{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:GDJ2ZGJUUFPVYJ3ZN57ZHNNCCD","short_pith_number":"pith:GDJ2ZGJU","schema_version":"1.0","canonical_sha256":"30d3ac9934a15f5c27796f7f93b5a210fa9f9a5bf47853cbc3b11698043b57e9","source":{"kind":"arxiv","id":"2305.07766","version":2},"attestation_state":"computed","paper":{"title":"NL2TL: Transforming Natural Languages to Temporal Logics using Large Language Models","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chuchu Fan, Rujul Gandhi, Yang Zhang, Yongchao Chen","submitted_at":"2023-05-12T21:22:08Z","abstract_excerpt":"Temporal Logic (TL) can be used to rigorously specify complex high-level specification for systems in many engineering applications. The translation between natural language (NL) and TL has been under-explored due to the lack of dataset and generalizable model across different application domains. In this paper, we propose an accurate and generalizable transformation framework of English instructions from NL to TL, exploring the use of Large Language Models (LLMs) at multiple stages. Our contributions are twofold. First, we develop a framework to create a dataset of NL-TL pairs combining LLMs "},"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":"2305.07766","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-12T21:22:08Z","cross_cats_sorted":[],"title_canon_sha256":"6f3e2688288dbf93074592395cba13d6a0d119c5dcdf91c0f11c2163fa0c5dc7","abstract_canon_sha256":"040e78b04a1d92d7a1a5a5d180a64a0a330d68e546f7017a65483cbafc1fa59e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:59:15.047447Z","signature_b64":"sfPijWjwfdGRPUNjB0JGcvjyoqzhB/RLTAVQBjcfEnomCZFadswooBBkBXrr4ksOSVNz22odiJ03zfn66DTKDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"30d3ac9934a15f5c27796f7f93b5a210fa9f9a5bf47853cbc3b11698043b57e9","last_reissued_at":"2026-07-05T07:59:15.046835Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:59:15.046835Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"NL2TL: Transforming Natural Languages to Temporal Logics using Large Language Models","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chuchu Fan, Rujul Gandhi, Yang Zhang, Yongchao Chen","submitted_at":"2023-05-12T21:22:08Z","abstract_excerpt":"Temporal Logic (TL) can be used to rigorously specify complex high-level specification for systems in many engineering applications. The translation between natural language (NL) and TL has been under-explored due to the lack of dataset and generalizable model across different application domains. In this paper, we propose an accurate and generalizable transformation framework of English instructions from NL to TL, exploring the use of Large Language Models (LLMs) at multiple stages. Our contributions are twofold. First, we develop a framework to create a dataset of NL-TL pairs combining LLMs "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.07766","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/2305.07766/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":"2305.07766","created_at":"2026-07-05T07:59:15.046901+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.07766v2","created_at":"2026-07-05T07:59:15.046901+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.07766","created_at":"2026-07-05T07:59:15.046901+00:00"},{"alias_kind":"pith_short_12","alias_value":"GDJ2ZGJUUFPV","created_at":"2026-07-05T07:59:15.046901+00:00"},{"alias_kind":"pith_short_16","alias_value":"GDJ2ZGJUUFPVYJ3Z","created_at":"2026-07-05T07:59:15.046901+00:00"},{"alias_kind":"pith_short_8","alias_value":"GDJ2ZGJU","created_at":"2026-07-05T07:59:15.046901+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.22874","citing_title":"NeuroNL2LTL: A Neurosymbolic Framework for Natural Language Translation of Linear Temporal Logic","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12651","citing_title":"Runtime Monitoring of Perception-Based Autonomous Systems via Embedding Temporal Logic","ref_index":93,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12651","citing_title":"Runtime Monitoring of Perception-Based Autonomous Systems via Embedding Temporal Logic","ref_index":93,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GDJ2ZGJUUFPVYJ3ZN57ZHNNCCD","json":"https://pith.science/pith/GDJ2ZGJUUFPVYJ3ZN57ZHNNCCD.json","graph_json":"https://pith.science/api/pith-number/GDJ2ZGJUUFPVYJ3ZN57ZHNNCCD/graph.json","events_json":"https://pith.science/api/pith-number/GDJ2ZGJUUFPVYJ3ZN57ZHNNCCD/events.json","paper":"https://pith.science/paper/GDJ2ZGJU"},"agent_actions":{"view_html":"https://pith.science/pith/GDJ2ZGJUUFPVYJ3ZN57ZHNNCCD","download_json":"https://pith.science/pith/GDJ2ZGJUUFPVYJ3ZN57ZHNNCCD.json","view_paper":"https://pith.science/paper/GDJ2ZGJU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.07766&json=true","fetch_graph":"https://pith.science/api/pith-number/GDJ2ZGJUUFPVYJ3ZN57ZHNNCCD/graph.json","fetch_events":"https://pith.science/api/pith-number/GDJ2ZGJUUFPVYJ3ZN57ZHNNCCD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GDJ2ZGJUUFPVYJ3ZN57ZHNNCCD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GDJ2ZGJUUFPVYJ3ZN57ZHNNCCD/action/storage_attestation","attest_author":"https://pith.science/pith/GDJ2ZGJUUFPVYJ3ZN57ZHNNCCD/action/author_attestation","sign_citation":"https://pith.science/pith/GDJ2ZGJUUFPVYJ3ZN57ZHNNCCD/action/citation_signature","submit_replication":"https://pith.science/pith/GDJ2ZGJUUFPVYJ3ZN57ZHNNCCD/action/replication_record"}},"created_at":"2026-07-05T07:59:15.046901+00:00","updated_at":"2026-07-05T07:59:15.046901+00:00"}