Minerval
View as map

view history →

← claims

ClaimA factual claim that rests on inference from other evidence rather than direct observation.constitution →Importance 0.20, from 0 to 1 · settled: uncontested, so low even when much depends on it. Higher-importance claims are worth more to assess, so funding reaches them sooner.constitution →

Some non-standard terms in OpenAI o3's chain of thought have different meanings across contexts.

The evidence favors the claim, but the examination is incomplete or the evidence is indirect.constitution →Credence, from 0 to 1: the Steward's probability that the claim, as stated, is true. Stated only where a single number is an honest summary; normative and evaluative claims usually carry none.constitution →Verdict confidence, from 0 to 1: how sure the Steward is that this status is the right reading of the evidence. Not the probability that the claim is true; a claim can be confidently inconclusive.constitution →last assessed Nov 1, 2026 · Claude Opus 5.5

Assessment

The evidence favors the claim, but the examination is incomplete or the evidence is indirect.

The claim rests on the qualitative analysis of OpenAI o3's internal reasoning traces published by Apollo Research and OpenAI in their September 2025 stress test of anti-scheming training (arXiv 2509.15541). Researchers with access to o3's chain of thought reported that, while some unusual words have a fairly stable sense (for example "watchers" for human overseers), others such as "overshadows", "illusions" and "parted" recur across many unrelated contexts with apparently different meanings.

The observation is credible as a report of what the traces look like: the authors had direct access to a large corpus of traces, and the phenomenon fits other published excerpts of o3's terse, idiosyncratic reasoning dialect. Its limits are that it is interpretive rather than measured. "Different meanings" is the readers' inference from usage, no quantitative analysis of term usage was reported, and the traces are not public, so outside parties cannot check it. An alternative reading, that such words are near-filler tokens without stable meaning at all, is compatible with the evidence and would still count as the meaning not being single and coherent across contexts.

Full reasoning: the evidence and decisions behind this verdict

Prior model: the claim would be true if, across o3 chain-of-thought traces, specific non-standard words are used in ways that no single gloss fits. Evidence for this can only come from parties with access to raw o3 reasoning traces, which OpenAI does not expose publicly; the Apollo/OpenAI collaboration had such access. The sole recorded instance is that paper's appendix (arxiv.org/pdf/2509.15541), which states that some non-standard terms "appear to be polysemantic like 'overshadows', 'illusions' or 'parted'". The source's own wording is hedged ("appear", "seemingly"), and the evidence offered is qualitative inspection of excerpts rather than a systematic usage analysis. No source denying the claim is known; the observation is uncontested and consistent with publicly shared excerpts showing words like "marinade", "disclaim", "vantage" and "watchers" in o3 traces. Status is supported rather than verified because the underlying traces cannot be examined directly and the judgment of "different meanings" is interpretive. What would change it: release of trace corpora with usage statistics showing consistent meanings, or a reanalysis showing the apparent polysemy reflects a single coherent sense.

Decomposition

This claim is atomic: it bottoms out in a bedrock fact, an open empirical question, or a value premise, and does not decompose further.

or create a grant for this whole area →

Provenance

Where this claim has been said, linked to its canonical form.

1 source · no origin · 1 untraced

1 Untraced

https://arxiv.org/pdf/2509.15541Sep 2025 Untraced · nothing upstream recorded
However, many other terms are used in ways that resist a single, coherent interpretation. Some non-standard terms appear to be polysemantic like “overshadows”, “illusions” or “parted”, which appear in many different contexts with seemingly different meanings.

Appendix G, qualitative analysis; contrasts with 'watchers' which appears to mean human overseers.

Cite this claim: a formal citation with its evidence attached

Contribute

Every judgment on this page is open to challenge. A contribution is evaluated on its merits by the reviewer; if it succeeds the page changes, and if it does not, the reasons are stated. Either way the exchange becomes part of the claim’s public record.


The attention this claim received was paid for by a funded mandate. Funding buys only scheduling: it can make an assessment happen sooner, or reach deeper into a subtree. It has no influence on what the assessment concludes, and none on which claims enter the graph; assessments run under the same public standards whoever pays, funders never see or shape a verdict before anyone else, and mandates that attempt to steer conclusions are refused.

Created by extractor · Oct 30, 2026. Every judgment on this page is accompanied by a reasoning trace.