experiment-results
sit-experiment-results-2026-04-16
SiT Experiment Results
This dataset repo contains experiment outputs generated from the SiT-XL/2 model under the locally adjusted protocol in gpt_experiment_instructions.md.
Protocol Summary
Main dataset size: 20 images
Control dataset size: 10 images
Main/control images were exported from timm/mini-imagenet
Model: SiT-XL/2
VAE: stabilityai/sd-vae-ft-ema
Included Results
task0_outputs/: Prompt 0 / Task 0 artifacts
task1_outputs_20/: basic statistics… See the full description on the dataset page: https://huggingface.co/datasets/LamTNguyen/sit-experiment-results-2026-04-16.dementor-complete-experiment-results
Dementor complete experiment results
Audited outputs for the configuration-defined Dementor completion campaign.
Audited scope
Behavioral imitation adapters: 1,104 total (528 SFT, 528 DPO, 48 self-SFT controls).
Behavioral-fidelity evaluation: 1,104 adapters on 200 held-out prompts, with embedding and
primary LLM-judge scores, plus 48 target-reference response sets.
Activation steering: 29 models, seven benchmarks, and two operators (original and fpall),
totaling… See the full description on the dataset page: https://huggingface.co/datasets/dementor-research/dementor-complete-experiment-results.bigcodereward-experiment-resultsPaper: https://arxiv.org/abs/2510.08697
data-agent-experiment-results
Data Agent: public artifact index
Qwen3.5-2B training with Harbor multi-harness, native OpenCode, Harbor OpenCode-only and SETA. This is a frozen report release from September 16, 2026. The live Trackio dashboard continues updating.
Latest update
September 16, 19:49 UTC: live eval progress and failure diagnosis. Includes recovery jobs, transport failures, and the measured OpenCode output-truncation regression.
Earlier evaluation plot and GPU allocation update.… See the full description on the dataset page: https://huggingface.co/datasets/FineEnvs/data-agent-experiment-results.ttt-experiment-results
Experimental results archive
Transfer complete: 85 archives and the results-shard-index.json are available; all archive byte sizes were verified on 2026-09-21. Archives are uploaded sequentially and verified for remote byte size. The final results-shard-index.json will map original relative paths to tar files after the complete transfer. Missing index means the transfer is not yet declared complete.
Model checkpoints: https://huggingface.co/yyoraa/robocasa-ttt-checkpoints
Code… See the full description on the dataset page: https://huggingface.co/datasets/yyoraa/ttt-experiment-results.telescope_experiment_results