MAB Optimizer for Estimating Math Question Difficulty via Inverse CV without NLP Article Swipe
The evolution of technology and education is driving the emergence of Intelligent & Autonomous Tutoring Systems (IATS), where objective and domain-agnostic methods for determining question difficulty are essential. Traditional human labeling is subjective, and existing NLP-based approaches fail in symbolic domains like algebra. This study introduces the Approach of Passive Measures among Educands (APME), a reinforcement learning-based Multi-Armed Bandit (MAB) framework that estimates difficulty solely from solver performance data -- marks obtained and time taken -- without requiring linguistic features or expert labels. By leveraging the inverse coefficient of variation as a risk-adjusted metric, the model provides an explainable and scalable mechanism for adaptive assessment. Empirical validation was conducted on three heterogeneous datasets. Across these diverse contexts, the model achieved an average R2 of 0.9213 and an average RMSE of 0.0584, confirming its robustness, accuracy, and adaptability to different educational levels and assessment formats. Compared with baseline approaches-such as regression-based, NLP-driven, and IRT models-the proposed framework consistently outperformed alternatives, particularly in purely symbolic domains. The findings highlight that (i) item heterogeneity strongly influences perceived difficulty, and (ii) variance in solver outcomes is as critical as mean performance for adaptive allocation. Pedagogically, the model aligns with Vygotskys Zone of Proximal Development by identifying tasks that balance challenge and attainability, supporting motivation while minimizing disengagement. This domain-agnostic, self-supervised approach advances difficulty tagging in IATS and can be extended beyond algebra wherever solver interaction data is available
Related Topics
Concepts
No concepts available.
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- http://arxiv.org/abs/2508.19014
- https://arxiv.org/pdf/2508.19014
- OA Status
- green
- OpenAlex ID
- https://openalex.org/W4416681690
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4416681690Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2508.19014Digital Object Identifier
- Title
-
MAB Optimizer for Estimating Math Question Difficulty via Inverse CV without NLPWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2025Year of publication
- Publication date
-
2025-08-26Full publication date if available
- Authors
-
R. RajendranList of authors in order
- Landing page
-
https://arxiv.org/abs/2508.19014Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2508.19014Direct link to full text PDF
- Open access
-
YesWhether a free full text is available
- OA status
-
greenOpen access status per OpenAlex
- OA URL
-
https://arxiv.org/pdf/2508.19014Direct OA link when available
- Cited by
-
0Total citation count in OpenAlex
Full payload
| id | https://openalex.org/W4416681690 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2508.19014 |
| ids.doi | https://doi.org/10.48550/arxiv.2508.19014 |
| ids.openalex | https://openalex.org/W4416681690 |
| fwci | |
| type | preprint |
| title | MAB Optimizer for Estimating Math Question Difficulty via Inverse CV without NLP |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | |
| biblio.first_page | |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| language | en |
| locations[0].id | pmh:oai:arXiv.org:2508.19014 |
| locations[0].is_oa | True |
| locations[0].source.id | https://openalex.org/S4306400194 |
| locations[0].source.issn | |
| locations[0].source.type | repository |
| locations[0].source.is_oa | True |
| locations[0].source.issn_l | |
| locations[0].source.is_core | False |
| locations[0].source.is_in_doaj | False |
| locations[0].source.display_name | arXiv (Cornell University) |
| locations[0].source.host_organization | https://openalex.org/I205783295 |
| locations[0].source.host_organization_name | Cornell University |
| locations[0].source.host_organization_lineage | https://openalex.org/I205783295 |
| locations[0].license | |
| locations[0].pdf_url | https://arxiv.org/pdf/2508.19014 |
| locations[0].version | submittedVersion |
| locations[0].raw_type | text |
| locations[0].license_id | |
| locations[0].is_accepted | False |
| locations[0].is_published | False |
| locations[0].raw_source_name | |
| locations[0].landing_page_url | http://arxiv.org/abs/2508.19014 |
| locations[1].id | doi:10.48550/arxiv.2508.19014 |
| locations[1].is_oa | True |
| locations[1].source.id | https://openalex.org/S4306400194 |
| locations[1].source.issn | |
| locations[1].source.type | repository |
| locations[1].source.is_oa | True |
| locations[1].source.issn_l | |
| locations[1].source.is_core | False |
| locations[1].source.is_in_doaj | False |
| locations[1].source.display_name | arXiv (Cornell University) |
| locations[1].source.host_organization | https://openalex.org/I205783295 |
| locations[1].source.host_organization_name | Cornell University |
| locations[1].source.host_organization_lineage | https://openalex.org/I205783295 |
| locations[1].license | cc-by |
| locations[1].pdf_url | |
| locations[1].version | |
| locations[1].raw_type | article |
| locations[1].license_id | https://openalex.org/licenses/cc-by |
| locations[1].is_accepted | False |
| locations[1].is_published | |
| locations[1].raw_source_name | |
| locations[1].landing_page_url | https://doi.org/10.48550/arxiv.2508.19014 |
| indexed_in | arxiv, datacite |
| authorships[0].author.id | https://openalex.org/A5083055130 |
| authorships[0].author.orcid | https://orcid.org/0000-0003-0487-7347 |
| authorships[0].author.display_name | R. Rajendran |
| authorships[0].author_position | middle |
| authorships[0].raw_author_name | Rajendran, Ram Kumar |
| authorships[0].is_corresponding | True |
| has_content.pdf | False |
| has_content.grobid_xml | False |
| is_paratext | False |
| open_access.is_oa | True |
| open_access.oa_url | https://arxiv.org/pdf/2508.19014 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | MAB Optimizer for Estimating Math Question Difficulty via Inverse CV without NLP |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-28T20:34:03.301133 |
| primary_topic | |
| cited_by_count | 0 |
| locations_count | 2 |
| best_oa_location.id | pmh:oai:arXiv.org:2508.19014 |
| best_oa_location.is_oa | True |
| best_oa_location.source.id | https://openalex.org/S4306400194 |
| best_oa_location.source.issn | |
| best_oa_location.source.type | repository |
| best_oa_location.source.is_oa | True |
| best_oa_location.source.issn_l | |
| best_oa_location.source.is_core | False |
| best_oa_location.source.is_in_doaj | False |
| best_oa_location.source.display_name | arXiv (Cornell University) |
| best_oa_location.source.host_organization | https://openalex.org/I205783295 |
| best_oa_location.source.host_organization_name | Cornell University |
| best_oa_location.source.host_organization_lineage | https://openalex.org/I205783295 |
| best_oa_location.license | |
| best_oa_location.pdf_url | https://arxiv.org/pdf/2508.19014 |
| best_oa_location.version | submittedVersion |
| best_oa_location.raw_type | text |
| best_oa_location.license_id | |
| best_oa_location.is_accepted | False |
| best_oa_location.is_published | False |
| best_oa_location.raw_source_name | |
| best_oa_location.landing_page_url | http://arxiv.org/abs/2508.19014 |
| primary_location.id | pmh:oai:arXiv.org:2508.19014 |
| primary_location.is_oa | True |
| primary_location.source.id | https://openalex.org/S4306400194 |
| primary_location.source.issn | |
| primary_location.source.type | repository |
| primary_location.source.is_oa | True |
| primary_location.source.issn_l | |
| primary_location.source.is_core | False |
| primary_location.source.is_in_doaj | False |
| primary_location.source.display_name | arXiv (Cornell University) |
| primary_location.source.host_organization | https://openalex.org/I205783295 |
| primary_location.source.host_organization_name | Cornell University |
| primary_location.source.host_organization_lineage | https://openalex.org/I205783295 |
| primary_location.license | |
| primary_location.pdf_url | https://arxiv.org/pdf/2508.19014 |
| primary_location.version | submittedVersion |
| primary_location.raw_type | text |
