diff --git a/.github/workflows/test.yml b/.github/workflows/test.yml
index 9c4e232bc..dff88e440 100644
--- a/.github/workflows/test.yml
+++ b/.github/workflows/test.yml
@@ -295,6 +295,10 @@ jobs:
           coverage run -a --source=src/lenskit -m lenskit data fetch -D data/az18 --amazon --edition 2018 Video_Games
           coverage run -a --source=src/lenskit -m lenskit data fetch -D data/az14 --amazon --edition 2014 Video_Games
           coverage run -a --source=src/lenskit -m lenskit data fetch --ms-web
+          if [[ ! -f data/australian_users_items.json.gz ]]; then
+            curl -fsL -o data/australian_users_items.json.gz.tmp https://mcauleylab.ucsd.edu/public_datasets/data/steam/australian_users_items.json.gz
+            mv data/australian_users_items.json.gz.tmp data/australian_users_items.json.gz
+          fi
 
       - name: Run Eval Tests
         run: |
@@ -302,7 +306,7 @@ jobs:
 
       - name: 🕺🏻 Test LensKit CLI
         run: |
-          mise run test-cli -- --coverage --cov-append tests/cli/test-tune.sh
+          mise run test-cli -- --coverage --cov-append
         shell: bash -e {0}
         env:
           LK_TUNE_JOBS: 2
diff --git a/Cargo.lock b/Cargo.lock
index 8c4b116d8..530b7ff82 100644
--- a/Cargo.lock
+++ b/Cargo.lock
@@ -644,6 +644,7 @@ dependencies = [
  "ntest",
  "numpy",
  "ordered-float",
+ "peg",
  "pyo3",
  "rand",
  "rand_pcg",
@@ -868,6 +869,33 @@ dependencies = [
  "num-traits",
 ]
 
+[[package]]
+name = "peg"
+version = "0.8.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "0aad070be5b63aa72103f2fcdd70a83adbd5e90112ce5b574171ff1c65501773"
+dependencies = [
+ "peg-macros",
+ "peg-runtime",
+]
+
+[[package]]
+name = "peg-macros"
+version = "0.8.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "ddd8ef6825cae95355031ae26a99b616a2a21f22ba2de0197c43dfb05acbe7ee"
+dependencies = [
+ "peg-runtime",
+ "proc-macro2",
+ "quote",
+]
+
+[[package]]
+name = "peg-runtime"
+version = "0.8.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "7011d97b484a5ebdc4b1fdb3b12d5e4bbbea56e9d22b688f2e79e04b65a7d8a6"
+
 [[package]]
 name = "pin-project-lite"
 version = "0.2.17"
diff --git a/Cargo.toml b/Cargo.toml
index 49a454844..cbe6d373a 100644
--- a/Cargo.toml
+++ b/Cargo.toml
@@ -28,6 +28,7 @@ rand_pcg = "^0.10"
 rustc-hash = "^2.1.1"
 sha1 = "^0.11"
 
+peg = "^0.8"
 serde = { version = "^1.0", features = ["derive"] }
 serde_json = "^1.0"
 
diff --git a/docs/releases/2026.rst b/docs/releases/2026.rst
index 339272157..8bd1ec1f9 100644
--- a/docs/releases/2026.rst
+++ b/docs/releases/2026.rst
@@ -17,6 +17,9 @@ rough corners polished off the interfaces, and hopefully fewer bugs.
 
 Third release in 2026, with more feature updates and bug fixes.
 
