{"id":"W4400367343","doi":"10.7717/peerj-cs.2097","title":"Knowledge enhanced bottom-up affordance grounding for robotic interaction","year":2024,"lang":"en","type":"article","venue":"PeerJ Computer Science","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Canadian Institute for Advanced Research","keywords":"Affordance; Computer science; Artificial intelligence; Ground; Natural language; Robot; Human–computer interaction; Top-down and bottom-up design; Natural language processing; Robotics; Machine learning; Programming language; Engineering","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"simulation_or_modeling","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low","status":"direct model label, unvalidated"},{"model":"gpt","categories":[],"domain":null,"study_design":"simulation_or_modeling","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"medium","status":"direct model label, unvalidated"}],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001109912,0.000215388,0.0001950844,0.0004485782,0.000579641,0.001621911,0.00218767,0.00004580387,0.000005918372],"category_scores_gemma":[0.0001051232,0.0002041474,0.0001106238,0.002054154,0.0001923891,0.002042648,0.0006069292,0.00032096,0.0002759598],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002744713,"about_ca_system_score_gemma":0.0003040761,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004427261,"about_ca_topic_score_gemma":0.000007201647,"domain_scores_codex":[0.997497,0.00004572282,0.0003043265,0.00117794,0.0004080292,0.0005670201],"domain_scores_gemma":[0.9981895,0.0004976819,0.00008395185,0.0007906862,0.0002640114,0.0001741369],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000003769448,0.00007113071,0.00004485568,0.0001206376,0.00001348373,0.000002431735,0.003048283,0.01644839,0.01964718,0.2753898,0.0009664962,0.6842435],"study_design_scores_gemma":[0.0001317748,0.00008156268,0.002073815,0.0001117784,0.000005954421,0.00003076114,0.000007435834,0.9849921,0.004756396,0.004277552,0.003281401,0.000249481],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01764677,0.0001727554,0.9720742,0.001825095,0.006318614,0.0004113003,9.1377e-7,0.0009301219,0.000620284],"genre_scores_gemma":[0.6912135,0.000003245899,0.3079115,0.0001026714,0.0003199262,0.0001092634,0.000002041724,0.00001272384,0.0003251124],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9685437,"threshold_uncertainty_score":0.9994145,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02984032551845931,"score_gpt":0.3521874768477354,"score_spread":0.3223471513292761,"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."}}