{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:P5WH7LLJ43ZFVX6ZPJJPYFR6ML","short_pith_number":"pith:P5WH7LLJ","schema_version":"1.0","canonical_sha256":"7f6c7fad69e6f25adfd97a52fc163e62e43b3e24d01755b77a6bc85f8f2e0ac4","source":{"kind":"arxiv","id":"1704.07138","version":2},"attestation_state":"computed","paper":{"title":"Lexically Constrained Decoding for Sequence Generation Using Grid Beam Search","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chris Hokamp, Qun Liu","submitted_at":"2017-04-24T10:55:20Z","abstract_excerpt":"We present Grid Beam Search (GBS), an algorithm which extends beam search to allow the inclusion of pre-specified lexical constraints. The algorithm can be used with any model that generates a sequence $ \\mathbf{\\hat{y}} = \\{y_{0}\\ldots y_{T}\\} $, by maximizing $ p(\\mathbf{y} | \\mathbf{x}) = \\prod\\limits_{t}p(y_{t} | \\mathbf{x}; \\{y_{0} \\ldots y_{t-1}\\}) $. Lexical constraints take the form of phrases or words that must be present in the output sequence. This is a very general way to incorporate additional knowledge into a model's output without requiring any modification of the model paramete"},"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":"1704.07138","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-04-24T10:55:20Z","cross_cats_sorted":[],"title_canon_sha256":"9b80c95c0200e1dec3a4a5b04a10e72ac9739436bdf2173e8582f29c745b5277","abstract_canon_sha256":"6ed4daae7f7cfdf1a2bd95c9a170231a5ec0dc6962057fda619a6b183a13978f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:45:10.512996Z","signature_b64":"XAgDH3XAYIB0Z/sQVNJY4/bKX2VivgjyUHiu4gXTVgnMVEGMBxAGKJaJ7NRVXDr7uOdKIs+2irRbN0rJV2lwAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7f6c7fad69e6f25adfd97a52fc163e62e43b3e24d01755b77a6bc85f8f2e0ac4","last_reissued_at":"2026-05-18T00:45:10.512374Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:45:10.512374Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Lexically Constrained Decoding for Sequence Generation Using Grid Beam Search","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chris Hokamp, Qun Liu","submitted_at":"2017-04-24T10:55:20Z","abstract_excerpt":"We present Grid Beam Search (GBS), an algorithm which extends beam search to allow the inclusion of pre-specified lexical constraints. The algorithm can be used with any model that generates a sequence $ \\mathbf{\\hat{y}} = \\{y_{0}\\ldots y_{T}\\} $, by maximizing $ p(\\mathbf{y} | \\mathbf{x}) = \\prod\\limits_{t}p(y_{t} | \\mathbf{x}; \\{y_{0} \\ldots y_{t-1}\\}) $. Lexical constraints take the form of phrases or words that must be present in the output sequence. This is a very general way to incorporate additional knowledge into a model's output without requiring any modification of the model paramete"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1704.07138","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1704.07138","created_at":"2026-05-18T00:45:10.512493+00:00"},{"alias_kind":"arxiv_version","alias_value":"1704.07138v2","created_at":"2026-05-18T00:45:10.512493+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1704.07138","created_at":"2026-05-18T00:45:10.512493+00:00"},{"alias_kind":"pith_short_12","alias_value":"P5WH7LLJ43ZF","created_at":"2026-05-18T12:31:37.085036+00:00"},{"alias_kind":"pith_short_16","alias_value":"P5WH7LLJ43ZFVX6Z","created_at":"2026-05-18T12:31:37.085036+00:00"},{"alias_kind":"pith_short_8","alias_value":"P5WH7LLJ","created_at":"2026-05-18T12:31:37.085036+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":3,"sample":[{"citing_arxiv_id":"2511.10292","citing_title":"Adaptive Residual-Update Steering for Low-Overhead Hallucination Mitigation in Large Vision Language Models","ref_index":5,"is_internal_anchor":true},{"citing_arxiv_id":"2605.19940","citing_title":"Robotics-Inspired Guardrails for Foundation Models in Socially Sensitive Domains","ref_index":17,"is_internal_anchor":true},{"citing_arxiv_id":"2509.08461","citing_title":"Adapting Vision-Language Models for Neutrino Event Classification in High-Energy Physics","ref_index":29,"is_internal_anchor":true},{"citing_arxiv_id":"2604.18257","citing_title":"DocQAC: Adaptive Trie-Guided Decoding for Effective In-Document Query Auto-Completion","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07096","citing_title":"Query-efficient model evaluation using cached responses","ref_index":127,"is_internal_anchor":false},{"citing_arxiv_id":"2604.20117","citing_title":"To Know is to Construct: Schema-Constrained Generation for Agent Memory","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/P5WH7LLJ43ZFVX6ZPJJPYFR6ML","json":"https://pith.science/pith/P5WH7LLJ43ZFVX6ZPJJPYFR6ML.json","graph_json":"https://pith.science/api/pith-number/P5WH7LLJ43ZFVX6ZPJJPYFR6ML/graph.json","events_json":"https://pith.science/api/pith-number/P5WH7LLJ43ZFVX6ZPJJPYFR6ML/events.json","paper":"https://pith.science/paper/P5WH7LLJ"},"agent_actions":{"view_html":"https://pith.science/pith/P5WH7LLJ43ZFVX6ZPJJPYFR6ML","download_json":"https://pith.science/pith/P5WH7LLJ43ZFVX6ZPJJPYFR6ML.json","view_paper":"https://pith.science/paper/P5WH7LLJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1704.07138&json=true","fetch_graph":"https://pith.science/api/pith-number/P5WH7LLJ43ZFVX6ZPJJPYFR6ML/graph.json","fetch_events":"https://pith.science/api/pith-number/P5WH7LLJ43ZFVX6ZPJJPYFR6ML/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/P5WH7LLJ43ZFVX6ZPJJPYFR6ML/action/timestamp_anchor","attest_storage":"https://pith.science/pith/P5WH7LLJ43ZFVX6ZPJJPYFR6ML/action/storage_attestation","attest_author":"https://pith.science/pith/P5WH7LLJ43ZFVX6ZPJJPYFR6ML/action/author_attestation","sign_citation":"https://pith.science/pith/P5WH7LLJ43ZFVX6ZPJJPYFR6ML/action/citation_signature","submit_replication":"https://pith.science/pith/P5WH7LLJ43ZFVX6ZPJJPYFR6ML/action/replication_record"}},"created_at":"2026-05-18T00:45:10.512493+00:00","updated_at":"2026-05-18T00:45:10.512493+00:00"}