{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:UBM5KOE5LCEJ5WGLIIHJA4YZGN","short_pith_number":"pith:UBM5KOE5","schema_version":"1.0","canonical_sha256":"a059d5389d58889ed8cb420e907319336ae40f773adc8af9cce6c1f46804b637","source":{"kind":"arxiv","id":"2305.13971","version":6},"attestation_state":"computed","paper":{"title":"Grammar-Constrained Decoding for Structured NLP Tasks without Finetuning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Martin Josifoski, Maxime Peyrard, Robert West, Saibo Geng","submitted_at":"2023-05-23T11:54:37Z","abstract_excerpt":"Despite their impressive performance, large language models (LMs) still struggle with reliably generating complex output structures when not finetuned to follow the required output format exactly. To address this issue, grammar-constrained decoding (GCD) can be used to control the generation of LMs, guaranteeing that the output follows a given structure. Most existing GCD methods are, however, limited to specific tasks, such as parsing or code generation. In this work, we demonstrate that formal grammars can describe the output space for a much wider range of tasks and argue that GCD can serve"},"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":"2305.13971","kind":"arxiv","version":6},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-23T11:54:37Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"2e8982282da2a2d1d0d1e590193ec10d73579647246f2b75948bbd30933e8421","abstract_canon_sha256":"f30882d514ebab80b3aebd773039955174f2e19b4a7e331abdcf78188fe5183c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:34:48.286542Z","signature_b64":"lmh+Mjyq8XlakIn8sW6w/cuKYNKN6wtmxTteJfj9bMgpMSuRyOdtz2rKAWq3vTCVegtIzhUoJwgD+tBYEV5gBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a059d5389d58889ed8cb420e907319336ae40f773adc8af9cce6c1f46804b637","last_reissued_at":"2026-07-05T07:34:48.286077Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:34:48.286077Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Grammar-Constrained Decoding for Structured NLP Tasks without Finetuning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Martin Josifoski, Maxime Peyrard, Robert West, Saibo Geng","submitted_at":"2023-05-23T11:54:37Z","abstract_excerpt":"Despite their impressive performance, large language models (LMs) still struggle with reliably generating complex output structures when not finetuned to follow the required output format exactly. To address this issue, grammar-constrained decoding (GCD) can be used to control the generation of LMs, guaranteeing that the output follows a given structure. Most existing GCD methods are, however, limited to specific tasks, such as parsing or code generation. In this work, we demonstrate that formal grammars can describe the output space for a much wider range of tasks and argue that GCD can serve"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.13971","kind":"arxiv","version":6},"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/2305.13971/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":"2305.13971","created_at":"2026-07-05T07:34:48.286134+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.13971v6","created_at":"2026-07-05T07:34:48.286134+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.13971","created_at":"2026-07-05T07:34:48.286134+00:00"},{"alias_kind":"pith_short_12","alias_value":"UBM5KOE5LCEJ","created_at":"2026-07-05T07:34:48.286134+00:00"},{"alias_kind":"pith_short_16","alias_value":"UBM5KOE5LCEJ5WGL","created_at":"2026-07-05T07:34:48.286134+00:00"},{"alias_kind":"pith_short_8","alias_value":"UBM5KOE5","created_at":"2026-07-05T07:34:48.286134+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":10,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.22586","citing_title":"Text2DSL: LLM-Based Code Generation for Domain-Specific Languages","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2606.09603","citing_title":"Automated IEP Generation from Traditional Chinese Parent-Teacher Interviews via Corpus-Grounded Feature Diffusion","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2607.00527","citing_title":"AI Native Games: A Survey and Roadmap","ref_index":58,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31808","citing_title":"Large Databases Need Small, Open-Weight Language Models","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2606.20608","citing_title":"CourseBlueprint: A Structured Pipeline for Adaptive Pedagogical Video Generation Grounded in Course Corpora","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2605.28328","citing_title":"Learning the Error Patterns of Language Models","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17528","citing_title":"CasualSynth: Generating Structurally Sound Synthetic Data","ref_index":9,"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":18,"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":2,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18257","citing_title":"DocQAC: Adaptive Trie-Guided Decoding for Effective In-Document Query Auto-Completion","ref_index":16,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UBM5KOE5LCEJ5WGLIIHJA4YZGN","json":"https://pith.science/pith/UBM5KOE5LCEJ5WGLIIHJA4YZGN.json","graph_json":"https://pith.science/api/pith-number/UBM5KOE5LCEJ5WGLIIHJA4YZGN/graph.json","events_json":"https://pith.science/api/pith-number/UBM5KOE5LCEJ5WGLIIHJA4YZGN/events.json","paper":"https://pith.science/paper/UBM5KOE5"},"agent_actions":{"view_html":"https://pith.science/pith/UBM5KOE5LCEJ5WGLIIHJA4YZGN","download_json":"https://pith.science/pith/UBM5KOE5LCEJ5WGLIIHJA4YZGN.json","view_paper":"https://pith.science/paper/UBM5KOE5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.13971&json=true","fetch_graph":"https://pith.science/api/pith-number/UBM5KOE5LCEJ5WGLIIHJA4YZGN/graph.json","fetch_events":"https://pith.science/api/pith-number/UBM5KOE5LCEJ5WGLIIHJA4YZGN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UBM5KOE5LCEJ5WGLIIHJA4YZGN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UBM5KOE5LCEJ5WGLIIHJA4YZGN/action/storage_attestation","attest_author":"https://pith.science/pith/UBM5KOE5LCEJ5WGLIIHJA4YZGN/action/author_attestation","sign_citation":"https://pith.science/pith/UBM5KOE5LCEJ5WGLIIHJA4YZGN/action/citation_signature","submit_replication":"https://pith.science/pith/UBM5KOE5LCEJ5WGLIIHJA4YZGN/action/replication_record"}},"created_at":"2026-07-05T07:34:48.286134+00:00","updated_at":"2026-07-05T07:34:48.286134+00:00"}