Unverified50% confidenceFactExact time
PORTAL draws on the best-arm identification idea from multi-armed bandits; the goal is not to maximize cumulative reward but to identify the currently best candidate with the fewest queries.
1
Sources
50%
Confidence
Long-term
Relevance
10/28/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedWhen selecting a model, one should focus on sub-scores for the dimensions relevant to the specific application scenario rather than blindly pursuing the top overall ranking.65% similarUnverifiedHeterogeneous activation probabilities cause the optimal strategy to have to weigh the problem of preferentially occupying scarce arms, which is equivalent to a combinatorial optimization problem with conflict constraints, and the feasible assignment space grows exponentially with the number of players and the number of arms.61% similarUnverifiedLinUCB assumes that the expected reward has a linear relationship with contextual features, computes the upper confidence bound by maintaining parameter estimates for each arm, and prioritizes the option with the highest upper bound.60% similarUnverifiedWhen a judge cannot verify an answer, it latches onto available cues such as position to make a judgment, and bait provides more useful cues.59% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1106248API
curl https://kongchang.com/api/v1/knowledge/claims/1106248MCP
get_claim(id=1106248)