Skip to content

OPEN SOURCE · LOCAL FIRST · REPRODUCIBLE

ScienceXResearch Twin Workbench

Reproduce research digitally. Move the next cycle forward as evidence returns.

ScienceX maps research objects, experimental conditions, and evidence into digital experiments that can run, replay, and be compared. It pins data and experiment versions, invokes authorized models and tools, and turns evidence differences into candidate next directions.

Download ScienceX

Check each Release for the latest included research features

  • Local first
  • Pinned versions
  • Deterministic replay
  • Human confirmation
SXVALIDATED NOW · SIMULATED TEACHING CASELOCAL
Research questionDoes SX-101 reduce HepG2 relative viability as concentration increases?
Fit quality
R² > 0.99
Relative IC50
≈ 1 µM
Replay verified3 research artifacts
01

RESEARCH TWIN

Turn the research processinto a runnable research twin

For a focused research object, ScienceX organizes the question, data, experiment, run evidence, and research decisions into a continuously corresponding digital state. Every cycle can expose its version, compare differences, and return to the next question.

RESEARCH TWIN ≠ VISUALIZATIONA research twin is neither an experiment screenshot nor a flowchart

A useful research twin exists only when the research object, experimental conditions, execution, evidence, and decisions remain traceably aligned and can be run and compared again.

  1. 01OBJECT

    Object layer

    Research object, scientific question, observables, and data structure.

  2. 02EXPERIMENT

    Experiment layer

    Variables, controls, conditions, protocol versions, and acceptance criteria.

  3. 03EXECUTION

    Execution layer

    Models, algorithms, tools, parameters, environments, and authorization state.

  4. 04EVIDENCE

    Evidence layer

    Inputs, outputs, logs, sources, hashes, failures, and uncertainty.

  5. 05DECISION

    Decision layer

    Researcher-approved boundaries, open questions, and next hypotheses.

MINIMUM VIABLE TWIN
Object modelVersioned experimentReplayable runEvidence returnHuman decision

A result without conditions and versions is not a twin. A workflow without replayable evidence is not a twin either.

02

CURRENT TWIN UNIT

Not a concept diagram: an experiment twin that can run, fail, and replay

The HepG2 × SX-101 teaching case generates simulated data locally, then runs a versioned experiment design, deterministic 4PL analysis, technical-evidence evaluation, and replay. It preserves failures and inconclusive evidence as well.

03 MINLocal teaching example
24 WELLSVersioned assay design
SHA-256Input and artifact hashes
REPLAYPinned-version replay

Four reproducible run outcomes

Dose responseCompletes analysis and creates 3 artifacts
Changed dataThe pinned old version still replays
Missing wellFails explicitly without filling values
Weak responseRun completes with inconclusive evidence

Simulated teaching data. It does not establish efficacy, wet-lab validation, or a scientific conclusion.

03

TWIN LOOP

Results return to twin state.Research enters the next cycle.

ScienceX currently provides a researcher-driven digital experiment loop: pin versions, run analyses, preserve technical evidence, and replay comparisons. Only after calibrated real-world sources are connected can experimental feedback update the research twin.

  1. 01QuestionResearch focus
  2. 02HypothesisCandidate explanation
  3. 03EvidenceData and sources
  4. 04ExperimentExperiment / compute
  5. 05ResultOutcome and boundary
  6. 06Next questionContinue the loop
STATE LAYERResearch Memory

Goals · candidate hypotheses · dataset versions · evidence relations · decisions · results · open questions

The current loop is researcher-driven. ScienceX assists execution, recording, and replay; it does not replace the final scientific judgment.

04

EVIDENCE TO NEXT

Insight is not a random guess.It emerges from differences in evidence.

ScienceX compares versions, conditions, and run outcomes to expose evidence gaps, sensitive variables, and sources of conflict. It produces testable candidate hypotheses and experiment suggestions for researcher review.

01

Evidence gaps

Find claims that lack controls, replicates, critical conditions, or source support.

02

Parameter sensitivity

Compare which variable changes are most likely to alter the current result.

03

Cross-run differences

Trace changes in data, design, parameters, and outcomes across versions.

