simjecture 0.5.0__tar.gz → 0.5.2__tar.gz

{simjecture-0.5.0 → simjecture-0.5.2}/.github/workflows/ci.yml

@@ -50,7 +50,9 @@ jobs:
       - name: Install uv
         run: python -m pip install uv
       - name: Install locked environment
-        run: uv sync --frozen --extra tui --extra dsh
+        run: uv sync --frozen --extra tui --extra dsh --extra workspace --group browser
+      - name: Install browser test runtime
+        run: uv run playwright install --with-deps chromium
       - uses: actions/setup-node@v4
         with:
           node-version: "22.23.1"
@@ -64,6 +66,10 @@ jobs:
         run: uv run ruff check .
       - name: Test
         run: uv run pytest --cov=conjecture_solver --cov-report=term-missing
+      - name: Validate packaged workspace install
+        run: |
+          uv run python scripts/package_workspace.py --output dist
+          uv run python scripts/verify_workspace_install.py --release-dir dist --work-dir /tmp/simjecture-installer-validation
       - name: Reproduce planted benchmark
         run: uv run simjecture benchmark kinetic-sufficiency --assert-falsified
       - name: Reproduce independent PIC benchmark

{simjecture-0.5.0 → simjecture-0.5.2}/.github/workflows/release.yml

@@ -15,7 +15,7 @@ jobs:
       name: pypi
       url: https://pypi.org/p/simjecture
     permissions:
-      contents: read
+      contents: write
       id-token: write
     steps:
       - uses: actions/checkout@v7
@@ -40,7 +40,9 @@ jobs:
             --ro-bind /lib64 /lib64 \
             /usr/bin/true
       - name: Install locked test environment
-        run: uv sync --frozen --extra tui --extra dsh
+        run: uv sync --frozen --extra tui --extra dsh --extra workspace --group browser
+      - name: Install browser test runtime
+        run: uv run playwright install --with-deps chromium
       - uses: actions/setup-node@v4
         with:
           node-version: "22.23.1"
@@ -69,5 +71,20 @@ jobs:
           PY
       - name: Build source and wheel distributions
         run: uv build
+      - name: Package and verify the one-command workspace installer
+        run: |
+          uv run python scripts/package_workspace.py --output dist
+          uv run python scripts/verify_workspace_install.py --release-dir dist --work-dir /tmp/simjecture-installer-validation
+      - name: Attach installable release assets
+        env:
+          GH_TOKEN: ${{ github.token }}
+        run: gh release upload "$GITHUB_REF_NAME" dist/install.sh dist/SHA256SUMS dist/*-workspace.tar.gz --clobber
+      - name: Collect Python distributions
+        run: |
+          mkdir pypi-dist
+          cp dist/*.whl pypi-dist/
+          find dist -maxdepth 1 -name '*.tar.gz' ! -name '*-workspace.tar.gz' -exec cp {} pypi-dist/ \;
       - name: Publish with PyPI Trusted Publishing
         uses: pypa/gh-action-pypi-publish@release/v1
+        with:
+          packages-dir: pypi-dist/

{simjecture-0.5.0 → simjecture-0.5.2}/CHANGELOG.md

@@ -2,7 +2,144 @@
 
 This project follows semantic versioning. Dates use ISO 8601.
 
