{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:CKYP4DT5DOCCQTMMLDEOPXNHNS","short_pith_number":"pith:CKYP4DT5","schema_version":"1.0","canonical_sha256":"12b0fe0e7d1b84284d8c58c8e7dda76c87d9f8e2d4c90e33007d07cbb5546395","source":{"kind":"arxiv","id":"2010.12884","version":2},"attestation_state":"computed","paper":{"title":"NeuroLogic Decoding: (Un)supervised Neural Text Generation with Predicate Logic Constraints","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chandra Bhagavatula, Peter West, Ronan Le Bras, Rowan Zellers, Ximing Lu, Yejin Choi","submitted_at":"2020-10-24T11:55:22Z","abstract_excerpt":"Conditional text generation often requires lexical constraints, i.e., which words should or shouldn't be included in the output text. While the dominant recipe for conditional text generation has been large-scale pretrained language models that are finetuned on the task-specific training data, such models do not learn to follow the underlying constraints reliably, even when supervised with large amounts of task-specific examples.\n  We propose NeuroLogic Decoding, a simple yet effective algorithm that enables neural language models -- supervised or not -- to generate fluent text while satisfyin"},"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":"2010.12884","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-10-24T11:55:22Z","cross_cats_sorted":[],"title_canon_sha256":"2907741e6bd406cba3e00e285269f5004e582468ccb2ab041c164df034dfc887","abstract_canon_sha256":"d16de64872c0b6f1428a1e8f3a492c569e5a4b754f22b2f5772fe9605c7a63ba"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:33:55.420667Z","signature_b64":"+ohRekqNbDDDDvkTGjSK8qfHJZCOzzSgxVjlzs2MC6jr/Fdmiekh3Rn0Qf5Xy7wpqz58R1SaoBrMqJ+BKJxGAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"12b0fe0e7d1b84284d8c58c8e7dda76c87d9f8e2d4c90e33007d07cbb5546395","last_reissued_at":"2026-07-05T02:33:55.420158Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:33:55.420158Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"NeuroLogic Decoding: (Un)supervised Neural Text Generation with Predicate Logic Constraints","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chandra Bhagavatula, Peter West, Ronan Le Bras, Rowan Zellers, Ximing Lu, Yejin Choi","submitted_at":"2020-10-24T11:55:22Z","abstract_excerpt":"Conditional text generation often requires lexical constraints, i.e., which words should or shouldn't be included in the output text. While the dominant recipe for conditional text generation has been large-scale pretrained language models that are finetuned on the task-specific training data, such models do not learn to follow the underlying constraints reliably, even when supervised with large amounts of task-specific examples.\n  We propose NeuroLogic Decoding, a simple yet effective algorithm that enables neural language models -- supervised or not -- to generate fluent text while satisfyin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.12884","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2010.12884/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":"2010.12884","created_at":"2026-07-05T02:33:55.420237+00:00"},{"alias_kind":"arxiv_version","alias_value":"2010.12884v2","created_at":"2026-07-05T02:33:55.420237+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.12884","created_at":"2026-07-05T02:33:55.420237+00:00"},{"alias_kind":"pith_short_12","alias_value":"CKYP4DT5DOCC","created_at":"2026-07-05T02:33:55.420237+00:00"},{"alias_kind":"pith_short_16","alias_value":"CKYP4DT5DOCCQTMM","created_at":"2026-07-05T02:33:55.420237+00:00"},{"alias_kind":"pith_short_8","alias_value":"CKYP4DT5","created_at":"2026-07-05T02:33:55.420237+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2402.05070","citing_title":"A Roadmap to Pluralistic Alignment","ref_index":73,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CKYP4DT5DOCCQTMMLDEOPXNHNS","json":"https://pith.science/pith/CKYP4DT5DOCCQTMMLDEOPXNHNS.json","graph_json":"https://pith.science/api/pith-number/CKYP4DT5DOCCQTMMLDEOPXNHNS/graph.json","events_json":"https://pith.science/api/pith-number/CKYP4DT5DOCCQTMMLDEOPXNHNS/events.json","paper":"https://pith.science/paper/CKYP4DT5"},"agent_actions":{"view_html":"https://pith.science/pith/CKYP4DT5DOCCQTMMLDEOPXNHNS","download_json":"https://pith.science/pith/CKYP4DT5DOCCQTMMLDEOPXNHNS.json","view_paper":"https://pith.science/paper/CKYP4DT5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2010.12884&json=true","fetch_graph":"https://pith.science/api/pith-number/CKYP4DT5DOCCQTMMLDEOPXNHNS/graph.json","fetch_events":"https://pith.science/api/pith-number/CKYP4DT5DOCCQTMMLDEOPXNHNS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CKYP4DT5DOCCQTMMLDEOPXNHNS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CKYP4DT5DOCCQTMMLDEOPXNHNS/action/storage_attestation","attest_author":"https://pith.science/pith/CKYP4DT5DOCCQTMMLDEOPXNHNS/action/author_attestation","sign_citation":"https://pith.science/pith/CKYP4DT5DOCCQTMMLDEOPXNHNS/action/citation_signature","submit_replication":"https://pith.science/pith/CKYP4DT5DOCCQTMMLDEOPXNHNS/action/replication_record"}},"created_at":"2026-07-05T02:33:55.420237+00:00","updated_at":"2026-07-05T02:33:55.420237+00:00"}