Pranav Bhave
Public record — every marked claim bound in the ledger Registry v0.4 · 21 claims CI prosecution: weekly + every push

Cubits11 / the research world of Pranav Bhave

Keep the wonder.
Check the claim.

The interesting part is what the numbers leave out.
I build ways to see it, question it, and check it.

Same scores. Different worlds.Construction / 01
Constructed 100-item world: A misses ten, B misses ten, both miss 0.
0 togetherA misses 10. B misses 10.
Constructed 100-item world: A misses ten, B misses ten, both miss 10.
10 togetherA misses 10. B misses 10.
A missesB misses100 items in each world

Both worlds fit the scores. The overlap changes everything.
Illustrative construction · bound and scope

Pranav Bhave — AI Assurance · Security Engineering · Evidence Systems

Four guardrails. Four scores.
One missing column.

Guardrail evaluations score each detector and usually omit what the declared stack misses together — the one number a deployment decision actually rests on.

Illustrative: four guardrails with individual catch rates, and an unreported final column for a declared static composition.
Guard AGuard BGuard CGuard DTHE STACK
91%88%94%86%not reported

Illustrative numbers; the gap is the point — no arithmetic on the four printed columns recovers the fifth. I measure what AI guardrail stacks miss together, and build evidence systems that show exactly what data can and cannot establish.

A benchmark can score each supervisor jointly across detection, false positives, latency, and cost; a deployed stack still needs union and all-miss rates on the same items.

20 evaluations examined 5 preserve joint evidence 0 at matched thresholds

MC-001: the 14 shared-item rows and the 14 no-joint-artifact rows are different sets; 0 document matched thresholds with full exposure — 2026-09-01 sensitivity.

Reproduce it in 60 seconds · Publish the missing row · Work with me · Résumé

Pranav Bhave on a sunlit lawn in a navy polo and sunglasses, smiling, chin resting on his hand
Pranav Bhave · Penn State B.S. CS ’26 · Philadelphia

Start with your question

A research front door before the dossier.

The Missing Column — a source-bound census

Which public evaluations preserve the joint evidence, and which leave it unmeasured?

A bounded, single-reviewer inventory of public guardrail evaluations, examined against primary sources. Every row binds to its source with quoted passages, a fixed classification, and its own correction history. The inclusion wording is locked in repository history before any row was classified, the headline is regenerated from a file anyone can mechanically make false, and a qualifying artifact the search missed rejects the current counts rather than being absorbed quietly.

Two guardrails each fail 10% of the time. How often do they fail together? The common answer is 1%. The evidence permits anywhere from 0% to 10% — multiplying the two rates quietly chose one world out of many, and never said so. Choose for yourself:

Two 10 percent failure rates permit anywhere from 0 to 10 percent joint failure A rectangle of area one represents the population. Two shaded strips each cover ten percent of it, one per guardrail. Their overlap is the probability both fail on the same input. The overlap can be set anywhere from zero to ten percent while neither individual rate ever changes. A vertical cyan scale marks the full supported interval from 0 to 10 percent, with a dashed amber mark at 1 percent — the single value that assuming independence selects. The zero-overlap and full-overlap positions are the lower and upper endpoint witnesses. The population — area = 1 10% upper witness 0% lower witness 1% — what independence picks π(q) = (0.80, 0.10, 0.10, 0.00) · P(A) = P(B) = 10% in every frameP(both fail) = 0% · P(at least one fails) = 20% · the lower endpoint witness0% π(q) = (0.81, 0.09, 0.09, 0.01) · P(A) = P(B) = 10% in every frameP(both fail) = 1% · P(at least one fails) = 19% · the world independence assumes1% π(q) = (0.82, 0.08, 0.08, 0.02) · P(A) = P(B) = 10% in every frameP(both fail) = 2% · P(at least one fails) = 18% · one feasible world2% π(q) = (0.83, 0.07, 0.07, 0.03) · P(A) = P(B) = 10% in every frameP(both fail) = 3% · P(at least one fails) = 17% · one feasible world3% π(q) = (0.84, 0.06, 0.06, 0.04) · P(A) = P(B) = 10% in every frameP(both fail) = 4% · P(at least one fails) = 16% · one feasible world4% π(q) = (0.85, 0.05, 0.05, 0.05) · P(A) = P(B) = 10% in every frameP(both fail) = 5% · P(at least one fails) = 15% · one feasible world5% π(q) = (0.86, 0.04, 0.04, 0.06) · P(A) = P(B) = 10% in every frameP(both fail) = 6% · P(at least one fails) = 14% · one feasible world6% π(q) = (0.87, 0.03, 0.03, 0.07) · P(A) = P(B) = 10% in every frameP(both fail) = 7% · P(at least one fails) = 13% · one feasible world7% π(q) = (0.88, 0.02, 0.02, 0.08) · P(A) = P(B) = 10% in every frameP(both fail) = 8% · P(at least one fails) = 12% · one feasible world8% π(q) = (0.89, 0.01, 0.01, 0.09) · P(A) = P(B) = 10% in every frameP(both fail) = 9% · P(at least one fails) = 11% · one feasible world9% π(q) = (0.90, 0.00, 0.00, 0.10) · P(A) = P(B) = 10% in every frameP(both fail) = 10% · P(at least one fails) = 10% · the upper endpoint witness10%
q = 0% — the lower endpoint witness Dragging changes only the overlap of the two failures. Each guard's marginal failure rate remains ten percent.
Fig. 02 — the same two scores, every world they permit. Both guardrails fail 10% of the time in every position. Only the overlap moves. The cyan scale is the full supported interval; independence is the amber tick — one named assumption-world, not the answer. The endpoint worlds are witnessed, and the geometry of every frame is asserted in CI. The full argument →

Current programs

Three programs, and no more. Evidence markers apply to the technical project claims below; biographical facts are owner-attested unless linked. Chips with a solid dot open public evidence. Attested means stated on my responsibility, dated, with no public artifact yet — provenance, not proof. Exact bindings — commit SHAs, executable review triggers, falsifiers, forbidden rescues, non-claims — live in the evidence ledger, and each claim also has its own page carrying the falsifier next to the proposition. Everything older or superseded is in the archive, with its succession recorded.

Research framework · Python · MIT · 2025 — present

CC-Framework

Treats composed-guardrail failure as a partial-identification problem: individual rail failure rates are known, their joint dependence is not. Given marginal evidence and declared dependence assumptions, it computes sharp Fréchet–Hoeffding bounds on stacked-system failure with endpoint witnesses, and records the boundary of the resulting claim — claim envelopes, evidence roles, receipts, decay semantics. Its flagship computation and witnesses are re-reproduced from a clean clone by this site's CI, weekly.

S2 Lab, Penn State · verification research · in development

Ghost-Ark

A verifier and measurement harness for the provenance limits of AI-governance receipts. Its research claim: receipt soundness is a ternary relation — Sound(C, Σ, P) — and a receipt identifies an execution only up to the kernel of its whole parse → canonicalize → digest pipeline, so soundness does not persist by default as pathologies and consumers grow. Collisions are demonstrated as possible, not measured as prevalent — and the repo says so.

Non-claim — a verifying receipt does not establish that the governed action was safe, authorized, or semantically correct.

Field artifact P₀ · evidence-bound interfaces · experimental

The record itself

This site is the third program: a claim registry rendered into a generated ledger, bound to immutable commits, watched by executable review triggers, re-reproduced from clean clones in CI. The claim observatory renders the registry as one field of capsules, bindings, and decay clocks. The central hypothesis — that claim-bound interfaces improve a reader's comprehension or calibration — is untested; the control study is designed, not run.

Non-claim — aesthetic coherence is not epistemic reliability; what this interface does to readers is an open question.

Ghost Visualizer A seven-scene visual essay, “Why AI Safety Scores Lie”: identical marginal guardrail scores hiding shared misses, with computed bounds, endpoint witnesses, and an inspectable receipt object. Runs locally; no hosted deployment yet — and its own readiness review scopes it to private demos, so this stays a source link.
Inspect source ↗
Assay Early-stage, private: enclave-attested media processing on AWS Nitro Enclaves — which provenance claims can a verifier actually derive from attestation, and which can it not. Attestation cannot establish a file's history prior to the first attested operation; the boundary is the project.
Attested · 2026-08 — stated on my responsibility; no public artifact linked yet
Earlier work GCE and the superseded guardrail-composition line are preserved in the archive as intellectual lineage, each with what it explored, what was wrong, and what replaced it.
Enter the archive →

The five-card discipline

One experimental protocol — E₁ — not a universal grammar. It fits controlled tests; theorems, historical claims, and calibration problems need other test designs. The general form is the claim envelope, below.