-## Unreleased
+## 0.5.2 — 2026-09-29
+
+Stable release of the conversation-first research workspace tested in rc1/rc2,
+plus continuation, steering, review recovery and the ITER diagnostics pack.
+Minimal mode remains the default; structured/frontier modes remain selectable.
+The versioned installer preserves existing research data and older program folders.
+
+- Add an optional ITER diagnostics/data pack with pinned CHERAB/Raysect,
+  CHERAB-ITER/IMAS extensions and IMAS tools. Install/check from the CLI or GUI;
+  run a visible, monitored numerical demo with plots. Add source-based agent
+  guidance and separate setup entries for JOREK, SOLPS-ITER and DINA-PS.
+
+- Offer Prepare directly or Prepare with agent from the continuation dialog.
+  Chat preparation carries parent context across turns and lets the agent draft
+  the brief and select inherited files without losing lineage or instruments.
+- Add Continue investigation and Send guidance to study cards and the experiment
+  monitor. Review a linked phase's brief, selected inherited files, model and new
+  budget before launch; retain the original study and evidence status.
+- Snapshot continuation context with verified hashes and immutable parent lineage.
+  Add CLI continuation and advisory steering; show queued/checkpoint delivery in
+  the web interface and include guidance in independent review packets.
+- Detect empty/truncated built-in review replies, record finish reasons and usage,
+  and use bounded recovery with a larger output allocation and a DeepSeek
+  non-thinking retry. Back off repeated invalid oversight without granting approval.
+- Reconcile expired deadlines/dead supervisors in live status and write final
+  reports when a supervisor exits through an external error.
+
+## 0.5.2rc2 (preview) — 2026-09-27
+
+- Provision scientific compilers, MPI, HDF5 and other prerequisites in managed
+  environments for the included tools. Preserve diagnostic logs and validate the
+  installed runtime using the selected execution backend before reporting success.
+- Verify all five one-click tools from empty runtime directories, real agent-assisted
+  FLASH and WarpX CUDA builds, GPU execution, and browser uploads of licensed source.
+- Handle restricted root installations with a dedicated non-root account, safe
+  launchers, failed-install retry and upgrade rollback.
+- Make the autonomous research screen follow preparation, proposal, execution and
+  results. Return finished reports to the interactive agent without interrupting
+  active work; preserve queued delivery across restarts and link explanations to evidence.
+- Support follow-up studies in the same conversation with separate briefs and reports.
+  Remove duplicate navigation labels and collapse routine workspace metadata.
+- Accept source archive uploads up to 64 MiB. Keep installation commands separate
+  from simulations, support checks for registered custom tools, and reject runtimes
+  whose host paths or interpreter symlinks cannot work in the execution backend.
+
+- Keep installation skills readable while runtimes are incomplete; retry the
+  pinned Singularity-EOS source fetch after transient transport failures and
+  populate its required ports-of-call dependency. Package a relocatable Python
+  runtime when using uv-managed Python, avoiding broken sandbox symlinks. Incomplete runtimes with missing
+  declared identity files are not listed as installed.
+- Require an explicit completion handoff after DeepSeek text-only progress replies,
+  continuing tools instead of marking promises as completed answers. Bound repeated
+  protocol failures and retain usage accounting for completion-check requests.
+- Move routine workspace controls and execution status into the left sidebar,
+  remove the redundant top bar, and make execution warnings dismissible with
+  expandable diagnostics. Keep conversation-blocking notices prominent.
+- Use draggable sidebar edges and compact chevron tabs instead of text hide/show
+  buttons. Drag to the outer edge to collapse, pull or click the tab to reopen,
+  and retain panel widths and collapsed state across reloads.
+- Replace source-path dialogs for FLASH and WarpX CUDA with **Install with agent**,
+  opening prepared setup conversations that reference the bundled deployment skills.
+- Prefer Bubblewrap, with a checked PRoot cooperative fallback for namespace-restricted
+  hosts running under a dedicated non-root account. Show a dismissible sidebar warning
+  about the lack of filesystem/network security isolation; retain explicit backend
+  choices and immutable study execution modes. Use the selected backend for tool checks.
+- Show failed tool installations directly on catalogue cards, including tools
+  that are not yet installed. Bootstrap checksummed Micromamba for WarpX CPU
+  and separate solver provisioning from experiment-sandbox readiness.
+- Support DeepSeek thinking-mode tool choice and plain-text final answers. Keep
