[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-186662-en":3,"doc-seo-186662-105":30,"detail-sidebar-cat-0-en-105":92},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},186662,962088121634,"supergirl","https://ap-avatar.wpscdn.com/davatar_9964176cb1d06d4a9deccf72a44ae3dc",8,"Research & Report","Comprehensive Difficulty Coefficient Model - Automatic Identification Method","A theoretical and computational study compares Classic Test Theory, the Comprehensive Difficulty Coefficient Model, and Cognitive Load Theory for modeling how questions relate to difficulty. It details variable sources and feasibility of automation, then defines cognitive-load dimensions and scene/item-level features. The work proposes automatic identification methods using text-extracted features and neural models, and reports weighting schemes, dataset configurations, and model performance metrics for background and hiddenness accuracy.","| Theory | Classic Test\u003Cbr>Theory (CTT) | Comprehensive\u003Cbr>Difficulty\u003Cbr>Coefficient Model | Cognitive\u003Cbr>Load Theory\u003Cbr>(CLT) |\n| --- | --- | --- | --- |\n| Theoretical focus | QuestionSubject Interaction | Multi-dimensional weighting of content, operation, reasoning, background, etc | Immediate allocation of working memory resources |\n| Variable source | Post-event statistics (pvalue, discrimination degree) | Manual coding\u003Cbr>(expert scoring | Cognitive psychology\u003Cbr>Experiment (Working Memory\u003Cbr>Capacity Limitation) |\n| Feasibility of automation | Large sample\u003Cbr>measured data is required | Each item needs\u003Cbr>to be marked by an expert | Features can be directly extracted from text through LLM |\n\n\n| Tags | dimension | level | Automatic\u003Cbr>identification\u003Cbr>method |\n| --- | --- | --- | --- |\n| extrinsic\u003Cbr>cognitive load[9] | Scene d1\u003Cbr>Questionsolving speed d4 | without\u003Cbr>background k11\u003Cbr>background of life k12\u003Cbr>Slowly k41\u003Cbr>Medium k42\u003Cbr>Sharp k43 | CNN; RNN [31]\u003Cbr>- |\n| intrinsic\u003Cbr>cognitive load[9] | Number of\u003Cbr>symbols d3\u003Cbr>Hidden d2\u003Cbr>Expression steps d5\u003Cbr>Number of subexpressions d6 | Low k31\u003Cbr>Medium k32\u003Cbr>High k33\u003Cbr>None k21\u003Cbr>Medium K22\u003Cbr>Hard k23\u003Cbr>Lower k51\u003Cbr>High k52\u003Cbr>Lower k61\u003Cbr>Medium k62\u003Cbr>High k63 | DNS;\u003Cbr>Graph2TREE;\u003Cbr>[32]\u003Cbr>CNN; RNN\u003Cbr>TRANSFORMER;\u003Cbr>[33]\u003Cbr>Math-en; Bert; HMS [34]\u003Cbr>Bert; DNS; GTS [32] |\n\n| dimension | Scene 0.59 |  | Hidden\u003Cbr>1.17 |  | NS\u003Cbr>1.17 |  | QSS\u003Cbr>0.52 | ES\u003Cbr>1.86 |  | NOS\u003Cbr>0.81 | CR |\n| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |\n| level\u003Cbr>weights\u003Cbr>CR | K11 K12\u003Cbr>0.34 1.66\u003Cbr>0.00738 | K21\u003Cbr>0.33 | K22 K23\u003Cbr>0.96 1.71\u003Cbr>0.00617 | K31\u003Cbr>0.3 | K32 K33\u003Cbr>0.78 1.92\u003Cbr>0.00390 | K41\u003Cbr>0.3 | K42 K43\u003Cbr>0.78 1.92\u003Cbr>0.00617 | K51 K52\u003Cbr>0.5 1.5\u003Cbr>0.00738 | K61\u003Cbr>0.24 | K62 K63\u003Cbr>0.57 2.19\u003Cbr>0.00794 | 0.00746 |\n\n| n t\u003Cbr>|  |\n| --- | --- |\n| | \u003Cbr>ns |\n\n| Input | The second-grade students of Zhengu Haile School went to plant trees on one side ofa path. They planted one tree every 2 meters (trees were planted at both ends of the road). Finally, they found that a total of 11 trees had been planted. How long is this path? |  |\n| --- | --- | --- |\n| Output | Expression： x=44*20 Cot：\u003Cbr>Determine the number of trees on each side: 11 Calculate the number of intervals on each side: Since there are 11 trees on each side, the number of intervals on each side is 11-1 = 10. Determine the length of each side: Since each interval is 20 meters, the length of each side is calculated as 10 intervals * 20 meters/interval = 200 meters.\u003Cbr>Calculate the perimeter of the square: The perimeter of a square is the sum of the lengths of all four sides. Since each side is 200 meters, the perimeter is 4 * 200 meters = 800 meters. | Number of symbols:\u003Cbr>low Reasonin\u003Cbr>g ability: low Number of subexpressions: low Questionsolving speed:\u003Cbr>moderate |\n\n\n| Original\u003Cbr>dataset | \"original text\": \" In a square flower bed, 44 willows were planted along its 4 sides. The distance between each two willows is 20 meters. What is the perimeter of this square?\"\u003Cbr>\"equation\": \" Zhou planted 44 willow trees. The distance between every two willow trees is 20 meters. What is the perimeter of this square? Solution: 20 􀃗 44 = 880 (meters) Answer: The perimeter of this square is 880 meters.