Every investigation eventually reaches the same moment: two competent people look at the same evidence and walk away believing different things. We compare their conclusions, not their reasoning. We argue over who is right. We almost never ask where they first began thinking differently.

Reasoning Diff Lab v2.0.0 is a local-first research prototype built to change that. It records and compares two independently authored reasoning paths against the same evidence set. The goal isn't to determine truth or rank investigators. It's to make the relationship between their reasoning inspectable.

The project passes 58 tests with 0 failures. A full build produces 22 divergence events across three synthetic cases. That proves the instrument runs as designed. It does not prove investigators will find it useful — that's exactly what the pilot is designed to determine.

What it actually is

Each analyst breaks their reasoning into small typed pieces: an observation, an assumption, an inference, a claim, an explicit unknown. They tag which evidence and which earlier piece each one depends on, with a confidence level attached. A reviewer who authored neither path matches the two sets: same position, related but distinct, or unrelated. Contradiction is separate — it must be declared by the reviewer and is never guessed by the system.

From there, everything is mechanical. The tool walks the matched and unmatched pieces and reports what it finds. If the report says two analysts diverged, you can trace that line back to the exact evidence, the exact dependency chain, and the exact reviewer decision that produced it.

What it surfaces in practice

  • Shared evidence, different interpretation. Both analysts cite the same authentication log. One reads it as stolen credentials. The other reads it as expired-token behavior. Same source, materially different explanation.
  • Evidence used by only one side. One analyst built part of their case on the deployment timeline. The other never touched it — maybe for a good reason, maybe because they never saw it.
  • Confidence divergence. Two analysts land on the same conclusion. One is 90% sure. The other is 55%. That gap is invisible if all you ever compare is the final sentence.
  • Undeclared support. A claim exists with no evidence and no stated reasoning behind it. The tool doesn't call this wrong. It only reports, accurately, that nothing was declared.

What it doesn't do

It does not determine truth, rank investigators, or declare one analyst better than the other. It does not infer a contradiction from wording — a contradiction only exists in its output if a human reviewer explicitly confirms one. It does not replace human review; it tries to make that review faster to start, and harder to skip a step in.

Where this falls short

Match suggestions are lexical keyword overlap, nothing smarter. A human reviewer has to confirm or reject every one. Structured entry is a genuine cost: breaking your own reasoning into typed pieces takes more effort than writing a paragraph. The five-part taxonomy might not fit how every investigator actually thinks.

The first draft was much bigger — a graph canvas, real-time collaboration, permission tiers, an API, a database, export pipelines, dashboards. None of that answers the only question that matters right now: does comparing reasoning paths reveal useful differences a normal review misses? So it was cut down to exactly what's needed to test that.

The test

The next step is small on purpose: two analysts, one reviewer, three cases — one straightforward, one genuinely ambiguous with no single correct answer, one noisy and incomplete on purpose. Each case also gets reviewed the ordinary way, prose only, no structure, as the baseline this has to beat.

What gets measured: how long structured entry takes, how long review takes with the tool versus without it, how many reported differences a reviewer judges genuinely useful and non-obvious rather than just accurate, how many are misleading or simply wrong, what important differences the reviewer finds that the tool never surfaced at all, and whether anyone involved would choose to use it again.

None of those numbers exist yet. That's the entire point of running the test instead of writing more code.

Why it matters for developers

Reasoning Diff Lab is built for anyone who investigates things for a living — incident response, intelligence, digital forensics, journalism, medicine, security research, or even debugging. The tool is open source, and the repository includes a research assessment covering prior art (SEAS, CISpaces, W3C PROV, argument mapping, structured analytic techniques), failure modes, the full data model, and the pilot protocol with predefined continuation and failure thresholds.

The pilot requires two independent analysts and one reviewer, takes approximately 90 minutes, runs locally, and does not require participants to submit real investigative evidence. Everything needed to inspect or run the pilot is available in the repository.

The bottom line

Maybe this is a terrible idea. The reports may surface differences nobody actually cares about. The pilot may reveal months spent building an elegant answer to a question nobody was asking. But there's another possibility: maybe disagreement isn't something to eliminate — maybe it's something to inspect. Maybe the interesting artifact was never the final conclusion. Maybe it's the moment two careful people quietly stopped thinking the same way.

Evidence tells us what happened. Reasoning tells us how we came to believe it. One is preserved. The other is lost. Reasoning Diff Lab is an attempt to preserve the reasoning.