Unverified50% confidenceBenchmarkExact time
Four language models that had never previously encountered tok, relying only on a one-page reference document, achieved valid tok generation rates of 85.7% to 100% on 87 process descriptions, while the corresponding BPMN XML could be generated for every description.
1
Sources
50%
Confidence
Long-term
Relevance
11/6/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedIn the experiment of writing tok from only a one-page reference document, the strongest model used 25% and 19% fewer tokens to write tok than to write BPMN XML.74% similarUnverifiedThe tok checker achieved a detection rate of 98.2% on 1,411 injected faults, while the combination of XML Schema with bpmnlint achieved a detection rate of 85.8%.66% similarUnverifiedOn 120 template-related requests, the full workflow achieved 98.3% first-round specification and decision accuracy, versus 92.5% for pattern-assisted single attempts and 82.5% for the model-only approach.66% similarUnverifiedAfter implementing a process of downloading sources first and then letting the model write, 36 of 39 research citations were verbatim correct, and 95% of quotations in thinker biographies passed source verification.65% similarUnverifiedAfter 15 training epochs on the demonstration dataset, the text classification model achieves an accuracy of 99%, with a total of 110,000 model parameters (16,000 for Attention, 33,000 for FFN, and the remainder for Embedding)65% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1142420API
curl https://kongchang.com/api/v1/knowledge/claims/1142420MCP
get_claim(id=1142420)