\" |\n| --- | --- |\n| Example 1 | How many sides does a square have? |\n| Example 2 | How many willows are there on each side? |\n| Example 3 | What is the distance in meters between each pair of willow trees? |\n| Example 4 | What is the length of each side in meters? |\n| Example 5\u003Cbr>Solution： | What is the total perimeter of the square in meters? |\n\n\n| Dataset | \\#Train | \\#Test |\n| --- | --- | --- |\n| Math23K | 22,162 | 1,000 |\n\n| Hyperparamet\u003Cbr>ers names | Type/Val\u003Cbr>ue | Hyperparameters names | Type/Val\u003Cbr>ue |\n| --- | --- | --- | --- |\n| Learning_rate | 5e-5 | gradient_accumulation_steps | 8 |\n| Batch size | 2 | Temperature | 0.6 |\n| Epoch | 8 | Top_p | 0.9 |\n| Optim","cbCaidyqaupHSZAA","https://ap.wps.com/l/cbCaidyqaupHSZAA","pdf",857771,1,15,"English","en",105,"# Theory Framework Comparison\n## Classic Test Theory (CTT)\n## Comprehensive Difficulty Coefficient Model\n## Cognitive Load Theory (CLT)\n# Feature Design and Tagging\n## Cognitive Load Dimensions\n## Scene and Level Features\n# Model Automation Approach\n## Text/LLM Feature Extraction\n## Neural Identification Methods\n# Experimental Setup and Results\n## Datasets and Train/Test Counts\n## Hyperparameters and Training Settings\n## Accuracy Metrics","[{\"question\":\"How does the Comprehensive Difficulty Coefficient Model define difficulty variables?\",\"answer\":\"It uses multi-dimensional weighting across content, operation, reasoning, and background. Difficulty is represented through a structured set of dimensions and levels rather than post-event statistics alone.\"},{\"question\":\"What feasibility differences exist among CTT, the coefficient model, and CLT?\",\"answer\":\"CTT requires large measured data, the coefficient model needs expert marking per item, and CLT features can be directly extracted from text through LLM-based methods.\"},{\"question\":\"Which feature dimensions are used for automatic identification?\",\"answer\":\"The document defines extrinsic cognitive load and intrinsic cognitive load dimensions, including solving speed, background knowledge level, number of symbols, hiddenness, expression steps, and subexpression counts, mapped to automatic identification methods such as CNN, RNN, and transformer-based models.\"}]","Comprehensive Difficulty Coefficient Model - Automatic Identification Method | PDF",1788375865,38,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":87,"head_meta":89,"extra_data":91,"updated_unix":28},"comprehensive-difficulty-coefficient-model-automatic-identification-method","",{"@graph":36,"@context":86},[37,54,69],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/comprehensive-difficulty-coefficient-model-automatic-identification-method/186662/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":63,"encodingFormat":61,"isAccessibleForFree":64,"interactionStatistic":65},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-09-04","2026-09-02",true,{"@type":66,"interactionType":67,"userInteractionCount":20},"InteractionCounter",{"@type":68},"ViewAction",{"@type":70,"mainEntity":71},"FAQPage",[72,78,82],{"name":73,"@type":74,"acceptedAnswer":75},"How does the Comprehensive Difficulty Coefficient Model define difficulty variables?","Question",{"text":76,"@type":77},"It uses multi-dimensional weighting across content, operation, reasoning, and background. Difficulty is represented through a structured set of dimensions and levels rather than post-event statistics alone.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"What feasibility differences exist among CTT, the coefficient model, and CLT?",{"text":81,"@type":77},"CTT requires large measured data, the coefficient model needs expert marking per item, and CLT features can be directly extracted from text through LLM-based methods.",{"name":83,"@type":74,"acceptedAnswer":84},"Which feature dimensions are used for automatic identification?",{"text":85,"@type":77},"The document defines extrinsic cognitive load and intrinsic cognitive load dimensions, including solving speed, background knowledge level, number of symbols, hiddenness, expression steps, and subexpression counts, mapped to automatic identification methods such as CNN, RNN, and transformer-based models.","https://schema.org",{"og:url":52,"og:type":88,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":90,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":93},[94,98,102,106,111,116,121,124,129,132,136],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":95,"show_sort_weight":96,"slug":97},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":99,"show_sort_weight":100,"slug":101},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":103,"show_sort_weight":104,"slug":105},"Exam",70,"exam",{"id":107,"doc_module":4,"doc_module_name":46,"category_name":108,"show_sort_weight":109,"slug":110},5,"Comic",60,"comic",{"id":112,"doc_module":4,"doc_module_name":46,"category_name":113,"show_sort_weight":114,"slug":115},6,"Technology",50,"technology",{"id":117,"doc_module":4,"doc_module_name":46,"category_name":118,"show_sort_weight":119,"slug":120},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":122,"slug":123},30,"research-report",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":126,"show_sort_weight":127,"slug":128},9,"Religion & Spirituality",20,"religion-spirituality",{"id":127,"doc_module":4,"doc_module_name":46,"category_name":130,"show_sort_weight":127,"slug":131},"World Cup","world-cup",{"id":133,"doc_module":4,"doc_module_name":46,"category_name":134,"show_sort_weight":133,"slug":135},10,"Lifestyle","lifestyle",{"id":137,"doc_module":4,"doc_module_name":46,"category_name":138,"show_sort_weight":107,"slug":139},19,"General","general"]