04

External conflicts

Locate differences in object, conditions, or measurement between literature and local results.

ILLUSTRATIVE CANDIDATE

After a weak response, what should the next cycle test?

SCIENCEX / NEXT
Observation
The run completed, but the dose response is weak and the technical evidence remains inconclusive.
Candidate account
The current concentration range may not cover an identifiable response region.
Proposed next step
Extend the concentration range and add replicates and controls around the critical region.
Required validation
A researcher reviews the design; only real experiments or independent data can update scientific judgment.
DECISION STATEAwaiting researcher confirmation

A candidate next step is a testable suggestion grounded in technical evidence. It is not autonomous discovery and does not start a real experiment automatically.

05

HOW IT WORKS

How ScienceX carriesone twin run

Models generate candidate reasoning. ScienceX orchestrates authorized tools, records inputs and outputs, and preserves research state; the researcher makes the important judgments.

  1. 01
    Understand

    Read the question, research thread, and current evidence.

  2. 02
    Plan

    Break down the task and define the next execution path.

  3. 03
    Act

    Call capabilities installed locally and explicitly authorized.

  4. 04
    Verify

    Inspect inputs, results, warnings, and artifacts.

  5. 05
    Preserve

    Save conclusions, boundaries, and next steps after researcher confirmation.

STATE LAYERResearch Memory

Goals · candidate hypotheses · dataset versions · evidence relations · decisions · results · open questions

Preserving research state does not update model weights automatically, and automated execution is not a scientific conclusion.

06

PRODUCT IN USE

The twin is not just a concept diagram.It runs inside today’s workbench.

Research projects, threads, scheduled tasks, and research Skills carry the twin through daily work. These are cropped, privacy-safe views of the current product.

ScienceX research thread showing structured next actions and the prompt composer
01

A thread carries the question forward

Keep the research question, process notes, files, and proposed actions in one record that can continue.

ScienceX scheduled tasks screen with a create-task action and local runtime notice
02

Recurring work can run on a schedule

Create and manage scheduled desktop tasks. Local tasks run only while the app is open and the device stays awake.

RESEARCH SKILLS20

Methods are visible capabilities, not hidden prompts

Research Skills appear independently in the product so researchers can inspect their names, sources, and operating boundaries.

ScienceX CAPABILITY INDEX

The interface evolves by release. Actual availability depends on the current release, local dependencies, connection state, and authorization.

07

DAILY RESEARCH

Let daily workkeep the research twin running

Search, organization, review, and expression no longer disappear across disconnected tools. They add evidence, maintain state, and create reviewable artifacts for one research object while researchers retain close reading, judgment, and direction.

01Artifact

Find sources

Search and screen by scope, source, date, and acceptance format.

Artifact
A sourced paper table and evidence brief
Researcher keeps
What deserves close reading and trust
Example promptFind representative papers on X from the last three years. Cite every item.
02Artifact

Track progress

Organize planned, active, completed, and paused work in the research thread.

Artifact
Progress board, review, and next-step list
Researcher keeps
Priority and research direction
Example promptSummarize this week, blockers, and the three most important next steps.
03Artifact

Trace logic

Interrogate premises, evidence, counterexamples, and scope one claim at a time.

Artifact
Argument gaps and questions to verify
Researcher keeps
Answers and changes to the argument
Example promptAct as a rigorous reviewer and ask what makes each claim hold.
04Artifact

Refine expression

Correct, polish, and normalize terms while recording each type of change.

Artifact
Suggestions, diffs, and a style record
Researcher keeps
Position, conclusion, and personal voice
Example promptShow original, revision, and reason. Do not rewrite my conclusion.

Repetitive work becomes valuable when it updates a shared research state instead of losing context across chats, files, code, and experiment records.

08

RESEARCH SKILLS

20 research Skills.Methods across the twin lifecycle.

Skills help build, run, verify, and update research twins. They are inspectable methods; runtime requirements, external access, and real-instrument connections are never implied.

20research Skills integrated with ScienceX
Read the Skills guide
013

Build the twin

Define the research object, experiment design, and verifiable data baseline.

