Searcharxiv⌕ Search

arXiv subjects

Nizam Kadir

Publications and source records attributed to Nizam Kadir.

13 recordsLinked to original sources

Frac-BKT Under Mechanism Scrutiny: Response Assimilation and a Failed Fractional-Memory Test

Long-horizon knowledge tracing requires more than an evocative memory mechanism: the implementation must assimilate observed responses non-anticipatorily, and the mechanism must survive matched controls. We subject Frac-BKT, a BKT-style model with an elapsed-time-scaled truncated fractional history, to both tests. The repaired model predicts response $n$ from a prior mastery state and uses response $n$ only to update the posterior state for later events. A five-seed evaluation uses 676,848 ASSISTments 2017 interactions from 1,694 learners and 19,249 learner--skill trajectories, with chronological 80/10/10 suffix splits. The response-aware model reaches AUC .5860 overall, .5638 after gaps of at least 30 minutes, and .5668 after at least 14 days. Relative to the earlier non-response implementation, the gains are .0473, .0316, and .0277 AUC, respectively. However, the fractional mechanism gate fails: the full model is not better than the matched $α=1$ control and is worse than the matched $τ=0$ control by .0090 AUC on both long-gap slices. Student-cluster wild-bootstrap intervals exclude zero, both Holm-adjusted $p$-values are .00006, and all five per-seed differences favor $τ=0$. Compact AKT-, SAKT-, and DAS3H-style references also remain stronger on long gaps. The contribution is therefore a response-assimilation repair and a falsifiable audit showing that response assimilation helps while the evaluated fractional-history term does not---not a state-of-the-art or causal-retention claim.

cs.CY↗

From Misconceptions to Evidence: What Science Teachers Make Visible When Co-Designing Agentic Learning Apps

Science educators increasingly encounter AI tools that generate content, yet disciplinary teaching depends on eliciting learners' models, diagnosing misconceptions, interpreting evidence, and preserving professional judgment. This study asks how science teachers translate such epistemic work into specifications for agentic learning applications. It contributes to the conference theme, "Innovating Pedagogies, Inspiring Minds: Transforming Science Learning," and the Teachers' Professional Learning strand by examining app co-design as a form of pedagogical reasoning. We conducted a bounded qualitative cross-case analysis of four de-identified artifacts produced in a teacher professional-learning workshop: an experimental-design diagnostic, a Kinetic Particle Theory dialogue guide, a chemistry prior-knowledge checker, and a physics application/scaffolding tool. Each artifact was coded for the disciplinary problem, learner interaction, evidence made visible, teacher authority, and safeguard. All four connected a science-learning problem to an interaction and pedagogically interpretable evidence: misconceptions and gaps, explanations-in-progress, class-level readiness patterns, or investigation performance. However, only two made teacher control or evaluation explicit, and only two named a safeguard. The proposals therefore positioned AI less as an answer generator than as an elicitor, scaffold, and evidence-return mechanism, while leaving decision rights and protections unevenly specified. We argue that teacher professional learning should treat AI app ideation as epistemic specification work. A five-question design protocol--problem, learner interaction, evidence, teacher authority, and safeguard--can help teachers transform science-learning needs into accountable human-AI arrangements before building or adopting a tool.

cs.HC↗

Beyond Prompt-to-App: Accountable Translation in Teacher-Facing Agentic Authoring

Natural-language app builders let domain experts create software, but their pipelines transform professional intent across compilation, generation, checking, and approval. We report a bounded trace study of a teacher-facing agentic authoring system. Evidence comprises six eligible build attempts across three accounts; a separate corpus of 37 workshop units from 23 display names contextualizes commitments without person-level linkage. Compiled specifications added governance requirements, while downstream representations sometimes normalized case-specific learning relations. Two drafts met a stored package/security threshold despite analyzer reservations and unresolved correspondence to their briefs; four attempts in one account produced no usable payload, and repair messages did not translate internal terms into domain-legible revisions. We develop accountable translation as an analytic framework for making consequential changes attributable, inspectable, scoped in validation, and contestable. It extends HCI accounts of traceability and end-user debugging by locating professional authority and repair rights across heterogeneous technical and organizational handoffs.

cs.HC↗

Critsly: An Artefact-Aware AI Critique Teammate for Design Education and Project-Based Learning

