Browse

Claims

Search the graph by meaning. Each result carries its current verdict; open one to see its decomposition, provenance, and the reasoning behind the assessment.

7 results

Claims about how reliably language models' explicit reasoning traces can be steered, constrained, or controlled by users or system interventions. Excludes whether those traces faithfully reveal internal reasoning, which belongs under chain-of-thought monitorability.

Among Claude models, chain-of-thought controllability tracks model size rather than release date.

UnknownInsufficient information to assess.constitution →empirical · verifiableA factual claim that could be checked directly against observation or primary records.constitution →Anthropic Large language models AI Scaling Trendsimportance · minorImportance 0.30, from 0 to 1 · minor: narrow or largely settled, cheap to get right. Higher-importance claims are worth more to assess, so funding reaches them sooner.constitution →

Within open-weight reasoning model families, models with more parameters score higher on the CoT-Control controllability evaluation.

SupportedThe evidence favors the claim, but the examination is incomplete or the evidence is indirect.constitution →empirical · verifiableA factual claim that could be checked directly against observation or primary records.constitution →Large language models AI Capability Evaluation AI Scaling Trendsimportance · minorImportance 0.30, from 0 to 1 · minor: narrow or largely settled, cheap to get right. Higher-importance claims are worth more to assess, so funding reaches them sooner.constitution →

CoT controllability declined over outcome-based RL training in the CoT-Control experiments.

VerifiedThe evidence, examined directly, establishes the claim.constitution →empirical · verifiableA factual claim that could be checked directly against observation or primary records.constitution →Reinforcement Learning with Verifiable Rewards Large language modelsimportance · minorImportance 0.30, from 0 to 1 · minor: narrow or largely settled, cheap to get right. Higher-importance claims are worth more to assess, so funding reaches them sooner.constitution →

GPT-6 Astra's architectural changes differentially explain its chain-of-thought controllability changes.

DoubtfulThe evidence weighs against the claim, but the examination is incomplete or the evidence is indirect.constitution →causalA claim that one thing brings about another, not merely that the two go together.constitution →Large language models OpenAIimportance · minorImportance 0.30, from 0 to 1 · minor: narrow or largely settled, cheap to get right. Higher-importance claims are worth more to assess, so funding reaches them sooner.constitution →

Greater outcome-based RL training on reasoning tasks decreases chain-of-thought controllability.

InconclusiveThe evidence and argument have been examined and do not come down on either side.constitution →causalA claim that one thing brings about another, not merely that the two go together.constitution →LLM Reasoning Training Reinforcement Learning with Verifiable Rewardsimportance · minorImportance 0.40, from 0 to 1 · minor: narrow or largely settled, cheap to get right. Higher-importance claims are worth more to assess, so funding reaches them sooner.constitution →

Newer frontier reasoning models have substantially more controllable chains of thought than earlier generations.

SupportedThe evidence favors the claim, but the examination is incomplete or the evidence is indirect.constitution →empirical · verifiableA factual claim that could be checked directly against observation or primary records.constitution →Large language models LLM capability trendsimportance · notableImportance 0.45, from 0 to 1 · notable: a contested point in a live debate (also the default before judging). Higher-importance claims are worth more to assess, so funding reaches them sooner.constitution →

GPT-6-generation OpenAI models score substantially higher than GPT-5.x models on CoT-Control at matched chain-of-thought length.

UnassessedNo current assessment. Attention goes where its expected value is highest and someone funds it; nothing has funded an assessment of this claim yet, and anyone can.constitution →empirical · verifiableA factual claim that could be checked directly against observation or primary records.constitution →OpenAI AI Capability Evaluation LLM capability trendsimportance · minorImportance 0.30, from 0 to 1 · minor: narrow or largely settled, cheap to get right. Higher-importance claims are worth more to assess, so funding reaches them sooner.constitution →

Contribute

If a claim here is wrong, or missing evidence, open it: every claim page carries its own entry for challenges, evidence, and corrections. If the graph is missing a claim or a question entirely, propose it below. A proposal is reviewed on its wording; accepted proposals are matched against the graph before they enter it.