{"id":"https://openalex.org/W7141426947","doi":"https://doi.org/10.48550/arxiv.2603.24961","title":"Can MLLMs Read Students' Minds? Unpacking Multimodal Error Analysis in Handwritten Math","display_name":"Can MLLMs Read Students' Minds? Unpacking Multimodal Error Analysis in Handwritten Math","publication_year":2026,"publication_date":"2026-03-26","ids":{"openalex":"https://openalex.org/W7141426947","doi":"https://doi.org/10.48550/arxiv.2603.24961"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.24961","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.24961","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2603.24961","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5070339842","display_name":"Dingjie Song","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Song, Dingjie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130756502","display_name":"Tianlong Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Tianlong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130789772","display_name":"Yi-Fan Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Yi-Fan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130755178","display_name":"Hang Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Hang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084483307","display_name":"Zhiling Yan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yan, Zhiling","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130778328","display_name":"Xing Fan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fan, Xing","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130766145","display_name":"Haoyang Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Haoyang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130762142","display_name":"Lichao Sun","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sun, Lichao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5130750291","display_name":"Qingsong Wen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wen, Qingsong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10130","display_name":"Mathematics Education and Teaching Techniques","score":0.16269999742507935,"subfield":{"id":"https://openalex.org/subfields/3304","display_name":"Education"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10130","display_name":"Mathematics Education and Teaching Techniques","score":0.16269999742507935,"subfield":{"id":"https://openalex.org/subfields/3304","display_name":"Education"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11902","display_name":"Intelligent Tutoring Systems and Adaptive Learning","score":0.09359999746084213,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.061500001698732376,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/unpacking","display_name":"Unpacking","score":0.6640999913215637},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5598000288009644},{"id":"https://openalex.org/keywords/multimodality","display_name":"Multimodality","score":0.5121999979019165},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.45419999957084656},{"id":"https://openalex.org/keywords/bridge","display_name":"Bridge (graph theory)","score":0.43050000071525574},{"id":"https://openalex.org/keywords/error-analysis","display_name":"Error analysis","score":0.4239000082015991},{"id":"https://openalex.org/keywords/handwriting-recognition","display_name":"Handwriting recognition","score":0.32269999384880066}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7343999743461609},{"id":"https://openalex.org/C2777256151","wikidata":"https://www.wikidata.org/wiki/Q7897273","display_name":"Unpacking","level":2,"score":0.6640999913215637},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5755000114440918},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5598000288009644},{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.5121999979019165},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5069000124931335},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.45419999957084656},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.43050000071525574},{"id":"https://openalex.org/C3018824978","wikidata":"https://www.wikidata.org/wiki/Q2894891","display_name":"Error analysis","level":2,"score":0.4239000082015991},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3801000118255615},{"id":"https://openalex.org/C112640561","wikidata":"https://www.wikidata.org/wiki/Q2440634","display_name":"Handwriting recognition","level":3,"score":0.32269999384880066},{"id":"https://openalex.org/C103088060","wikidata":"https://www.wikidata.org/wiki/Q1062839","display_name":"Error detection and correction","level":2,"score":0.3021000027656555},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.27630001306533813},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.2752000093460083},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2750999927520752},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.274399995803833},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2721000015735626},{"id":"https://openalex.org/C43971567","wikidata":"https://www.wikidata.org/wiki/Q3142865","display_name":"Logical reasoning","level":2,"score":0.26269999146461487}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.24961","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.24961","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2603.24961","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.24961","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.9042641520500183,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Assessing":[0],"student":[1,66],"handwritten":[2,41,87],"scratchwork":[3],"is":[4,123],"crucial":[5],"for":[6,80,176],"personalized":[7],"educational":[8,25],"feedback":[9],"but":[10,53],"presents":[11],"unique":[12],"challenges":[13],"due":[14],"to":[15,153,187],"diverse":[16],"handwriting,":[17],"complex":[18],"layouts,":[19],"and":[20,32,36,82,99,111,138,160,182],"varied":[21],"problem-solving":[22],"approaches.":[23],"Existing":[24],"NLP":[26],"primarily":[27],"focuses":[28],"on":[29,146],"textual":[30],"responses":[31],"neglects":[33],"the":[34],"complexity":[35],"multimodality":[37],"inherent":[38],"in":[39,85,157],"authentic":[40,86],"scratchwork.":[42,89],"Current":[43],"multimodal":[44],"large":[45,170],"language":[46],"models":[47,164,172],"(MLLMs)":[48],"excel":[49],"at":[50],"visual":[51,158],"reasoning":[52,171],"typically":[54],"adopt":[55],"an":[56],"\"examinee":[57],"perspective\",":[58],"prioritizing":[59],"generating":[60],"correct":[61],"answers":[62],"rather":[63],"than":[64],"diagnosing":[65],"errors.":[67],"To":[68],"bridge":[69],"these":[70],"gaps,":[71],"we":[72],"introduce":[73],"ScratchMath,":[74,147],"a":[75],"novel":[76],"benchmark":[77],"specifically":[78],"designed":[79],"explaining":[81],"classifying":[83],"errors":[84],"mathematics":[88,94],"Our":[90],"dataset":[91,122],"comprises":[92],"1,720":[93],"samples":[95],"from":[96],"Chinese":[97],"primary":[98],"middle":[100],"school":[101],"students,":[102],"supporting":[103],"two":[104],"key":[105],"tasks:":[106],"Error":[107,112],"Cause":[108,113],"Explanation":[109],"(ECE)":[110],"Classification":[114],"(ECC),":[115],"with":[116,169],"seven":[117],"defined":[118],"error":[119,177],"types.":[120],"The":[121],"meticulously":[124],"annotated":[125],"through":[126],"rigorous":[127],"human-machine":[128],"collaborative":[129],"approaches":[130],"involving":[131],"multiple":[132],"stages":[133],"of":[134],"expert":[135],"labeling,":[136],"review,":[137],"verification.":[139],"We":[140],"systematically":[141],"evaluate":[142],"16":[143],"leading":[144],"MLLMs":[145],"revealing":[148],"significant":[149],"performance":[150],"gaps":[151],"relative":[152],"human":[154],"experts,":[155],"especially":[156],"recognition":[159],"logical":[161],"reasoning.":[162],"Proprietary":[163],"notably":[165],"outperform":[166],"open-source":[167],"models,":[168],"showing":[173],"strong":[174],"potential":[175],"explanation.":[178],"All":[179],"evaluation":[180],"data":[181],"frameworks":[183],"are":[184],"publicly":[185],"available":[186],"facilitate":[188],"further":[189],"research.":[190]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-03-28T00:00:00"}