Research / Engineering / News / Blog
The latest published work.
Research papers, engineering notes, company news, and practical Blog articles from Licklider, newest first.
Latest entries
November 9, 2026
Engineering / Upstream report
MCP Python SDK can turn an HTTP image into corrupted text
A valid PNG loses its original bytes when HttpResource decodes it as text, while the same image returned through BinaryResource is preserved.
MCP Python SDK #3843 open; contributor reproduction reported; maintainer confirmation and repair pending
November 9, 2026
Engineering / Upstream report
python-flint merges a repair that preserves decimal error bounds
python-flint merged the reported constructor repair and regression tests, preserving midpoint uncertainty when tuple radii are added to inexact decimal inputs.
Fix merged upstream in python-flint PR #449; issue #448 closed; release pending
November 9, 2026
Engineering / Upstream report
Large integers can change SciPy’s Mann–Whitney U decision
Eight distinct integers become artificial ties inside SciPy, changing an exact p-value from 1/35 to 2/35 without changing the original ordering.
Fix proposed in SciPy PR #26667 · open
September 27, 2026
Engineering / Upstream report
SciPy returns zero for a representable Student-t tail
A Welch test and two lower-level Student-t functions return zero for a positive subnormal probability that remains representable in binary64.
Closed as not planned on September 30, 2026 — MPArray recommended; no NumPy-backend fix merged
September 27, 2026
News / Public consultation
nomue Protocol opens public discussion on an exact-value Welch successor
Public comment is open on a proposed bounded successor for Welch checks, with exact-value evidence, explicit domain limits and a Contract-bearing Record format.
Discussion ended; no decision published — Release 1 unchanged
September 23, 2026
Research / Publication
Reducing the cost of historical-analysis reuse decisions with nomue: a paired, equal-evidence LLM evaluation
Adding nomue reduced API cost by 78.1% and task time by 62.9% on historical-analysis reuse decisions the ordinary-tool comparator also answered correctly.
Preprint v1 — not peer reviewed; synthetic Welch tasks; aggregate reproduction supplement available
September 23, 2026
Engineering / Upstream report
jStat returns zero for a probability near 44%
Independent integration and a mathematical lower bound expose a noncentral-t probability collapse that remains after an earlier convergence safeguard.
Reported in jStat issue #300 — upstream confirmation pending
September 22, 2026
Engineering / Upstream report
statsmodels returns zero for a representable chi-square tail
A reported p-value collapse for a representable chi-square tail led to a merged statsmodels repair with regression coverage for related contingency-table paths.
Fix merged into statsmodels main in PR #10276 — not yet released
September 19, 2026
Engineering / Implementation note
Preserving Welch confidence intervals near zero
A public-source verifier repair retains precision before nearly equal quantities are subtracted, with independent reference checks around the boundary where the repair takes over.
Merged source repair; not in the published npm 0.2.1-rc.1; no Protocol scope or tolerance change
September 19, 2026
Engineering / Implementation note
Keeping independent checks visible when verification fails
An experimental Holm verifier preserves eligible Record checks when the caller’s expected context differs, and explains why dependent checks cannot run.
Unreleased development version; research review and implementation not finished; no new supported capability