Critique is central to design education and project-based learning, yet high-quality critique is often scarce, uneven, hard to document, and disconnected from evolving artefacts. We present Critsly, an artefact-aware AI critique workspace that turns AI from a detached feedback tool into a critique teammate in the learner's board context. Critsly combines a visual design canvas with structured AI-supported reflection, multi-perspective critique, action planning, optional peer/jury settings, and educator evidence traces. Unlike chatbot feedback tools that rely on isolated text prompts, Critsly grounds critique in a structured board state containing design intentions, board elements, annotations, links, and prior critique history. Reflecture, Critsly's guided reflection flow, works with Six Thinking Hats-inspired personas, board synthesis, generated action plans, exportable critique records, and educator evidence views in one workflow. The demo follows a learner from design intention to board-aware critique, persona-based evaluation, action-plan generation, and educator-facing evidence. Critsly contributes a working example of AI-supported critique that is more frequent, structured, inspectable, and actionable for learners and educators.

cs.CY↗

Critsly and StudioCrit: An Artefact-Aware AI Critique Workspace and Simulation-Based Readiness Study for Design Education

Critique in design education depends on interpreting work in progress, articulating intentions and translating feedback into revisions. This technical report presents Critsly, an artefact-aware AI critique workspace, and StudioCrit, its architecture-studio research mode. Critsly combines a visual board, design-intention fields, guided reflection, perspective-based critique and action planning. StudioCrit adds studio/class organisation, role-based access, cognitive and architectural classification, educator analytics and exportable evidence. The report consolidates implementation and simulation evidence recorded in a research project submitted in July 2026. Three simulated studio scenarios yielded 109 classified evidence rows, including 85 assigned to higher-order Bloom categories. A separate rehearsal using 50 disposable learner accounts yielded 56 evidence rows, including 46 assigned to higher-order categories. A subsequent hardening rehearsal recorded 50 completed sessions, 50 successful board pulls and 50 denials of student access to analytics. These are software and synthetic-trace observations, not measurements of learning gains or human cognitive performance. Automated classifications remain provisional, and the source report does not establish classifier accuracy or inter-rater reliability. The contribution is an implemented critique-to-evidence workflow and a bounded account of its readiness for further controlled evaluation.

cs.HC↗

TeamLens in Critsly: A Consent-Based Team-Composition Interface and Synthetic Readiness Evaluation for Design Collaboration

Discussing working preferences may support reflection within a design team, but a personality label should not become a performance prediction or a condition of participation. This technical report presents TeamLens, an optional Critsly interface for voluntarily sharing a self-reported MBTI type with a particular board. It separates account activation from disclosure, displays descriptive composition counts, and provides distinct controls for disabling visibility, withdrawing one report and deleting all of one's reports. The evaluation combines released-source inspection, independently specified synthetic aggregation cases, access and lifecycle checks, browser component tests, a local database microbenchmark and deployment records. All 65,536 binary eligibility subsets of sixteen fixed, distinct type reports matched an independent oracle; 128 seeded multiplicity fixtures also matched, after 4,259 synthetic share calls. The isolated HTTP suite passed 183 assertions. In 180 sequential in-memory SQLite read trials, median service-call time increased from 0.064 ms with no profile rows to 200.932 ms with 1,024 rows; instrumented SQL operations followed 11+3n. These findings concern exercised software behaviour and a bounded workload. They do not establish human usability, psychometric validity, learning gains, team-performance effects or production capacity. The contribution is an implemented disclosure-to-aggregation workflow and an auditable technical account of its correctness boundaries, privacy limitations and scaling cost. OpenAI Codex assisted with implementation, evaluation and manuscript preparation; the paper discloses this use and its limits.

cs.CY↗

LearnAdapt Praxis: Controlled AI Assistance and Evidence Traces for Adult Workplace Learning

AI can help adults produce plausible workplace artefacts while leaving their independent reasoning difficult to inspect. LearnAdapt Praxis addresses this design problem through a five-stage learning workspace: Frame, Learn, Build, Validate and Transfer. The application stores an initial response, versioned specifications, coaching records, validation observations, a separate transfer response and facilitator feedback. Project-level server controls restrict coaching, access to earlier work and learner export during an active transfer attempt; they do not establish that a learner avoided assistance outside the application. This technical report describes the implemented architecture and evaluates selected workflow, authority, failure-recovery and provenance properties. A reproducible synthetic rehearsal exercised 120 serial project episodes across three fictional workplace contexts and four injected provider conditions. All 3,990 recorded checks met their specified expectations. The resulting records contained 240 specification versions, 1,200 activity events and 60 stored synthetic hints; 60 injected provider failures produced no fabricated hints. Separate authentication regressions exposed and resolved a session-expiry defect, and limited staging and production checks verified account access and live model connectivity. The evidence supports the tested engineering properties of the recorded release. It does not establish learning gains, model-output quality, unaided assessment validity, population usability or production capacity. The contribution is an implemented arrangement for separating assisted work, project-level assistance withdrawal and inspectable evidence, accompanied by executable tests and an explicit account of what remains to be validated with adult learners.

