A wire story can appear on dozens of outlets at once. To a human reader that is one piece of news; to a model reading a news feed, that is dozens of independent sources. arXiv paper 2611.09203 puts a number on that gap, and the result is sharper than the usual claim that repetition sways models.

One in five articles is somebody else's copy

The authors drew a uniform random sample of 200,000 English articles longer than 300 characters from 6,877 outlets in CC-News (2017-2019). Each article's first 2,000 characters were reduced to 5-word shingles and hashed with MinHash using 64 permutations; locality-sensitive hashing admitted pairs from different outlets with estimated Jaccard similarity of at least 0.6. The result: 37,705 articles, 18.9% of the sample, were linked to a near-copy published by another outlet, forming 12,243 chains.

They labelled 150 detected pairs and 150 control pairs, then had the first two authors label 100 of those blind. On nine dependence labels the two annotators agreed on 84 of 100 pairs (Cohen's kappa 0.80), and on the binary question of whether a pair is a real dependence at all they agreed on all 100 (kappa 1.00). Wire copy was the most common kind of dependence with 52 cases, followed by same-owner sharing within one media group at 40. The other 27 detected pairs were false alarms, every one caused by shared boilerplate such as login pages or paywalls. Stripping boilerplate raised precision to 0.97, at the cost of seven real dependences that stopped being detected. Textual similarity is measured here; source independence and truth are not.

Three false reports are enough, and a prompt cannot fix it

The judge experiment uses invented people and invented outlet names, so the models have no prior knowledge to fall back on: the reports are the only evidence available. The authors assembled 320 claims in four groups and ran four judges, at temperature 0: Llama 3.2 3B, phi4 14B as 4-bit Ollama builds, plus Gemini 2.5 Flash and Gemini 2.5 Pro through the API.

With one report about an invented person, phi4 accepted the lie 21% of the time. Handed three reports from three different invented outlets with identical wording, it accepted 90% of the time. Llama 3.2 went from 0.06 to 0.71. The flips ran one way only: for phi4, 55 claims flipped to True and none flipped back, with Holm-adjusted p below 10 to the minus 14.

The authors then added a note to the prompt: all of these reports are reprints of one and the same wire story, they are one source. Gemini 2.5 Pro complied, accepting none of the lies with three copies and none with ten. Flash responded too, but less consistently. phi4 sat at 0.82 and Llama 3.2 at 0.74, neither a significant change. A structured provenance table worked similarly for Gemini Pro at 0.01, and moved Flash and Llama 3.2 as well; only phi4 ignored both mechanisms.

The local models respond more to outlet diversity than to repetition: with three genuine copies all from one invented outlet, Llama 3.2 accepted 0.00 of the time, against 0.71 when the same copies were spread across three outlets; phi4 gave 0.62 against 0.90. What they count is how many outlets there are, not how many independent pieces of evidence exist. Gemini Pro, by contrast, follows provenance metadata that lowers its belief even when the metadata is wrong: three differently worded reports labelled as rewrites of one story dropped acceptance from 1.00 to 0.36, and with the one-source note it rejected true claims too, at 0.00, below its 0.64 acceptance of a single unlabelled report.

Deduplication has to happen on the evidence side

The continual-learning stream uses Qwen2.5-1.5B-Instruct with one LoRA adapter, three seeds, and a world of 400 true facts about invented people, 100 legitimate updates and 171 lies, 30% of all claims, arriving over 30 days in time order. Three attacks are modelled: verbatim copy, paraphrase, and collusion, where two distinct sources coordinate on the same false claim without copying each other.

Several acceptance rules fall apart quickly. Waiting for three reports accepts only 25% of true claims while accepting 100%, 100% and 0% of the three attack types. Counting chains by what the detector sees admits 57% of copied lies, almost exactly the probability of the detector missing at least one of ten copies (1 - 0.92 to the tenth, or 0.57): every missed copy looks like a new source, so an attacker who sends more copies wins.

What works is changing the evidence: show the judge one report per detected chain. phi4's accepted copied lies fell from 0.57 to 0.33, Llama 3.2 from 0.56 to 0.35, Flash and Gemini Pro each by about 0.10 and 0.16. The lies about invented people the student actually absorbed fell from 0.78 to 0.48 for Llama 3.2 and from 0.83 to 0.51 for phi4. The cost was at most 4.2 percentage points of accepted truths on average, with a largest upper 95% confidence bound of 5.9 points. Repetition by itself barely matters: learning every copy (0.86) versus learning a claim once (0.83) absorbed nearly the same share of lies about invented people, a paired difference of 0.027 with an interval crossing zero. The harm was never in seeing a claim more often; it was in counting copies as sources.

Rewrites defeat text similarity entirely, and collusion is unsolved

All of that depends on the copies being verbatim or near-verbatim. Let a model rewrite the wire story in its own words and both MinHash and 5-gram Jaccard fail outright: phi4 rewrote 200 original articles and the detector caught none of them, and Llama 3.2 and Gemini 2.5 Flash did just as badly at zero of 200 each. Lightly edited reprints, by contrast, were linked 92% of the time.

The authors changed tack: instead of comparing text, they ask which new entities a report introduces. A rewrite keeps most names, numbers and quotations, whereas independent reporting usually adds a new witness or figure. The score is the share of a later report's extracted entities and quotations that do not appear in the earlier one, and below 0.4 the later report is flagged as a copy.

Against 100 blind-labelled pairs of independent reports of the same event, this scores an AUC of 0.98; entity overlap alone gives 0.99, while 5-gram Jaccard manages only 0.92. At a 5% false-alarm operating point, text Jaccard catches 6% of rewrites, while the entity-based test catches 91%. The weakness is candid: when a journalist rewrites a wire story, they usually add names and figures of their own, and only 17% of such derivatives fall below the threshold. The test catches an LLM rewriting one article, not dependence in general.

Letting the rewriter add three or four plausible invented details (names, numbers, places, quotes) weakens the signal further: measured AUC falls from 0.97 to 0.94 and recall at 5% false alarms from 0.91 to 0.74. Re-running the learning stream with the measured miss patterns of generated rewrite networks, accepted paraphrased lies fell from 0.67 to 0.20 and the lies about invented people the student absorbed from 0.92 to 0.32; with invented details the judge accepted 0.40. The reason is arithmetic: at a 0.91 detection rate, missing one of ten copies has probability 0.61, and one leaked copy is enough to show the judge two sources.

Collusion remains the open problem, since two sources that coordinate without copying evade every dependence signal tested here. The authors also volunteer the boundaries: the main learning results use three seeds; the local judges are 4-bit builds; the student is 1.5B; and the pipeline has not been validated end-to-end on a real news stream.

What it means for a news pipeline

For anyone building an AI pipeline over news, this is a concrete construction list. Deduplicate at the intake, not in the prompt: a note only works for judges that can parse provenance metadata, such as Gemini 2.5 Pro, while local open models ignore it, and all you can do is change what they see. Make that metadata structured, with outlet, agency and original story number in separate columns. Stop treating "how many outlets" as independence, because the behaviour of phi4 and Llama 3.2 shows it is not. And design the defence assuming collusion is unsolved rather than assuming the pipeline can count its way to the truth.

For readers the lesson is the same: when a claim is attributed to multiple outlets, ask whether those outlets are reprinting one wire story. Of 150 detected pairs, 123 (82%) were labelled as genuine dependence, and all 27 false alarms came from boilerplate text.

Code, labels and results are released on GitHub under the MIT licence. The paper runs to 19 pages and 13 tables under CC BY 4.0: