4.98 MB

Ctrl+K

1 contributor

History: 13 commits

Chucks90

README: how the study was run, the gate protocol, and what failed

cf1e782 verified 20 days ago

arch
covtoken: label-free lesion-subspace token economy (reframed) + gated eval + paper draft 5 months ago
backbone
covtoken: label-free lesion-subspace token economy (reframed) + gated eval + paper draft 5 months ago
configs
covtoken: label-free lesion-subspace token economy (reframed) + gated eval + paper draft 5 months ago
coverage
covtoken: label-free lesion-subspace token economy (reframed) + gated eval + paper draft 5 months ago
data
covtoken: label-free lesion-subspace token economy (reframed) + gated eval + paper draft 5 months ago
eval
covtoken: label-free lesion-subspace token economy (reframed) + gated eval + paper draft 5 months ago
gate
covtoken: label-free lesion-subspace token economy (reframed) + gated eval + paper draft 5 months ago
gate_reports
verify two reviewer-probe claims: (1) measured lesion spectra REFUTE 'low internal rank' (RankMe 339>307) -> correct attribution to RARITY across papers #1/#2/NEGATIVE_RESULT; (2) verified MedDINOv3/DINOv3=RoPE vs DINOv2=learned-absolute, paper #3 §3 stated precisely 5 months ago
jobs
rarity-route verified: spanning reproduces 0.46, sits between population & concentration, redundancy RULED OUT (incr rank 0.75m); candidate closed form rejected (over-predicts). Paper #2 §2 = two routes: low-rank existence proof (2a) + measured rarity mechanism (2b) 5 months ago
paper
regenerate figures as 650-dpi LZW TIFFs, flattened RGB (publication-ready) 5 months ago
research_specs
G1c FINO-style adapter: metadata guidance offsets SSL-globalization directionally (+0.014) but no CI-significant recovery; F1b not de-risked at adapter scale (honest) 5 months ago
research_v2
research programs v2 (S1-S5) + v3 (F1-F4) + cross-objective mechanism; paper drafts #2/#3; specs; figures 5 months ago
research_v3
v4: concentration-steering NEGATIVE (globalization is entangling, not removable); multi-seed rigor (S1 exact law, S2 tail-gap selector regret 0.006); papers updated 5 months ago
research_v4
rarity-route verified: spanning reproduces 0.46, sits between population & concentration, redundancy RULED OUT (incr rank 0.75m); candidate closed form rejected (over-predicts). Paper #2 §2 = two routes: low-rank existence proof (2a) + measured rarity mechanism (2b) 5 months ago
subspace
covtoken: label-free lesion-subspace token economy (reframed) + gated eval + paper draft 5 months ago
tests
covtoken: label-free lesion-subspace token economy (reframed) + gated eval + paper draft 5 months ago
.gitattributes

2.03 kB
regenerate figures as 650-dpi LZW TIFFs, flattened RGB (publication-ready) 5 months ago
.gitignore

59 Bytes
covtoken: label-free lesion-subspace token economy (reframed) + gated eval + paper draft 5 months ago
DATA_AVAILABILITY.md

3.06 kB
add DATA_AVAILABILITY.md: what's included, public dataset/backbone sources, reproduce-via-HF-Jobs, DOI note 5 months ago
README.md

5.4 kB
README: how the study was run, the gate protocol, and what failed 20 days ago
RESEARCH_OVERVIEW.md

5.55 kB
G1c FINO-style adapter: metadata guidance offsets SSL-globalization directionally (+0.014) but no CI-significant recovery; F1b not de-risked at adapter scale (honest) 5 months ago
__init__.py

0 Bytes
covtoken: label-free lesion-subspace token economy (reframed) + gated eval + paper draft 5 months ago
run_phase0.py

1.95 kB
covtoken: label-free lesion-subspace token economy (reframed) + gated eval + paper draft 5 months ago