{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:OAGY7TNOTHOFLPOLISV2AWNL4Q","short_pith_number":"pith:OAGY7TNO","schema_version":"1.0","canonical_sha256":"700d8fcdae99dc55bdcb44aba059abe4304919f2c06a055b57dbf0a7c4cfc7ed","source":{"kind":"arxiv","id":"2407.02742","version":1},"attestation_state":"computed","paper":{"title":"A Comparative Study of DSL Code Generation: Fine-Tuning vs. Optimized Retrieval Augmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.SE","authors_text":"Chhaya Methani, Nastaran Bassamzadeh","submitted_at":"2024-07-03T01:28:51Z","abstract_excerpt":"Natural Language to Code Generation has made significant progress in recent years with the advent of Large Language Models(LLMs). While generation for general-purpose languages like C, C++, and Python has improved significantly, LLMs struggle with custom function names in Domain Specific Languages or DSLs. This leads to higher hallucination rates and syntax errors, specially for DSLs having a high number of custom function names. Additionally, constant updates to function names add to the challenge as LLMs need to stay up-to-date. In this paper, we present optimizations for using Retrieval Aug"},"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":"2407.02742","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2024-07-03T01:28:51Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"850e35235979cf88d5ba36d272c2febdfd0029015fc56537670259c4a9d3b197","abstract_canon_sha256":"93d227bbd61e9f460f0d789b45e929b6c0b99a36cb6180fc5e7b8853a4f8fe3f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:39:40.936933Z","signature_b64":"+6XJ+XFgwMFAbNAXiMuNgX7DIwf8onvTX/YTMuJMmFjjdiAhOsYzp9ZqoVemM/1/h+Xk5C/v076Ye6M9TL5yCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"700d8fcdae99dc55bdcb44aba059abe4304919f2c06a055b57dbf0a7c4cfc7ed","last_reissued_at":"2026-07-05T08:39:40.936491Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:39:40.936491Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Comparative Study of DSL Code Generation: Fine-Tuning vs. Optimized Retrieval Augmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.SE","authors_text":"Chhaya Methani, Nastaran Bassamzadeh","submitted_at":"2024-07-03T01:28:51Z","abstract_excerpt":"Natural Language to Code Generation has made significant progress in recent years with the advent of Large Language Models(LLMs). While generation for general-purpose languages like C, C++, and Python has improved significantly, LLMs struggle with custom function names in Domain Specific Languages or DSLs. This leads to higher hallucination rates and syntax errors, specially for DSLs having a high number of custom function names. Additionally, constant updates to function names add to the challenge as LLMs need to stay up-to-date. In this paper, we present optimizations for using Retrieval Aug"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.02742","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/2407.02742/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":"2407.02742","created_at":"2026-07-05T08:39:40.936550+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.02742v1","created_at":"2026-07-05T08:39:40.936550+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.02742","created_at":"2026-07-05T08:39:40.936550+00:00"},{"alias_kind":"pith_short_12","alias_value":"OAGY7TNOTHOF","created_at":"2026-07-05T08:39:40.936550+00:00"},{"alias_kind":"pith_short_16","alias_value":"OAGY7TNOTHOFLPOL","created_at":"2026-07-05T08:39:40.936550+00:00"},{"alias_kind":"pith_short_8","alias_value":"OAGY7TNO","created_at":"2026-07-05T08:39:40.936550+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.08740","citing_title":"Workflow as Knowledge: Semantic Persistence for LLM-Mediated Workflows","ref_index":1,"is_internal_anchor":true},{"citing_arxiv_id":"2606.25193","citing_title":"LLM4MTLs: Automated Generation and Empirical Evaluation of Model Transformation Languages","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2604.24678","citing_title":"Leveraging LLMs for Multi-File DSL Code Generation: An Industrial Case Study","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09952","citing_title":"SLM Finetuning for Natural Language to Domain Specific Code Generation in Production","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21765","citing_title":"PrismaDV: Automated Task-Aware Data Unit Test Generation","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OAGY7TNOTHOFLPOLISV2AWNL4Q","json":"https://pith.science/pith/OAGY7TNOTHOFLPOLISV2AWNL4Q.json","graph_json":"https://pith.science/api/pith-number/OAGY7TNOTHOFLPOLISV2AWNL4Q/graph.json","events_json":"https://pith.science/api/pith-number/OAGY7TNOTHOFLPOLISV2AWNL4Q/events.json","paper":"https://pith.science/paper/OAGY7TNO"},"agent_actions":{"view_html":"https://pith.science/pith/OAGY7TNOTHOFLPOLISV2AWNL4Q","download_json":"https://pith.science/pith/OAGY7TNOTHOFLPOLISV2AWNL4Q.json","view_paper":"https://pith.science/paper/OAGY7TNO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.02742&json=true","fetch_graph":"https://pith.science/api/pith-number/OAGY7TNOTHOFLPOLISV2AWNL4Q/graph.json","fetch_events":"https://pith.science/api/pith-number/OAGY7TNOTHOFLPOLISV2AWNL4Q/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OAGY7TNOTHOFLPOLISV2AWNL4Q/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OAGY7TNOTHOFLPOLISV2AWNL4Q/action/storage_attestation","attest_author":"https://pith.science/pith/OAGY7TNOTHOFLPOLISV2AWNL4Q/action/author_attestation","sign_citation":"https://pith.science/pith/OAGY7TNOTHOFLPOLISV2AWNL4Q/action/citation_signature","submit_replication":"https://pith.science/pith/OAGY7TNOTHOFLPOLISV2AWNL4Q/action/replication_record"}},"created_at":"2026-07-05T08:39:40.936550+00:00","updated_at":"2026-07-05T08:39:40.936550+00:00"}