+- Added initial support for importing Steam user/item data
+  (:py:mod:`lenskit.data.sources.steam`, :pr:`1111`).
+
 .. _2026.2.1:
 
 2026.2.1
diff --git a/src/accel/data/mod.rs b/src/accel/data/mod.rs
index 11b46ec96..0957af7fb 100644
--- a/src/accel/data/mod.rs
+++ b/src/accel/data/mod.rs
@@ -20,6 +20,7 @@ mod cooc;
 mod coordinates;
 mod index;
 mod pairs;
+mod pyon;
 mod sampling;
 mod scatter;
 mod selection;
@@ -48,6 +49,7 @@ pub fn register_data(parent: &Bound<'_, PyModule>) -> PyResult<()> {
     data.add_function(wrap_pyfunction!(cooc::count_cooc, &data)?)?;
     data.add_function(wrap_pyfunction!(cooc::dense_cooc, &data)?)?;
     data.add_function(wrap_pyfunction!(hash_array, &data)?)?;
+    data.add_function(wrap_pyfunction!(pyon::pyon_loads, &data)?)?;
 
     Ok(())
 }
diff --git a/src/accel/data/pyon.rs b/src/accel/data/pyon.rs
new file mode 100644
index 000000000..aac90d086
--- /dev/null
+++ b/src/accel/data/pyon.rs
@@ -0,0 +1,146 @@
+// This file is part of LensKit.
+// Copyright (C) 2018-2023 Boise State University.
+// Copyright (C) 2023-2026 Drexel University.
+// Licensed under the MIT license, see LICENSE.md for details.
+// SPDX-License-Identifier: MIT
+
+//! Support for reading invalid JSON that is actually valid Python expression syntax.
+
+use std::borrow::Cow;
+
+use log::*;
+use pyo3::{
+    exceptions::PyValueError,
+    prelude::*,
+    types::{PyBool, PyDict, PyFloat, PyInt, PyList, PyNone, PyString},
+};
+
+use serde_json::{Number, Value};
+
+/// Parse a “pyson” object.
+#[pyfunction]
+pub fn pyon_loads<'py>(py: Python<'py>, text: &str) -> PyResult<Bound<'py, PyAny>> {
+    match pyon_parser::expr(text) {
+        Ok(ast) => {
+            let obj = realize_value(py, ast)?;
+            Ok(obj)
+        }
+        Err(e) => {
+            error!(
+                "parse error at {}:{}: found {}, expected {:}",
+                e.location.line,
+                e.location.column,
+                text.chars()
+                    .nth(e.location.offset)
+                    .map(|c| format!("“{}”", c))
+                    .unwrap_or("<EOF>".into()),
+                e.expected
+            );
+            Err(PyValueError::new_err(format!("parse error: {:}", e)))
+        }
+    }
+}
+
+peg::parser! {
+    grammar pyon_parser() for str {
+        rule _ = quiet!{[' ' | '\n' | '\t' | '\r' | '\n']*}
+
+        rule digit() = ['0'..='9']
+        rule digits() -> &'input str
+        = $(digit()+)
+
+        rule number() -> Value
+        = e:$("-"? digits() "." digits()) {Value::Number(Number::from_f64(e.parse::<f64>().unwrap()).unwrap())}
+        / e:$("-" digits()) {Value::Number(e.parse::<i64>().unwrap().into())}
+        / e:digits() {Value::Number(e.parse::<u64>().unwrap().into())}
+
+        rule boolean() -> Value
+        = ("true" / "True") { Value::Bool(true)}
+        / ("false" / "False") { Value::Bool(false)}
+
+        rule null() -> Value
+        = ("null" / "None") { Value::Null}
+
+        rule _string() -> String
