{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:SVTFN2E2LUPQKFNOSAI224QLI2","short_pith_number":"pith:SVTFN2E2","schema_version":"1.0","canonical_sha256":"956656e89a5d1f0515ae9011ad720b46a8eec9e2c0a539313245525fc4e9b433","source":{"kind":"arxiv","id":"2401.09967","version":4},"attestation_state":"computed","paper":{"title":"Sketch-Guided Constrained Decoding for Boosting Blackbox Large Language Models without Logit Access","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Berkay D\\\"oner, Chris Wendler, Martin Josifoski, Robert West, Saibo Geng","submitted_at":"2024-01-18T13:31:24Z","abstract_excerpt":"Constrained decoding, a technique for enforcing constraints on language model outputs, offers a way to control text generation without retraining or architectural modifications. Its application is, however, typically restricted to models that give users access to next-token distributions (usually via softmax logits), which poses a limitation with blackbox large language models (LLMs). This paper introduces sketch-guided constrained decoding (SGCD), a novel approach to constrained decoding for blackbox LLMs, which operates without access to the logits of the blackbox LLM. SGCD utilizes a locall"},"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":"2401.09967","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-18T13:31:24Z","cross_cats_sorted":[],"title_canon_sha256":"b75f069dd228c5501d6bb216f5ab9b59754e82dc5f3d3466c163ba70163b0782","abstract_canon_sha256":"8f8dc4dcd41ee2a8a478df617adf83ac2a5cfe5bb4a8b793d8fce8989bb974b4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:46:20.814407Z","signature_b64":"RSYzVju3PJsVowKq1+MHdDeCFPOR6qbT+vdhMZRkFPMMmUtFdxCk5worFIVD6IbQ4CBs52bTPx1D89Y9my6ODA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"956656e89a5d1f0515ae9011ad720b46a8eec9e2c0a539313245525fc4e9b433","last_reissued_at":"2026-07-05T08:46:20.814026Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:46:20.814026Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sketch-Guided Constrained Decoding for Boosting Blackbox Large Language Models without Logit Access","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Berkay D\\\"oner, Chris Wendler, Martin Josifoski, Robert West, Saibo Geng","submitted_at":"2024-01-18T13:31:24Z","abstract_excerpt":"Constrained decoding, a technique for enforcing constraints on language model outputs, offers a way to control text generation without retraining or architectural modifications. Its application is, however, typically restricted to models that give users access to next-token distributions (usually via softmax logits), which poses a limitation with blackbox large language models (LLMs). This paper introduces sketch-guided constrained decoding (SGCD), a novel approach to constrained decoding for blackbox LLMs, which operates without access to the logits of the blackbox LLM. SGCD utilizes a locall"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.09967","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/2401.09967/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":"2401.09967","created_at":"2026-07-05T08:46:20.814085+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.09967v4","created_at":"2026-07-05T08:46:20.814085+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.09967","created_at":"2026-07-05T08:46:20.814085+00:00"},{"alias_kind":"pith_short_12","alias_value":"SVTFN2E2LUPQ","created_at":"2026-07-05T08:46:20.814085+00:00"},{"alias_kind":"pith_short_16","alias_value":"SVTFN2E2LUPQKFNO","created_at":"2026-07-05T08:46:20.814085+00:00"},{"alias_kind":"pith_short_8","alias_value":"SVTFN2E2","created_at":"2026-07-05T08:46:20.814085+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2511.22277","citing_title":"TreeCoder: Systematic Exploration and Optimisation of Decoding and Constraints for LLM Code Generation","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21525","citing_title":"Job Skill Extraction via LLM-Centric Multi-Module Framework","ref_index":17,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SVTFN2E2LUPQKFNOSAI224QLI2","json":"https://pith.science/pith/SVTFN2E2LUPQKFNOSAI224QLI2.json","graph_json":"https://pith.science/api/pith-number/SVTFN2E2LUPQKFNOSAI224QLI2/graph.json","events_json":"https://pith.science/api/pith-number/SVTFN2E2LUPQKFNOSAI224QLI2/events.json","paper":"https://pith.science/paper/SVTFN2E2"},"agent_actions":{"view_html":"https://pith.science/pith/SVTFN2E2LUPQKFNOSAI224QLI2","download_json":"https://pith.science/pith/SVTFN2E2LUPQKFNOSAI224QLI2.json","view_paper":"https://pith.science/paper/SVTFN2E2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.09967&json=true","fetch_graph":"https://pith.science/api/pith-number/SVTFN2E2LUPQKFNOSAI224QLI2/graph.json","fetch_events":"https://pith.science/api/pith-number/SVTFN2E2LUPQKFNOSAI224QLI2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SVTFN2E2LUPQKFNOSAI224QLI2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SVTFN2E2LUPQKFNOSAI224QLI2/action/storage_attestation","attest_author":"https://pith.science/pith/SVTFN2E2LUPQKFNOSAI224QLI2/action/author_attestation","sign_citation":"https://pith.science/pith/SVTFN2E2LUPQKFNOSAI224QLI2/action/citation_signature","submit_replication":"https://pith.science/pith/SVTFN2E2LUPQKFNOSAI224QLI2/action/replication_record"}},"created_at":"2026-07-05T08:46:20.814085+00:00","updated_at":"2026-07-05T08:46:20.814085+00:00"}