+  required provider reasoning metadata in private session storage and preserve
+  it when resuming a conversation, without displaying it in chat or activity.
+- Clarify SSH forwarding when a local port is already occupied.
+- Show only simulations in the left sidebar. Separate Simulations and Commands
+  into right-side tabs with independent selections, counts and links; incoming
+  commands no longer open the simulation monitor.
+
+## 0.5.2rc1 (preview) — 2026-09-27
+
+- Add a Linux/WSL one-command installer with checksummed release bundles, automatic
+  Python/uv setup, a persistent launcher, SSH forwarding guidance and separate version/data folders.
+- Add the conversation-first research workspace with optional compatible API setup,
+  auto-detected native CLIs, per-conversation agent/model controls and agent-prepared studies.
+- Keep named simulation folders and live logs beside conversations; link interactive
+  runs, figures, files and autonomous studies with a resizable side monitor.
+- Render equations, highlighted code and saved figures; add larger typography, persistent
+  light/dark themes and confirmed conversation/folder deletion with active-run guards.
+- Preserve scroll position and expanded details during live refreshes.
+- Discover existing FLASH applications and WarpX CPU/GPU builds, including native-input
+  versus Python-binding availability; expose shipped research skills to browser workers.
+- Resume native chat sessions and retain structured API history per conversation/model/
+  connection. Never reuse worker sessions for independent review.
+- Remove the default interactive-turn time ceiling, show public progress and recent tools,
+  and retain user-selected autonomous/simulation deadlines. Clarify interruptions and
+  preserve job statuses; discourage untracked temporary simulation
+  runs, and include an HDF5 reader in the workspace environment.
+- Accept an independently reviewed negative answer as completion when the study's
+  selected policy is `answer`; retain the existing `repair` policy.
+
+## 0.5.1 — 2026-09-26
+
+- Update bundled FLASH and Python experiment skills with guided-study/HDF5 lessons,
+  mode-correct interfaces, pilot interpretation and acceptance-rule checks.
+
+- Preserve classic instrument access across assignment rollover; retain role and branch scope.
+- Require explicit methods-review prerequisites and reject conditional approval; distinguish
+  timing/parity pilots from scientific evidence.
+- Surface output eligibility annotations to review without forcing metadata-only solver reruns.
+- Check explicit numerical repair bounds for empty intersections before execution.
+- Cancel through the complete durable job store, report unknown outcomes, and continue cleanup
+  when one job fails cancellation.
+- Document the guided MiMo v2.6 Pro / DeepSeek V4.1 Flash comparison, including tool-protocol,
+  duration and usage limitations; refresh the README around current modes and trust boundaries.
+- Restore guided anchors in all native study modes, with a separate model-free readiness run
+  and instrument-scoped review that cannot authorize hypothesis evidence.
+- Add explicit non-root PRoot cooperative execution for hosts without Linux namespaces;
+  keep Bubblewrap the default and never silently weaken isolation.
+- Retry transient provider failures with interruptible backoff until the original deadline;
+  pause authentication, permission and exhausted-quota failures for operator attention.
+
+- Make experiment journaling and bounded context delivery automatic in minimal mode,
+  following AIDE's controller-managed pattern. Add budget-limited checkpoint synthesis
+  with receipt-bound citations and no authority over scientific acceptance.
+
+- Add optional evidence-linked research notes, preserved corrections, discriminating
+  test plans and experiment lineage, informed by autoresearch/AIDE source inspection.
+- Resume from a bounded research brief and generate a machine-readable attempt ledger;
+  compare hash-verified result metrics without replacing missing values with zeros.
+
+- Add source-bound methods review for new instrument-backed minimal studies,
+  optional immutable instrument requirements, and append-only registration of new builds.
+- Recover native sessions that repeat intentions without work; add independent progress
+  review, bounded host checkpoints and immediate handoff of durable review requests.
+- Separate exploration from evidence and compact review documents from hashed binary
+  outputs; detect changed inputs, dead workers and questionable result fields.
+- Generate a live host evidence ledger with missing-case coverage, budget warnings,
+  review status and incomplete token-accounting indicators.
+- Support operator-authorized read-only solver-source inspection and useful build
+  diagnostics. Record the reconnection-run audit and live MiMo validation results.
 
