Error code:   ConfigNamesError
Exception:    TypeError
Message:      list_() takes at least 1 positional argument (0 given)
Traceback:    Traceback (most recent call last):
                File "/src/services/worker/src/worker/job_runners/dataset/config_names.py", line 66, in compute_config_names_response
                  config_names = get_dataset_config_names(
                                 ^^^^^^^^^^^^^^^^^^^^^^^^^
                File "/usr/local/lib/python3.12/site-packages/datasets/inspect.py", line 161, in get_dataset_config_names
                  dataset_module = dataset_module_factory(
                                   ^^^^^^^^^^^^^^^^^^^^^^^
                File "/usr/local/lib/python3.12/site-packages/datasets/load.py", line 1031, in dataset_module_factory
                  raise e1 from None
                File "/usr/local/lib/python3.12/site-packages/datasets/load.py", line 1004, in dataset_module_factory
                  ).get_module()
                    ^^^^^^^^^^^^
                File "/usr/local/lib/python3.12/site-packages/datasets/load.py", line 605, in get_module
                  dataset_infos = DatasetInfosDict.from_dataset_card_data(dataset_card_data)
                                  ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
                File "/usr/local/lib/python3.12/site-packages/datasets/info.py", line 386, in from_dataset_card_data
                  dataset_info = DatasetInfo._from_yaml_dict(dataset_card_data["dataset_info"])
                                 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
                File "/usr/local/lib/python3.12/site-packages/datasets/info.py", line 317, in _from_yaml_dict
                  yaml_data["features"] = Features._from_yaml_list(yaml_data["features"])
                                          ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
                File "/usr/local/lib/python3.12/site-packages/datasets/features/features.py", line 2031, in _from_yaml_list
                  return cls.from_dict(from_yaml_inner(yaml_data))
                                       ^^^^^^^^^^^^^^^^^^^^^^^^^^
                File "/usr/local/lib/python3.12/site-packages/datasets/features/features.py", line 2027, in from_yaml_inner
                  return {name: from_yaml_inner(_feature) for name, _feature in zip(names, obj)}
                                ^^^^^^^^^^^^^^^^^^^^^^^^^
                File "/usr/local/lib/python3.12/site-packages/datasets/features/features.py", line 2016, in from_yaml_inner
                  Value(obj["dtype"])
                File "<string>", line 5, in __init__
                File "/usr/local/lib/python3.12/site-packages/datasets/features/features.py", line 540, in __post_init__
                  self.pa_type = string_to_arrow(self.dtype)
                                 ^^^^^^^^^^^^^^^^^^^^^^^^^^^
                File "/usr/local/lib/python3.12/site-packages/datasets/features/features.py", line 150, in string_to_arrow
                  return pa.__dict__[datasets_dtype + "_"]()
                         ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
                File "pyarrow/types.pxi", line 4942, in pyarrow.lib.list_
              TypeError: list_() takes at least 1 positional argument (0 given)

Need help to make the dataset viewer work? Make sure to review how to configure the dataset viewer, and open a discussion for direct support.

WithinUsAI/All_Known_Species_Index_25k — Master Scholars Academics (25k)

A real-species index dataset sampled from NCBI Taxonomy (taxdump) at the species rank, formatted for Tiny-Recursive-Model-friendly fine-tuning.

What this is (and is not)

This dataset contains 25,000 real species records sampled from the NCBI taxonomy graph (rank=species).
It does not enumerate every described species name (the full list is far larger and updated continuously).
If you want “all known species” as a full index, generate it from the same official NCBI taxdump or other backbones (Catalogue of Life, GBIF, WoRMS). This repo provides the schema and can be scaled.

Task

Each row asks the model to return a taxonomy classification JSON for the given taxid + scientific name, with keys among:

superkingdom, kingdom, phylum, class, order, family, genus, species

Output contract: JSON only.

Source

Official data backbone:

NCBI Taxonomy FTP: taxdump.tar.gz
https://ftp.ncbi.nlm.nih.gov/pub/taxonomy/taxdump.tar.gz

Accessed: 2026-01-04T03:02:03Z

Schema

prompt.messages[]: system + user
response: JSON string containing taxid, scientific_name, and classification
meta: ids, task, ranks, tags
fact_sources: official anchor
artifacts: output contract and token hints

Example

{
  "prompt": {
    "messages": [
      {"role": "system", "content": "You are WithinUsAI Master Scholars Taxonomy Indexer. Output must be valid JSON only, no extra text."},
      {"role": "user", "content": "NCBI Taxonomy species indexing task..."}
    ]
  },
  "response": "{\"taxid\": 9606, \"scientific_name\": \"Homo sapiens\", \"classification\": {\"superkingdom\": \"Eukaryota\", \"kingdom\": \"Metazoa\", \"phylum\": \"Chordata\", \"class\": \"Mammalia\", \"order\": \"Primates\", \"family\": \"Hominidae\", \"genus\": \"Homo\", \"species\": \"Homo sapiens\"}}",
  "meta": {
    "id": "WUA_ALL_SPECIES_25K_000001",
    "domain": "all_known_species_index",
    "subdomain": "ncbi_taxonomy::species",
    "task": "taxonomy_indexing",
    "truth_mode": "verifiable_from_ncbi_taxdump",
    "wrapper": "json_only",
    "created_utc": "2026-01-04T03:02:03Z",
    "license": "cc-by-4.0"
  }
}

Citation

If you use this dataset in research or releases, cite it as: Within Us AI — WithinUsAI/All_Known_Species_Index_25k (NCBI Taxonomy Sample).

Downloads last month: 10