{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:SVLX5XHIH7CU5Z5KVKCD3VZNWO","short_pith_number":"pith:SVLX5XHI","schema_version":"1.0","canonical_sha256":"95577edce83fc54ee7aaaa843dd72db3bacc29fe4bfc72906a81611d8e71e186","source":{"kind":"arxiv","id":"2403.01632","version":4},"attestation_state":"computed","paper":{"title":"SynCode: LLM Generation with Grammar Augmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.FL","cs.PL","cs.SE"],"primary_cat":"cs.LG","authors_text":"Gagandeep Singh, Hangoo Kang, Sasa Misailovic, Shubham Ugare, Tarun Suresh","submitted_at":"2024-03-03T22:38:35Z","abstract_excerpt":"LLMs are widely used in complex AI applications. These applications underscore the need for LLM outputs to adhere to a specific format, for their integration with other components in the systems. Typically the format rules e.g., for data serialization formats such as JSON, YAML, or Code in Programming Language are expressed as context-free grammar (CFG). Due to the hallucinations and unreliability of LLMs, instructing LLMs to adhere to specified syntax becomes an increasingly important challenge.\n  We present SynCode, a novel framework for efficient and general syntactical decoding with LLMs, "},"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":"2403.01632","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-03-03T22:38:35Z","cross_cats_sorted":["cs.FL","cs.PL","cs.SE"],"title_canon_sha256":"65db2cab8f13e6231896a0db23a367275c373f0c27f731b2be2494d1f247bbfe","abstract_canon_sha256":"116d86de93a02c0d55b291cbaea0d293521ec75bfebd02015427c4268fbccd83"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:31:43.896740Z","signature_b64":"yNoONnGPT36wUttNK7TsgNpIDCKApOYhoISeIg1yZ6kjtU9yQunYsEaxhwLSKqtnVwWBABLOiBbdr07924TdBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"95577edce83fc54ee7aaaa843dd72db3bacc29fe4bfc72906a81611d8e71e186","last_reissued_at":"2026-07-05T09:31:43.896236Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:31:43.896236Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SynCode: LLM Generation with Grammar Augmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.FL","cs.PL","cs.SE"],"primary_cat":"cs.LG","authors_text":"Gagandeep Singh, Hangoo Kang, Sasa Misailovic, Shubham Ugare, Tarun Suresh","submitted_at":"2024-03-03T22:38:35Z","abstract_excerpt":"LLMs are widely used in complex AI applications. These applications underscore the need for LLM outputs to adhere to a specific format, for their integration with other components in the systems. Typically the format rules e.g., for data serialization formats such as JSON, YAML, or Code in Programming Language are expressed as context-free grammar (CFG). Due to the hallucinations and unreliability of LLMs, instructing LLMs to adhere to specified syntax becomes an increasingly important challenge.\n  We present SynCode, a novel framework for efficient and general syntactical decoding with LLMs, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.01632","kind":"arxiv","version":4},"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/2403.01632/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":"2403.01632","created_at":"2026-07-05T09:31:43.896293+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.01632v4","created_at":"2026-07-05T09:31:43.896293+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.01632","created_at":"2026-07-05T09:31:43.896293+00:00"},{"alias_kind":"pith_short_12","alias_value":"SVLX5XHIH7CU","created_at":"2026-07-05T09:31:43.896293+00:00"},{"alias_kind":"pith_short_16","alias_value":"SVLX5XHIH7CU5Z5K","created_at":"2026-07-05T09:31:43.896293+00:00"},{"alias_kind":"pith_short_8","alias_value":"SVLX5XHI","created_at":"2026-07-05T09:31:43.896293+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":9,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.09395","citing_title":"Empirical Study for Structured Output Control in LLMs for Software Engineering","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13076","citing_title":"TruncProof: A Guardrail for LLM-based JSON Generation under Token-Length Constraints","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2504.16584","citing_title":"Case Study: Fine-tuning Small Language Models for Accurate and Private CWE Detection in Python Code","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2506.08980","citing_title":"AdaDec: A Uncertainty-Guided Lookahead Decoding Framework for LLM-Based Code Generation","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2509.01082","citing_title":"RefineStat: Efficient Exploration for Probabilistic Program Synthesis","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2511.22277","citing_title":"TreeCoder: Systematic Exploration and Optimisation of Decoding and Constraints for LLM Code Generation","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13076","citing_title":"TruncProof: A Guardrail for LLM-based JSON Generation under Token-Length Constraints","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05150","citing_title":"Compiled AI: Deterministic Code Generation for LLM-Based Workflow Automation","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02363","citing_title":"When Correct Isn't Usable: Improving Structured Output Reliability in Small Language Models","ref_index":23,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SVLX5XHIH7CU5Z5KVKCD3VZNWO","json":"https://pith.science/pith/SVLX5XHIH7CU5Z5KVKCD3VZNWO.json","graph_json":"https://pith.science/api/pith-number/SVLX5XHIH7CU5Z5KVKCD3VZNWO/graph.json","events_json":"https://pith.science/api/pith-number/SVLX5XHIH7CU5Z5KVKCD3VZNWO/events.json","paper":"https://pith.science/paper/SVLX5XHI"},"agent_actions":{"view_html":"https://pith.science/pith/SVLX5XHIH7CU5Z5KVKCD3VZNWO","download_json":"https://pith.science/pith/SVLX5XHIH7CU5Z5KVKCD3VZNWO.json","view_paper":"https://pith.science/paper/SVLX5XHI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.01632&json=true","fetch_graph":"https://pith.science/api/pith-number/SVLX5XHIH7CU5Z5KVKCD3VZNWO/graph.json","fetch_events":"https://pith.science/api/pith-number/SVLX5XHIH7CU5Z5KVKCD3VZNWO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SVLX5XHIH7CU5Z5KVKCD3VZNWO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SVLX5XHIH7CU5Z5KVKCD3VZNWO/action/storage_attestation","attest_author":"https://pith.science/pith/SVLX5XHIH7CU5Z5KVKCD3VZNWO/action/author_attestation","sign_citation":"https://pith.science/pith/SVLX5XHIH7CU5Z5KVKCD3VZNWO/action/citation_signature","submit_replication":"https://pith.science/pith/SVLX5XHIH7CU5Z5KVKCD3VZNWO/action/replication_record"}},"created_at":"2026-07-05T09:31:43.896293+00:00","updated_at":"2026-07-05T09:31:43.896293+00:00"}