+        = "b"? "'" parts:((_str_part_sq() / echar())*) "'" {parts.into_iter().collect()}
+        / "b"? "\"" parts:((_str_part_dq() / echar())*) "\"" {parts.into_iter().collect()}
+
+        rule _str_part_sq() -> Cow<'input, str>
+        = s:$([^'\'' | '\\']+) {Cow::Borrowed(s)}
+
+        rule _str_part_dq() -> Cow<'input, str>
+        = s:$([^'"' | '\\']+) {Cow::Borrowed(s)}
+
+        rule string() -> Value
+        = s:_string() {Value::String(s)}
+
+        rule echar() -> Cow<'input, str>
+        = "\\t" {"\t".into()}
+        / "\\r" {"\r".into()}
+        / "\\n" {"\n".into()}
+        / "\\u" x:$(['a'..='f'| 'A'..='F'| '0'..='9']*<4,4>) {
+            let s = format!("0x{}", x);
+            let c = u32::from_str_radix(x, 16).expect("invalid hex");
+            String::from_iter([char::from_u32(c).expect("invalid cahracter")]).into()
+        }
+        / "\\U" x:$(['a'..='f'| 'A'..='F'| '0'..='9']*<8,8>) {
+            let s = format!("0x{}", x);
+            let c = u32::from_str_radix(x, 16).expect("invalid hex");
+            String::from_iter([char::from_u32(c).expect("invalid cahracter")]).into()
+        }
+        / "\\" c:$([_]) {c.into()}
+
+        rule list() -> Value
+        = "[" e:(expr() ** ",") _ ","? "]" {Value::Array(e)}
+
+        rule object() -> Value
+        = "{" entries:(object_entry() ** ",") _ ","? "}" {Value::Object(entries.into_iter().collect())}
+
+        rule object_entry() -> (String, Value)
+        = _ k:_string() _ ":" v:expr() {(k, v)}
+
+        rule _expr() -> Value
+        = null()
+        / boolean()
+        / number()
+        / string()
+        / list()
+        / object()
+
+        pub rule expr() -> Value = _ e:_expr() _ {e}
+}
+}
+
+fn realize_value<'py>(py: Python<'py>, ast: Value) -> PyResult<Bound<'py, PyAny>> {
+    match ast {
+        Value::Null => Ok(PyNone::get(py).to_owned().into_any()),
+        Value::Bool(val) => Ok(PyBool::new(py, val).to_owned().into_any()),
+        Value::Number(n) => {
+            if let Some(i) = n.as_i64() {
+                Ok(PyInt::new(py, i).into_any())
+            } else if let Some(x) = n.as_f64() {
+                Ok(PyFloat::new(py, x).into_any())
+            } else {
+                Err(PyValueError::new_err(format!("invalid number {:?}", n)))
+            }
+        }
+        Value::String(s) => Ok(PyString::new(py, &s).into_any()),
+        Value::Array(list) => {
+            let out = PyList::empty(py);
+            for elt in list {
+                out.append(realize_value(py, elt)?)?;
+            }
+
+            Ok(out.into_any())
+        }
+        Value::Object(dict) => {
+            let out = PyDict::new(py);
+
+            for (k, v) in dict {
+                out.set_item(k, realize_value(py, v)?)?;
+            }
+
+            Ok(out.into_any())
+        }
+    }
+}
diff --git a/src/lenskit/_accel/data.pyi b/src/lenskit/_accel/data.pyi
index 8ff274290..a2a2a309f 100644
--- a/src/lenskit/_accel/data.pyi
+++ b/src/lenskit/_accel/data.pyi
@@ -2,6 +2,7 @@ from __future__ import annotations
 