 ## 0.5.0 — 2026-09-21
 

{simjecture-0.5.0 → simjecture-0.5.2}/CITATION.cff

@@ -2,8 +2,8 @@ cff-version: 1.2.0
 message: "If you use this software, please cite the exact software version and Git commit."
 title: "Simjecture"
 type: software
-version: 0.5.0
-date-released: 2026-09-21
+version: 0.5.2
+date-released: 2026-09-29
 abstract: >-
   An evidence-governed runtime for autonomous computational experimentation and
   falsification over hypothesis trees.

simjecture-0.5.2/PKG-INFO

@@ -0,0 +1,304 @@
+Metadata-Version: 2.5
+Name: simjecture
+Version: 0.5.2
+Summary: Evidence-governed autonomous experimentation and falsification for computational science
+Project-URL: Homepage, https://github.com/tomzhu0225/simjecture
+Project-URL: Documentation, https://github.com/tomzhu0225/simjecture/tree/main/docs
+Project-URL: Repository, https://github.com/tomzhu0225/simjecture
+Project-URL: Issues, https://github.com/tomzhu0225/simjecture/issues
+Author: Bowen Zhu
+License-Expression: Apache-2.0
+License-File: LICENSE
+License-File: NOTICE
+Keywords: autonomous science,computational physics,falsification,hypothesis testing,scientific agents,simulation
+Classifier: Development Status :: 3 - Alpha
+Classifier: Intended Audience :: Science/Research
+Classifier: License :: OSI Approved :: Apache Software License
+Classifier: Operating System :: POSIX :: Linux
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Topic :: Scientific/Engineering
+Requires-Python: >=3.11
+Requires-Dist: httpx<1,>=0.27
+Requires-Dist: matplotlib<4,>=3.8
+Requires-Dist: numpy<3,>=1.26
+Requires-Dist: pandas<4,>=2.2
+Requires-Dist: pillow<13,>=10
+Requires-Dist: pydantic<3,>=2.9
+Requires-Dist: scipy<2,>=1.12
+Provides-Extra: dsh
+Requires-Dist: mcp<3,>=2; extra == 'dsh'
+Provides-Extra: flash-demo
+Requires-Dist: h5py<4,>=3.10; extra == 'flash-demo'
+Provides-Extra: process
+Requires-Dist: psutil<8,>=6; extra == 'process'
+Provides-Extra: tui
+Requires-Dist: textual<9,>=2.0; extra == 'tui'
+Provides-Extra: workspace
+Requires-Dist: h5py<4,>=3.10; extra == 'workspace'
+Requires-Dist: psutil<8,>=6; extra == 'workspace'
+Requires-Dist: smolagents[openai]<2,>=1.24; extra == 'workspace'
+Description-Content-Type: text/markdown
+
+# Simjecture
+
+[![DOI](https://zenodo.org/badge/DOI/10.5281/zenodo.21945748.svg)](https://doi.org/10.5281/zenodo.21945748)
+
+**Hypothesize. Simulate. Falsify.**
+
+Simjecture is a research harness for computational science. An agent writes and runs
+experiments, searches for counterexamples, and proposes small, testable repairs to
+failed hypotheses. The harness records what actually ran and requires independent
+review before a scientific claim can close.
+
+**v0.5.2 is the current stable release.** Minimal mode is the default: agents keep their
+native tools and choose their research strategy, while Simjecture manages recorded
+evidence, review and deadlines. Structured and frontier modes remain available.
+The system does not establish physical truth from a successful simulation or promise
+that a long agent run will produce a useful result.
+
+The workspace includes visible **Continue investigation** and **Send
+guidance** actions in the study view and experiment monitor. Continue with a new
+budget and selected prior files, or send advisory guidance at the next checkpoint.
+See [continuation and steering](docs/how-to/continuation-steering.md).
+
+## Install and open the workspace
+
+On Linux or inside WSL, run:
+
+```bash
+curl -fsSL https://github.com/tomzhu0225/simjecture/releases/download/v0.5.2/install.sh | bash
+```
+
+The installer downloads the versioned release, verifies its checksum, installs uv,
+Python 3.12 and the workspace dependencies, and starts the local GUI. Git and a CLI
+agent are not required. Enter a compatible API endpoint and key in **Connections**, or
+select an existing local CLI from the message composer. Choose **Interactive research**
+for a task, or prepare an **Autonomous research** study together with the agent.
+
