{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:BVN67A6FWBXV3OUHXBOU2M3JJK","short_pith_number":"pith:BVN67A6F","schema_version":"1.0","canonical_sha256":"0d5bef83c5b06f5dba87b85d4d33694a9f82aa59bc38097ef1b053bc7e279bed","source":{"kind":"arxiv","id":"2410.18494","version":2},"attestation_state":"computed","paper":{"title":"Assured Automatic Programming via Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.PL"],"primary_cat":"cs.SE","authors_text":"Abhik Roychoudhury, Abhishek Kr Singh, Andreea Costea, Martin Mirchev","submitted_at":"2024-10-24T07:29:15Z","abstract_excerpt":"With the advent of AI-based coding engines, it is possible to convert natural language requirements to executable code in standard programming languages. However, AI-generated code can be unreliable, and the natural language requirements driving this code may be ambiguous. In other words, the intent may not be accurately captured in the code generated from AI-coding engines like Copilot. The goal of our work is to discover the programmer intent, while generating code which conforms to the intent and a proof of this conformance. Our approach to intent discovery is powered by a novel repair engi"},"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":"2410.18494","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2024-10-24T07:29:15Z","cross_cats_sorted":["cs.LG","cs.PL"],"title_canon_sha256":"5873bd1664d96575f8529a91b5c027395333e5d8adf15942699b71cb2e422cf0","abstract_canon_sha256":"0f6cd84e06b65e55bea1dcaf86e4010f449bc7adc582ab934623d4a727bb029a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:31:09.742538Z","signature_b64":"jS5FzkcrxG5shI2Uyw6owNVBFPNO0SVcJCIv8STtzuTn987/SaMjVZeZWLm/h/ulK+hlbtJqoS3ebzyOp3oDCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0d5bef83c5b06f5dba87b85d4d33694a9f82aa59bc38097ef1b053bc7e279bed","last_reissued_at":"2026-07-05T09:31:09.742038Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:31:09.742038Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Assured Automatic Programming via Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.PL"],"primary_cat":"cs.SE","authors_text":"Abhik Roychoudhury, Abhishek Kr Singh, Andreea Costea, Martin Mirchev","submitted_at":"2024-10-24T07:29:15Z","abstract_excerpt":"With the advent of AI-based coding engines, it is possible to convert natural language requirements to executable code in standard programming languages. However, AI-generated code can be unreliable, and the natural language requirements driving this code may be ambiguous. In other words, the intent may not be accurately captured in the code generated from AI-coding engines like Copilot. The goal of our work is to discover the programmer intent, while generating code which conforms to the intent and a proof of this conformance. Our approach to intent discovery is powered by a novel repair engi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.18494","kind":"arxiv","version":2},"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/2410.18494/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":"2410.18494","created_at":"2026-07-05T09:31:09.742096+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.18494v2","created_at":"2026-07-05T09:31:09.742096+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.18494","created_at":"2026-07-05T09:31:09.742096+00:00"},{"alias_kind":"pith_short_12","alias_value":"BVN67A6FWBXV","created_at":"2026-07-05T09:31:09.742096+00:00"},{"alias_kind":"pith_short_16","alias_value":"BVN67A6FWBXV3OUH","created_at":"2026-07-05T09:31:09.742096+00:00"},{"alias_kind":"pith_short_8","alias_value":"BVN67A6F","created_at":"2026-07-05T09:31:09.742096+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.05820","citing_title":"SpecRL: Reinforcement Learning with Test-Based Completeness Rewards for Formal Specification Synthesis","ref_index":37,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BVN67A6FWBXV3OUHXBOU2M3JJK","json":"https://pith.science/pith/BVN67A6FWBXV3OUHXBOU2M3JJK.json","graph_json":"https://pith.science/api/pith-number/BVN67A6FWBXV3OUHXBOU2M3JJK/graph.json","events_json":"https://pith.science/api/pith-number/BVN67A6FWBXV3OUHXBOU2M3JJK/events.json","paper":"https://pith.science/paper/BVN67A6F"},"agent_actions":{"view_html":"https://pith.science/pith/BVN67A6FWBXV3OUHXBOU2M3JJK","download_json":"https://pith.science/pith/BVN67A6FWBXV3OUHXBOU2M3JJK.json","view_paper":"https://pith.science/paper/BVN67A6F","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.18494&json=true","fetch_graph":"https://pith.science/api/pith-number/BVN67A6FWBXV3OUHXBOU2M3JJK/graph.json","fetch_events":"https://pith.science/api/pith-number/BVN67A6FWBXV3OUHXBOU2M3JJK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BVN67A6FWBXV3OUHXBOU2M3JJK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BVN67A6FWBXV3OUHXBOU2M3JJK/action/storage_attestation","attest_author":"https://pith.science/pith/BVN67A6FWBXV3OUHXBOU2M3JJK/action/author_attestation","sign_citation":"https://pith.science/pith/BVN67A6FWBXV3OUHXBOU2M3JJK/action/citation_signature","submit_replication":"https://pith.science/pith/BVN67A6FWBXV3OUHXBOU2M3JJK/action/replication_record"}},"created_at":"2026-07-05T09:31:09.742096+00:00","updated_at":"2026-07-05T09:31:09.742096+00:00"}