{"id":"W2166141468","doi":"10.1093/llc/fqu061","title":"Citation segmentation from sparse & noisy data: A joint inference approach with Markov logic networks","year":2014,"lang":"en","type":"article","venue":"Digital Scholarship in the Humanities","topic":"Topic Modeling","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Excellence; Scholarship; Library science; Inference; Citation; Computer science; Artificial intelligence; Philosophy; Political science; Epistemology","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0008852497,0.0001699229,0.0001506331,0.00009244792,0.0001935867,0.003133175,0.001518656,0.00005611438,0.000005492643],"category_scores_gemma":[0.000198209,0.0001205257,0.00002289457,0.000199387,0.00009658946,0.004228723,0.0003665114,0.0003360799,0.00002250532],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004725995,"about_ca_system_score_gemma":0.00003171103,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009897212,"about_ca_topic_score_gemma":0.0003318761,"domain_scores_codex":[0.9983819,0.0002205918,0.000265543,0.0004585164,0.0004222555,0.0002512007],"domain_scores_gemma":[0.9984148,0.0003126828,0.000131152,0.00104983,0.00006391337,0.00002768315],"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":[0.00009195279,0.000589125,0.05621132,0.0001021266,0.0001020072,0.00002916847,0.04046556,0.05352517,0.00009211444,0.6937484,0.000275428,0.1547676],"study_design_scores_gemma":[0.001521665,0.000240474,0.1062941,0.0003082725,0.00003725972,0.00004219568,0.00339811,0.6426268,0.00002766171,0.2420122,0.002344798,0.001146416],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1932351,0.00007028774,0.7988678,0.00009429045,0.00009544906,0.000208765,0.000009201903,0.00008619137,0.007332931],"genre_scores_gemma":[0.9679132,0.000004019954,0.03079599,0.0006944695,0.0001298314,0.00003442138,0.0003223791,0.000009770072,0.00009591923],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7746781,"threshold_uncertainty_score":0.9979017,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1734865759425414,"score_gpt":0.2799996284789401,"score_spread":0.1065130525363987,"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."}}