Random Unreliable Narrator Evidence Deck Generator

Description

Compose supplied fictional assertions and conflicting evidence with an exact contradiction count, shuffled exhibits, and an explicit consistency key.

A structured creative brief combines a supplied bank of fictional material with explicit sequencing, timing, or compatibility rules. IDs and tags make those constraints inspectable; they do not assess the artistic meaning or quality of a scene.

Compose supplied fictional assertions and conflicting evidence with an exact contradiction count, shuffled exhibits, and an explicit consistency key.

When to use this tool

Use this generator to create reproducible unreliable narrator evidence cases from the supplied model or bank. Inspect the returned evidence before using cases in a test or exercise.

How to use the tool and how it works

Supply facts, narratorTemplates, count, contradictionCount, wrapWidth in the field shapes below. Set seed when you need an explicit replay.
Run the tool and correct any input error. For generated controls, distinguish a successful fixture containing an invalid case from failure to generate the fixture.
Read statements, evidence, consistencyKey, provenance. Use the conventions below and keep answer-bearing fields separate when presenting an exercise.

Select an exact number of supplied fictional facts, reserving exactly contradictionCount facts with alternatives. Render narrator assertions using either established or conflicting values and matching evidence from the established value, wrap text and shuffle exhibits while retaining a consistency key.^[1]

Delegated operations used for this result: word wrap. Their calculation or parsing conventions apply to the corresponding result fields.^[2]

Input field	Meaning and units	Accepted input
facts	Facts	Required. Array of Object; no unknown keys.; minimum items 1; maximum items 64.
facts[].id	Literal identifier used to match records, independently of their display labels.	Required. Text; minimum UTF-16 length 1; maximum UTF-16 length 128.
facts[].label	Caller-facing text label; not a globally unique identifier.	Required. Text; minimum UTF-16 length 1; maximum UTF-16 length 128.
facts[].truthValue	Truth Value	Required. Text; minimum UTF-16 length 1; maximum UTF-16 length 128.
facts[].alternativeValues	Alternative Values	Required. Array of Text; minimum UTF-16 length 1; maximum UTF-16 length 128.; minimum items 0; maximum items 16.
facts[].evidenceTemplates	Evidence Templates	Required. Array of Text; maximum UTF-16 length 4096.; minimum items 1; maximum items 16.
narratorTemplates	Narrator Templates	Required. Array of Text; maximum UTF-16 length 4096.; minimum items 1; maximum items 16.
count	Requested count; the mechanics explain whether one draw expands into several returned records.	Required. Safe integer; minimum 1; maximum 64.
contradictionCount	Contradiction Count	Required. Safe integer; minimum 0; maximum 64.
wrapWidth	Wrap Width	Required. Safe integer; minimum 1; maximum 4096.
seed	Optional numeric seed; takes precedence over context randomness. Without either, use the fixed tool.io default seed.	Optional. Safe integer.

Output field	Interpretation	Returned shape
statements	Statements	Required. Array of Object; no unknown keys.; minimum items 1; maximum items 64.
statements[].id	Literal identifier used to match records, independently of their display labels.	Required. Text; minimum UTF-16 length 1; maximum UTF-16 length 128.
statements[].factId	Fact Id	Required. Text; minimum UTF-16 length 1; maximum UTF-16 length 128.
statements[].text	Text	Required. Text; maximum UTF-16 length 65536.
statements[].lineCount	Line Count	Required. Safe integer; minimum 0.
evidence	Evidence	Required. Array of Object; no unknown keys.; minimum items 1; maximum items 64.
evidence[].id	Literal identifier used to match records, independently of their display labels.	Required. Text; minimum UTF-16 length 1; maximum UTF-16 length 128.
evidence[].factId	Fact Id	Required. Text; minimum UTF-16 length 1; maximum UTF-16 length 128.
evidence[].text	Text	Required. Text; maximum UTF-16 length 65536.
evidence[].lineCount	Line Count	Required. Safe integer; minimum 0.
consistencyKey	Consistency Key	Required. Array of Object; no unknown keys.; minimum items 1; maximum items 64.
consistencyKey[].statementId	Statement Id	Required. Text; minimum UTF-16 length 1; maximum UTF-16 length 128.
consistencyKey[].evidenceId	Evidence Id	Required. Text; minimum UTF-16 length 1; maximum UTF-16 length 128.
consistencyKey[].factId	Fact Id	Required. Text; minimum UTF-16 length 1; maximum UTF-16 length 128.
consistencyKey[].assertedValue	Asserted Value	Required. Text; minimum UTF-16 length 1; maximum UTF-16 length 128.
consistencyKey[].establishedValue	Established Value	Required. Text; minimum UTF-16 length 1; maximum UTF-16 length 128.
consistencyKey[].contradicts	Contradicts	Required. Boolean.
provenance	Provenance	Required. Text; exactly "caller-supplied-fiction".
randomness	Replay metadata: source is seed or context; seed is the normalized 32-bit seed or null for a context source.	Required. Object; no unknown keys.
randomness.seed	Optional numeric replay seed; normalization and precedence are explained below.	Required. Safe integer. or Null.
randomness.source	Source	Required. Text; one of "context", "seed".

