English
time-series
benchmark
conditional-generation

ConTSG-Bench Checkpoints (Public Subset)

This repository hosts the official public checkpoint release for ConTSG-Bench.

Release Scope

The current public release includes checkpoints and reproducibility assets for:

  • synth-u
  • synth-m

Checkpoints for other benchmark datasets are not publicly released at this stage.

Repository Structure

.
├── experiments/
│   └── <model>/
│       ├── synth-u/
│       │   └── seed{0,1,2}/
│       │       ├── checkpoints/
│       │       │   └── finetune/
│       │       │       └── best.ckpt
│       │       ├── config.template.yaml
│       │       ├── results/
│       │       │   └── expected_seed_metrics.json
│       │       └── summary.json
│       └── synth-m/
│           └── seed{0,1,2}/
│               ├── checkpoints/
│               │   └── finetune/
│               │       └── best.ckpt
│               ├── config.template.yaml
│               ├── results/
│               │   └── expected_seed_metrics.json
│               └── summary.json
├── resources/
│   └── cttp/
│       ├── synth-u/
│       │   ├── clip_model_best.pth
│       │   └── model_configs.yaml
│       └── synth-m/
│           ├── clip_model_best.pth
│           └── model_configs.yaml
├── expected/
│   ├── full_results_synth.csv
│   ├── results_mean_std_synth.csv
│   └── seed_metrics_nested.json
└── manifests/
    └── release_manifest_public.json

Reproducibility Notes

  • This release is designed to support leaderboard reproducibility for the public subset.
  • Some config templates contain placeholders (for example ${LONGCLIP_ROOT}) that should be set to your local dependency path before running.

Related Links

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Dataset used to train mldi-lab/ConTSG-Bench-Checkpoints

Free AI Image Generator No sign-up. Instant results. Open Now