{"id":"W4382463985","doi":"10.1609/aaai.v37i13.27068","title":"NL2LTL – a Python Package for Converting Natural Language (NL) Instructions to Linear Temporal Logic (LTL) Formulas","year":2023,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":37,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"","keywords":"Computer science; Programming language; Python (programming language); Natural language; IBM; Linear temporal logic; Temporal logic; Extensibility; Natural language processing","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006787507,0.0002909862,0.0003236059,0.0003396316,0.0003669573,0.0002624992,0.002339628,0.0001307918,0.00001249482],"category_scores_gemma":[0.001573703,0.0002162429,0.0001807479,0.001740922,0.0001555999,0.0006009995,0.0007159503,0.0004117416,0.00008113742],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007653882,"about_ca_system_score_gemma":0.0001038919,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006411693,"about_ca_topic_score_gemma":0.00002942349,"domain_scores_codex":[0.9977181,0.00001682506,0.0005910288,0.0006344651,0.0004800119,0.0005595614],"domain_scores_gemma":[0.998206,0.0001518892,0.0003800681,0.0003945746,0.0007479572,0.0001195509],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00008312042,0.0000563453,0.00009166705,0.0001283129,0.00001647517,0.000002387407,0.003923857,0.00001223075,0.2565642,0.6343434,0.0006321127,0.1041458],"study_design_scores_gemma":[0.00003688256,0.0001984323,0.00002626727,0.0002463881,0.000009505152,0.000008718062,0.0009004323,0.05526827,0.763418,0.1794708,0.0001393381,0.0002769141],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5477901,0.0003039723,0.4145628,0.02393449,0.003448679,0.003935756,0.00007113893,0.003998907,0.001954212],"genre_scores_gemma":[0.9046772,0.000006851552,0.09404843,0.0005014947,0.0001303997,0.000106441,0.000003757458,0.00002517693,0.0005002993],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5068538,"threshold_uncertainty_score":0.881813,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0672773486059246,"score_gpt":0.3422182075960282,"score_spread":0.2749408589901036,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}