Follow
Superconducting Qubit And Device Design and Simulation database 9
Nov 16 Yesterday 21:42 Model card: QCap logo (light and dark) in place of the SQuADDS header image, SQuADDS link kept 20:45 Card: the hosted API serves qcap and qcap-fast 20:44 Card: paper title 'QCap: a physics-corrected graph neural network for the capacitance matrix of any planar superconducting device layout' 20:42 Card: paper title back to 'A physics-corrected graph neural network for the capacitance matrix of any planar superconducting circuit layout' 20:27 Card: the paper's title is now 'QCap: a physics-corrected graph neural network for the capacitance matrix of any planar superconducting device layout' 20:09 README: the models are QCap, QCap-Lite and QCap-Fast (folders qcap/, qcap-lite/, qcap-fast/; API ids qcap, qcap-fast) Nov 14 3 days ago 22:49 README: models, not tiers 19:35 README: links to the paper, data, models, collections and the SQuADDS ML inference API 19:06 README: hosted API section 18:55 README: no links to private repositories 17:16 README: paper page moved to /ml-paper/ 17:02 Add the Balanced tier (balanced/), README: short card in the paper's language with links Nov 7 10 days ago 03:38 Card: Fast is an improved release of the paper's fast model; each tier quotes its own in-sample fit and B5, the paper's held-out numbers are labelled as the paper's version; physical-check warning Nov 4 13 days ago 02:34 Model card: other substrates (calibrated substrate route; Fast rescales and warns) Oct 30 18 days ago 06:06 Model card: SQuADDS package timings on GH200 and x86, cold-start note 04:26 Add PlanarCapacitance-flagship checkpoints, sha256 list and model card