{"id":"W4319323278","doi":"10.48550/arxiv.2302.01403","title":"Self-Supervised Relation Alignment for Scene Graph Generation","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Alliance de recherche numérique du Canada; Compute Canada; Natural Sciences and Engineering Research Council of Canada; Government of Canada; Canadian Institute for Advanced Research","keywords":"Computer science; Scene graph; Graph; Message passing; Artificial intelligence; Regularization (linguistics); Machine learning; Pattern recognition (psychology); Theoretical computer science; Parallel computing","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003605912,0.0002536741,0.0002148594,0.0003104587,0.0003108324,0.0001382278,0.001155787,0.0002594691,0.00000543955],"category_scores_gemma":[0.00004191125,0.0003160287,0.0002013649,0.0005945354,0.00002745079,0.0002442739,0.0008258593,0.0003387388,0.0001370163],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002675906,"about_ca_system_score_gemma":0.0001273803,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003142148,"about_ca_topic_score_gemma":0.00002969861,"domain_scores_codex":[0.9980949,0.0001282385,0.0002267624,0.001162749,0.000111219,0.0002760993],"domain_scores_gemma":[0.9981075,0.0001349557,0.0002417811,0.001214645,0.0001802837,0.0001208199],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000006846644,0.00009224997,0.002308473,0.00007662061,0.00009059552,0.00000803045,0.0002938251,0.7377714,0.0003935334,0.2574534,0.0004365852,0.001068459],"study_design_scores_gemma":[0.0004215581,0.00003259332,0.004092544,0.00001902014,0.00006015959,6.119969e-7,0.000008995607,0.9584094,0.0001966808,0.03604287,0.0004113328,0.00030425],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09230739,0.00001414365,0.9043463,0.0005922883,0.0005436808,0.0009355586,0.000022457,0.0009809607,0.0002572479],"genre_scores_gemma":[0.9127916,0.00007122028,0.08607128,0.00006771155,0.0001660998,0.00002661692,0.000231375,0.00003055632,0.0005436206],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8204842,"threshold_uncertainty_score":0.9999292,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1117332198758273,"score_gpt":0.2218685285960819,"score_spread":0.1101353087202545,"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."}}