{"id":"W2756654724","doi":"10.18653/v1/d17-1202","title":"Shortest-Path Graph Kernels for Document Similarity","year":2017,"lang":"en","type":"article","venue":"","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":54,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Computer science; Graph; Similarity measure; Shortest path problem; Kernel (algebra); Similarity (geometry); Macro; Data mining; Artificial intelligence; Pattern recognition (psychology); Theoretical computer science; Mathematics; Combinatorics","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":[],"consensus_categories":[],"category_scores_codex":[0.0002238975,0.0001036372,0.0001110135,0.00005803631,0.0004940039,0.0007744386,0.002076445,0.00006679186,0.00002947793],"category_scores_gemma":[0.0001327217,0.00008333742,0.00007942157,0.00005100374,0.00009181792,0.000915802,0.0004165021,0.00006124202,0.000034901],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002140419,"about_ca_system_score_gemma":0.00002758143,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002816525,"about_ca_topic_score_gemma":0.00001274392,"domain_scores_codex":[0.9991156,0.000007190845,0.0001552489,0.0003415322,0.0001575201,0.0002229247],"domain_scores_gemma":[0.9981591,0.00005249089,0.000124061,0.00154578,0.00006826867,0.0000503162],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000001846973,0.0000342465,0.003814014,0.000003478748,0.000009293375,0.000001038372,0.0000364016,0.000002112572,0.0003291697,0.9292241,0.01117301,0.05537129],"study_design_scores_gemma":[0.0006619311,0.0001654583,0.05026225,0.00001153613,0.000009831933,0.000002831657,0.00006159761,0.007502892,0.03850405,0.8436001,0.05881664,0.0004008877],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005608544,0.00003536202,0.9712582,0.01189723,0.0003429043,0.0003420626,0.000002663062,0.0007905407,0.009722557],"genre_scores_gemma":[0.9089508,0.0000350353,0.0879635,0.0002577048,0.00002412913,0.00009648561,0.000001591227,0.000004399402,0.002666323],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9033423,"threshold_uncertainty_score":0.7467929,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04094903064209897,"score_gpt":0.3136976083326138,"score_spread":0.2727485776905149,"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."}}