{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001575363,0.001841021,0.001190856,0.00293563,0.000582313,0.001220975,0.001849537,0.001296389,0.003395802],"category_scores_gemma":[0.006959504,0.0004571477,0.001327372,0.003393087,0.000540944,0.004544405,0.00135818,0.001824159,0.002595276],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008763269,"about_ca_system_score_gemma":0.001513232,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006598474,"about_ca_topic_score_gemma":0.008332763,"domain_scores_codex":[0.9989778,0.0002322473,0.00009210547,0.0003439191,0.0002708142,0.00008326107],"domain_scores_gemma":[0.9982427,0.0006524723,0.0001561692,0.0004695818,0.0004089185,0.00007017555],"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":[0.0001827162,0.0001572816,0.001853593,0.0002109002,0.0001759964,0.0001045771,0.0002574665,0.04725923,0.007063147,0.009052941,0.02077189,0.9129102],"study_design_scores_gemma":[0.00007195415,0.0002333454,0.001263827,0.00004699248,0.00008394821,0.0003520747,0.000117363,0.9350787,0.009928769,0.03745967,0.01528812,0.00007528917],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01625718,0.0010318,0.9737663,0.0002249216,0.000181338,0.0001905691,0.001099742,0.005908148,0.001340021],"genre_scores_gemma":[0.2103889,0.001234199,0.7725758,0.0003192747,0.000357339,0.000714623,0.007361595,0.0008612505,0.006187007],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006598474,"threshold_uncertainty_score":0.01312011,"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."}}