| primary_location.license_id | |
| primary_location.is_accepted | False |
| primary_location.is_published | False |
| primary_location.raw_source_name | |
| primary_location.landing_page_url | http://arxiv.org/abs/2508.19014 |
| publication_date | 2025-08-26 |
| publication_year | 2025 |
| referenced_works_count | 0 |
| abstract_inverted_index.a | 54, 91 |
| abstract_inverted_index.-- | 69, 75 |
| abstract_inverted_index.By | 83 |
| abstract_inverted_index.R2 | 122 |
| abstract_inverted_index.an | 97, 120, 126 |
| abstract_inverted_index.as | 90, 148, 182, 184 |
| abstract_inverted_index.be | 224 |
| abstract_inverted_index.by | 200 |
| abstract_inverted_index.in | 38, 160, 178, 220 |
| abstract_inverted_index.is | 6, 31, 181, 232 |
| abstract_inverted_index.of | 2, 10, 48, 88, 123, 129, 197 |
| abstract_inverted_index.on | 109 |
| abstract_inverted_index.or | 80 |
| abstract_inverted_index.to | 137 |
| abstract_inverted_index.(i) | 168 |
| abstract_inverted_index.IRT | 152 |
| abstract_inverted_index.The | 0, 164 |
| abstract_inverted_index.and | 4, 19, 33, 72, 99, 125, 135, 141, 151, 175, 206, 222 |
| abstract_inverted_index.are | 26 |
| abstract_inverted_index.can | 223 |
| abstract_inverted_index.for | 22, 102, 187 |
| abstract_inverted_index.its | 132 |
| abstract_inverted_index.the | 8, 46, 85, 94, 117, 191 |
| abstract_inverted_index.was | 107 |
| abstract_inverted_index.(ii) | 176 |
| abstract_inverted_index.IATS | 221 |
| abstract_inverted_index.RMSE | 128 |
| abstract_inverted_index.This | 43, 213 |
| abstract_inverted_index.Zone | 196 |
| abstract_inverted_index.data | 68, 231 |
| abstract_inverted_index.fail | 37 |
| abstract_inverted_index.from | 65 |
| abstract_inverted_index.item | 169 |
| abstract_inverted_index.like | 41 |
| abstract_inverted_index.mean | 185 |
| abstract_inverted_index.that | 61, 167, 203 |
| abstract_inverted_index.time | 73 |
| abstract_inverted_index.with | 145, 194 |
| abstract_inverted_index.& | 12 |
| abstract_inverted_index.(MAB) | 59 |
| abstract_inverted_index.among | 51 |
| abstract_inverted_index.human | 29 |
| abstract_inverted_index.marks | 70 |
| abstract_inverted_index.model | 95, 118, 192 |
| abstract_inverted_index.study | 44 |
| abstract_inverted_index.taken | 74 |
| abstract_inverted_index.tasks | 202 |
| abstract_inverted_index.these | 114 |
| abstract_inverted_index.three | 110 |
| abstract_inverted_index.where | 17 |
| abstract_inverted_index.while | 210 |
| abstract_inverted_index.0.9213 | 124 |
| abstract_inverted_index.Across | 113 |
| abstract_inverted_index.Bandit | 58 |
| abstract_inverted_index.aligns | 193 |
| abstract_inverted_index.beyond | 226 |
| abstract_inverted_index.expert | 81 |
| abstract_inverted_index.levels | 140 |
| abstract_inverted_index.purely | 161 |
| abstract_inverted_index.solely | 64 |
| abstract_inverted_index.solver | 66, 179, 229 |
| abstract_inverted_index.(APME), | 53 |
| abstract_inverted_index.(IATS), | 16 |
| abstract_inverted_index.0.0584, | 130 |
| abstract_inverted_index.Passive | 49 |
| abstract_inverted_index.Systems | 15 |
| abstract_inverted_index.algebra | 227 |
| abstract_inverted_index.average | 121, 127 |
| abstract_inverted_index.balance | 204 |
| abstract_inverted_index.diverse | 115 |
| abstract_inverted_index.domains | 40 |
| abstract_inverted_index.driving | 7 |
| abstract_inverted_index.inverse | 86 |
| abstract_inverted_index.labels. | 82 |
| abstract_inverted_index.methods | 21 |
| abstract_inverted_index.metric, | 93 |
| abstract_inverted_index.tagging | 219 |
| abstract_inverted_index.without | 76 |
| abstract_inverted_index.Approach | 47 |
| abstract_inverted_index.Compared | 144 |
| abstract_inverted_index.Educands | 52 |
| abstract_inverted_index.Measures | 50 |
| abstract_inverted_index.Proximal | 198 |
| abstract_inverted_index.Tutoring | 14 |
| abstract_inverted_index.achieved | 119 |
| abstract_inverted_index.adaptive | 103, 188 |
| abstract_inverted_index.advances | 217 |
| abstract_inverted_index.algebra. | 42 |
| abstract_inverted_index.approach | 216 |
| abstract_inverted_index.baseline | 146 |
| abstract_inverted_index.critical | 183 |
| abstract_inverted_index.domains. | 163 |
