{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001366543,0.0007786215,0.00118146,0.004747808,0.0004898114,0.00159605,0.001300497,0.001106022,0.001535813],"category_scores_gemma":[0.009130389,0.0002246146,0.0007870893,0.00552367,0.0008999269,0.005089116,0.00129743,0.001277796,0.001031114],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001147037,"about_ca_system_score_gemma":0.0007558967,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001821679,"about_ca_topic_score_gemma":0.001186729,"domain_scores_codex":[0.9973346,0.0006555648,0.0002291485,0.0005704549,0.001082519,0.0001278019],"domain_scores_gemma":[0.9950593,0.002129908,0.0006528549,0.0009255527,0.001073095,0.0001593847],"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":[0.0006155827,0.0003732977,0.005890562,0.0007464065,0.0003382791,0.0002450389,0.0003933897,0.14022,0.03008263,0.07771613,0.006129683,0.737249],"study_design_scores_gemma":[0.00002306225,0.000225315,0.003655941,0.00003942317,0.00006190482,0.0005177412,0.0001285729,0.9097321,0.01122952,0.06648511,0.007823278,0.0000779541],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03325514,0.00143483,0.9622416,0.0001094651,0.00007016034,0.0000899673,0.0002652803,0.001194364,0.001339145],"genre_scores_gemma":[0.6163772,0.001070422,0.3785362,0.00008578769,0.000141903,0.0001967743,0.001258654,0.0002962133,0.002036894],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004747808,"threshold_uncertainty_score":0.008322358,"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."}}