• using R version 4.5.2 Patched (2026-01-31 r89382)
• using platform: aarch64-apple-darwin20
• R was compiled by     Apple clang version 16.0.0 (clang-1600.0.26.6)     GNU Fortran (GCC) 14.2.0
• running under: macOS Ventura 13.7.8
• using session charset: UTF-8
• checking for file ‘lambdastar/DESCRIPTION’ ... OK
• checking extension type ... Package
• this is package ‘lambdastar’ version ‘0.8.1’
• package encoding: UTF-8
• checking package namespace information ... OK
• checking package dependencies ... OK
• checking if this is a source package ... OK
• checking if there is a namespace ... OK
• checking for executable files ... OK
• checking for hidden files and directories ... OK
• checking for portable file names ... OK
• checking for sufficient/correct file permissions ... OK
• checking whether package ‘lambdastar’ can be installed ... [2s/2s] OK See the install log for details.
• checking installed package size ... OK
• checking package directory ... OK
• checking DESCRIPTION meta-information ... OK
• checking top-level files ... OK
• checking for left-over files ... OK
• checking index information ... OK
• checking package subdirectories ... OK
• checking code files for non-ASCII characters ... OK
• checking R files for syntax errors ... OK
• checking whether the package can be loaded ... [0s/0s] OK
• checking whether the package can be loaded with stated dependencies ... [0s/0s] OK
• checking whether the package can be unloaded cleanly ... [0s/0s] OK
• checking whether the namespace can be loaded with stated dependencies ... [0s/0s] OK
• checking whether the namespace can be unloaded cleanly ... [0s/0s] OK
• checking loading without being on the library search path ... [0s/0s] OK
• checking dependencies in R code ... OK
• checking S3 generic/method consistency ... OK
• checking replacement functions ... OK
• checking foreign function calls ... OK
• checking R code for possible problems ... [2s/2s] OK
• checking Rd files ... [0s/0s] OK
• checking Rd metadata ... OK
• checking Rd cross-references ... OK
• checking for missing documentation entries ... OK
• checking for code/documentation mismatches ... OK
• checking Rd \usage sections ... OK
• checking Rd contents ... OK
• checking for unstated dependencies in examples ... OK
• checking installed files from ‘inst/doc’ ... OK
• checking examples ... [0s/0s] OK
• checking for unstated dependencies in ‘tests’ ... OK
• checking tests ... [15s/15s] ERROR   Running ‘core.R’ [15s/15s] Running the tests in ‘tests/core.R’ failed. Complete output:   > library(lambdastar)   >   > # Deliberately base R: the tests need no optional testing installation.   > .count <- 0L   > .failures <- character()   > test <- function(name, code) {   + tryCatch({ force(code); .count <<- .count + 1L; cat("PASS:", name, "\n") },   + error = function(e) {   + .failures <<- c(.failures, paste(name, conditionMessage(e), sep = ": "))   + cat("FAIL:", tail(.failures, 1), "\n")   + })   + }   > equal <- function(actual, expected, tol = 1e-10) {   + result <- all.equal(actual, expected, tolerance = tol, check.attributes = TRUE)   + if (!isTRUE(result)) stop(paste(result, collapse = "; "))   + }   > relative <- function(actual, expected, tol = 1e-8) {   + stopifnot(length(actual) == length(expected), all(is.finite(actual)),   + all(is.finite(expected)), all(expected != 0),   + all(abs(actual / expected - 1) <= tol))   + }   > fails <- function(code, pattern) {   + err <- tryCatch({ force(code); NULL }, error = identity)   + if (is.null(err) || !grepl(pattern, conditionMessage(err)))   + stop("Expected error matching: ", pattern)   + }   > test_root <- if (dir.exists("cases")) "." else "tests"   > fixture <- function(name) file.path(test_root, "fixtures", name)   > for (file in list.files(file.path(test_root, "cases"), full.names = TRUE)) source(file)   PASS: measurement API preserves scale and case provenance   PASS: matrix, formula, lm and H1 paths agree   PASS: two-group adapter agrees with pooled-variance t-test   PASS: ANOVA, ANCOVA and interaction use the full encoded model   PASS: recoding preserves projection but can change geometry and F_H   PASS: lm stored contrasts survive changes to global contrast options   PASS: response mismatches and external formula variables are rejected   PASS: lm validates saved cases, design and response against common data   PASS: weights, offsets and other model families are rejected   PASS: rank deficiency, lost levels and invalid explicit row identity fail   PASS: mean response and F_H temperature stay coupled under item scaling   PASS: null model and temperature singularity remain explicit   PASS: required data, indicators, resolution and settings are validated   PASS: S3 summaries and printing expose estimates without full matrices   PASS: bootstrap defaults and explicit overrides are resolved and validated   PASS: same seed gives identical joint draws and changing seed changes draws   PASS: bootstrap preserves RNG kind and present or absent caller seed   PASS: joint resampling