Daniel KliewerThe book

Concept

Provenance and evidence

Every claim keeps the trail back to what supports it, including when the trail ends nowhere.

Provenance is usually treated as metadata. It is better treated as a constraint: a claim without a traceable source is not a weaker claim, it is a different kind of object.

The interesting case is when the trail terminates somewhere empty — the source does not exist, or does not say what it was cited for. A system that can represent that outcome is more useful than one that silently drops the claim, because the empty trail is itself the finding.

This is why the archive project renders the trail as a physical object in the film: the beam from claim to source, and the plinth with nothing on it.

Implementation

Where this runs

A concept that never left a document is a hypothesis. These are the systems that implement it.

2026-10-01

GanymedeA knowledge compiler: source material in, structured and validated knowledge units out.

→

2026-07-06

Sovereign Intelligence ObservatoryInstrumentation for watching a local intelligence system evolve over time.

→

Writing

13 articles on this

Aug 9, 2026

Hermes Atlas v0.1: A Local-First, Incrementally-Compiled, Falsifiable Knowledge SystemHermes Atlas v0.1 is a local-first, incrementally-compiled, falsifiable knowledge system. This is a full replication guide: every command was run for real, and the failure modes are the findings.

7 min

Aug 9, 2026

Hermes Atlas v0.2: Claim-Level Coverage, a Determinism Gate, and a Knowledge-Mutation CanaryHermes Atlas v0.2 is a benchmark-and-fix release: claim-level coverage localisation, a determinism gate that proves compile reproducibility, and a knowledge-mutation canary. Every number below was measured, not asserted.

7 min

Aug 9, 2026

Hermes Atlas v0.3: An Evidence Ledger, a Provable Claim Lifecycle, and an Explain CommandHermes Atlas v0.3 adds an evidence ledger to every claim, a provable claim lifecycle (including DELETE-driven invalidation that retains history), and an `atlas explain` command. Every number below was measured, not asserted.

7 min

Aug 9, 2026

Hermes Atlas v0.4: Proving the Evidence Ledger & Claim Lifecycle with a Gold-Labeled BenchmarkHermes Atlas v0.4 proves the v0.3 evidence ledger and provable claim lifecycle with a gold-labeled benchmark. Every number was measured on a fixed, model-free corpus; two real bugs were found and fixed in the process. Everything below is reproducible.

8 min

Jul 26, 2026

Does the Compiler Know When It's Wrong? Semantic Rediscovery and the Limits of Falsification-AwarenessPopper-ORKG ended with two honest failures: temporal rediscovery was near-zero, and the compiler confidently rebuilt Lamarckian inheritance. v4 exists to ask whether those are fixable weaknesses or fundamental limits — by adding measurement, not by tuning the scorer. The answer turned out to be one of each. Mechanism-level semantic matching shows rediscovery was a measurement artifact all along (0.63 vs 0.005 exact-match, flat across temporal gaps). But a falsification-awareness consensus check could not downgrade Lamarckism or caloric: the ORKG index contains no detectable refutation edges, so the near-miss is a genuine limit of the knowledge substrate. Everything in popper/ and orkg/ stayed byte-for-byte frozen, md5-verified. Run locally on a 35B model.

8 min

Jul 25, 2026

Does the Hypothesis Compiler Generalize? Running Popper on a Corpus I Did Not BuildPopper beat its controls on five hand-curated benchmark literatures — but I built those corpora, so the result could be an artifact of clean data. This experiment removes that objection: the identical pipeline, byte-for-byte, run on a corpus I did not build — the Open Research Knowledge Graph, 6.3 million triples across 65,689 papers and seven scientific disciplines. Same schema, same rubric, same four-way controls; the only independent variable is the corpus. The compiler still wins (0.85 composite vs 0.56 keyword vs 0.00 ungrounded), an ablation proves the architecture is load-bearing (remove graph reasoning and it collapses to zero), and the grounding audit finds zero hallucinated citations across 265 evidence items. It also fails honestly: exact temporal rediscovery is near-zero, and it confidently rebuilds Lamarckian inheritance. Run locally on a 35B model.

11 min

Jul 24, 2026

Popper: Making the Hypothesis Compiler Falsifiable — Rediscovery Benchmarks, Negative Controls, and the Move From Plausible to ProvableThe last experiment proved a knowledge-graph compiler survives scale. This one asks a harder question: are its hypotheses scientifically meaningful, or only linguistically convincing? Popper stops trying to make the compiler smarter and starts making it falsifiable — a strict hypothesis schema, source-level provenance, three negative controls, and a historical rediscovery benchmark where the discovery paper is removed and the system must reconstruct the leap from prior literature alone. Run locally on a 35B model: the compiler scored 0.89–0.97 composite against 0.00 for ungrounded generation, and reconstructed the CTLA-4 checkpoint-blockade and nucleoside-modified-mRNA discoveries from their prior literature — while honestly failing on CRISPR and refusing to confidently rebuild phlogiston.

9 min

Jul 23, 2026

Building the Scientific Question Compiler: A Map of What We Do Not KnowWe built the second compiler in the Scientific State program: the Scientific Question Compiler, which turns a corpus into a map of what humanity does not yet know. Local-first, running on a 35B model on our own hardware. Here is what we built, what broke, and what it means.

7 min

Jul 23, 2026

Compiling the State of Human Understanding: A Roadmap for the Scientific State CompilerA research roadmap: the four compiler directions — Mechanistic Reasoning, Scientific Question, Scientific State, and Discovery — are not competing projects. They are five passes in one architecture that compiles the scientific corpus into a versioned, executable model of human understanding. Here is the full plan.

14 min

Jul 22, 2026

If the Loop Is the Product, Observability Becomes the Operating SystemYesterday I argued scientific knowledge needs a compiler, not a better research assistant. Today I built the general one — five discovery passes, local-first version control for understanding, and a live explorer. This is what it means when the loop, not the model, is the product.

9 min

Jul 21, 2026

Compiling Medical Evidence: A Clinical Research Compiler That Turns Guidelines and Trials Into a Queryable Knowledge ArtifactHow to compile medical guidelines, trials, and literature into a provenance-tracked, queryable Clinical Knowledge Artifact — and deploy a live evidence explorer to Vercel — by extending the Research Compiler Agent SDK into a Clinical Research Compiler.

9 min

Jul 21, 2026

A Research Compiler for Scientific Understanding, Not a Better Research AssistantA research vision: why scientific knowledge needs a new computational architecture. The Clinical Research Compiler SDK is an early prototype of a scientific reasoning compiler that transforms literature into versioned understanding — not a better research assistant.

13 min

Jul 20, 2026

Compile-Time Intelligence: Building a Research Compiler Agent That Compiles Knowledge Instead of Re-Reading ItAn autonomous Research Compiler Agent that compiles web sources into a persistent, queryable, provenance-tracked Knowledge Artifact — moving semantic computation from runtime inference into reusable artifacts (Compile-Time Intelligence). Built on the Knowledge Compiler SDK; local-first and reproducible.

9 min

← All concepts