StochStack

prototype 02

Site Feasibility with Human Feedback

Team policy learns from multi-user feedback. Repeated single-user dislikes are capped; weight shifts require consensus.

Base Filter Context

Team Feedback Console

Reason tags

Effective Weights

Experience24.0%
Startup speed18.0%
PI capacity14.0%
Competitor coverage14.0%
CTGov relevance16.0%
Execution stability10.0%
Sponsor fit4.0%

Before (Team Baseline)

#1 Research Site

Seoul, South Korea

score: 89.5

#2 Research Site

Bangkok, Thailand

score: 84.7

#3 Research Site

São Paulo, Brazil

score: 81

#4 Research Site

Taipei, Taiwan

score: 81

#5 Research Site

Shanghai, China

score: 79.4

#6 Research Site

Sofia, Bulgaria

score: 76

#7 Research Site

Porto Alegre, Brazil

score: 68.7

#8 Research Site

Budapest, Hungary

score: 68.7

After (Team Learned Policy)

#1 Research Site

Seoul, South Korea

score: 89.5

#2 Research Site

Bangkok, Thailand

score: 84.7

#3 Research Site

São Paulo, Brazil

score: 81

#4 Research Site

Taipei, Taiwan

score: 81

#5 Research Site

Shanghai, China

score: 79.4

#6 Research Site

Sofia, Bulgaria

score: 76

#7 Research Site

Porto Alegre, Brazil

score: 68.7

#8 Research Site

Budapest, Hungary

score: 68.7

Rank Shift

#1 Research Siteafter #1 (0)
#2 Research Siteafter #2 (0)
#3 Research Siteafter #3 (0)
#4 Research Siteafter #4 (0)
#5 Research Siteafter #5 (0)
#6 Research Siteafter #6 (0)
#7 Research Siteafter #7 (0)
#8 Research Siteafter #8 (0)
#9 Research Siteafter #9 (0)
#10 Research Siteafter #10 (0)

Consensus Guardrails

Feedback Log (Audit)

No feedback yet.

    update log

    Prototype Change Log

    1. 2026-03-01 · v0.3.0

      Team Policy Persistence and Consensus Aggregation

      • - Added persistent team profiles and server-side feedback event store.
      • - Added multi-user consensus aggregation for effective weight updates.
      • - Added anti-abuse controls: single-user daily cap, repeated action decay, and max per-reason shift.

    2. 2026-03-01 · v0.2.0

      Human Feedback Reinforcement Layer Added

      • - Added before-vs-after ranking comparison.
      • - Added explicit feedback actions (like/dislike) with reason tags.
      • - Introduced adaptive weight updates and audit feedback log.