{"id":"W4289711940","doi":"10.7717/peerj-cs.1066","title":"Causal graph extraction from news: a comparative study of time-series causality learning techniques","year":2022,"lang":"en","type":"article","venue":"PeerJ Computer Science","topic":"Topic Modeling","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"Agencia Nacional de Promoción Científica y Tecnológica; Universidad Nacional del Sur; Consejo Nacional de Investigaciones Científicas y Técnicas; Compute Canada","keywords":"Causal structure; Computer science; Causality (physics); Machine learning; Graph; Artificial intelligence; Time series; Causal inference; Event (particle physics); Natural language processing; Theoretical computer science; Data mining; Information retrieval; Data science; Econometrics; Mathematics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.001215742,0.0001828345,0.0003264239,0.0003200333,0.0008556932,0.0002488465,0.001987604,0.00002367577,0.00003042434],"category_scores_gemma":[0.00002387524,0.0001870976,0.00005428075,0.001418283,0.0002095309,0.001427931,0.001999939,0.0004008009,0.000007080579],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001347416,"about_ca_system_score_gemma":0.0001946733,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001821831,"about_ca_topic_score_gemma":0.00007398872,"domain_scores_codex":[0.9967501,0.0003640691,0.0004243195,0.0009121704,0.001209768,0.0003396173],"domain_scores_gemma":[0.9984453,0.0001486454,0.0002926099,0.0008167594,0.0001955735,0.0001011568],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001796054,0.004914843,0.08138537,0.00004699116,0.0002196651,0.0002333308,0.2007128,0.36122,0.1102791,0.02150598,0.001605619,0.2176966],"study_design_scores_gemma":[0.0005372689,0.002102281,0.02107839,0.00002141076,0.00001868482,0.00005560193,0.002088786,0.9511283,0.01599785,0.005151666,0.001234877,0.0005849035],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4421037,0.00001834866,0.5567247,0.0001656482,0.0003793428,0.0002350289,0.000002321354,0.0002399802,0.0001310193],"genre_scores_gemma":[0.8324881,0.000001365933,0.1672665,0.0000552774,0.00007133409,0.00004294981,0.000002093275,0.000005166454,0.00006727073],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5899082,"threshold_uncertainty_score":0.7629619,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04088231282822022,"score_gpt":0.3120596989749664,"score_spread":0.2711773861467461,"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."}}