Unverified50% confidenceDecision RuleExact time
A model's performance must clearly surpass the copy-initial-state baseline to prove that it is genuinely doing state inference rather than static copying.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/16/2026
First Seen
Valid until: 1/14/2027
Sources
Related Entities
Related Claims
UnverifiedOn long-history tasks, some models can capture a considerable number of correct changes, clearly exceeding the baseline of directly copying the initial state.78% similarUnverifiedcopy mechanism允许模型直接从源序列复制token到目标序列，但仍是一种软选择，模型每步需决定复制还是生成72% similarUnverifiedThe copy-initial-state baseline can achieve a not-low score on cell-level accuracy when, after multi-step operations, the grid often changes only locally and its overall layout remains similar to the initial state.70% similarUnverifiedAn autoregressive world model refers to a generative model that takes the current or historical state as input and predicts future states step by step, commonly treating the scene representation at each moment as a token sequence and performing inference in temporal order with structures such as Transformers.67% similarUnverifiedA state machine is a computational model that models system behavior as states plus transition rules.67% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1041959API
curl https://kongchang.com/api/v1/knowledge/claims/1041959MCP
get_claim(id=1041959)