Unverified50% confidenceFactExact time
Calibration Court generates 25 deterministic questions per day, and all question results are parsed from public price data.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/17/2026
First Seen
Valid until: 1/15/2027
Sources
Related Entities
Related Claims
UnverifiedEach question in the test is scored out of 100 points, consisting of 70 points for correctness plus 30 points for quality, with different questions carrying different weights.62% similarUnverifiedA document evidence model agreed with the reference labels on 36 out of 40 observations, for an accuracy of 90%.61% similarUnverifiedCalibration refers to a judge who is 70% confident in 100 events having approximately 70 of those events actually occur, in which case the judge is said to be well-calibrated.60% similarUnverifiedIn the evaluation, gpt-4o judging had the highest agreement with the author's own 115 blind judgments (κ 0.86), and CSR judgments matched human judgment on 25 to 27 of 30 blind cases.60% similarUnverifiedAfter the 1-billion-parameter model was adapted to a fraud detection scenario, detection accuracy improved by 24% compared to the previous solution.59% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1055723API
curl https://kongchang.com/api/v1/knowledge/claims/1055723MCP
get_claim(id=1055723)