{"id":"W4412944139","doi":"10.18653/v1/2025.trl-1.10","title":"Table Understanding and (Multimodal) LLMs: A Cross-Domain Case Study on Scientific vs. Non-Scientific Data","year":2025,"lang":"en","type":"preprint","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Deutsche Forschungsgemeinschaft; Institute for Catastrophic Loss Reduction","keywords":"Table (database); Computer science; Domain (mathematical analysis); Data science; Data mining; Mathematics","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":[0.008223644,0.001174519,0.0007303384,0.003037422,0.0008294193,0.003003625,0.001476963,0.002279494,0.005755227],"category_scores_gemma":[0.04775232,0.000294888,0.00115187,0.002924092,0.001102979,0.008015174,0.003968692,0.001899165,0.002231601],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001061204,"about_ca_system_score_gemma":0.001078304,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004218391,"about_ca_topic_score_gemma":0.004981005,"domain_scores_codex":[0.9905902,0.005087885,0.0008251725,0.001550075,0.001631901,0.0003147689],"domain_scores_gemma":[0.9305237,0.05750067,0.001731194,0.006073342,0.003306689,0.0008642671],"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":[0.004356481,0.003023454,0.03739596,0.01343801,0.0006693424,0.00769328,0.02170166,0.0473615,0.04946474,0.01146207,0.125422,0.6780115],"study_design_scores_gemma":[0.0007567576,0.003112165,0.06458434,0.002922888,0.000656392,0.01133725,0.04626337,0.3394457,0.1287389,0.03460677,0.3669231,0.0006523347],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.777819,0.007005599,0.1417648,0.00501266,0.0006613802,0.001574759,0.02360072,0.01964214,0.02291899],"genre_scores_gemma":[0.7323015,0.001694739,0.2258717,0.001652262,0.0002054272,0.0007148769,0.02955105,0.001923665,0.006084772],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.008223644,"threshold_uncertainty_score":0.04349124,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0829351396306667,"score_gpt":0.3709488091003247,"score_spread":0.288013669469658,"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."}}