Build a stable hashed manifest of bounded public/synthetic artifact contents, declared dependencies, algorithm version, seed, and parameters. Verify declared content hashes; reject duplicate/dangling dependencies and cycles. No artifact fetching, execution replay, signing, or authenticity guarantee.

Calculate X, Y and Z Pauli expectations for a supplied valid single-qubit density matrix. Returns basis conventions; not a hardware measurement.

Calculate squared Uhlmann fidelity and purity for two supplied single-qubit density matrices. Explicit conventions; no experimental certification.

Invert a supplied single-qubit readout calibration and report sensitivity and nonphysical corrected fractions without clipping. Calibration uncertainty not estimated.

Lint up to 128 declared gates on eight qubits for arity, target, angle and post-measurement errors. Returns scheduling depth; no simulation or equivalence proof.

Fit a bounded damped Rabi/Ramsey trace by frequency-decay grid search; report residuals, resolution, aliasing refusal and edge hits. No parameter confidence interval.

For agents reviewing shot-count results: return probabilities and binomial confidence intervals with the interval method and independence assumptions.

Paired finite-state replay of onset/dwell and hysteretic release settings over at most 512 labelled offline scores. Timers and state carry across contiguous trials. At equal timestamps score changes precede timers; no event fires at the final endpoint. Reports paired false-event, miss and latency metrics. No hardware or live control.

Exact minimum-cost set cover over at most 12 stations and 16 declared requirements. Enumerates at most 4,095 nonempty subsets; breaks equal costs by station count then sorted keys. Reports infeasible coverage explicitly. Coverage and costs are caller declarations, not field verification.

Compute earliest/latest starts and finishes and slack on a declared DAG of at most 48 tasks. Rejects cycles and unknown dependencies. Reports peak overlap of declared unit resource claims at the earliest schedule; does not optimize a resource-constrained schedule or verify physical resources.

Fit supplied randomized-benchmarking decay observations with residuals and protocol-bound error estimates. Not a platform-independent quantum-computer ranking.

Check a supplied single-qubit complex density matrix for unit trace, Hermiticity and positive semidefiniteness with explicit tolerance; no hardware validation.

Summarize supplied per-residue pLDDT scores into explicit confidence bins. Does not assess missing residues, folding correctness, function or clinical suitability.

Check supplied FASTA records for malformed headers, duplicate identifiers and invalid sequence characters before dataset ingestion. No functional or safety inference.

Compare caller-declared qubit count, connectivity and gate-duration requirements with supplied architecture capability records. No verified best-platform recommendation.

Calculate a surface-code resource scenario under an explicitly named layout and supplied error assumptions. For planning; not a demonstrated physical implementation.

Check supplied Ct replicates, efficiency and control declarations against fixed research QC bands; report Ct SD and failed conditions. No diagnostic validation.

Check supplied stabilizer generators for commutation, independence and inconsistent constraints before analysing a code. No logical-error or fault-tolerance guarantee.

Calculate stock and working concentrations from supplied quantities with unit and feasibility checks. For arithmetic verification; no chemical-handling or safety guidance.

Calculate a Pfaffl expression ratio from supplied Ct values and amplification efficiencies; require a declared stable reference. No diagnostic interpretation.