their posterior likelihoods. This implies that estimating the quality of a ranked list -- akin to "},"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":"2507.05200","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-07-07T17:01:17Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"46689219aeccb752eca914b5cb91e01a602f4b6f8f75580f3dca7bf98f0ef465","abstract_canon_sha256":"eb8f334980a5be4488fd5404035b72ed4f34b2972d9444fd4d8916927ea4713f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:33:10.599104Z","signature_b64":"d5srQGaWjtCRHmn/1cbGnqYtt9U12QmqYt074+fyN3Jl8SJB4OOKZnxiLIrjgfuScpXj24Zs1EEQyjxfksUGDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"795bafc56cb392163675164a29eb141c412ead53c0c79513919260cfe8cd8d56","last_reissued_at":"2026-07-05T11:33:10.598622Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:33:10.598622Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"In-Context Learning as an Effective Estimator of Functional Correctness of LLM-Generated Code","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.SE","authors_text":"Debasis Ganguly, Gul Calikli, Madhusudan Ghosh, Priyanka Swami, Susmita Das","submitted_at":"2025-07-07T17:01:17Z","abstract_excerpt":"When applying LLM-based code generation to software development projects that follow a feature-driven or rapid application development approach, it becomes necessary to estimate the functional correctness of the generated code in the absence of test cases. Just as a user selects a relevant document from a ranked list of retrieved ones, a software generation workflow requires a developer to choose (and potentially refine) a generated solution from a ranked list of alternative solutions, ordered by their posterior likelihoods. This implies that estimating the quality of a ranked list -- akin to "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.05200","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/2507.05200/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":"2507.05200","created_at":"2026-07-05T11:33:10.598678+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.05200v1","created_at":"2026-07-05T11:33:10.598678+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.05200","created_at":"2026-07-05T11:33:10.598678+00:00"},{"alias_kind":"pith_short_12","alias_value":"PFN27RLMWOJB","created_at":"2026-07-05T11:33:10.598678+00:00"},{"alias_kind":"pith_short_16","alias_value":"PFN27RLMWOJBMNTV","created_at":"2026-07-05T11:33:10.598678+00:00"},{"alias_kind":"pith_short_8","alias_value":"PFN27RLM","created_at":"2026-07-05T11:33:10.598678+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/PFN27RLMWOJBMNTVCZFCT2YUDR","json":"https://pith.science/pith/PFN27RLMWOJBMNTVCZFCT2YUDR.json","graph_json":"https://pith.science/api/pith-number/PFN27RLMWOJBMNTVCZFCT2YUDR/graph.json","events_json":"https://pith.science/api/pith-number/PFN27RLMWOJBMNTVCZFCT2YUDR/events.json","paper":"https://pith.science/paper/PFN27RLM"},"agent_actions":{"view_html":"https://pith.science/pith/PFN27RLMWOJBMNTVCZFCT2YUDR","download_json":"https://pith.science/pith/PFN27RLMWOJBMNTVCZFCT2YUDR.json","view_paper":"https://pith.science/paper/PFN27RLM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.05200&json=true","fetch_graph":"https://pith.science/api/pith-number/PFN27RLMWOJBMNTVCZFCT2YUDR/graph.json","fetch_events":"https://pith.science/api/pith-number/PFN27RLMWOJBMNTVCZFCT2YUDR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PFN27RLMWOJBMNTVCZFCT2YUDR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PFN27RLMWOJBMNTVCZFCT2YUDR/action/storage_attestation","attest_author":"https://pith.science/pith/PFN27RLMWOJBMNTVCZFCT2YUDR/action/author_attestation","sign_citation":"https://pith.science/pith/PFN27RLMWOJBMNTVCZFCT2YUDR/action/citation_signature","submit_replication":"https://pith.science/pith/PFN27RLMWOJBMNTVCZFCT2YUDR/action/replication_record"}},"created_at":"2026-07-05T11:33:10.598678+00:00","updated_at":"2026-07-05T11:33:10.598678+00:00"}