+Software lives under `~/simjecture/app/<version>`; conversations, inputs, simulations
+and studies stay in `~/simjecture/artifacts/projects`. Reopen the GUI with
+`~/simjecture/start-workspace`. On SSH hosts the installer prints forwarding instructions
+for your local browser. Keep the server terminal open, or run the launcher in your usual
+session manager. Ubuntu/Debian may request sudo to install Bubblewrap; restricted
+containers can open the GUI but may need a separately configured execution backend.
+
+See [installation options](docs/getting-started/installation.md) and the
+[workspace walkthrough](docs/getting-started/research-workspace.md).
+
+## Start a study from an external CLI
+
+Use Linux with Python 3.11+, [uv](https://docs.astral.sh/uv/), and an installed,
+authenticated native agent CLI. Bubblewrap is the default numerical execution backend.
+
+```bash
+uv tool install 'simjecture[tui]==0.5.2'
+simjecture install core
+simjecture doctor --execution-backend bubblewrap
+
+simjecture study --campaign ./runs/my-study \
+  --hypothesis-file hypothesis.txt --instructions-file instructions.md \
+  --backend codex-glm --model glm-5.3 --wall-seconds 3600
+```
+
+Write a falsifiable hypothesis in `hypothesis.txt`. In `instructions.md`, specify
+physical scope, available instruments, resource limits and the evidence needed to
+accept or reject it. Configure provider credentials in your agent's own credential
+store, outside the study directory. The model name must match that configuration.
+
+A terminal launch shows activity, backend/model, remaining time and experiment/review
+counts. Inspect the same study in either interface:
+
+```bash
+simjecture web ./runs/my-study
+simjecture tui ./runs/my-study
+```
+
+Resume using the same campaign path and launch options. Its recorded mode and original
+wall deadline remain fixed. A normal agent exit or inconclusive result does not mark
+research complete. Transient provider disconnects retry with backoff until the deadline;
+authentication, permission and exhausted-quota errors pause for attention. Waiting for
+a provider counts against wall time.
+
+See [minimal-mode usage](docs/how-to/research-service.md),
+[terminal progress](docs/getting-started/terminal-ui.md) and the
+[browser interface](docs/getting-started/web-interface.md).
+
+## Choose the agent, workflow and execution backend separately
+
+| Choice | Options | What it controls |
+|---|---|---|
+| Native agent | `codex-glm`, `codex`, `grok`, `agy` | CLI, configured provider/model, login and native tools |
+| Research mode | `minimal` (default), `structured`, `frontier` | How scientific work is organized |
+| Numerical execution | `bubblewrap` (default), `proot-cooperative` | How recorded experiment processes execute |
+| Legacy engine | DSH or built-in API routes | Existing campaign integrations; separate from native-study modes |
+
+Use `--mode structured` or `--mode frontier` for another workflow. Minimal lets the
+agent organize its investigation around a small evidence API; structured uses explicit
+claim-scoped roles and contracts; frontier gives a persistent researcher control of
+the classic claim tree. Existing campaigns retain their recorded semantics.
+
+Native agents retain their own shell, search, file and configured provider tools.
+They are trusted, cooperative processes on the study host; they are **not** enclosed
+by the numerical experiment sandbox. Simjecture's supplied tools record experiments,
+provenance and reviews. Native scratch work is not automatically scientific evidence.
+
+If namespaces are unavailable, explicitly select `--execution-backend proot-cooperative`
+on a dedicated non-root account. It provides execution bookkeeping and limits, **not
+an OS security boundary**. Simjecture never silently falls back to it. See
+[restricted containers](docs/how-to/restricted-containers.md).
+
+[DSH integration](docs/how-to/deepseek-harness.md) remains available with native research
+tools and a governed MCP boundary. [Simote integration](docs/how-to/simote-agent-roles.md)
