{"id":"https://openalex.org/W7134065888","doi":"https://doi.org/10.48550/arxiv.2603.04905","title":"Deterministic Preprocessing and Interpretable Fuzzy Banding for Cost-per-Student Reporting from Extracted Records","display_name":"Deterministic Preprocessing and Interpretable Fuzzy Banding for Cost-per-Student Reporting from Extracted Records","publication_year":2026,"publication_date":"2026-03-05","ids":{"openalex":"https://openalex.org/W7134065888","doi":"https://doi.org/10.48550/arxiv.2603.04905"},"language":null,"primary_location":{"id":"pmh:doi:10.48550/arxiv.2603.04905","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"publisher-specific-oa","license_id":"https://openalex.org/licenses/publisher-specific-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":null,"any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5056788814","display_name":"Shane Lee","orcid":"https://orcid.org/0000-0001-7264-5658"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Lee, Shane","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5128274423","display_name":"Stella Ng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ng, Stella","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5056788814"],"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/T11902","display_name":"Intelligent Tutoring Systems and Adaptive Learning","score":0.0934000015258789,"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"}},"topics":[{"id":"https://openalex.org/T11902","display_name":"Intelligent Tutoring Systems and Adaptive Learning","score":0.0934000015258789,"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/T12884","display_name":"Educational Assessment and Pedagogy","score":0.04320000112056732,"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/T13197","display_name":"Spreadsheets and End-User Computing","score":0.03920000046491623,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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/workbook","display_name":"Workbook","score":0.8046000003814697},{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.5547000169754028},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.5503000020980835},{"id":"https://openalex.org/keywords/byte","display_name":"Byte","score":0.414000004529953},{"id":"https://openalex.org/keywords/fuzzy-logic","display_name":"Fuzzy logic","score":0.3580999970436096},{"id":"https://openalex.org/keywords/correctness","display_name":"Correctness","score":0.3562000095844269},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.33559998869895935}],"concepts":[{"id":"https://openalex.org/C2778202681","wikidata":"https://www.wikidata.org/wiki/Q8034663","display_name":"Workbook","level":2,"score":0.8046000003814697},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.659600019454956},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.5547000169754028},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.5503000020980835},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4726000130176544},{"id":"https://openalex.org/C43364308","wikidata":"https://www.wikidata.org/wiki/Q8799","display_name":"Byte","level":2,"score":0.414000004529953},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.37540000677108765},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36039999127388},{"id":"https://openalex.org/C58166","wikidata":"https://www.wikidata.org/wiki/Q224821","display_name":"Fuzzy logic","level":2,"score":0.3580999970436096},{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.3562000095844269},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.34299999475479126},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.33559998869895935},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.3337000012397766},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.29440000653266907},{"id":"https://openalex.org/C2780031656","wikidata":"https://www.wikidata.org/wiki/Q859161","display_name":"Glossary","level":2,"score":0.2930999994277954},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.2784999907016754},{"id":"https://openalex.org/C42011625","wikidata":"https://www.wikidata.org/wiki/Q1055058","display_name":"Fuzzy