 import numpy as np
 import pyarrow as pa
+from pydantic import JsonValue
 from typing_extensions import TypeVar
 
 from lenskit.data.matrix import SparseRowArray
@@ -52,6 +53,7 @@ def sample_negatives(
     seed: int,
 ) -> np.ndarray[tuple[int, int], np.dtype[np.int32]]: ...
 def hash_array(arr: pa.Array, /) -> str: ...
+def pyon_loads(data: str) -> JsonValue: ...
 
 class IDIndex:
     """
diff --git a/src/lenskit/cli/data/convert.py b/src/lenskit/cli/data/convert.py
index f46d09b84..c6648967d 100644
--- a/src/lenskit/cli/data/convert.py
+++ b/src/lenskit/cli/data/convert.py
@@ -8,8 +8,6 @@
 
 import click
 
-from lenskit.data import load_amazon_ratings, load_movielens
-from lenskit.data.msweb import load_ms_web
 from lenskit.logging import get_logger
 
 _log = get_logger(__name__)
@@ -19,6 +17,7 @@
 @click.option("--movielens", "format", flag_value="movielens", help="Convert MovieLens data.")
 @click.option("--amazon", "format", flag_value="amazon", help="Convert Amazon rating data.")
 @click.option("--ms-web", "format", flag_value="ms-web", help="Convert MSWeb visit logs.")
+@click.option("--steam", "format", flag_value="steam", help="Convert Steam interaction data")
 @click.option(
     "--item-lists", is_flag=True, help="Convert to an ItemListCollection instead of Dataset."
 )
@@ -40,14 +39,25 @@ def convert(format: str | None, src: list[Path], dst: Path, item_lists: bool = F
             _log.error("no data format specified")
             raise click.UsageError("no data format specified")
         case "movielens":
+            from lenskit.data.sources.movielens import load_movielens
+
             log.info("loading MovieLens data")
             if len(src) != 1:
                 log.error("received %d source paths, MovieLens only takes one", len(src))
+
             data = load_movielens(src[0])
         case "amazon":
+            from lenskit.data.sources.amazon import load_amazon_ratings
+
             data = load_amazon_ratings(*src)
         case "ms-web":
+            from lenskit.data.sources.msweb import load_ms_web
+
             data = load_ms_web(src[0])
+        case "steam":
+            from lenskit.data.sources.steam import load_steam
+
+            data = load_steam(src[0])
         case _:
             raise ValueError(f"unknown data format {format}")
 
diff --git a/src/lenskit/cli/data/describe.py b/src/lenskit/cli/data/describe.py
index 8b4f17b48..176a52d5f 100644
--- a/src/lenskit/cli/data/describe.py
+++ b/src/lenskit/cli/data/describe.py
@@ -12,7 +12,7 @@
 from rich.console import Console
 from rich.markdown import Markdown
 
-from lenskit.data import Dataset, load_amazon_ratings, load_movielens
+from lenskit.data import Dataset
 from lenskit.data._summary import save_stats
 from lenskit.logging import get_logger
 
@@ -20,27 +20,40 @@
 
 
 @click.command("describe")
-@click.option("--movielens", "format", flag_value="movielens", help="describe MovieLens data")
-@click.option("--amazon", "format", flag_value="amazon", help="describe Amazon rating data")
+@click.option("--movielens", "format", flag_value="movielens", help="Describe MovieLens data.")
+@click.option("--amazon", "format", flag_value="amazon", help="Describe Amazon rating data.")
+@click.option("--steam", "format", flag_value="steam", help="Describe Steam interaction data.")
 @click.option("--markdown", is_flag=True, help="output raw Markdown")
-@click.argument("path", type=Path)
-def describe(format: str | None, markdown: bool, path: Path):
+@click.argument("path", type=Path, nargs=-1, required=True)
+def describe(format: str | None, markdown: bool, path: list[Path]):
     """
     Describe a data set.
     """
 
-    log = _log.bind(path=str(path))
+    if len(path) == 1:
+        log = _log.bind(path=str(path[0]))
+    else:
+        log = _log.bind(path=[str(p) for p in path])
 
     match format:
         case None:
             log.info("loading LensKit native data")
-            data = Dataset.load(path)
+            data = Dataset.load(path[0])
         case "movielens":
+            from lenskit.data.sources.movielens import load_movielens
+
             log.info("loading MovieLens data")
-            data = load_movielens(path)
+            data = load_movielens(path[0])
         case "amazon":
+            from lenskit.data.sources.amazon import load_amazon_ratings
+
             log.info("loading Amazon data")
-            data = load_amazon_ratings(path)
+            data = load_amazon_ratings(path[0])
+        case "steam":
+            from lenskit.data.sources.steam import load_steam
+
+            log.info("loading Steam data")
+            data = load_steam(*path)
         case _:
             raise ValueError(f"unknown data format {format}")
 
