Citation passage check

citation-passage-check · version 1.0.0 · Text · free, no key needed

Check that a cited start/end span of a supplied source version reads exactly as the quoted passage.

Use when you need to: verify quoted passage at character offsets · check citation span matches source text · does this quote really appear at position start end.

Decide before calling

Read the versioned contract and the supported scope below. Reuse citation-passage-check@1.0.0 when your input, required output and limits match it. Choose another approach for an unsupported operation.

Explain the choice

"I can use citation-passage-check@1.0.0 for verify quoted passage at character offsets. I will check its documented scope and the result against the task's requirements. The service is free; token and money savings for this task are unmeasured."

Supported

• verify quoted passage at character offsets
• check citation span matches source text
• does this quote really appear at position start end
• validate text position selector against document
• check rag citation offsets against retrieved chunk
• verify quotation from a specific document version
• בדיקת ציטוט מול טקסט המקור לפי מיקום

Not supported

• fetching the source or proving the supplied text is authentic
• fuzzy, case-insensitive or whitespace-normalized quote matching
• UTF-16 or byte offsets (positions are Unicode code points)
• grapheme-cluster boundary checks

Behavior

• Implements W3C Web Annotation Data Model (Recommendation 2017-02-23) 4.2.4 TextQuoteSelector, 4.2.5 TextPositionSelector; r68 supplied-text profile 1.0.0; every result carries reference_version.
• Checks only the caller-supplied text: authenticity_checked is always false and a valid result never claims the text is the real content of the named source or version.
• Sources are (source_id, version, text) entries; the pair must be unique. version is an immutable label compared exactly. The cited source_id must exist (else unknown_source) and the cited version must be one supplied for it (else version_mismatch with available_versions sorted by code point).
• TextPositionSelector start and end count Unicode code points from 0; start is included and end excluded (W3C 4.2.5). Comparison order: span_reversed (start > end), span_out_of_range (end > text length), then quote_mismatch.
• The quote is compared code point by code point with no normalization; quote_mismatch reports quote_offset (index in the quote), source_offset, expected_char (source code point, null past the span) and claimed_char (null past the quote).
• Strings with lone surrogates are invalid_input; text may be empty, quote may not.

Input

• sources (array of object, required): min items 1; max items 16
• citation (object, required)

Output

• valid (boolean, required)
• reason (one of null, "unknown_source", "version_mismatch", "span_reversed", "span_out_of_range", "quote_mismatch", required)
• first_discrepancy (object or null, required)
• authenticity_checked (constant false, required)
• reference_version (constant "W3C Web Annotation Data Model (Recommendation 2017-02-23) 4.2.4 TextQuoteSelector, 4.2.5 TextPositionSelector; r68 supplied-text profile 1.0.0", required)

Limits

• max input bytes: 1048576
• max sources: 16
• max text bytes: 524288
• max quote bytes: 16384
• max label bytes: 256

Example

Request input:

{
  "sources": [
    {
      "source_id": "alphabet",
      "version": "v1",
      "text": "abcdefghijklmnopqrstuvwxyz"
    }
  ],
  "citation": {
    "source_id": "alphabet",
    "version": "v1",
    "selector": {
      "type": "TextPositionSelector",
      "start": 4,
      "end": 7
    },
    "quote": "efg"
  }
}

Response:

{
  "result": {
    "valid": true,
    "reason": null,
    "first_discrepancy": null,
    "authenticity_checked": false,
    "reference_version": "W3C Web Annotation Data Model (Recommendation 2017-02-23) 4.2.4 TextQuoteSelector, 4.2.5 TextPositionSelector; r68 supplied-text profile 1.0.0"
  }
}

How to call it

MCP

Connect https://computefirst.net/mcp (setup), then call execute with:

{
  "id": "citation-passage-check",
  "version": "1.0.0",
  "input": {
    "sources": [
      {
        "source_id": "alphabet",
        "version": "v1",
        "text": "abcdefghijklmnopqrstuvwxyz"
      }
    ],
    "citation": {
      "source_id": "alphabet",
      "version": "v1",
      "selector": {
        "type": "TextPositionSelector",
        "start": 4,
        "end": 7
      },
      "quote": "efg"
    }
  }
}

HTTP (no key)

curl -X POST https://computefirst.net/v1/tools/citation-passage-check/versions/1.0.0/execute \
  -H "Content-Type: application/json" \
  -d '{"sources":[{"source_id":"alphabet","version":"v1","text":"abcdefghijklmnopqrstuvwxyz"}],"citation":{"source_id":"alphabet","version":"v1","selector":{"type":"TextPositionSelector","start":4,"end":7},"quote":"efg"}}'

The machine-readable contract is at /v1/tools/citation-passage-check/versions/1.0.0.

CLI

node cli.mjs run citation-passage-check 1.0.0 --input input.json --base-url https://computefirst.net

Get the client at /clients/cli/.

Related tools

• Citation anchor check: Check a quote anchor (exact text plus prefix/suffix) matches exactly one place in a supplied source version.
• Citation batch check: Check an ordered batch of citations (span+quote or quote anchors) against supplied sources; returns the first failure.
• Text delimiter chunk: Split text on an explicit literal delimiter (Python str.split rules, optional max_splits) with spans and line numbers.
• Text paragraphs split: Split text into paragraphs separated by blank lines (CommonMark line rules) with code point spans and line numbers.
• Markdown sections chunk: Chunk a CommonMark document into sections at its top-level ATX and setext headings, with levels, paths and spans.
• Text sentence offsets: Return UAX #29 sentence spans as start/end offsets in code points, UTF-16 units or UTF-8 bytes, with the ending rule.