{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:3BA5KQRQ273X5W6CFOAWPAYF33","short_pith_number":"pith:3BA5KQRQ","schema_version":"1.0","canonical_sha256":"d841d54230d7f77edbc22b81678305dec5b2929fc0672cd48765765be65bf1e7","source":{"kind":"arxiv","id":"2508.10111","version":1},"attestation_state":"computed","paper":{"title":"Constrained Decoding of Diffusion LLMs with Context-Free Grammars","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.FL","cs.PL","cs.SE"],"primary_cat":"cs.LG","authors_text":"Jasper Dekoninck, Martin Vechev, Niels M\\\"undler","submitted_at":"2025-08-13T18:09:09Z","abstract_excerpt":"Large language models (LLMs) have shown promising performance across diverse domains. Many practical applications of LLMs, such as code completion and structured data extraction, require adherence to syntactic constraints specified by a formal language. Yet, due to their probabilistic nature, LLM output is not guaranteed to adhere to such formal languages. Prior work has proposed constrained decoding as a means to restrict LLM generation to particular formal languages. However, existing works are not applicable to the emerging paradigm of diffusion LLMs, when used in practical scenarios such a"},"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":"2508.10111","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-08-13T18:09:09Z","cross_cats_sorted":["cs.FL","cs.PL","cs.SE"],"title_canon_sha256":"562f904d7b925df61a9503b86cccb072a0c29019ffa6f9ac44da638b8ef57499","abstract_canon_sha256":"a53f4427a3049e0018b63fd4493bbacc82fb6341623a730ae0ce63f0afd64e77"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:54:32.119981Z","signature_b64":"cONZX8hOFWlPCy6kHHmaHHfqflSWxgqAHF4453eYKvkKDtWA0lHHb4z66yo2ke6U+3qwpB256DVAOvWh5OetCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d841d54230d7f77edbc22b81678305dec5b2929fc0672cd48765765be65bf1e7","last_reissued_at":"2026-07-05T11:54:32.119531Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:54:32.119531Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Constrained Decoding of Diffusion LLMs with Context-Free Grammars","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.FL","cs.PL","cs.SE"],"primary_cat":"cs.LG","authors_text":"Jasper Dekoninck, Martin Vechev, Niels M\\\"undler","submitted_at":"2025-08-13T18:09:09Z","abstract_excerpt":"Large language models (LLMs) have shown promising performance across diverse domains. Many practical applications of LLMs, such as code completion and structured data extraction, require adherence to syntactic constraints specified by a formal language. Yet, due to their probabilistic nature, LLM output is not guaranteed to adhere to such formal languages. Prior work has proposed constrained decoding as a means to restrict LLM generation to particular formal languages. However, existing works are not applicable to the emerging paradigm of diffusion LLMs, when used in practical scenarios such a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.10111","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/2508.10111/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":"2508.10111","created_at":"2026-07-05T11:54:32.119586+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.10111v1","created_at":"2026-07-05T11:54:32.119586+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.10111","created_at":"2026-07-05T11:54:32.119586+00:00"},{"alias_kind":"pith_short_12","alias_value":"3BA5KQRQ273X","created_at":"2026-07-05T11:54:32.119586+00:00"},{"alias_kind":"pith_short_16","alias_value":"3BA5KQRQ273X5W6C","created_at":"2026-07-05T11:54:32.119586+00:00"},{"alias_kind":"pith_short_8","alias_value":"3BA5KQRQ","created_at":"2026-07-05T11:54:32.119586+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.21619","citing_title":"The Alignment Problem in Constrained Code Generation","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16829","citing_title":"Constrained Code Generation with Discrete Diffusion","ref_index":20,"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":14,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3BA5KQRQ273X5W6CFOAWPAYF33","json":"https://pith.science/pith/3BA5KQRQ273X5W6CFOAWPAYF33.json","graph_json":"https://pith.science/api/pith-number/3BA5KQRQ273X5W6CFOAWPAYF33/graph.json","events_json":"https://pith.science/api/pith-number/3BA5KQRQ273X5W6CFOAWPAYF33/events.json","paper":"https://pith.science/paper/3BA5KQRQ"},"agent_actions":{"view_html":"https://pith.science/pith/3BA5KQRQ273X5W6CFOAWPAYF33","download_json":"https://pith.science/pith/3BA5KQRQ273X5W6CFOAWPAYF33.json","view_paper":"https://pith.science/paper/3BA5KQRQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.10111&json=true","fetch_graph":"https://pith.science/api/pith-number/3BA5KQRQ273X5W6CFOAWPAYF33/graph.json","fetch_events":"https://pith.science/api/pith-number/3BA5KQRQ273X5W6CFOAWPAYF33/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3BA5KQRQ273X5W6CFOAWPAYF33/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3BA5KQRQ273X5W6CFOAWPAYF33/action/storage_attestation","attest_author":"https://pith.science/pith/3BA5KQRQ273X5W6CFOAWPAYF33/action/author_attestation","sign_citation":"https://pith.science/pith/3BA5KQRQ273X5W6CFOAWPAYF33/action/citation_signature","submit_replication":"https://pith.science/pith/3BA5KQRQ273X5W6CFOAWPAYF33/action/replication_record"}},"created_at":"2026-07-05T11:54:32.119586+00:00","updated_at":"2026-07-05T11:54:32.119586+00:00"}