An explicit safe-integer seed takes precedence over injected context randomness and is normalized to an unsigned 32-bit integer. With no seed and no context source, replay uses the fixed tool.io default seed. A context source must return finite values from zero inclusive to one exclusive; its advancing state must be retained separately. randomness records the source and normalized seed, or null for context. These generators are not cryptographic random sources.

json

{
  "input": {
    "facts": [
      {
        "id": "gate",
        "label": "gate state",
        "truthValue": "open",
        "alternativeValues": [
          "closed"
        ],
        "evidenceTemplates": [
          "The log records {label}: {value}."
        ]
      },
      {
        "id": "parcel",
        "label": "parcel color",
        "truthValue": "blue",
        "alternativeValues": [
          "red"
        ],
        "evidenceTemplates": [
          "The log records {label}: {value}."
        ]
      }
    ],
    "narratorTemplates": [
      "I recall {label}: {value}."
    ],
    "count": 2,
    "contradictionCount": 1,
    "wrapWidth": 80,
    "seed": 42
  },
  "output": {
    "statements": [
      {
        "id": "statement-1",
        "factId": "parcel",
        "text": "I recall parcel color: red.",
        "lineCount": 1
      },
      {
        "id": "statement-2",
        "factId": "gate",
        "text": "I recall gate state: open.",
        "lineCount": 1
      }
    ],
    "evidence": [
      {
        "id": "evidence-2",
        "factId": "gate",
        "text": "The log records gate state: open.",
        "lineCount": 1
      },
      {
        "id": "evidence-1",
        "factId": "parcel",
        "text": "The log records parcel color: blue.",
        "lineCount": 1
      }
    ],
    "consistencyKey": [
      {
        "statementId": "statement-1",
        "evidenceId": "evidence-1",
        "factId": "parcel",
        "assertedValue": "red",
        "establishedValue": "blue",
        "contradicts": true
      },
      {
        "statementId": "statement-2",
        "evidenceId": "evidence-2",
        "factId": "gate",
        "assertedValue": "open",
        "establishedValue": "open",
        "contradicts": false
      }
    ],
    "provenance": "caller-supplied-fiction",
    "randomness": {
      "seed": 42,
      "source": "seed"
    }
  }
}

Limitations and assumptions

Alternative values must differ from the fictional truth, and templates must expose the value token. Consistency is against the supplied story facts, not real-world fact checking or an automatic assessment of narrator reliability.
A replay requires the same complete input and implementation. Randomized construction does not guarantee uniform coverage of every feasible output; finite samples can repeat unless a distinct-selection rule is explicitly stated.
The field tables state structural bounds; cross-field constraints and bounded search or output budgets also apply. Unknown keys are rejected where the object contract disallows them. Input errors are distinct from null fields and deliberate invalid controls in a successful output.

Alternative or Complementary methods

For a supplied example, inspect the returned construction or delegated check directly. To evaluate a consumer, also test cases chosen for its own boundaries; a generated finite corpus does not establish exhaustive coverage.

References

Tool behavior and example: Random Unreliable Narrator Evidence Deck Generator — tool.io
Calculation or validation: text/word-wrap — tool.io

Similar or alternative tools

Random Improv Dialogue Word Ban Challenge Generator
Select supplied forbidden tokens and compatible substitute objectives with a literal checklist and disclosed matching convention; speech monitoring remains outside the tool.
Random Improv Emotion Transition Sequence Generator
Order supplied fictional emotion labels through explicit transition cues and hold counts using bounded search; no participant psychology is classified.