MachineTradecraft
Global site search

Search guides, labs, glossary, and research

Type two or more characters to search.

Start with a channel, artifact, or defense term

Examples include zero-width, metadata, tokenizer, or prompt injection.
    Model Signals · Statistical signal

    Synthetic Probability Signal Simulator

    The simulator uses a fixed toy distribution. It demonstrates logit bias, surprisal, and class proportions without reproducing a production watermark or steganographic encoder.

    Browse all labs Open universal Machine View
    Quick answer

    What does the Probability Signals show?

    The simulator uses a fixed toy distribution. It demonstrates logit bias, surprisal, and class proportions without reproducing a production watermark or steganographic encoder.

    Human visibility
    Individual choices look ordinary
    Machine receiver
    Distribution-aware statistic
    Robustness
    Sequence- and model-dependent

    Research boundary: this page uses bounded, inert data and fixed safe examples. It never executes decoded content, requests secrets, calls third-party services, or performs actions against external systems.

    FIRST RUN / THREE STEPS

    Start with the prepared, bounded workflow.

    Nothing runs automatically
    1. Review the prepared starter input

      A bounded benign input is already present. Change it only when you are ready to test a different authorized artifact.

    2. Run Run synthetic simulation

      Run the normal local synthetic simulation with the values above.

    3. Scan before expanding

      Read the summary first, then scan findings and expand only the machine views you need.

    INPUT / CONTROL PLANE

    Prepare the input and choose one action.

    Ready

    The recommended first run is separated from alternate analyses. Inputs and selected files stay on this host.

    Current input state Moderate bias loaded

    These bounded starter values are ready to inspect. Review them before running the recommended action.

    Enter the bounded numeric value used for this run.

    Allowed range: 0 to 3 in steps of 0.1.

    Choose the preferred class used for this run. The selection changes only this local analysis.

    Switch prepared example3 options

    Loading a sample changes only the form values. Review the result and run an action yourself.

    Prepared benign examples
    ACTION HIERARCHY

    Run the recommended first pass.

    Alternate actions remain available below, but the first pass is the clearest place to start.

    Inputs remain on this host. Text operations are size-limited; uploaded files are processed from PHP’s temporary upload and are not retained by the application.

    OUTPUT / MACHINE VIEWS

    Scan the result from summary to evidence.

    Run Run synthetic simulation to create the first result.

    The prepared starter input is ready. The output will lead with a summary and visible qualifications before the expandable machine views.

    SummaryFindingsMachine views
    Interpretation framework

    The same artifact can produce several valid observations.

    01

    Human view

    What a person naturally reads, sees, or hears.

    02

    Structural view

    What a parser, DOM, container reader, or metadata extractor exposes.

    03

    Decoder view

    What becomes meaningful only with a rule, key, tokenizer, model, or tool.

    04

    Defensive view

    What normalization, rendering, OCR, canonicalization, or policy changes.

    Evidence and decision boundary

    Use the result as bounded evidence, not as a universal verdict.

    The simulator uses a fixed toy distribution. It demonstrates logit bias, surprisal, and class proportions without reproducing a production watermark or steganographic encoder.

    Interpretation rule

    Record the receiver and transformation.

    Machine-decodable is receiver-relative. Record the parser, preprocessing, codebook, tokenizer, key, model, and transformation path before generalizing from one result.

    Limitations

    What this page does not prove

    The numbers are synthetic and do not represent any commercial model. Detection from a short sequence is uncertain and depends on the correct source distribution.

    Continue the investigation

    Related labs and source reports

    Tokenizer Explorer Exact tokenizer and normalizer Watermark Simulator Key-aware statistical detector Pattern Detector Statistical analyzer Hidden Structure in Text: Human-Subtle, Model- and Decoder-Detectable Patterns Research report Machine-Targeted Linguistic Signals in LLMs Research report
    Continue exploring

    Move from the current explanation to a related guide, evidence source, or controlled workbench.

    Laboratory catalogChoose a focused local experimentBrowse 40 bounded laboratories spanning representation, files, messages, models, provenance, agents, supply chains, and defense.Open this path Channel atlasCompare machine-readable channel familiesMatch each carrier to its receiver, failure modes, survival properties, and defensive comparison.Open this path Defensive architectureBuild a safer model-ingestion boundaryPreserve evidence, compare representations, canonicalize allowlisted fields, retain provenance, and minimize privilege.Open this path