datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
ouroboros-osworld-verified-opus5
Ouroboros on OSWorld-Verified: 90.69%, the highest result reported to date
Status: Self-reported result over all 361 tasks. The official per-task
scores, prompts, manifests and feasibility records are public here, together
with every acting task record that the run produced.
Start here
Result
90.69% (327.39 / 361)
Model
anthropic/claude-opus-5
Method
Screenshot only, one rollout, 100 policy turns
Exact evidence
f52ebf2 and evidence.json… See the full description on the dataset page: https://huggingface.co/datasets/razzant/ouroboros-osworld-verified-opus5.ouroboros-osworld-verified-sonnet46
Ouroboros on OSWorld-Verified: best published result on Claude Sonnet 4.6
Status: Self-reported result over all 361 task packages. Prompts,
manifests, outcomes and feasibility records are public for every task. The
official evaluator produced 360 score files; one unscored task is counted as zero.
Start here
Result
83.27% (300.59 / 361)
Model
anthropic/claude-sonnet-4.6
Method
Screenshot only, one rollout, 100 policy turns
Exact evidence… See the full description on the dataset page: https://huggingface.co/datasets/razzant/ouroboros-osworld-verified-sonnet46.ouroboros-clbench-traces
Ouroboros × CL-Bench: full execution traces
Status: Self-reported result with an open upstream submission. The complete
runner traces, runtime logs, evolving memory and score inputs are public here.
Start here
Result
0.2301 normalized reward, rank 1
Model
anthropic/claude-sonnet-4.6
Upstream
Submission PR #10
Exact evidence
85958a2 and evidence.json
Read the technical report,
Browse all Ouroboros benchmark runs,
open the no-key explorer… See the full description on the dataset page: https://huggingface.co/datasets/razzant/ouroboros-clbench-traces.llama-9b-bulk-npzOur1-2b-Datasetouroboros-pasterski-research-program
Ouroboros Pasterski Research Program - PAUSED
A proof-carrying research campaign in which the Ouroboros AI System turned public scholarship into 49 exact, independently replayable computational result packages. The campaign ran for 18 h 11 min before the operator paused it at a stable boundary; PAUSED means the research program remains open, not that the released results are provisional.
Independent project; no affiliation or endorsement. This work is not affiliated with… See the full description on the dataset page: https://huggingface.co/datasets/cjc0013/ouroboros-pasterski-research-program.ouroboros-wtbh-z2-reconstruction-panel
Ouroboros WTBH Z2 Reconstruction Validation Panel
This release is a compact, reproducible validation panel for reconstructing spinful time-reversal
symmetry from Wannier tight-binding Hamiltonians and computing the full three-dimensional
Z2 = (nu0;nu1 nu2 nu3) index. It was produced by Ouroboros, an AI research system.
Result
Material
JARVIS ID
Literature context
Reconstructed
Wilson-loop orientations
Gates
SnS
JVASP-7855
(0;000)
(0;000)
12/12
pass… See the full description on the dataset page: https://huggingface.co/datasets/cjc0013/ouroboros-wtbh-z2-reconstruction-panel.ouroboros-trace-help
Trace Help — does an execution trace help a model answer questions about a run?
In one minute. Twelve small programs in six languages (Python, JavaScript, C,
C++, Go, Elixir). Each was run once with a fixed command. Five questions per
program ask what actually happened on that one run: how many times a function
was called, what a particular call returned, what it was called with, whether a
function ran at all, which function raised. Sixty questions in total.
Every record carries… See the full description on the dataset page: https://huggingface.co/datasets/digitable-lol/ouroboros-trace-help.ouroboros-kernel-corpus
OUROBOROS Verified Kernel Corpus
A set of fused Triton GPU kernels, written almost entirely by open-weight models inside the
OUROBOROS loop and then checked by a verifier the models can't fool. Every kernel here compiled,
matched PyTorch on an adversarial correctness sweep, and beat torch.compile max-autotune
before it was allowed in. No human-labeled data. The only teacher signal is the verifier's
verdict.
This is the training and evidence data behind:
the Kernel Mint Space… See the full description on the dataset page: https://huggingface.co/datasets/YMRohit/ouroboros-kernel-corpus.aeon-ouroboros_recursive-survivability-tracesÆon-Ouroboros: Recursive Survivability Traces
Summary
This dataset contains non-dialogic survivability cycles documenting how a system responds to perturbation under explicit constraints.
The focus is recovery, coherence, and ethical load management, not output quality or task performance.
These records are intended to support research into recursive systems, constraint-first intelligence, and survivability under stress.
What This Dataset Is
A collection of cycle-level traces, not samples… See the full description on the dataset page: https://huggingface.co/datasets/basheuvel/aeon-ouroboros_recursive-survivability-traces.