Claim to Source Mapping: Showing Your Work, Line by Line

Good writing shows its work. When an article states a fact, a reader should be able to follow that fact back to a source and check it, and an editor should be able to do the same without hunting through the whole document. Claim-to-source mapping is the discipline of making that link explicit: each claim is paired with the source that supports it, one line at a time, so that gaps become visible instead of hiding in a long bibliography. The Claim Source Mapper supports this process by mapping pasted claims to pasted sources, line by line. It works on the text you supply, so it cannot verify that a source is accurate or trustworthy; it can only show which claims have a paired source and which do not.

How it works

The first step is to separate claims from other kinds of sentence. A claim is a statement that can be true or false, such as a date, a statistic, a causal statement or a quotation. An opinion, a recommendation or a rhetorical question is not a claim in this sense, and it does not need a source in the same way, although it may still benefit from evidence. A practical method is to go through a draft and underline every sentence that asserts a fact, then ask of each one whether a reader could check it and where they would look. Sentences that survive that question are the claim list, and sentences that do not are either opinions or claims that need a source found before publication.

Where it goes wrong

The second step is to judge whether a source actually supports its claim, which is stricter than merely mentioning the same topic. A source that discusses a subject in general does not support a specific statistic from that subject. A source that reports a preliminary finding does not support a statement written as a settled fact. A source that is itself quoting another source is weaker than the original, and the chain should be followed back where it matters. Dates matter too: a source from ten years ago may not support a claim about the present, even if it supported the same claim when it was written. Mapping makes these judgements visible, because a weak pairing can be questioned in a way that an unmapped claim cannot.

Worked example

Worked example with sample values. Suppose you paste 8 sample claims and 6 sample sources. The mapper pairs 6 claims with a source each, leaving 2 claims unmapped. The mapped rate is 6 divided by 8, which equals 0.75, or 75 percent. The unmapped rate is 2 divided by 8, which equals 0.25, or 25 percent, and 75 plus 25 equals 100, which confirms the counts account for every claim. The two unmapped claims are the actionable result: each one needs either a source found, a rewrite into an opinion or a qualified statement, or removal. A draft with 75 percent of its claims mapped is not three-quarters finished in any meaningful sense, because a single unsupported claim in a prominent position can undermine the whole piece. The sample counts here are illustrative.

Mistakes to avoid

Common failures follow a pattern. The first is a bibliography that exists but is never linked to specific claims, so a reader cannot tell which source supports which statement. The second is a single source cited for a whole paragraph containing several distinct claims, only some of which the source actually supports. The third is a source that is cited from memory or from a summary, without checking the original wording, which leads to claims that drift from what the source says. The fourth is a claim that is technically sourced but whose source is unreliable for that kind of claim, such as a marketing page cited for a technical specification. Each of these is easier to catch when claims and sources are laid out side by side.

Putting it into practice

Use the mapper during editing, not as a last-minute check before publication. Extract the claims, paste the sources, read the unmapped list first, and resolve every gap before moving on. Keep the mapping with the draft so that a later editor can see why each claim was believed, and update the mapping when a claim is rewritten, since a rewrite can change what a source needs to support. The goal is not a perfect percentage but a draft in which every factual statement can be traced, questioned and defended, which is the foundation of trust between a writer and a reader.

Related tools and reading: the Word Counter and the JSON Studio cover neighbouring checks that pair naturally with this one, and the guide at [/blog/fact-check-ai-content/] extends the same topic with further background and examples for readers who want to go deeper.

Key points

• Factual claims separated from opinions before mapping
• Each claim paired with a specific source, not a general list
• Sources checked for actual support, not mere topic overlap
• Every unmapped claim sourced, rewritten or removed
• Mapping kept with the draft and updated after rewrites

In short: Every factual claim deserves a source a reader can check. The mapper pairs pasted claims with pasted sources, line by line. An unmapped claim is a gap, not a minor formatting issue. A source must support the claim, not merely mention the topic.

One habit ties all of this together: re-check after every change. A result from the Claim Source Mapper is only as current as the text it was run on, so a fix, a redesign, or a new version of the underlying material deserves a fresh run rather than reliance on an old report. Keep the previous result alongside the new one, note what changed between them, and treat any new finding as a question to investigate rather than a verdict to accept or dismiss. That loop of checking, fixing, re-checking and recording is what turns a one-off test into a reliable routine, and it costs far less time than debugging a problem that a second check would have caught early.