matches independent pairwise moments and lm.fit   PASS: percentile intervals use requested level and joint kappa ratios   PASS: missingness and strata use one original selection and retain row mapping   PASS: fixed-mixture variance requires estimable within-stratum variances   PASS: comparison shares draws with separate matrix/formula/lm pipelines   PASS: data-dependent transformations rebuild while factor coding stays fixed   PASS: lost factor levels fail only the affected model and never get replaced   PASS: zero temperature skips every CI including temperature without sampling   PASS: zero total structure never yields an invented kappa interval   PASS: item scaling transforms both point and interval noncentralities   PASS: retention is optional, thresholds explicit, summaries include diagnostics   PASS: numerical eta agrees with independent 90-digit Decimal reference   PASS: tiny eta follows analytic three-bin limit instead of 0.5   PASS: capacity scaling, vectorization and high-resolution behavior   PASS: thermal boundaries and smooth small-temperature stability   PASS: direct quadrature agrees with known primitive and small-ratio limit   PASS: lookup agrees with direct integration across range and off-grid   PASS: numerical controls are validated and limits fail explicitly   PASS: comparison equals separate evaluations and obeys swap/self identities   PASS: common missingness selection precedes both data-dependent designs   PASS: matrix missingness joins the same common complete-case selection   PASS: lm case omissions are accepted only when they match the common rows   PASS: two explicit models and a common matrix are required   PASS: comparison retains each formula coding and common numerical settings   PASS: transform-created missing and nonfinite values never alter cases silently   PASS: E3 preserves 0.5.0 whole and conditional adaptive-basis outputs   PASS: general multirow L agrees with independently fitted restricted models   PASS: coefficient, matrix and lm sources retain the same conditional geometry   PASS: full coefficient restrictions reduce to a whole-model state   PASS: L units and invertible recoding preserve capture but retain F_H geometry   PASS: L input errors and nonidentifiability are explicit   PASS: derived null and target are rebuilt for every complete-case bootstrap draw   PASS: contrast cluster draws preserve all rows and variable sample sizes   PASS: fixed and reevaluated polynomial/spline blocks reproduce their declared draw estimators   PASS: fixed adaptive nuisance and whole-model encoding are learned after selection   PASS: simple and explicitly averaged grid effects agree with named coefficient L   PASS: grid prediction uses learned poly, spline and scale coordinates   PASS: fixed grid contrasts use original learned basis with draw-specific restricted fits   PASS: fixed named polynomial coefficients differ from reevaluated coordinates as declared   PASS: grid validation prevents implicit weighting and unsupported prediction recipes   PASS: Fourier and explicitly fixed-knot piecewise/spline recipes equal encoded matrices   PASS: rank failures remain original draw failures without replacement   PASS: multirow grid recoding shares one null reference and retains factor coding   PASS: contrast singular temperature and undefined kappa retain their meanings   PASS: parallel measurements agree with independent pairwise identities   PASS: two-replicate identity and default composite scale   PASS: partition identity, scaling, and preserved observation identity   PASS: zero bath is singular while zero signal has undefined kappa   PASS: invalid measurements and row mismatches are rejected   PASS: tiny positive temperature is not clipped to zero   PASS: 0.4.1 baseline points, geometry, draws and intervals remain compatible   PASS: saved designs retain coding independently of global contrasts and caller functions   PASS: lm and matrix design objects preserve their encoded models   PASS: bound designs reject stale predictors and row order but permit new measurements   PASS: conditional blocks match restricted fits and actual encoded geometry on unequal cells   PASS: block transformations are rebuilt after shared selection and inside each draw   PASS: additional nuisance and conditional cluster bootstrap keep common row provenance   PASS: comparison requires explicit compatible references and preserves paired draws   PASS: conditional comparisons share nuisance while retaining distinct target columns   Tracing function ".nuisance_space" in package "namespace:lambdastar"   Tracing function ".thermal_terms" in package "namespace:lambdastar"   Untracing function ".nuisance_space" in package   "namespace:lambdastar"   Untracing function ".thermal_terms" in package "namespace:lambdastar"   PASS: shared point evaluation prepares nuisance and thermal terms only once   PASS: term selections, omissions and rank failures have explicit meaning   PASS: designs preserve singular temperatures and raw coding sensitivity   PASS: panel time trend matches explicit person dummy least squares   PASS: default panel occasion effect is categorical with literal coding   PASS: additional nuisance is projected within persons with correct rank   PASS: panel target blocks express group by occasion effects after person adjustment   PASS: person slopes rebuild separate copies in every bootstrap draw   PASS: unbalanced panel bootstrap retains each selected person's entire pattern   PASS: person resampling keeps stratum counts and rejects time-varying strata   PASS: panel complete selection removes whole persons on common comparison variables   PASS: panel comparisons reuse the same measurement and standalone numerical F   PASS: person fixed effects can be targets with distinct bootstrap identities   PASS: paired two-occasion reduction agrees with E6a lambda values and scaled F   PASS: panel scale and person-constant shifts preserve appropriate quantities   PASS: panel validation rejects ambiguous maps and incompatible estimator paths   PASS: panel fixed non-person bases and explicit matrices remain usable   PASS: declared person factor contrasts survive panel preparation and resampling   PASS: panel zero temperature and zero signal retain explicit diagnostic meanings   PASS: saturated person by occasion interactions retain positive bath df   PASS: unavailable library percentiles return diagnostics without substituted bounds   PASS: single-model F_H agrees with independent lm and determinant   PASS: recoding changes F_H solely through geometry   PASS: singular inference is distinct from the mathematical boundary   PASS: null model, smooth opt-in, and response-scale covariance   PASS: population estimator is independent of bootstrap and confidence level   PASS: every stored draw matches independent pairwise moments and OLS   PASS: percentile construction agrees with boot on the identical person draws   PASS: weak signal records undefined ratios without substituting an interval   PASS: valid zero/one ratios and degenerate distributions retain their percentiles   PASS: fixed-stratum population draws match independent mixture variance   PASS: null models have valid zero localization for positive signal   PASS: saturated models keep finite-person F_H and identify unestimable population projection   PASS: singular temperature draws preserve temperature zeros and report dependent failures   PASS: zero total point retains a lambda interval and an undefined kappa point   PASS: unrepresentable tail probabilities are reported without substituting limits   PASS: known orthogonal energy partition is 9 plus 16   PASS: encoded geometry differs while recoded projection agrees   PASS: null, one direction, rank loss, and bad projection   PASS: reduced factor contrasts agree across formula, matrix, lm and comparison bootstrap   PASS: two reduced contrasts retain their directions with rebuilt transformations and interactions   PASS: paper is the default and selected points are the CI statistics   PASS: nuisance formula and full matrix reproduce independent conditional moments   PASS: nuisance and cluster columns participate in the common case selection   PASS: cluster sampling preserves whole clusters and refits nuisance for every draw   PASS: nuisance rank loss is diagnosed without replacing bootstrap draws   PASS: nuisance transforms are rebuilt and explicit row ordering is enforced   PASS: conditional encoded geometry governs F_H after nuisance adjustment   FAIL: paper saturation is supported and nuisance temperature zero stays singular: 1 string mismatch   PASS: reference mean uses N degrees of freedom and preserves its direction   PASS: reference null and free mean share measurement and numerical F components   PASS: reference formula and matrix use uncentered encoded geometry   PASS: translation and paired sign preserve magnitudes without hiding direction   PASS: explicit nuisance retains only the declared reference space   PASS: explicit affine L beta=c matches independent constrained least squares   PASS: fixed-reference case draws carry row-specific origins and exact percentiles   PASS: reference cluster draws recompute N and resample the origin vector   PASS: reference comparison rejects changed origins and implicit centered partners   PASS: paired differences are recomputed on the supplied pair coding   PASS: paired selection keeps complete persons and response units   PASS: reference zero-signal and zero-temperature cases keep their meaning   PASS: reference and centered saturated ranks have their appropriate dimensions   PASS: reference response rescaling changes temperatures and F but not noncentrality   > cat(sprintf("\nLambda Star: %d passed, %d failed.\n", .count, length(.failures)))      Lambda Star: 138 passed, 1 failed.   > if (length(.failures)) stop(paste(.failures, collapse = "\n"))   Error: paper saturation is supported and nuisance temperature zero stays singular: 1 string mismatch   Execution halted
• checking PDF version of manual ... [4s/4s] OK
• DONE

Status: 1 ERROR