Rumour detection in Bangla remains severely under-resourced, with prior work conflating it with fake news classification and lacking domain-stratified analysis of the linguistic properties that distinguish misinformation from authentic content. We introduce MisInfo-11K, a domain-stratified corpus of 11,198 instances spanning seven topical domains, constructed from Bangla fact-checking portals and verified news outlets. Using 14 linguistically motivated markers, we show via chi-square and Kruskal-Wallis analysis that 13 of 14 exhibit significant cross-domain variation, revealing distinct deception strategies (e.g., authority mimicry in political rumours, fear amplification in health rumours). Building on this, we introduce the Marker Signal Void (MSV), a chi-square-weighted scoring framework identifying rumour instances with no net discriminative surface signal, establishing Macro-F1 = 0.9843 as the ceiling achievable by this 14-marker set. Benchmarking three pretrained transformers (BanglaBERT, MuRIL, XLM-RoBERTa) against five traditional models, MuRIL achieves the strongest performance (Macro-F1 0.9800), while a marker-augmented Random Forest reaches 0.9750, surpassing XLM-RoBERTa. The gap between the MSV ceiling and transformer performance quantifies the contribution of contextual semantic representations beyond surface-level linguistic cues.

It remains unclear whether LLM capabil- ity gains translate into measurable student learning. We analyze 137 educational NLP papers (2022–2025) across four sectors— assessment and grammatical error correc- tion, feedback and writing support, content and question generation, and tutoring and dialogue—introducing three metrics: Valid- ity Gap (VG, share of studies not evaluat- ing learning outcomes), Deployment Readi- ness Index (DRI, real-world evaluation ex- tent), and Multilingual Equity Index (MEI, language coverage). We find a high validity gap (VG = 0.927), low deployment readiness (DRI = 0.126), and limited multilingual cov- erage (MEI = 0.126); grammatical error cor- rection shows no learning-improvement evi- dence at all (VG = 1.000). DRI correlates with learning-outcome evaluation (ρ = 0.425, p < 0.001). Our taxonomy and metrics offer the first quantitative audit of educational NLP in the LLM era.