set","level":3,"score":0.27059999108314514},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.2702000141143799},{"id":"https://openalex.org/C117884012","wikidata":"https://www.wikidata.org/wiki/Q94489","display_name":"n-gram","level":3,"score":0.2556999921798706},{"id":"https://openalex.org/C10551718","wikidata":"https://www.wikidata.org/wiki/Q5227332","display_name":"Data pre-processing","level":2,"score":0.25440001487731934},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.2540000081062317}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:doi:10.48550/arxiv.2603.04905","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"publisher-specific-oa","license_id":"https://openalex.org/licenses/publisher-specific-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},{"id":"doi:10.48550/arxiv.2603.04905","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.04905","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":"article"}],"best_oa_location":{"id":"pmh:doi:10.48550/arxiv.2603.04905","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"publisher-specific-oa","license_id":"https://openalex.org/licenses/publisher-specific-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.4455486536026001,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Administrative":[0],"extracts":[1],"are":[2,159,172,195],"often":[3],"exchanged":[4],"as":[5,11,151,197],"spreadsheets":[6],"and":[7,21,66,70,75,96,107,114,163,177,218,229,239],"may":[8],"be":[9,38],"read":[10],"reports":[12],"in":[13,54,183],"their":[14],"own":[15],"right":[16],"during":[17],"budgeting,":[18],"workload":[19],"review,":[20],"governance":[22],"discussions.":[23],"When":[24],"an":[25],"exported":[26],"workbook":[27,65,88,127,240],"becomes":[28],"the":[29,35,125,136,160,166,215],"reference":[30],"snapshot":[31],"for":[32],"such":[33],"decisions,":[34],"transformation":[36],"can":[37],"checked":[39],"by":[40],"recomputation":[41],"against":[42],"a":[43,59,86,121,139,184,207,211,223,226,230],"clearly":[44],"identified":[45],"input.":[46],"A":[47,203],"deterministic,":[48],"rule-governed,":[49],"file-based":[50],"workflow":[51,137],"is":[52],"implemented":[53],"cad_processor.py.":[55],"The":[56,117,156],"script":[57],"ingests":[58],"Casual":[60],"Academic":[61],"Database":[62],"(CAD)":[63],"export":[64],"aggregates":[67],"inclusive":[68],"on-costs":[69],"student":[71],"counts":[72],"into":[73],"subject-year":[74],"school-year":[76,148],"totals,":[77],"from":[78,214],"which":[79],"it":[80],"derives":[81],"cost-per-student":[82,101,149],"ratios.":[83,169,219],"It":[84],"writes":[85],"processed":[87],"with":[89,180],"four":[90],"sheets:":[91],"Processing":[92],"Summary":[93],"(run":[94],"record":[95,119],"counters),":[97],"Trend":[98],"Analysis":[99],"(schoolyear":[100],"matrix),":[102],"Report":[103],"(wide":[104],"subject-level":[105],"table),":[106],"Fuzzy":[108],"Bands":[109],"(per-year":[110],"anchors,":[111],"membership":[112],"weights,":[113],"band":[115,212],"labels).":[116],"run":[118],"includes":[120,222],"SHA-256":[122],"hash":[123],"of":[124,165,210],"input":[126],"bytes":[128],"to":[129,237],"support":[130],"snapshot-matched":[131],"recomputation.":[132],"For":[133],"within-year":[134],"interpretation,":[135],"adds":[138],"simple":[140],"fuzzy":[141],"banding":[142],"layer":[143],"that":[144,233],"labels":[145],"finite,":[146,167],"positive":[147,168],"values":[150],"Low,":[152,190],"Medium,":[153],"or":[154],"High.":[155],"per-year":[157],"anchors":[158,217],"minimum,":[161],"median,":[162],"maximum":[164],"Membership":[170],"weights":[171,194],"computed":[173],"using":[174],"left-shoulder,":[175],"triangular,":[176],"right-shoulder":[178],"functions,":[179],"deterministic":[181],"tie-breaking":[182],"fixed":[185],"priority":[186],"order":[187],"(Medium,":[188],"then":[189,191],"High).":[192],"These":[193],"treated":[196],"decision-support":[198],"signals":[199],"rather":[200],"than":[201],"probabilities.":[202],"worked":[204],"example":[205],"provides":[206],"reproducible":[208],"calculation":[209],"assignment":[213],"reported":[216],"Supplementary":[220],"material":[221],"claim-to-evidence":[224],"matrix,":[225],"reproducibility":[227],"note,":[228],"short":[231],"glossary":[232],"links":[234],"selected":[235],"statements":[236],"code":[238],"artefacts.":[241]},"counts_by_year":[],"updated_date":"2026-05-05T08:41:31.759640","created_date":"2026-03-07T00:00:00"}