{"id":"W2997394441","doi":"10.1609/aaai.v34i05.6292","title":"P-SIF: Document Embeddings Using Partition Averaging","year":2020,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Topic Modeling","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Institute for Catastrophic Loss Reduction; Microsoft Research","keywords":"Computer science; Simple (philosophy); Word (group theory); Set (abstract data type); Correctness; Representation (politics); Partition (number theory); Natural language processing; Artificial intelligence; Algorithm; Pattern recognition (psychology); Mathematics; Combinatorics","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":[],"consensus_categories":[],"category_scores_codex":[0.0003524292,0.0002090858,0.0002369916,0.00007216707,0.0002077481,0.0003541128,0.001665908,0.00006677601,0.00006620182],"category_scores_gemma":[0.0002596628,0.0001714472,0.0001151447,0.000557971,0.0001100357,0.0006995485,0.000536228,0.0002851018,0.00007109181],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007270229,"about_ca_system_score_gemma":0.00009412756,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004616785,"about_ca_topic_score_gemma":0.000001584419,"domain_scores_codex":[0.9979612,0.00001603386,0.0005532372,0.0005702876,0.0005455469,0.0003537256],"domain_scores_gemma":[0.9988475,0.00003996567,0.0003540141,0.0002460995,0.0003762869,0.0001361665],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002317535,0.00003684587,0.0001892166,0.00004830493,0.00001183938,8.017245e-7,0.004143947,0.001755916,0.08381902,0.8788776,0.00005409091,0.03103919],"study_design_scores_gemma":[0.0000189304,0.00006325656,0.00001758006,0.0001311566,0.000008240836,0.0000028885,0.0003827313,0.5638609,0.3530245,0.08224939,0.00008116686,0.000159245],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4290373,0.00002467233,0.5517275,0.0132509,0.0005013533,0.0004398439,0.00000183203,0.0002016241,0.004814983],"genre_scores_gemma":[0.9826547,0.00001334087,0.01625661,0.0008931572,0.0001277388,0.00001004572,1.71505e-7,0.00001137197,0.00003285231],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7966282,"threshold_uncertainty_score":0.6991415,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1353446073366855,"score_gpt":0.311139876853131,"score_spread":0.1757952695164456,"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."}}