{"id":"W4410914800","doi":"10.1007/978-3-031-93806-1_3","title":"GSTAM: Efficient Graph Distillation with Structural Attention-Matching","year":2025,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Data Stream Mining Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Distillation; Matching (statistics); Graph; Theoretical computer science; Mathematics; Chemistry; Statistics","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005265621,0.0005621386,0.0004710822,0.001154827,0.000371969,0.0008146457,0.003290082,0.0002235615,0.000008147354],"category_scores_gemma":[0.00005633214,0.000460574,0.0001067709,0.0009359741,0.0005935805,0.0005371576,0.001582611,0.0006758118,0.000007937079],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003204508,"about_ca_system_score_gemma":0.0004440723,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000587811,"about_ca_topic_score_gemma":0.00008512458,"domain_scores_codex":[0.9961538,0.00003388018,0.0004797967,0.001672696,0.001082853,0.0005770019],"domain_scores_gemma":[0.9971673,0.0003791299,0.0003428993,0.001733637,0.000256313,0.000120741],"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":[0.00001246992,0.00002105359,0.0003379207,0.00008806335,0.00002725788,0.000106868,0.0006752618,0.05826368,0.00009353506,0.1217482,0.00006001085,0.8185657],"study_design_scores_gemma":[0.0003381958,0.0002677037,0.001618914,0.001972748,0.00002619633,0.000123402,4.136974e-7,0.6810263,0.0005927971,0.3124098,0.0003995765,0.001223879],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0008677141,0.0001042051,0.9937612,0.0003512828,0.000902041,0.0004338967,0.00002265293,0.0005070982,0.003049946],"genre_scores_gemma":[0.3231968,0.000007389253,0.6761407,0.0002768673,0.0001229955,0.000008812861,0.00002951776,0.00002337308,0.0001934916],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8173418,"threshold_uncertainty_score":0.9997846,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008323788612343046,"score_gpt":0.2417154149636319,"score_spread":0.2333916263512889,"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."}}