datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
spiral-bench
SPIRAL-Bench v0
A small benchmark for testing whether the wording of a retrieval query changes the
balance of the evidence a retriever returns.
Built for the Ouroboros project, which studies self-confirming retrieval loops in agentic RAG.
The question this dataset exists to answer
In agentic RAG, the system writes its own follow-up search queries, and it writes them using
what it currently believes. A retriever ranks documents by how closely they match the wording… See the full description on the dataset page: https://huggingface.co/datasets/vigneshwar234/spiral-bench.spectrum-bio-reactor-tape
Spectrum Bio-Reactor Tape
SHA-256-chained telemetry from one aerobic batch fermentation. Each line is one sealed state of a deterministic integration. Chain integrity is checked by recomputing every digest from the genesis frame to the tip.
Rows
721
Format
JSONL, one sealed frame per line
Integrator
Classical RK4, 100 substeps per hour
Tape cadence
0.1 h
Duration
0 h to 72 h
Vessel
1 m³, aspect ratio H/T = 2, 280 rpm
File
bio_reactor_tape.jsonl… See the full description on the dataset page: https://huggingface.co/datasets/spiderpilot89/spectrum-bio-reactor-tape.spectrum-materials-load-tape
Spectrum Materials Load Tape
SHA-256-chained telemetry from a Ti-6Al-4V uniaxial tension path. Each line is one sealed state of a deterministic integration. Chain integrity is checked by recomputing every digest from the genesis frame to the tip.
Rows
1,502
Format
JSONL, one sealed frame per line
Integrator
Prescribed-strain stepping at 1000 Hz (dt = 0.001 s)
Tape cadence
0.1 s, plus yield onset and fracture
Duration
0 s to 150.0 s (fracture)
File… See the full description on the dataset page: https://huggingface.co/datasets/spiderpilot89/spectrum-materials-load-tape.spectrum-orbital-reentry-tape
Spectrum Orbital Reentry Tape
SHA-256-chained telemetry from a Stardust-class atmospheric reentry. Each line is one sealed state of a deterministic integration. Chain integrity is checked by recomputing every digest from the genesis frame to the tip.
Rows
2,466
Format
JSONL, one sealed frame per line
Integrator
Explicit Euler, 1000 Hz (dt = 0.001 s)
Tape cadence
0.1 s of simulation time, plus the terminal step
Duration
0 s to 246.45 s
File… See the full description on the dataset page: https://huggingface.co/datasets/spiderpilot89/spectrum-orbital-reentry-tape.DavidAU__L3.1-Dark-Planet-SpinFire-Uncensored-8B-details
Dataset Card for Evaluation run of DavidAU/L3.1-Dark-Planet-SpinFire-Uncensored-8B
Dataset automatically created during the evaluation run of model DavidAU/L3.1-Dark-Planet-SpinFire-Uncensored-8B
The dataset is composed of 38 configuration(s), each one corresponding to one of the evaluated task.
The dataset has been created from 1 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The "train" split is… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard/DavidAU__L3.1-Dark-Planet-SpinFire-Uncensored-8B-details.spider-classifier-training-data
Spider Classifier — Training Manifest
Public release of the training manifest used to fine-tune the
Spiders of New Hampshire species
classifier.
This manifest enumerates every photo used to train, validate, and test the
model. Each row links back to the original observation and photo on
iNaturalist, preserving full attribution and
license metadata.
Source
Model run: 20260528_104624_licensed_dinov2_l_14_reg4_518
Generated: 2026-05-29T02:17:00.691986+00:00… See the full description on the dataset page: https://huggingface.co/datasets/bwirth/spider-classifier-training-data.DavieLion__Llama-3.2-1B-SPIN-iter0-details
Dataset Card for Evaluation run of DavieLion/Llama-3.2-1B-SPIN-iter0
Dataset automatically created during the evaluation run of model DavieLion/Llama-3.2-1B-SPIN-iter0
The dataset is composed of 38 configuration(s), each one corresponding to one of the evaluated task.
The dataset has been created from 2 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The "train" split is always pointing to the latest… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard/DavieLion__Llama-3.2-1B-SPIN-iter0-details.DavieLion__Llama-3.2-1B-SPIN-iter2-details
Dataset Card for Evaluation run of DavieLion/Llama-3.2-1B-SPIN-iter2
Dataset automatically created during the evaluation run of model DavieLion/Llama-3.2-1B-SPIN-iter2
The dataset is composed of 38 configuration(s), each one corresponding to one of the evaluated task.
The dataset has been created from 1 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The "train" split is always pointing to the latest… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard/DavieLion__Llama-3.2-1B-SPIN-iter2-details.DavieLion__Llama-3.2-1B-SPIN-iter3-details
Dataset Card for Evaluation run of DavieLion/Llama-3.2-1B-SPIN-iter3
Dataset automatically created during the evaluation run of model DavieLion/Llama-3.2-1B-SPIN-iter3
The dataset is composed of 38 configuration(s), each one corresponding to one of the evaluated task.
The dataset has been created from 3 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The "train" split is always pointing to the latest… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard/DavieLion__Llama-3.2-1B-SPIN-iter3-details.DavieLion__Llama-3.2-1B-SPIN-iter1-details
Dataset Card for Evaluation run of DavieLion/Llama-3.2-1B-SPIN-iter1
Dataset automatically created during the evaluation run of model DavieLion/Llama-3.2-1B-SPIN-iter1
The dataset is composed of 38 configuration(s), each one corresponding to one of the evaluated task.
The dataset has been created from 1 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The "train" split is always pointing to the latest… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard/DavieLion__Llama-3.2-1B-SPIN-iter1-details.