| abstract_inverted_index.existing | 34 |
| abstract_inverted_index.extended | 225 |
| abstract_inverted_index.features | 79 |
| abstract_inverted_index.findings | 165 |
| abstract_inverted_index.formats. | 143 |
| abstract_inverted_index.labeling | 30 |
| abstract_inverted_index.obtained | 71 |
| abstract_inverted_index.outcomes | 180 |
| abstract_inverted_index.proposed | 154 |
| abstract_inverted_index.provides | 96 |
| abstract_inverted_index.question | 24 |
| abstract_inverted_index.scalable | 100 |
| abstract_inverted_index.strongly | 171 |
| abstract_inverted_index.symbolic | 39, 162 |
| abstract_inverted_index.variance | 177 |
| abstract_inverted_index.wherever | 228 |
| abstract_inverted_index.Empirical | 105 |
| abstract_inverted_index.NLP-based | 35 |
| abstract_inverted_index.Vygotskys | 195 |
| abstract_inverted_index.accuracy, | 134 |
| abstract_inverted_index.available | 233 |
| abstract_inverted_index.challenge | 205 |
| abstract_inverted_index.conducted | 108 |
| abstract_inverted_index.contexts, | 116 |
| abstract_inverted_index.datasets. | 112 |
| abstract_inverted_index.different | 138 |
| abstract_inverted_index.education | 5 |
| abstract_inverted_index.emergence | 9 |
| abstract_inverted_index.estimates | 62 |
| abstract_inverted_index.evolution | 1 |
| abstract_inverted_index.framework | 60, 155 |
| abstract_inverted_index.highlight | 166 |
| abstract_inverted_index.mechanism | 101 |
| abstract_inverted_index.objective | 18 |
| abstract_inverted_index.perceived | 173 |
| abstract_inverted_index.requiring | 77 |
| abstract_inverted_index.variation | 89 |
| abstract_inverted_index.Autonomous | 13 |
| abstract_inverted_index.approaches | 36 |
| abstract_inverted_index.assessment | 142 |
| abstract_inverted_index.confirming | 131 |
| abstract_inverted_index.difficulty | 25, 63, 218 |
| abstract_inverted_index.essential. | 27 |
| abstract_inverted_index.influences | 172 |
| abstract_inverted_index.introduces | 45 |
| abstract_inverted_index.leveraging | 84 |
| abstract_inverted_index.linguistic | 78 |
| abstract_inverted_index.minimizing | 211 |
| abstract_inverted_index.models-the | 153 |
| abstract_inverted_index.motivation | 209 |
| abstract_inverted_index.supporting | 208 |
| abstract_inverted_index.technology | 3 |
| abstract_inverted_index.validation | 106 |
| abstract_inverted_index.Development | 199 |
| abstract_inverted_index.Intelligent | 11 |
| abstract_inverted_index.Multi-Armed | 57 |
| abstract_inverted_index.NLP-driven, | 150 |
| abstract_inverted_index.Traditional | 28 |
| abstract_inverted_index.allocation. | 189 |
| abstract_inverted_index.assessment. | 104 |
| abstract_inverted_index.coefficient | 87 |
| abstract_inverted_index.determining | 23 |
| abstract_inverted_index.difficulty, | 174 |
| abstract_inverted_index.educational | 139 |
| abstract_inverted_index.explainable | 98 |
| abstract_inverted_index.identifying | 201 |
| abstract_inverted_index.interaction | 230 |
| abstract_inverted_index.performance | 67, 186 |
| abstract_inverted_index.robustness, | 133 |
| abstract_inverted_index.subjective, | 32 |
| abstract_inverted_index.adaptability | 136 |
| abstract_inverted_index.consistently | 156 |
| abstract_inverted_index.outperformed | 157 |
| abstract_inverted_index.particularly | 159 |
| abstract_inverted_index.alternatives, | 158 |
| abstract_inverted_index.heterogeneity | 170 |
| abstract_inverted_index.heterogeneous | 111 |
| abstract_inverted_index.reinforcement | 55 |
| abstract_inverted_index.risk-adjusted | 92 |
| abstract_inverted_index.Pedagogically, | 190 |
| abstract_inverted_index.attainability, | 207 |
| abstract_inverted_index.disengagement. | 212 |
| abstract_inverted_index.learning-based | 56 |
| abstract_inverted_index.approaches-such | 147 |
| abstract_inverted_index.domain-agnostic | 20 |
| abstract_inverted_index.self-supervised | 215 |
| abstract_inverted_index.domain-agnostic, | 214 |
| abstract_inverted_index.regression-based, | 149 |
| cited_by_percentile_year | |
| corresponding_author_ids | https://openalex.org/A5083055130 |
| countries_distinct_count | 0 |
| institutions_distinct_count | 1 |
| citation_normalized_percentile |