{"id":"W4387674059","doi":"10.1145/3622869","title":"Saggitarius: A DSL for Specifying Grammatical Domains","year":2023,"lang":"en","type":"article","venue":"Proceedings of the ACM on Programming Languages","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"Advanced Research Projects Agency; Defense Advanced Research Projects Agency; U.S. Department of Defense","keywords":"Computer science; Parsing; Rule-based machine translation; Suite; Natural language processing; Programming language; Grammar; Set (abstract data type); SQL; Artificial intelligence; Domain (mathematical analysis); Digital subscriber line; Context (archaeology); Linguistics","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":[0.000697947,0.0002298935,0.0002760444,0.000228202,0.0002453081,0.0003401926,0.004463002,0.0001141521,0.00000143684],"category_scores_gemma":[0.004550767,0.0001540728,0.0002024771,0.001192271,0.0001215147,0.0003963776,0.00165425,0.0002586163,0.000009801445],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000551071,"about_ca_system_score_gemma":0.00003000569,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001080182,"about_ca_topic_score_gemma":0.000001637097,"domain_scores_codex":[0.9981419,0.000009222876,0.0003298598,0.0004650021,0.0005057474,0.0005482124],"domain_scores_gemma":[0.9983084,0.0003800961,0.0002678652,0.0007346806,0.0002329642,0.00007596433],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00004335619,0.0001567374,0.001078891,0.001216277,0.00007639259,0.00001125762,0.004121204,0.000001260897,0.0295539,0.5302874,0.009610687,0.4238427],"study_design_scores_gemma":[0.000759014,0.0004710554,0.0006406833,0.000959691,0.00005920365,0.00004324919,0.001373939,0.001151227,0.3993211,0.585948,0.008628284,0.0006445751],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.7378742,0.006553829,0.1302701,0.08024204,0.002453607,0.01207579,0.00004761967,0.02560844,0.004874403],"genre_scores_gemma":[0.2885901,0.000009475267,0.7104005,0.0002548124,0.0001293422,0.0002148611,0.000002159672,0.00003296202,0.0003658002],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5801305,"threshold_uncertainty_score":0.8293442,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02529202171333791,"score_gpt":0.3076671340194601,"score_spread":0.2823751123061222,"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."}}