{"id":"W4226450763","doi":"10.1609/aaai.v36i7.20700","title":"Augmentation-Free Self-Supervised Learning on Graphs","year":2022,"lang":"en","type":"preprint","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"Institute for Information and Communications Technology Promotion; Ministry of Science and ICT, South Korea; Korea Advanced Institute of Science and Technology","keywords":"Computer science; Cluster analysis; Graph; Hyperparameter; Artificial intelligence; Machine learning; Semantics (computer science); Node (physics); Theoretical computer science; Programming language","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","open_science"],"consensus_categories":[],"category_scores_codex":[0.001113706,0.0004823269,0.0004670781,0.0004201201,0.000682924,0.0007426609,0.005744295,0.000195741,0.0005468128],"category_scores_gemma":[0.0008200009,0.000424406,0.0003358121,0.0009113927,0.0001803703,0.0003221686,0.003171388,0.002084348,0.0001191557],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001785922,"about_ca_system_score_gemma":0.0002931576,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005574827,"about_ca_topic_score_gemma":0.000004707353,"domain_scores_codex":[0.9960075,0.0001166163,0.000878286,0.001108458,0.001407944,0.0004812154],"domain_scores_gemma":[0.9971364,0.0002567102,0.001029447,0.0008087517,0.000623414,0.0001453502],"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":[0.00007962727,0.0002529857,0.0002336629,0.0001125488,0.00005966499,0.000001602236,0.006936277,0.006849362,0.002122449,0.9343299,0.0003321157,0.04868986],"study_design_scores_gemma":[0.0001397587,0.0006519927,0.0004145573,0.0005482986,0.00005215394,0.000004387078,0.004139822,0.4493635,0.03717656,0.5050664,0.001542185,0.0009004212],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.4619794,0.0002429411,0.1304851,0.03295388,0.01138552,0.006248514,0.00007623433,0.003491468,0.353137],"genre_scores_gemma":[0.9846483,0.0001256064,0.01335314,0.0006235226,0.00008216927,0.0001706956,0.000006557849,0.00003969873,0.0009502355],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.522669,"threshold_uncertainty_score":0.9998208,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07924101591751169,"score_gpt":0.3003966368884876,"score_spread":0.2211556209709759,"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."}}