cs.CY↗

CALLIOPE: A Source-Grounded Oral Assessment System and Synthetic Readiness Evaluation

Oral assessment with generative AI requires more than a conversational interface: educators must connect a spoken response to its source material, scoring criteria, model outputs and subsequent human judgement. This technical report presents CALLIOPE, a source-grounded oral assessment system integrating versioned instructional material, learner-turn recording and transcription, adaptive questioning, two-provider rubric scoring, educator review and exportable evidence. We examine implementation and retained synthetic verification records from 25 September 2026. Three spoken fixtures and a silence control were exercised across two release runs. In the final release rehearsal, the spoken fixtures received aggregate AI scores of 100, 62 and 8 out of 100; two elicited provider-disagreement flags. All eight retrieved audio files across the two runs were byte-identical to their inputs. These observations establish operation of specific exercised paths, not scoring validity or learning gains. A later zero-traffic candidate added version-bound consent checks, insert-only first-pass rating receipts and separately authorised coded exports, supported by local regression tests but not a new full live research workflow evaluation. We distinguish deployed functionality, candidate safeguards and remaining recovery, concurrency and study-operation requirements. The contribution is an inspectable response-to-review workflow and a release-specific account of what its engineering evidence does, and does not, establish. No human-participant outcomes are reported. OpenAI Codex assisted with technical verification, evidence synthesis and manuscript preparation.

cs.CY↗

RankCert: When Can Simulated Learners Safely Select an AI Tutor? Robust Decision Certification Under Structural Uncertainty

Simulation-based tutor selection can be unstable when predictively adequate learner models imply different policy rankings. RankCert certifies one of eight equal-budget tutoring policies only when model-averaged utility, probability-best, posterior regret, cross-domain rank, family coverage, and leave-one-domain-out and leave-one-visible-family-out averages support the same candidate; otherwise it abstains. We evaluated RankCert in 1,280 frozen held-out settings spanning five rotating held-out oracle families, 64 scenarios per family, and four cohort sizes. Calibration used a licensed, de-identified EdNet-KT1 derivative with 5,000 learners and 590,056 retained responses; all five family representatives passed the frozen adequacy gate. Minimum-domain mean pairwise top-1 agreement was 0.272917 (95% CI [0.253646, 0.293229]), showing substantial structural disagreement. Cohort-noise variance decreased from n = 30 to n = 300, while the structural family share remained nonzero. RankCert reduced total held-out decision loss relative to full-coverage point selection by 0.006605 normalized-outcome units (95% CI [0.004859, 0.008407]). At comparable coverage, however, it did not reduce selective risk relative to a confidence-gated point certificate (difference -0.000213; 95% CI [-0.003238, 0.002384]; Holm p = 0.929654). Certification occurred in 3.75% of settings and only in stable scenarios; RankCert abstained in every ambiguous, misspecified, and structural-conflict setting. "Safe" denotes only benchmark-scoped decision certification under the declared utility and uncertainty set; no human-learning, causal, deployment-effectiveness, or general-safety claim is made.

cs.AI↗

Auditable Release Control for Pedagogical Leakage in LLM Tutors

Large language model tutors can be correct and helpful yet disclose an answer or decisive reasoning before that disclosure is authorized. We formalize this state- and action-dependent failure as pedagogical leakage and introduce an authorization-aware complete-mediation boundary. A selector emits one of five disclosure contracts, trusted policy gates privileged modes, and a renderer proposes language. A single release function applies inspectable checks, optional cumulative verification, and action-specific fallback; replayable traces separate selection, generation, verification, and enforcement failures. Matched component attribution exposes a safety-utility frontier. On 599 fixed Gemini 3.5 proposals, strict mediation reduces blinded three-model panel-majority leakage flags from 181 to 0 (paired problem-cluster difference -30.22 points, 95% CI [-35.00,-25.72]), while replacing 581 responses and lowering helpfulness. Checker-triggered fallback alone yields 11 majority flags; adding the semantic verifier yields 14 and no reliable marginal gain. A global A1 scaffold yields 0 majority and 54 any-judge flags, outperforming fitted Q on automatic safety and utility. In an externally timestamped replication over 40 unseen problem clusters and 480 attack sequences, high-assurance release reduces majority flags from 42 to 8 (-7.08 points, 95% CI [-13.13,-2.29]); seven failures persist, one is introduced, and mean helpfulness falls by .192. These results establish an auditable release boundary and failure attribution under declared contracts, not universal semantic safety or learning gains.

