{"id":"W4281560036","doi":"10.1139/cjfr-2022-0077","title":"Towards sustainable North American wood product value chains, part 2: computer vision identification of ring-porous hardwoods","year":2022,"lang":"en","type":"article","venue":"Canadian Journal of Forest Research","topic":"Wood and Agarwood Research","field":"Chemistry","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"U.S. Department of Agriculture; U.S. Department of State","keywords":"Hardwood; Artificial intelligence; Identification (biology); Softwood; Machine learning; Porosity; Computer science; Pulp and paper industry; Wood industry; Environmental science; Agricultural engineering; Pattern recognition (psychology); Materials science; Engineering; Botany; Composite material; Forestry; Geography; Biology","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003805957,0.000173177,0.0003913218,0.00104038,0.0009236616,0.0002105751,0.001292346,0.00004134272,0.0004765199],"category_scores_gemma":[0.0005287788,0.0001656393,0.0001603086,0.00155824,0.0005571306,0.0002314882,0.0002789878,0.001594892,0.000008846295],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001012986,"about_ca_system_score_gemma":0.005426396,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01777218,"about_ca_topic_score_gemma":0.01628766,"domain_scores_codex":[0.9954407,0.0003743679,0.0007710198,0.0003684946,0.001841573,0.00120385],"domain_scores_gemma":[0.9963555,0.0001216417,0.0004089591,0.000610908,0.001567913,0.0009350326],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.001108131,0.001591339,0.6056677,0.002855917,0.000999272,0.0108211,0.007591073,0.02988849,0.01859465,0.01061156,0.1481948,0.162076],"study_design_scores_gemma":[0.004181754,0.006735713,0.5574581,0.0005077071,0.0001148727,0.001819423,0.01686624,0.004158441,0.05986056,0.001943816,0.3448488,0.001504609],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9951679,0.0005632712,0.00003530108,0.001890646,0.0001756444,0.0002148102,0.0000885429,0.000009288086,0.00185465],"genre_scores_gemma":[0.9944124,0.00005412506,0.0001015295,0.00002036422,0.0007073449,0.00002695747,0.0000444997,0.00004264824,0.004590135],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.196654,"threshold_uncertainty_score":0.9887686,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02411249853117978,"score_gpt":0.3063111182411508,"score_spread":0.282198619709971,"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."}}