{"id":"W4409364838","doi":"10.1609/aaai.v39i11.33225","title":"DCC: Differentiable Cardinality Constraints for Partial Index Tracking","year":2025,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Advanced Topics in Algebra","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Institute for Information and Communications Technology Promotion; Ministry of Science and ICT, South Korea; National Research Foundation of Korea; National Research Foundation","keywords":"Differentiable function; Cardinality (data modeling); Index (typography); Tracking (education); Mathematics; Computer science; Pure mathematics; Data mining; Psychology; Programming language","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":[0.0006014983,0.0002684814,0.000454104,0.0001106533,0.0002714472,0.0001315384,0.0009014856,0.0001537984,0.0001286076],"category_scores_gemma":[0.002613785,0.0002143369,0.0002303842,0.000370649,0.0006129316,0.000173585,0.0002111596,0.0003570593,0.000008409012],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008276699,"about_ca_system_score_gemma":0.0001212971,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009990584,"about_ca_topic_score_gemma":0.000009776037,"domain_scores_codex":[0.9979616,0.00001893419,0.0007522433,0.0004748947,0.0003655383,0.0004267438],"domain_scores_gemma":[0.997918,0.0004715997,0.0004257635,0.0003134338,0.0008077741,0.0000634066],"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":[0.0001266461,0.0001592925,0.0008690281,0.0002331923,0.0000534563,1.303387e-7,0.0002921645,0.000006322824,0.008610911,0.9576217,0.00023826,0.03178889],"study_design_scores_gemma":[0.00004790455,0.00005050538,0.0001173866,0.0002927636,0.00004511142,7.888601e-7,0.0004752324,0.001802815,0.3401449,0.6567241,0.000163957,0.0001345848],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6543281,0.00002920386,0.3011458,0.002749307,0.001354935,0.002251496,0.0000642842,0.0002105666,0.03786632],"genre_scores_gemma":[0.9947264,0.000006790983,0.00400426,0.0001120821,0.00009978509,0.0001050941,7.901409e-7,0.00001990641,0.0009248547],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3403983,"threshold_uncertainty_score":0.8740404,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1530567378393115,"score_gpt":0.385270675456156,"score_spread":0.2322139376168445,"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."}}