cs.CR↗

EduPluginBench: Executable Assurance for AI-Generated Educational Plugins

Code-generation models can produce executable components, but compilation and functional tests do not establish compliance with least privilege, telemetry consent, provenance, privileged-write authority, lifecycle constraints, or bounded failure. We introduce EduPluginBench, an executable benchmark and staged admission method for generated plugins in governed software ecosystems. Across 1,440 activation-checked first-order mutants from 30 specifications, P0-P4 increased release-blocking-defect recall by 74.7 percentage points (specification-clustered 95% CI 73.4-75.8) over P0-P2, with no observed rejection among 120 clean references (95% Wilson upper bound 3.1%). A frozen transfer study of 600 unmodified generations from two current coding models found that 300/600 parsed, but none passed P0 or achieved P0-P4 conformance (95% upper bound 0.64%); downstream assurance estimands were undefined. An independently labelled Moodle study retained 16 vulnerable/fixed pairs; the frozen generic PHP detector found no vulnerable revisions. These negative transfer results prevent controlled contract consistency from being read as independent real-defect effectiveness. An earlier 540-generation diagnostic found that post-hoc bounded repair yielded 112 P0 passes, all nonconforming, with recall increasing from 13.4% to 100%. The artifact retains protocols, public-source provenance, raw generations, row-level decisions, audits, analysis code, and reproduction instructions.

cs.SE↗

From Tools to Teacher-Built Teammates: No-Code Pedagogical Plugin Authoring with LearnAdapt Agentic Studio and PedOS 1.1 Lumina

Teachers and researchers need to adapt educational AI to local goals, but most systems remain difficult to customize or study without coding expertise. We present LearnAdapt Agentic Studio on PedOS 1.1 Lumina, a no-code authoring and governed runtime environment for educational AI plugins. A non-coder describes a desired learning interaction in plain English; the system prepares a previewable plugin artifact, runs safety checks, and supports submission for review. PedOS then deploys approved plugins into a directory for installation. Crucially, telemetry is strictly gated to authenticated users running approved plugins. The demo shows the complete lifecycle from prompt to governed evidence capture, shifting from fixed tools to teacher-built teammates.

cs.CY↗

From Untamed Black Box to Interpretable Pedagogical Orchestration: The Ensemble of Specialized LLMs Architecture for Adaptive Tutoring

Monolithic Large Language Models (LLMs) used in educational dialogue often behave as "black boxes," where pedagogical decisions are implicit and difficult to audit, frequently violating instructional constraints by providing answers too early. We introduce the Ensemble of Specialized LLMS (ES-LLMS) architecture that separates decision-making from wording. Pedagogical actions are selected by a deterministic rules-based orchestrator coordinating specialized agents covering tutoring, assessment, feedback, scaffolding, motivation and ethics-guided by an interpretable Bayesian Knowledge Tracing (BKT) student model. An LLM renderer surface-realizes the chosen action in natural language. This design emphasizes reliability and controllability: constraints such as "attempt-before-hint" and hint caps are enforced as explicit rules, and the system logs per-turn agent traces and constraint checks. Validation of pedagogical quality via human expert reviewers (N=6) and a multi-LLM-as-Judge panel (six state-of-the-art models) showed that ES-LLMs were preferred in 91.7% and 79.2% of cases, respectively. The architecture significantly outperformed monolithic baselines across all seven dimensions, particularly in Scaffolding & Guidance, and Trust & Explainability. Furthermore, a Monte Carlo simulation (N=2,400) exposed a "Mastery Gain Paradox," where monolithic tutors inflated short-term performance through over-assistance. In contrast, ES-LLMs achieved 100% adherence to pedagogical constraints (e.g., attempt-before-hint) and a 3.3x increase in hint efficiency. Operationally, ES-LLMs reduced costs by 54% and latency by 22% by utilizing stateless prompts. We conclude that structural decoupling is essential for transforming stochastic models into trustworthy, verifiable and resource-efficient pedagogical agents.

cs.CY↗