{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:CKYP4DT5DOCCQTMMLDEOPXNHNS","short_pith_number":"pith:CKYP4DT5","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"},"canonical_sha256":"12b0fe0e7d1b84284d8c58c8e7dda76c87d9f8e2d4c90e33007d07cbb5546395","source":{"kind":"arxiv","id":"2010.12884","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2010.12884","created_at":"2026-07-05T02:33:55Z"},{"alias_kind":"arxiv_version","alias_value":"2010.12884v2","created_at":"2026-07-05T02:33:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.12884","created_at":"2026-07-05T02:33:55Z"},{"alias_kind":"pith_short_12","alias_value":"CKYP4DT5DOCC","created_at":"2026-07-05T02:33:55Z"},{"alias_kind":"pith_short_16","alias_value":"CKYP4DT5DOCCQTMM","created_at":"2026-07-05T02:33:55Z"},{"alias_kind":"pith_short_8","alias_value":"CKYP4DT5","created_at":"2026-07-05T02:33:55Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:CKYP4DT5DOCCQTMMLDEOPXNHNS","target":"record","payload":{"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"},"canonical_sha256":"12b0fe0e7d1b84284d8c58c8e7dda76c87d9f8e2d4c90e33007d07cbb5546395","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"},"source_kind":"arxiv","source_id":"2010.12884","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:33:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+PuERYFgyZNpK4brwdLAsKyDAp3S9io3nOxjRlRDOlOLbXLTZlVuuiJhq+fpBkSgMZM7L6W+ezSLNd+xKpbTBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-21T13:49:51.827173Z"},"content_sha256":"08355126b8ee8a53eaa41a0a813b19e304b27aba062460e073debaaec1792741","schema_version":"1.0","event_id":"sha256:08355126b8ee8a53eaa41a0a813b19e304b27aba062460e073debaaec1792741"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:CKYP4DT5DOCCQTMMLDEOPXNHNS","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:33:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"c2hryd/iZsY9l+D2CaN7X2n95jf6Xwt2R8HOR2fPzweg819mkz23xXNlXR2qAsc0Bw6Nfn9MtTQQGraHXzfTCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-21T13:49:51.827566Z"},"content_sha256":"1b5f487119b0c9a6858b4f49b37ddedda088b50633fb056c1e0080308e5f9be5","schema_version":"1.0","event_id":"sha256:1b5f487119b0c9a6858b4f49b37ddedda088b50633fb056c1e0080308e5f9be5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CKYP4DT5DOCCQTMMLDEOPXNHNS/bundle.json","state_url":"https://pith.science/pith/CKYP4DT5DOCCQTMMLDEOPXNHNS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CKYP4DT5DOCCQTMMLDEOPXNHNS/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-21T13:49:51Z","links":{"resolver":"https://pith.science/pith/CKYP4DT5DOCCQTMMLDEOPXNHNS","bundle":"https://pith.science/pith/CKYP4DT5DOCCQTMMLDEOPXNHNS/bundle.json","state":"https://pith.science/pith/CKYP4DT5DOCCQTMMLDEOPXNHNS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CKYP4DT5DOCCQTMMLDEOPXNHNS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:CKYP4DT5DOCCQTMMLDEOPXNHNS","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"d16de64872c0b6f1428a1e8f3a492c569e5a4b754f22b2f5772fe9605c7a63ba","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-10-24T11:55:22Z","title_canon_sha256":"2907741e6bd406cba3e00e285269f5004e582468ccb2ab041c164df034dfc887"},"schema_version":"1.0","source":{"id":"2010.12884","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2010.12884","created_at":"2026-07-05T02:33:55Z"},{"alias_kind":"arxiv_version","alias_value":"2010.12884v2","created_at":"2026-07-05T02:33:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.12884","created_at":"2026-07-05T02:33:55Z"},{"alias_kind":"pith_short_12","alias_value":"CKYP4DT5DOCC","created_at":"2026-07-05T02:33:55Z"},{"alias_kind":"pith_short_16","alias_value":"CKYP4DT5DOCCQTMM","created_at":"2026-07-05T02:33:55Z"},{"alias_kind":"pith_short_8","alias_value":"CKYP4DT5","created_at":"2026-07-05T02:33:55Z"}],"graph_snapshots":[{"event_id":"sha256:1b5f487119b0c9a6858b4f49b37ddedda088b50633fb056c1e0080308e5f9be5","target":"graph","created_at":"2026-07-05T02:33:55Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2010.12884/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Chandra Bhagavatula, Peter West, Ronan Le Bras, Rowan Zellers, Ximing Lu, Yejin Choi","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-10-24T11:55:22Z","title":"NeuroLogic Decoding: (Un)supervised Neural Text Generation with Predicate Logic Constraints"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.12884","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:08355126b8ee8a53eaa41a0a813b19e304b27aba062460e073debaaec1792741","target":"record","created_at":"2026-07-05T02:33:55Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"d16de64872c0b6f1428a1e8f3a492c569e5a4b754f22b2f5772fe9605c7a63ba","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-10-24T11:55:22Z","title_canon_sha256":"2907741e6bd406cba3e00e285269f5004e582468ccb2ab041c164df034dfc887"},"schema_version":"1.0","source":{"id":"2010.12884","kind":"arxiv","version":2}},"canonical_sha256":"12b0fe0e7d1b84284d8c58c8e7dda76c87d9f8e2d4c90e33007d07cbb5546395","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"12b0fe0e7d1b84284d8c58c8e7dda76c87d9f8e2d4c90e33007d07cbb5546395","first_computed_at":"2026-07-05T02:33:55.420158Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:33:55.420158Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+ohRekqNbDDDDvkTGjSK8qfHJZCOzzSgxVjlzs2MC6jr/Fdmiekh3Rn0Qf5Xy7wpqz58R1SaoBrMqJ+BKJxGAA==","signature_status":"signed_v1","signed_at":"2026-07-05T02:33:55.420667Z","signed_message":"canonical_sha256_bytes"},"source_id":"2010.12884","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:08355126b8ee8a53eaa41a0a813b19e304b27aba062460e073debaaec1792741","sha256:1b5f487119b0c9a6858b4f49b37ddedda088b50633fb056c1e0080308e5f9be5"],"state_sha256":"4c1959d98d253792b885ec3fcaacdb4f7777faafc4d1c3b28e255969ad432419"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oE1iWR6vIMK7+ONJLbj01f9ynQdu0eJ0eQtlUClMfzwRGSNqDK+l0uNAe3CLTatDFbLoUkk5bFfMjdGcdfNAAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-21T13:49:51.829734Z","bundle_sha256":"cba3fb09387d585826e2e2f1c1828d865c57aac98708b208712e7d2f8a73defd"}}