{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:LF7YRW7UBVUHYJ55TEMRLMFBLL","short_pith_number":"pith:LF7YRW7U","schema_version":"1.0","canonical_sha256":"597f88dbf40d687c27bd991915b0a15ae698e80e310ace4039f70e7550d23482","source":{"kind":"arxiv","id":"2411.15100","version":3},"attestation_state":"computed","paper":{"title":"XGrammar: Flexible and Efficient Structured Generation Engine for Large Language Models","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.PL"],"primary_cat":"cs.CL","authors_text":"Charlie F. Ruan, Ruihang Lai, Tianqi Chen, Yaxing Cai, Yilong Zhao, Yixin Dong, Ziyi Xu","submitted_at":"2024-11-22T18:01:37Z","abstract_excerpt":"The applications of LLM Agents are becoming increasingly complex and diverse, leading to a high demand for structured outputs that can be parsed into code, structured function calls, and embodied agent commands. These developments bring significant demands for structured generation in LLM inference. Context-free grammar is a flexible approach to enable structured generation via constrained decoding. However, executing context-free grammar requires going through several stack states over all tokens in vocabulary during runtime, bringing non-negligible overhead for structured generation. In this"},"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":"2411.15100","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-22T18:01:37Z","cross_cats_sorted":["cs.AI","cs.PL"],"title_canon_sha256":"b40de5083135e93839d12febbbecd258960ee56957866fe04f28ba502f2f14ea","abstract_canon_sha256":"9b4054baf8ec01b5dea8f8c06108bfaef52de647afa07d4d706f1e8d20182417"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:01:28.999014Z","signature_b64":"P94/Flw1DeAQVOkhCEyf4jJ0DJ5AsYlVgCpJ6BFYCm1Ki13940H+1lpn3XiJ/hMRMC4CRUvB9HOv+UlwCXS9CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"597f88dbf40d687c27bd991915b0a15ae698e80e310ace4039f70e7550d23482","last_reissued_at":"2026-07-05T11:01:28.998499Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:01:28.998499Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"XGrammar: Flexible and Efficient Structured Generation Engine for Large Language Models","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.PL"],"primary_cat":"cs.CL","authors_text":"Charlie F. Ruan, Ruihang Lai, Tianqi Chen, Yaxing Cai, Yilong Zhao, Yixin Dong, Ziyi Xu","submitted_at":"2024-11-22T18:01:37Z","abstract_excerpt":"The applications of LLM Agents are becoming increasingly complex and diverse, leading to a high demand for structured outputs that can be parsed into code, structured function calls, and embodied agent commands. These developments bring significant demands for structured generation in LLM inference. Context-free grammar is a flexible approach to enable structured generation via constrained decoding. However, executing context-free grammar requires going through several stack states over all tokens in vocabulary during runtime, bringing non-negligible overhead for structured generation. In this"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.15100","kind":"arxiv","version":3},"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/2411.15100/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":"2411.15100","created_at":"2026-07-05T11:01:28.998558+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.15100v3","created_at":"2026-07-05T11:01:28.998558+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.15100","created_at":"2026-07-05T11:01:28.998558+00:00"},{"alias_kind":"pith_short_12","alias_value":"LF7YRW7UBVUH","created_at":"2026-07-05T11:01:28.998558+00:00"},{"alias_kind":"pith_short_16","alias_value":"LF7YRW7UBVUHYJ55","created_at":"2026-07-05T11:01:28.998558+00:00"},{"alias_kind":"pith_short_8","alias_value":"LF7YRW7U","created_at":"2026-07-05T11:01:28.998558+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":17,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.24937","citing_title":"The Hitchhiker's Guide to Agentic AI: From Foundations to Systems","ref_index":126,"is_internal_anchor":false},{"citing_arxiv_id":"2606.11817","citing_title":"Grammar-Constrained Decoding Can Jailbreak LLMs into Generating Malicious Code","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2606.09395","citing_title":"Empirical Study for Structured Output Control in LLMs for Software Engineering","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14113","citing_title":"ProtoMedAgent: Multimodal Clinical Interpretability via Privacy-Aware Agentic Workflows","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31808","citing_title":"Large Databases Need Small, Open-Weight Language Models","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17909","citing_title":"Ethical Hyper-Velocity (EHV): A Hardware-Rooted Zero-Trust Runtime Enforcement Architecture for Agentic AI Systems","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2411.15594","citing_title":"A Survey on LLM-as-a-Judge","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09997","citing_title":"GraphInstruct: A Progressive Benchmark for Diagnosing Capability Gaps in LLM Graph Generation","ref_index":61,"is_internal_anchor":false},{"citing_arxiv_id":"2509.01082","citing_title":"RefineStat: Efficient Exploration for Probabilistic Program Synthesis","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14113","citing_title":"ProtoMedAgent: Multimodal Clinical Interpretability via Privacy-Aware Agentic Workflows","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2603.25306","citing_title":"JSON Schema Inclusion through Refutational Normalization: Reconciling Efficiency and Completeness","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2603.27905","citing_title":"ATLAS-RTC: Closing the Loop on LLM Agent Output with Token-Level Runtime Control","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10835","citing_title":"Transcoda: End-to-End Zero-Shot Optical Music Recognition via Data-Centric Synthetic Training","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10065","citing_title":"NCO: A Versatile Plug-in for Handling Negative Constraints in Decoding","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09997","citing_title":"GraphInstruct: A Progressive Benchmark for Diagnosing Capability Gaps in LLM Graph Generation","ref_index":61,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05150","citing_title":"Compiled AI: Deterministic Code Generation for LLM-Based Workflow Automation","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2604.25359","citing_title":"The Structured Output Benchmark: A Multi-Source Benchmark for Evaluating Structured Output Quality in Large Language Models","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LF7YRW7UBVUHYJ55TEMRLMFBLL","json":"https://pith.science/pith/LF7YRW7UBVUHYJ55TEMRLMFBLL.json","graph_json":"https://pith.science/api/pith-number/LF7YRW7UBVUHYJ55TEMRLMFBLL/graph.json","events_json":"https://pith.science/api/pith-number/LF7YRW7UBVUHYJ55TEMRLMFBLL/events.json","paper":"https://pith.science/paper/LF7YRW7U"},"agent_actions":{"view_html":"https://pith.science/pith/LF7YRW7UBVUHYJ55TEMRLMFBLL","download_json":"https://pith.science/pith/LF7YRW7UBVUHYJ55TEMRLMFBLL.json","view_paper":"https://pith.science/paper/LF7YRW7U","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.15100&json=true","fetch_graph":"https://pith.science/api/pith-number/LF7YRW7UBVUHYJ55TEMRLMFBLL/graph.json","fetch_events":"https://pith.science/api/pith-number/LF7YRW7UBVUHYJ55TEMRLMFBLL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LF7YRW7UBVUHYJ55TEMRLMFBLL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LF7YRW7UBVUHYJ55TEMRLMFBLL/action/storage_attestation","attest_author":"https://pith.science/pith/LF7YRW7UBVUHYJ55TEMRLMFBLL/action/author_attestation","sign_citation":"https://pith.science/pith/LF7YRW7UBVUHYJ55TEMRLMFBLL/action/citation_signature","submit_replication":"https://pith.science/pith/LF7YRW7UBVUHYJ55TEMRLMFBLL/action/replication_record"}},"created_at":"2026-07-05T11:01:28.998558+00:00","updated_at":"2026-07-05T11:01:28.998558+00:00"}