{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:4AC66SWI7W2QUO67LIN4NSO3L3","short_pith_number":"pith:4AC66SWI","schema_version":"1.0","canonical_sha256":"e005ef4ac8fdb50a3bdf5a1bc6c9db5ec52e3f8fd32d338e1ab757274c20debb","source":{"kind":"arxiv","id":"2406.11925","version":2},"attestation_state":"computed","paper":{"title":"DocCGen: Document-based Controlled Code Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.SE","authors_text":"Ashok Pon Kumar, Mehant Kammakomati, Prince Kumar, Pushpak Bhattacharyya, Sameer Pimparkhede, Srikanth Tamilselvam","submitted_at":"2024-06-17T08:34:57Z","abstract_excerpt":"Recent developments show that Large Language Models (LLMs) produce state-of-the-art performance on natural language (NL) to code generation for resource-rich general-purpose languages like C++, Java, and Python. However, their practical usage for structured domain-specific languages (DSLs) such as YAML, JSON is limited due to domain-specific schema, grammar, and customizations generally unseen by LLMs during pre-training. Efforts have been made to mitigate this challenge via in-context learning through relevant examples or by fine-tuning. However, it suffers from problems, such as limited DSL "},"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":"2406.11925","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2024-06-17T08:34:57Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"80872aa2dfe5ff031f37c60b3a51e1200571ab8f39f5e6e9681f9d75c3264b6a","abstract_canon_sha256":"b57004886b883d23a994dd1d40fbfbccefb4c09c86c672776889d0ba946461af"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:39:35.138499Z","signature_b64":"WG6YX4i6t2bNmJL1FuE8ThOQS8f67L7doJI346reR9yVm39xiOBNl+4AC8ChFOQZ9Gcp60KfuxiUojbkSm+yBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e005ef4ac8fdb50a3bdf5a1bc6c9db5ec52e3f8fd32d338e1ab757274c20debb","last_reissued_at":"2026-07-05T08:39:35.138077Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:39:35.138077Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DocCGen: Document-based Controlled Code Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.SE","authors_text":"Ashok Pon Kumar, Mehant Kammakomati, Prince Kumar, Pushpak Bhattacharyya, Sameer Pimparkhede, Srikanth Tamilselvam","submitted_at":"2024-06-17T08:34:57Z","abstract_excerpt":"Recent developments show that Large Language Models (LLMs) produce state-of-the-art performance on natural language (NL) to code generation for resource-rich general-purpose languages like C++, Java, and Python. However, their practical usage for structured domain-specific languages (DSLs) such as YAML, JSON is limited due to domain-specific schema, grammar, and customizations generally unseen by LLMs during pre-training. Efforts have been made to mitigate this challenge via in-context learning through relevant examples or by fine-tuning. However, it suffers from problems, such as limited DSL "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.11925","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/2406.11925/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":"2406.11925","created_at":"2026-07-05T08:39:35.138134+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.11925v2","created_at":"2026-07-05T08:39:35.138134+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.11925","created_at":"2026-07-05T08:39:35.138134+00:00"},{"alias_kind":"pith_short_12","alias_value":"4AC66SWI7W2Q","created_at":"2026-07-05T08:39:35.138134+00:00"},{"alias_kind":"pith_short_16","alias_value":"4AC66SWI7W2QUO67","created_at":"2026-07-05T08:39:35.138134+00:00"},{"alias_kind":"pith_short_8","alias_value":"4AC66SWI","created_at":"2026-07-05T08:39:35.138134+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/4AC66SWI7W2QUO67LIN4NSO3L3","json":"https://pith.science/pith/4AC66SWI7W2QUO67LIN4NSO3L3.json","graph_json":"https://pith.science/api/pith-number/4AC66SWI7W2QUO67LIN4NSO3L3/graph.json","events_json":"https://pith.science/api/pith-number/4AC66SWI7W2QUO67LIN4NSO3L3/events.json","paper":"https://pith.science/paper/4AC66SWI"},"agent_actions":{"view_html":"https://pith.science/pith/4AC66SWI7W2QUO67LIN4NSO3L3","download_json":"https://pith.science/pith/4AC66SWI7W2QUO67LIN4NSO3L3.json","view_paper":"https://pith.science/paper/4AC66SWI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.11925&json=true","fetch_graph":"https://pith.science/api/pith-number/4AC66SWI7W2QUO67LIN4NSO3L3/graph.json","fetch_events":"https://pith.science/api/pith-number/4AC66SWI7W2QUO67LIN4NSO3L3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4AC66SWI7W2QUO67LIN4NSO3L3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4AC66SWI7W2QUO67LIN4NSO3L3/action/storage_attestation","attest_author":"https://pith.science/pith/4AC66SWI7W2QUO67LIN4NSO3L3/action/author_attestation","sign_citation":"https://pith.science/pith/4AC66SWI7W2QUO67LIN4NSO3L3/action/citation_signature","submit_replication":"https://pith.science/pith/4AC66SWI7W2QUO67LIN4NSO3L3/action/replication_record"}},"created_at":"2026-07-05T08:39:35.138134+00:00","updated_at":"2026-07-05T08:39:35.138134+00:00"}