  • /find-science-skills
  • /experiment-design
  • /research-baseline-builder
023

Add evidence

Find papers, retrieve sources, and build evidence that can be checked.

  • /giiisp-paper-search-apis
  • /scansci-pdf
  • /sci-employee-deep-research
032

Generate candidates

Turn evidence differences into candidate directions and expose gaps through reviewer-style questions.

  • /scispark
  • /good-question
046

Create research artifacts

Organize papers, figures, slides, videos, and course artifacts.

  • /academic-writing
  • /scientific-humanization
  • /giiisp-scientific-image-generation
  • /visual-deck-builder
  • /manim-agent
  • /practical-course-producer
054

Verify & update

Review papers and citations while preserving researcher-approved long-running state.

  • /thesis-audit-reviewer
  • /papercheck
  • /cognitive-profile
  • /world-threads-entry
062

Evaluate & extend

Assess MCP servers and Skills before adopting new tools or connectors.

  • /mcp-criticagent
  • /skill-criticagent
Execution environments connect after authorization
Local filesPDF / CSV / project folders
Code & terminalRepositories / commands / scripts
Model providersConfigured reasoning models
MCP servicesEnabled extension tools
Data sourcesAuthorized databases and services
ComputeExisting local compute capabilities

Integrated does not mean universally runnable. Some Skills require local dependencies, external services, or user authorization. ScienceX has no default access to paper libraries, databases, or other systems.

09

HUMAN IN THE LOOP

ScienceX executes and records.Researchers own judgment and direction.

ScienceX can take on repetitive, reviewable execution. It cannot choose trusted evidence, validate an experiment, or sign off on a scientific conclusion for the researcher. High-risk actions require explicit authorization.

EXECUTION

ScienceX

  • Search, read, and organize
  • Code, compute, and compare
  • Execute authorized tools
  • Preserve process and candidate hypotheses
JUDGMENT

Researcher

  • Ask important research questions
  • Review protocols and critical evidence
  • Decide what the results support
  • Choose the next research direction
CURRENT OPERATING MODELHuman-driven Research Loop · researchers initiate, authorize, review, and make the final judgment
  • 01AI assists expression; it does not author the conclusion
  • 02AI helps screen; it does not replace close reading
  • 03Sensitive data stays within defined boundaries
  • 04Technical evidence is not a scientific conclusion
10

CAPABILITY MATURITY

From a digital experiment twin to real-world feedback

The homepage separates product-object maturity from AI-role maturity. A digital experiment twin is validated now; domain structure, real feedback, and multi-path autonomy belong to later stages.

NOWAvailable now

Digital experiment twin

Versioned experiment designs, pinned data, deterministic analysis, technical evidence, artifacts, and replay.

VERSION → RUN → EVIDENCE → REPLAY
NEXTNext stage

Domain research twin

Stable data structures, specialist models, evaluation rules, and sustained research state for a focused domain.

DOMAIN MODEL → CONTROLLED STATE
CONNECTDedicated connection

Real-world feedback twin

Update twin state through validated ELN, LIMS, instrument, or observational-data connectors.

REAL FEEDBACK → VALIDATION → UPDATE
VISIONLong-term vision

Research twin network

Compare multiple candidate research paths in parallel while researchers govern, merge, retain, or stop them.

MULTI-PATH → COMPARE → DECIDE

The current product does not provide generic instrument control, unattended wet-lab operation, or automatic model-weight updates. MCP is an extension seam only.

11 ScienceX / RESEARCH TWIN WORKBENCH

Start with one runnable twin unit

Run the built-in simulated case to understand versions, evidence, and replay. Then define a verifiable digital experiment for your own research object.
  1. 01Run the built-in twin case
  2. 02Define the research object, variables, and acceptance criteria
  3. 03Inspect evidence and confirm the candidate next step
Research-object onboarding template
I want to build a research twin around X. The research object is [object], the input data are [format and version], the adjustable variables are [variables], the output metrics are [metrics], and the acceptance criteria are [criteria]. First identify missing conditions, and do not assume a real instrument is connected.

Released under the MIT License.