{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:6CYVDO3FEWZNJB4K3S2VI5SA4Q","short_pith_number":"pith:6CYVDO3F","schema_version":"1.0","canonical_sha256":"f0b151bb6525b2d4878adcb5547640e42bee7394737db6c7eae2ed36fb1dbe19","source":{"kind":"arxiv","id":"2208.05950","version":2},"attestation_state":"computed","paper":{"title":"Interactive Code Generation via Test-Driven User-Intent Formalization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.PL"],"primary_cat":"cs.SE","authors_text":"Aaditya Naik, Chenglong Wang, Curtis von Veh, Georgios Sakkas, Jeevana Priya Inala, Jianfeng Gao, Madanlal Musuvathi, Piali Choudhury, Saikat Chakraborty, Sarah Fakhoury, Shuvendu K. Lahiri","submitted_at":"2022-08-11T17:41:08Z","abstract_excerpt":"Large language models (LLMs) have shown great potential in automating significant aspects of coding by producing natural code from informal natural language (NL) intent. However, when interacting with LLMs, users have no guarantees that the code suggestions produced correctly satisfy the intent they provided. In fact, it is hard to define a notion of correctness since natural language can be ambiguous and lacks a formal semantics.\n  In this paper, we propose the workflow of {\\it interactive test-driven code generation}, which leverages lightweight user feedback to (a) formalize the user intent"},"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":"2208.05950","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2022-08-11T17:41:08Z","cross_cats_sorted":["cs.LG","cs.PL"],"title_canon_sha256":"38e2f111125da31b987427a2fc6515477dd9d68264de5c7a3585dde722dc2515","abstract_canon_sha256":"a96959766d2e1956b4884b9c6cb0e042bd0f0a9282c3ebcff736551b0313d566"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:56:52.705496Z","signature_b64":"XPxyHmrUv3tMUK5rZ1CgKKTMbh12nI9bie9Db4QpGVjchOYsQ5Plz126wiRdm7nhvvzqVfSEEKh+C3VMUH1BBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f0b151bb6525b2d4878adcb5547640e42bee7394737db6c7eae2ed36fb1dbe19","last_reissued_at":"2026-07-05T06:56:52.705010Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:56:52.705010Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Interactive Code Generation via Test-Driven User-Intent Formalization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.PL"],"primary_cat":"cs.SE","authors_text":"Aaditya Naik, Chenglong Wang, Curtis von Veh, Georgios Sakkas, Jeevana Priya Inala, Jianfeng Gao, Madanlal Musuvathi, Piali Choudhury, Saikat Chakraborty, Sarah Fakhoury, Shuvendu K. Lahiri","submitted_at":"2022-08-11T17:41:08Z","abstract_excerpt":"Large language models (LLMs) have shown great potential in automating significant aspects of coding by producing natural code from informal natural language (NL) intent. However, when interacting with LLMs, users have no guarantees that the code suggestions produced correctly satisfy the intent they provided. In fact, it is hard to define a notion of correctness since natural language can be ambiguous and lacks a formal semantics.\n  In this paper, we propose the workflow of {\\it interactive test-driven code generation}, which leverages lightweight user feedback to (a) formalize the user intent"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.05950","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/2208.05950/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":"2208.05950","created_at":"2026-07-05T06:56:52.705068+00:00"},{"alias_kind":"arxiv_version","alias_value":"2208.05950v2","created_at":"2026-07-05T06:56:52.705068+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.05950","created_at":"2026-07-05T06:56:52.705068+00:00"},{"alias_kind":"pith_short_12","alias_value":"6CYVDO3FEWZN","created_at":"2026-07-05T06:56:52.705068+00:00"},{"alias_kind":"pith_short_16","alias_value":"6CYVDO3FEWZNJB4K","created_at":"2026-07-05T06:56:52.705068+00:00"},{"alias_kind":"pith_short_8","alias_value":"6CYVDO3F","created_at":"2026-07-05T06:56:52.705068+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06636","citing_title":"Specification Grounding Drives Test Effectiveness for LLM Code","ref_index":10,"is_internal_anchor":true},{"citing_arxiv_id":"2604.02382","citing_title":"Ambig-IaC: Multi-level Disambiguation for Interactive Cloud Infrastructure-as-Code Synthesis","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11770","citing_title":"Enhancing Program Repair with Specification Guidance and Intermediate Behavioral Signals","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11514","citing_title":"DuET: Dual Execution for Test Output Prediction with Generated Code and Pseudocode","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09408","citing_title":"HiL-Bench (Human-in-Loop Benchmark): Do Agents Know When to Ask for Help?","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2604.13463","citing_title":"From Exploration to Specification: LLM-Based Property Generation for Mobile App Testing","ref_index":26,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6CYVDO3FEWZNJB4K3S2VI5SA4Q","json":"https://pith.science/pith/6CYVDO3FEWZNJB4K3S2VI5SA4Q.json","graph_json":"https://pith.science/api/pith-number/6CYVDO3FEWZNJB4K3S2VI5SA4Q/graph.json","events_json":"https://pith.science/api/pith-number/6CYVDO3FEWZNJB4K3S2VI5SA4Q/events.json","paper":"https://pith.science/paper/6CYVDO3F"},"agent_actions":{"view_html":"https://pith.science/pith/6CYVDO3FEWZNJB4K3S2VI5SA4Q","download_json":"https://pith.science/pith/6CYVDO3FEWZNJB4K3S2VI5SA4Q.json","view_paper":"https://pith.science/paper/6CYVDO3F","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2208.05950&json=true","fetch_graph":"https://pith.science/api/pith-number/6CYVDO3FEWZNJB4K3S2VI5SA4Q/graph.json","fetch_events":"https://pith.science/api/pith-number/6CYVDO3FEWZNJB4K3S2VI5SA4Q/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6CYVDO3FEWZNJB4K3S2VI5SA4Q/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6CYVDO3FEWZNJB4K3S2VI5SA4Q/action/storage_attestation","attest_author":"https://pith.science/pith/6CYVDO3FEWZNJB4K3S2VI5SA4Q/action/author_attestation","sign_citation":"https://pith.science/pith/6CYVDO3FEWZNJB4K3S2VI5SA4Q/action/citation_signature","submit_replication":"https://pith.science/pith/6CYVDO3FEWZNJB4K3S2VI5SA4Q/action/replication_record"}},"created_at":"2026-07-05T06:56:52.705068+00:00","updated_at":"2026-07-05T06:56:52.705068+00:00"}