Fetching metadata from the HF Docker repository...
Jun 20 20:55 Add 3-stage CIF fallback: pymatgen → CifParser(occ_tol=2) → ASE 20:55 Fix GitHub link (MujeebOnawole/PoreGCN) + robust CIF fallback parser May 4 07:46 app.py: remove inaccurate claim that Tb-MOF reproduces same Scenario pattern under both XAI modes 07:22 app.py: rename Full to Slow + plain-language Fast/Slow XAI explainer (predicted values are the same; only attribution method differs); add optional Goatcounter visitor-tracking pixel via GOATCOUNTER_CODE env var 07:11 app.py: drop the offline-pipeline bullet from the How-to-use list 07:06 app.py: per-property XAI in Fast mode (~35s, all rows correctly classified); Full stays target-only with Fast surrogate for other rows; About tab rewritten with honest how-to-use guidance 06:39 app.py: load property_means from per-ensemble JSON; classify_scenario uses manuscript dual criteria (ratio>=0.70 OR mean signed direction) 06:39 xai_engine.py: load property_means from per-ensemble JSON; classify_scenario uses manuscript dual criteria (ratio>=0.70 OR mean signed direction) 06:14 app.py: Fast/Full XAI toggle + skip +0.00 cavity labels + About Ensembles and XAI explainer 06:14 visualize.py: Fast/Full XAI toggle + skip +0.00 cavity labels + About Ensembles and XAI explainer 06:14 xai_engine.py: Fast/Full XAI toggle + skip +0.00 cavity labels + About Ensembles and XAI explainer 05:53 app.py: swap bundled CoRE MOF validation example to Tb-MOF (dual-method 5 of 7 Scenario A) 05:53 example_cifs: remove Zn-MOF-ChemSci2019 (replaced by dual-validated Tb-MOF) 05:53 example_cifs: bundle Tb-MOF (CrystEngComm 2023, dual-XAI-method validated CoRE MOF entry) 04:26 app.py: wire 4th example (Zn-MOF-ChemSci2019 -> core_mof) into KNOWN_MOFS + About Ensembles 04:26 example_cifs: bundle Zn-MOF (Chem. Sci. 2019, CoRE MOF entry) for trustworthiness validation 03:52 app.py: legend matches viewer (cornflower-blue metals + cavity attribution chips); slim footer with email 03:52 visualize.py: legend matches viewer (cornflower-blue metals + cavity attribution chips); slim footer with email 03:14 app.py: smaller cavity beads + per-bead attribution labels + wrap atoms to [0,1) + clip mesh to cell 03:14 visualize.py: smaller cavity beads + per-bead attribution labels + wrap atoms to [0,1) + clip mesh to cell 03:04 visualize.py: revert axis tip labels to crystallographic a/b/c 02:49 app.py: manual white wireframe + xyz labels; one example per ensemble; About Ensembles tab 02:49 visualize.py: manual white wireframe + xyz labels; one example per ensemble; About Ensembles tab 02:33 app.py: opaque mesh (0.55) + opaque beads + white wireframe + xyz axis labels 02:32 visualize.py: opaque mesh (0.55) + opaque beads + white wireframe + xyz axis labels 02:17 fix: align void mesh with 3Dmol standard CIF frame; switch viewer to black bg 01:56 visualize.py: harden void mesh (per-axis grid clamp, vertex cap, full failure fallback to atoms+beads) 01:51 requirements.txt: Mercury-style void isosurface (Path D, contact-surface mesh + attribution glyphs) 01:51 visualize.py: Mercury-style void isosurface (Path D, contact-surface mesh + attribution glyphs) May 3 22:08 visualize.py: cavity-scale pore spheres (Lisensky and Yaghi 2022 idiom) 14:10 Pore markers: fixed 0.6A radius (color carries signal, not size) 14:05 Replace per-node occlusion with gradient x input attribution (O(1) backward, ~150x faster) 13:56 Cap per-pore occlusion XAI to 40 largest pores (free CPU compute budget) 13:50 Polyhedra-style aesthetic: indigo metal SBUs 13:50 Robust Zeo++: try -nt2 then -vornet, copy CIF first 13:44 Wire CSV download in tab 4 13:44 Hover shows attribution + add CSV export helper 13:44 Drop -r from Zeo++ command (incompatible with -vornet) 13:33 Add 3Dmol hover tooltip + element legend 13:33 Fix Zeo++ command (-vornet with explicit output path) + parser for both formats 13:20 Use bundled Zeo++ tarball as primary source 13:20 Bundle Zeo++ source tarball (HF outbound network corrupts download) 13:03 Add stick bonds via 3Dmol auto-bond detection 12:54 Use Jmol colorscheme (bwr gradient name was invalid in 3Dmol.js) 12:41 Fix 3D viewer: render all atoms as spheres (sticks need bonds CIF lacks) 12:31 Initial PoreGCN web tool deployment 12:31 initial commit 