Claim

What I say the system does. Named first, in writing.

Falsifier

The observation that would end the claim. If none exists, neither does the claim.

Control

The comparison that could embarrass it — run on purpose.

Non-claim

What this evidence will never support, stated before anyone asks.

Result

Two distributions sharing every singleton and pairwise moment; three-way failure of 0% in one and 25% in the other. Measuring every pair does not identify the triple.

Supported within scope — controlled synthetic · decision: Narrow

Lock the first four before the result slot fills, then let the result disagree. The result above is E₁'s: it survived, and it narrowed the claim rather than widening it — claim CC-003 binds it. A story can start a question. It cannot finish an answer. Untested is not inconclusive: inconclusive means evidence arrived and failed to discriminate; untested means the world has not answered yet. This page keeps the two apart — and keeps its own rules scoped, as declared above.

Candidate C₁

The claim envelope

1 · Proposition

What exactly is asserted.

2 · Scope

Where it holds, and under which assumptions.

3 · Support

The evidence that bears on it, bound to immutable artifacts.

4 · Falsifier

The condition that defeats the proposition, with its fixed consequence.

5 · Test design

Control, comparator, calibration, proof, benchmark, or adversary.

6 · Status

Untested · supported within scope · partial · inconclusive · contradicted.

7 · Boundaries

What remains unestablished — and the post-falsification rescues the claim cannot use.

8 · Freshness

When, and on what trigger, it must be re-examined.

The evidence ledger is generated from a registry that implements these fields — propositions, separated provenance and status dimensions, immutable bindings, falsifier conditions with fixed consequences, forbidden rescues, executable review triggers that watch the bound evidence upstream, freshness windows, non-claims. Where a trigger can't be executed by CI, the ledger says manual, plainly.

Research & training

Aug — Dec 2025 · Penn State

Independent research — LLM safety guardrail composition

Reinforcement, interference, and dependence-driven failure in composed LLM safety systems, via probabilistic bounds and copula-family reasoning. Supervised by Dr. Peng Liu (IST 496). CC-Framework is the primary deliverable.

Jan — May 2025 · Penn State

Research assistant — logic & verification tooling

Python CNF-conversion tooling for SAT-solving workflows, and evaluation of LLM-assisted formalization of natural-language logic: translation reliability, ambiguity handling, verification-readiness.

May 2026

Pennsylvania State University

B.S. Computer Science, minor in Cybersecurity. Coursework: computer security, operating systems, algorithms, statistical inference, theory of computation.

Certified

AWS — Cloud Practitioner · AI Practitioner

Solutions Architect Associate (SAA-C03) and Security — Specialty in progress.

Certifications are owner-attested here: verification IDs are available on request rather than published.

The current question · frozen before any dataset was inspected

Can dependence evidence be measured at feasible cost — before it has to be assumed?

E2, the first empirical rung of the evidence ladder, is a shared-item measurement contract frozen in advance; no conforming dataset has been collected, so it is untested — and says so. The next artifact is a conforming observation set, or a documented failure to obtain one. What is moving right now →

Writing

When marginals are not enough The flagship case: two 10% guardrails, the interval the evidence actually supports, and the witnesses at both ends — with the kernel's recorded output at a bound commit.
Read the flagship case →
Noetic log 002 — the observatory ships, and gets graded The v0.4 shipping record rated without anesthesia, with a one-month lookback contract whose unflattering conclusion is pre-registered.
Read Noetic log 002 →
All writing Essays, field notes, and audit logs, with each piece's claim envelope where one applies.
Browse all writing →

Contact

Have a claim worth checking?
Bring it — I’ll bring the falsifier.

I’m looking for research, engineering, and independent consulting work where statistical assurance, provenance, and claim governance matter.