{"id":"W1806134291","doi":"10.5555/1793274.1793337","title":"Integrating structure and meaning: a new method for encoding structure for text classification","year":2008,"lang":"en","type":"article","venue":"","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; ENCODE; Natural language processing; Encoding (memory); Artificial intelligence; Representation (politics); Word (group theory); Semantics (computer science); Feature (linguistics); Syntactic structure; Curse of dimensionality; Computation; Scheme (mathematics); Information retrieval; Linguistics; Syntax; Algorithm; Mathematics","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":[],"consensus_categories":[],"category_scores_codex":[0.0001192354,0.0001544084,0.0001675653,0.0001344649,0.0003340734,0.0001640358,0.0005105815,0.0001375039,0.00001402222],"category_scores_gemma":[0.0003194557,0.0001192656,0.00005069758,0.000245837,0.00004170766,0.0005092772,0.00009226505,0.0001092225,5.59619e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003844891,"about_ca_system_score_gemma":0.00008294035,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001261254,"about_ca_topic_score_gemma":0.00002426634,"domain_scores_codex":[0.9989516,0.00001869432,0.0002398007,0.0004517281,0.0001241791,0.0002139587],"domain_scores_gemma":[0.9990021,0.0003105919,0.0001560996,0.0003629347,0.0001065282,0.0000617349],"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":[0.000004988978,0.000003617713,0.0002324442,0.00001301328,0.000008957629,1.19348e-7,0.0008503989,0.000005357437,0.04829386,0.7602622,0.003782249,0.1865428],"study_design_scores_gemma":[0.001062762,0.0001992926,0.001738698,0.00002161761,0.00001848359,0.00006295938,0.0009723227,0.2999657,0.1480797,0.519205,0.02821808,0.0004552749],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003075729,0.00005802229,0.9916162,0.003572539,0.0001381912,0.0005097504,0.000009055364,0.0004579954,0.0005624845],"genre_scores_gemma":[0.4104742,0.000006783131,0.5887297,0.000126954,0.00004354741,0.00002134088,0.00000719217,0.00000646626,0.0005838501],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4073985,"threshold_uncertainty_score":0.4863508,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05483125928167303,"score_gpt":0.3224206707254743,"score_spread":0.2675894114438012,"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."}}