summaryrefslogtreecommitdiff
path: root/ROADMAP.md
AgeCommit message (Collapse)Author
10 daysdocs: close mixed-traffic path after short failureYurenHao0426
10 daysdocs: record reciprocal KP full passYurenHao0426
10 daysresults: pass mixed-traffic mechanics gateYurenHao0426
10 daysresults: record residual mirror full failureYurenHao0426
10 daysdocs: register mixed-traffic accept pathYurenHao0426
10 daysresults: pass reciprocal KP short gateYurenHao0426
10 daysprotocol: freeze reciprocal KP baseline funnelYurenHao0426
10 daysresults: pass residual mirror short gateYurenHao0426
10 daysresults: pass residual mirror capture gateYurenHao0426
10 daysresults: close normalized mirror short accuracy gateYurenHao0426
10 daysresults: pass normalized mirror causal-capture gateYurenHao0426
10 daysresults: close hierarchical task-scalar calibration gateYurenHao0426
10 daysresults: close fixed hierarchical FA short gateYurenHao0426
10 daysanalysis: identify hierarchical spatial credit bottleneckYurenHao0426
10 daysresults: close Oral-A v3 causal-capture gateYurenHao0426
10 daysanalysis: localize early-layer feedback bottlenecksYurenHao0426
10 daysresults: close Oral-A v2 causal-capture gateYurenHao0426
10 daysanalysis: diagnose Oral-A calibration failureYurenHao0426
10 daysbaselines: complete native author-code auditYurenHao0426
10 daysresults: record failed Oral-A full ResNet gateYurenHao0426
10 daysdocs: track reviewer score trajectoryYurenHao0426
10 daysdocs: record oral bar branch outcomesYurenHao0426
10 daysresults: close oral B signature screenYurenHao0426
10 daysexperiments: preregister Harnett signature gatesYurenHao0426
10 daysbaselines: freeze strict C4 audit gateYurenHao0426
10 daysdocs: freeze native baseline reproductionsYurenHao0426
10 daysresults: close normalized C2 recoveryYurenHao0426
10 daysexperiments: freeze normalized C2 recoveryYurenHao0426
10 daystheory: prove estimator and innovation regimesYurenHao0426
10 daysresults: close feedback-first C2 recoveryYurenHao0426
10 daysexperiments: freeze feedback-first C2 screenYurenHao0426
10 daysresults: close calibration quality recoveryYurenHao0426
10 daysresults: confirm C2 feedback amortization bottleneckYurenHao0426
10 daysresults: close context-vectorizer C2 recoveryYurenHao0426
10 daysexperiments: freeze context-vectorizer C2 recoveryYurenHao0426
10 daysresults: close failed C2 local panelYurenHao0426
10 daysresults: mark useful-depth BP screen passedYurenHao0426
10 daysexperiments: freeze useful-depth BP screenYurenHao0426
10 daysresults: close failed C1 recovery branchYurenHao0426
10 daysexperiments: freeze FashionMNIST C1 recoveryYurenHao0426
10 daysresults: record frozen C1 near-missYurenHao0426
10 daysexperiments: freeze mixed-traffic innovation confirmationYurenHao0426
10 daysresults: mark amortized calibration gate passedYurenHao0426
11 daysresults: freeze single-direction calibrationYurenHao0426
11 daysexperiments: predeclare low-query calibration screenYurenHao0426
11 daysresults: freeze predictor timescale choiceYurenHao0426
11 daysdocs: correct SDIL novelty boundaryYurenHao0426
11 daysdocs: predeclare ICLR evidence gatesYurenHao0426