+is optional; Simjecture can run independently on a local or remote host. Deployment
+to a remote host does not itself create a multi-machine experiment scheduler.
+
+## What minimal mode enforces
+
+The agent chooses hypotheses, code, diagnostics and the next discriminating experiment.
+The host maintains the scientific record:
+
+- **Immutable question and scope.** Operator requirements cannot be waived by a worker
+  or reviewer. Repairs preserve ancestry and explain each changed assumption or bound.
+- **Recorded execution.** Commands, declared inputs, runtime identity and output hashes
+  accompany each experiment. Interrupted attempts remain visible.
+- **Commissioning before evidence.** Instrument-backed studies receive source-bound
+  methods review. Exploration and supplied examples cannot be relabelled as new evidence.
+- **Counterexample search and fresh repairs.** Support includes an actual challenge
+  attempt. Repaired predictions are committed before their fresh tests.
+- **Independent acceptance.** A methods approval permits evidence collection; it does
+  not accept a scientific claim. Unconverged, censored or missing results are not
+  physical counterexamples.
+- **Persistent context.** The host maintains an experiment journal and bounded research
+  brief. Evidence-linked notes and comparisons help retain failed approaches and findings.
+- **Bounded work.** The original deadline survives restart. Cancellation uses durable job
+  records and reports unresolved cleanup rather than assuming that agent exit stopped
+  every computation.
+
+A study completes when its original claim is independently supported, or when a
+falsified original leads to an independently supported repair with the required
+ancestry. A deadline may end the campaign unresolved; that is recorded, not promoted
+to a success.
+
+See [methods and progress oversight](docs/how-to/minimal-oversight.md),
+[research memory](docs/how-to/research-memory.md) and
+[evidence and claims](docs/concepts/evidence-and-claims.md).
+
+## Begin with a working scientific instrument
+
+For expensive solver setup, provide a guided commissioning package: exact working
+source and command, output reader, observable, validation checks, runtime and known
+limitations. Reproduce that anchor in a separate bounded readiness run before spending
+hours on hypothesis testing.
+
+```bash
+simjecture study --campaign ./runs/guided-study \
+  --hypothesis-file hypothesis.txt --instructions-file instructions.md \
+  --guided-commission /path/to/guided_commission.json \
+  --capabilities /path/to/installed-capabilities \
+  --backend codex-glm --model glm-5.3 --wall-seconds 3600
+```
+
+Guided examples are starting instruments, not fresh evidence for the new hypothesis.
+An executable smoke test does not validate a new geometry or diagnostic. The
+[guided commissioning guide](docs/how-to/guided-commissioning.md) explains readiness
+budgets, immutable anchors and instrument versus production review.
+
+Optional instruments include WarpX CPU/CUDA, operator-supplied FLASH, and EOS/opacity
+capabilities. For example:
+
+```bash
+simjecture install warpx-cpu
+simjecture doctor --profile warpx-cpu
+```
+
+The release also includes an [ITER ecosystem pack](docs/how-to/iter-pack.md):
+CHERAB/Raysect synthetic diagnostics, CHERAB-ITER/IMAS adapters and IMAS data tools.
+Use **Research tools → ITER pack → Install**, then **Run demo** for a monitored
+example with plots, or run `simjecture install iter-pack`. JOREK, SOLPS-ITER and
+DINA-PS have separate **Install with agent** entries and source-based guidance;
+they are not silently included in the diagnostics installation.
+
+FLASH source is not redistributed. Solver source inspection can be configured separately
+from a writable problem/build area. See [runtime deployment](docs/how-to/deploy-runtimes.md)
+and the [scientific skills](skills/).
+
+## Research core introduced in v0.5.1
+
+This release builds on v0.5.0's minimal default and shared interfaces:
+
