{"id":"W6947728179","doi":"10.48448/wmk6-t180","title":"LAGr: Label Aligned Graphs for Better Systematic Generalization in Semantic Parsing","year":2022,"lang":"en","type":"other","venue":"Underline Science Inc.","topic":"Species Distribution and Climate Change","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University; Minnow Environmental (Canada)","funders":"","keywords":"Parsing; Generalization; Task (project management); Natural language; Meaning (existential); Representation (politics); Graph; Baseline (sea)","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0007496558,0.0002209645,0.0003164608,0.0003106187,0.0002610899,0.0001013442,0.0005709576,0.00009954655,0.05120715],"category_scores_gemma":[0.0000811569,0.0002025075,0.00005300511,0.0011904,0.0004179569,0.0001378351,0.0002510101,0.00007670091,0.0002813175],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001040383,"about_ca_system_score_gemma":0.00003547602,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004252991,"about_ca_topic_score_gemma":0.002286042,"domain_scores_codex":[0.9978608,0.00006590614,0.0003453245,0.0005663371,0.0006907032,0.0004709449],"domain_scores_gemma":[0.9992446,0.00003948172,0.0002442655,0.0003693996,0.00001258613,0.00008964037],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00002415282,0.0009548868,0.02265962,0.007473566,0.00006140893,0.0000369294,0.001175623,0.0004901351,0.02011979,0.02856273,0.9169117,0.001529413],"study_design_scores_gemma":[0.01022944,0.001059413,0.009975083,0.006841179,0.0007647086,0.0001341272,0.01544503,0.1236374,0.002150941,0.0111364,0.8112274,0.007398804],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"other","genre_gemma":"other","genre_scores_codex":[0.06557598,0.00181023,0.01348846,0.004729203,0.005032098,0.0131836,0.001414699,0.001256561,0.8935091],"genre_scores_gemma":[0.415766,0.0007672916,0.01872109,0.01862307,0.0007086384,0.003573609,0.006442786,0.001857439,0.5335401],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.3599691,"threshold_uncertainty_score":0.9496602,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02903384472066008,"score_gpt":0.276883119031344,"score_spread":0.247849274310684,"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."}}