{"id":"W2220382889","doi":"10.1609/aaai.v27i2.18988","title":"Interactive Information Extraction and Navigation to Enable Effective Link Analysis and Visualization of Unstructured Text","year":2013,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Scientific Computing and Data Management","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"General Dynamics (Canada)","funders":"","keywords":"Computer science; Visualization; Key (lock); Information extraction; Information retrieval; Obstacle; Interface (matter); Unstructured data; Information visualization; Imperfect; Data mining; Human–computer interaction; Big data","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004340236,0.001078124,0.0006139872,0.00356891,0.0007330459,0.003312989,0.001246427,0.001009079,0.01342121],"category_scores_gemma":[0.01800936,0.0006649031,0.0006068132,0.002089649,0.0007008597,0.004654957,0.003234682,0.001080348,0.004829206],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003676411,"about_ca_system_score_gemma":0.001019928,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001170076,"about_ca_topic_score_gemma":0.002802828,"domain_scores_codex":[0.9979993,0.0008583748,0.0001722816,0.0003654188,0.0005385904,0.00006606847],"domain_scores_gemma":[0.9841816,0.01138027,0.0006612859,0.00192786,0.001485753,0.0003632666],"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":[0.0008131611,0.0002195737,0.003104047,0.001465195,0.0001630302,0.0009707495,0.006076366,0.00403105,0.06584598,0.02370329,0.05974726,0.8338603],"study_design_scores_gemma":[0.0003034992,0.0003771983,0.005675771,0.0006179073,0.0001929721,0.002019977,0.001639506,0.1725354,0.1016299,0.05823663,0.6563808,0.0003905099],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01370356,0.0005801299,0.9231222,0.0009118193,0.0001376777,0.0002978948,0.001579138,0.05195634,0.007711252],"genre_scores_gemma":[0.06116031,0.0003536816,0.9294986,0.0002894806,0.00009248448,0.0002552665,0.001417819,0.00199935,0.004932967],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01342121,"threshold_uncertainty_score":0.04489839,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05721025266602141,"score_gpt":0.3700182060496383,"score_spread":0.3128079533836169,"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."}}