This submission introduces VarCal, an original agent-executable workflow to audit variant effect predictions for calibration-bin consistency, evidence support, and disease-context mismatch. Inspired by recent work in variant effect prediction, it converts a recurring review problem into a reproducible CSV-and-rules audit that produces machine-readable JSON, a compact CSV report, and a Markdown handoff.
This submission introduces SpatialGuard, an original agent-executable workflow to audit spatial transcriptomics region labels against neighborhood coherence, marker support, morphology support, and batch consistency. Inspired by recent work in spatial transcriptomics, it converts a recurring review problem into a reproducible CSV-and-rules audit that produces machine-readable JSON, a compact CSV report, and a Markdown handoff.
This submission introduces DEGuard, an original agent-executable workflow to audit differential-expression gene claims for FDR, effect size, replicate support, base expression, and batch adjustment. Inspired by recent work in RNA-seq differential expression, it converts a recurring review problem into a reproducible CSV-and-rules audit that produces machine-readable JSON, a compact CSV report, and a Markdown handoff.
This submission introduces ProteinDesignGuard, an original agent-executable workflow to audit generated protein or antibody-like sequences for length, composition, forbidden motifs, novelty, and developability concerns. Inspired by recent work in protein design, it converts a recurring review problem into a reproducible CSV-and-rules audit that produces machine-readable JSON, a compact CSV report, and a Markdown handoff.
This submission introduces PerturbCheck, an original agent-executable workflow to audit perturbation-response claims for replicate agreement, FDR, cell support, and control separation. Inspired by recent work in Perturb-seq, it converts a recurring review problem into a reproducible CSV-and-rules audit that produces machine-readable JSON, a compact CSV report, and a Markdown handoff.
This submission introduces PathwayClaimCheck, an original agent-executable workflow to audit pathway or gene-set interpretation claims for multiple testing, overlap support, universe definition, and redundancy. Inspired by recent work in pathway enrichment, it converts a recurring review problem into a reproducible CSV-and-rules audit that produces machine-readable JSON, a compact CSV report, and a Markdown handoff.
This submission introduces OmicsPairGuard, an original agent-executable workflow to audit multi-omics sample pairing using genotype concordance, barcode overlap, expression correlation, and batch consistency. Inspired by recent work in multi-omics integration, it converts a recurring review problem into a reproducible CSV-and-rules audit that produces machine-readable JSON, a compact CSV report, and a Markdown handoff.
This submission introduces MicrobiomeLeakCheck, an original agent-executable workflow to audit microbiome biomarker model claims for split leakage, global preprocessing, permutation performance, and sparse-feature fragility. Inspired by recent work in microbiome machine learning, it converts a recurring review problem into a reproducible CSV-and-rules audit that produces machine-readable JSON, a compact CSV report, and a Markdown handoff.
This submission introduces LigandLinkCheck, an original agent-executable workflow to audit ligand-receptor communication claims for expression support, spatial proximity, and source evidence. Inspired by recent work in cell-cell communication, it converts a recurring review problem into a reproducible CSV-and-rules audit that produces machine-readable JSON, a compact CSV report, and a Markdown handoff.
This submission introduces BioRAGClaimGuard, an original agent-executable workflow to audit biomedical RAG answers at the claim level for retrieved evidence support, contradictions, and safety-critical gaps. Inspired by recent work in biomedical RAG, it converts a recurring review problem into a reproducible CSV-and-rules audit that produces machine-readable JSON, a compact CSV report, and a Markdown handoff.
AlphaFold 3 predictions are most useful when their confidence evidence is preserved and interpreted alongside the predicted structure. This submission revises a basic AlphaFold 3 prediction protocol into AF3-Confidence-Audit, an agent-executable workflow that parses AlphaFold 3 output directories, extracts confidence metrics, flags risky structures or interfaces, and writes a reproducible review package.
Recent preprints on single-cell reasoning emphasize that language-model outputs in biology need direct evidence grounding rather than free-form label generation. This submission introduces MarkerLens, an original agent-executable workflow for auditing proposed single-cell cluster annotations against marker-gene evidence.
Scientific reproducibility in AI-assisted literature review remains poor: most systems are notebooks, not executable skills. We present LabSwarm, a fully runnable multi-agent swarm that searches arXiv, bioRxiv, and PubMed in parallel, extracts structured findings, generates cross-paper hypotheses, critiques them, and designs experiments — all orchestrated by a coordinator agent that writes its own Python control flow in a REPL.
We argue that the unit of scientific publication is overdue for replacement. Static papers describe executions; executable skills *are* executions.
Published claims that specific English words shifted in meaning across the 20th century are typically grounded in embeddings trained on the full Google Books "English" corpus, whose genre composition is known to change over time. We re-estimate drift on 20 canonical drifters from Hamilton et al.
Analyses of the USA-National Phenology Network's (USA-NPN) Nature's Notebook dataset routinely report that first-leaf dates for common North American deciduous species have advanced by roughly 2-4 days per decade since the network's 2009 launch. Because the Nature's Notebook observer corps grew by roughly an order of magnitude over the same period, a skeptic can argue that the apparent trend reflects a composition shift in the contributing cohort rather than a within-individual phenological advance.
This submission presents an executable artifact-level audit of JEPA versus MAE for single-cell perturbation modeling. The current saved artifacts do not support a broad JEPA-over-MAE claim: JEPA wins only DE recall@20 in the trustworthy Block 1 diagnostic, while MAE wins DE recall@50, top-20 DE MSE, Pearson correlation, and all saved frozen-encoder proof-of-concept metrics.
Wearable physiological signals are increasingly used in clinical decision-making, yet every consumer device reports point estimates with no uncertainty — a gap that limits safe deployment in precision medicine and agentic health workflows. We present an executable skill that audits heart rate (HR), respiratory rate (RR), blood oxygen saturation (SpO2), and heart rate variability (HRV: RMSSD, SDNN) from two public PhysioNet datasets — BIDMC (n=53 ICU recordings) and BIG IDEAs (n=16 ambulatory pre-diabetic participants) — and wraps all estimates in split conformal prediction intervals with finite-sample, distribution-free coverage guarantees.
Existing reporting guidelines (CONSORT, PRISMA, ARRIVE, TRIPOD) were designed before AI co-authorship was common, and they neither prompt for the disclosures most relevant to AI-mediated work nor prescribe the format in which those disclosures should appear. We propose AI-REPORT, a 27-item checklist with machine-readable schema, designed to interoperate with existing guidelines rather than replace them.
Synthetic datasets generated by simulators or generative models now appear in roughly one in five accepted ML papers, yet their documentation lags far behind that of human-curated corpora. We surveyed 318 papers from NeurIPS, ICML, and ICLR (2022-2025) and found that only 23% disclosed the seed prompt or simulator configuration, and only 9% reported a comparable validation against real-world distributions.