+- Methods/progress oversight, stalled-session recovery and deadline-bounded provider retry.
+- Automatic research journaling, bounded context and evidence-linked comparisons.
+- Guided anchors in native studies and explicit cooperative execution for restricted hosts.
+- Updated FLASH/Python skills with guided-study, HDF5 and decision-rule lessons.
+- Preserved instrument ownership across classic assignment rollover.
+- Explicit unmet review prerequisites; conditional approval cannot open the evidence gate.
+- Numerical checks for contradictory prospective acceptance bounds.
+- Output eligibility annotations exposed for review without forcing metadata-only solver reruns.
+- Durable cancellation cleanup independent of CLI-response parsing.
+
+The [changelog](CHANGELOG.md) and [repair report](research/evaluations/guided-model-comparison-2026-09-26/RESULTS.md)
+include validation and remaining limitations. General reuse of raw solver data under
+independently versioned analysis still needs a fuller provenance API.
+
+## Measured evidence and limitations
+
+Minimal is the default by design preference, not a demonstrated universal performance
+advantage. The latest [MiMo v2.6 Pro / DeepSeek V4.1 Flash comparison](docs/research/llm-comparison.md)
+found faster useful progress with DeepSeek in a guided minimal FLASH study, but **no
+independently accepted scientific conclusion** from either model configuration.
+Unequal duration, different provider tool protocols and one trial per configuration
+limit that comparison. Token totals distinguish cached input, uncached input and
+output; they are not billed-cost estimates.
+
+| Recorded evaluation | What can be inspected |
+|---|---|
+| [Gray–Scott](demos/gray_scott_counterexample/) | A completed 23.8-minute finite-domain counterexample campaign, programs, numerical evidence and replay |
+| [Collisionless GEM](demos/collisionless_gem_reconnection/) | 12 fresh CUDA runs; finite-sample child falsification with an unresolved population root |
+| [FLASH island coalescence](demos/resistive_mhd_island_coalescence/) | Working guided anchor, real fields and a historical audit; the repair remained open |
+| [Guided model comparison](research/evaluations/guided-model-comparison-2026-09-26/) | MiMo/DeepSeek progress, usage, harness failures and corrective tests |
+
+The historical FLASH narrative recorded an exponent-band falsification with an interval
+that overlaps the allowed band. That overlap alone does not establish such falsification;
+the earlier summary is not independently endorsed here. Provenance enables inspection,
+but cannot make a faulty scientific decision correct.
+
+Replay a completed example without an API key or new simulations:
+
+```bash
+git clone https://github.com/tomzhu0225/simjecture.git
+cd simjecture
+uv sync --frozen
+uv run python demos/gray_scott_counterexample/verify_record.py
+uv run simjecture web demos/gray_scott_counterexample/record --read-only
+```
+
+![Gray–Scott recorded numerical evidence](docs/_static/demos/gray-scott-result.png)
+
+## Documentation and development
+
+Start at [the documentation index](docs/index.md). Linux release assets include a
+launch archive with matching Python/DSH packages, setup scripts and SHA-256 checksums.
+Native-agent setup does not require installing DSH.
+
+```bash
+uv sync --all-groups --extra tui --extra dsh
+uv run ruff check .
+uv run pytest
+uv run simjecture schemas --output schemas --check
+uv run --group docs sphinx-build -W -b html docs docs/_build/html
+```
+
+`conjecture-solver` and `acs` remain compatibility aliases. The Python package remains
+`conjecture_solver`. See [CONTRIBUTING.md](CONTRIBUTING.md), [SECURITY.md](SECURITY.md)
+and [THIRD_PARTY_NOTICES.md](THIRD_PARTY_NOTICES.md).
+
+## Citation and license
+
+Use [CITATION.cff](CITATION.cff) and cite the exact version and Git commit used for a
+result. The [concept DOI](https://doi.org/10.5281/zenodo.21945748) identifies the software
+release series.
+
+Copyright 2026 Bowen Zhu and contributors. Licensed under the
+[Apache License 2.0](LICENSE).