CRC-Screen: Certified DNA-Synthesis Hazard Screening Under Taxonomic Shift

Selective prediction with distribution-free risk control promises that, with confidence 1-delta over the calibration draw, the error rate of accepted inputs stays below a user budget alpha. We audit this promise on signal-domain detectors -- machine anomalous-sound detection (ASD) and AI-generated-image forensics -- for four calibration rules: uncertified empirical thresholding (NAIVE) and certified Hoeffding, Clopper-Pearson (CP), and betting (WSR) upper confidence bounds. We report three findings. (i) NAIVE thresholding, common in practice, exceeds its declared budget in 49-73% of synthetic trials (n=200 calibration points) and in up to 68% of real-data splits: a false sense of safety rather than a broken theorem, since the rule never had a certificate. (ii) Tightness matters: CP and WSR certify substantial coverage where Hoeffding certifies none, with zero observed budget overruns under exchangeable splits. (iii) Under grouped deployment (unseen machine types or generators), certified rules overrun in 9-30% of trials -- far above delta -- showing the failure lies in the broken exchangeability premise, not in the bounds; a conservative per-group threshold restores validity at a severe coverage cost.

Raw numerical datasets remain less systematically examined in integrity screening than images, plagiarism, or summary-statistic inconsistencies. We developed the Fabrication-risk Digit Randomness Screening model (FDRS), a statistical and machine-learning framework for detecting non-random digit-pattern irregularities in numerical research data. FDRS integrates single- and joint-decimal-digit tests, Cramer's V, entropy metrics, Kullback-Leibler divergence, digit-preference indices, progressive subsampling, and semi-supervised risk scoring. It was evaluated using an instrument-derived enzymatic absorbance dataset (RawData, n=253) and a blinded manually simulated irregular dataset (ErrData, n=255). RawData showed no significant deviation in single third-decimal-digit analysis, whereas ErrData showed a significant deviation. In joint third-fourth decimal digit analysis, ErrData showed higher Cramer's V, lower normalized entropy, higher KL divergence, and a more persistent progressive-subsampling deviation signal. In internal validation, Elastic-net Logistic Regression achieved the highest AUC (0.98395) and lowest Brier score (0.048439), while Random Forest achieved the highest accuracy (0.926667) and balanced accuracy (0.935). RawData received a low ensemble risk score of 0.124627 and was classified as Grade 0; ErrData received a score of 0.740760 and was classified as Grade 3. External real-world benchmarks supported graded risk stratification: three datasets without identified public post-publication concerns were classified as Grade 0 or 1, whereas two datasets from publicly questioned or institutionally handled articles were classified as Grade 2 or 3. FDRS can prioritize raw numerical datasets for further review by integrating interpretable statistical and machine-learning features. It is an auxiliary digit-structure screening tool, not standalone evidence of fabrication or misconduct.

Many biological discovery problems require experiments to be selected sequentially under constrained budgets. CRISPR screening is a prominent example, as exhaustive perturbation testing is often infeasible and candidate perturbations must instead be prioritized over multiple experimental rounds. Despite the importance of this problem, existing benchmarks for adaptive hit discovery remain limited in scale and diversity. Here, we introduce AssayBench-Loop, a large-scale benchmark for adaptive hit discovery comprising 1,389 CRISPR screens across five phenotype categories. Beyond enabling systematic evaluation, its scale makes it possible to learn acquisition strategies across historical experiments. Building on this resource, we introduce AssayLoop, a sequential experimental design framework combining AssayFormer, a transformer-based amortized acquisition policy trained across historical screens to adapt from experimental feedback, with LLM-derived biological priors through an adaptive handoff. In this view, completed experiments become training data for learning how accumulated evidence should guide what to test next, while LLMs provide prior biological knowledge to seed the search. We further introduce AssayLLM, showing that the same principle can be extended directly to an LLM through task-specific post-training. On temporally held-out screens, AssayLoop achieves a 5.67-fold enrichment over random selection and recovers 27.7% of hits after assaying approximately 5% of the candidate library, outperforming existing adaptive-design methods and standalone LLMs, and AssayFormer alone. Performance improves with increasing historical training data and transfers to phenotype categories excluded from training. These results demonstrate the value of learning acquisition policies across historical experiments and combining them with broad biological priors for efficient adaptive hit discovery.