diff --git a/src/lenskit/data/_builder.py b/src/lenskit/data/_builder.py
index 90f48c220..b0728200e 100644
--- a/src/lenskit/data/_builder.py
+++ b/src/lenskit/data/_builder.py
@@ -828,8 +828,7 @@ def add_scalar_attribute(
             raise DataError(f"no entities of class {cls}")
 
         nums = self._resolve_entity_ids(cls, entities, e_tbl)
-        if not np.all(nums.is_valid()):  # pragma: nocover
-            n_bad = nums.is_valid().sum().as_py()
+        if n_bad := nums.null_count:  # pragma: nocover
             raise DataError(f"{n_bad} unknown entity IDs")
 
         val_array: pa.Array = pa.array(values)  # type: ignore
@@ -915,8 +914,7 @@ def add_list_attribute(
         if e_tbl is None:  # pragma: nocover
             raise DataError(f"no entities of class {cls}")
         nums = self._resolve_entity_ids(cls, entities, e_tbl)
-        if not np.all(nums.is_valid()):  # pragma: nocover
-            n_bad = nums.is_valid().sum().as_py()
+        if n_bad := nums.null_count:  # pragma: nocover
             raise DataError(f"{n_bad} unknown entity IDs")
 
         val_array: pa.Array = pa.array(values)  # type: ignore
@@ -980,8 +978,7 @@ def add_vector_attribute(
         if e_tbl is None:  # pragma: nocover
             raise DataError(f"no entities of class {cls}")
         nums = self._resolve_entity_ids(cls, entities, e_tbl)
-        if not np.all(nums.is_valid()):  # pragma: nocover
-            n_bad = nums.is_valid().sum().as_py()
+        if n_bad := nums.null_count:  # pragma: nocover
             raise DataError(f"{n_bad} unknown entity IDs")
 
         tbl_valid = np.zeros(e_tbl.num_rows, dtype=np.bool_)
diff --git a/src/lenskit/data/msweb.py b/src/lenskit/data/msweb.py
index 060634cc2..39ef6990b 100644
--- a/src/lenskit/data/msweb.py
+++ b/src/lenskit/data/msweb.py
@@ -5,102 +5,20 @@
 # SPDX-License-Identifier: MIT
 
 """
-Support for the MSWeb datasets.
-"""
-
-import csv
-from pathlib import Path
-from typing import Literal, overload
-
-import pyarrow as pa
-from xopen import xopen
-
-from lenskit.logging import get_logger
-
-from ._builder import DatasetBuilder
-from ._collection import ItemListCollection
-from ._dataset import Dataset
+Legacy location of the MS Web import functions.
 
-_log = get_logger(__name__)
+.. deprecated:: 2026.3
 
+    Import from :mod:`lenskit.data` or :mod:`lenskit.data.sources.msweb` instead.
+"""
 
-@overload
-def load_ms_web(path: Path, format: Literal["dataset"] = "dataset") -> Dataset: ...
-@overload
-def load_ms_web(path: Path, format: Literal["collection"]) -> ItemListCollection: ...
-@overload
-def load_ms_web(
-    path: Path, format: Literal["dataset", "collection"] = "dataset"
-) -> Dataset | ItemListCollection: ...
-def load_ms_web(
-    path: Path, format: Literal["dataset", "collection"] = "dataset"
-) -> Dataset | ItemListCollection:
-    """
-    Load the MSWeb data set.
-
-    The Microsoft Anonymous Web data set was published by
-    :cite:t:`breeseEmpiricalAnalysisPredictive1998`, and is available from the
-    `UCI repository`_.
-
-    This function can load the data either as a :class:`Dataset` (useful for
-    training) or as an :class:`ItemListCollection` (for evaluation).
-
-    .. _UCI repository: https://kdd.ics.uci.edu/databases/msweb/msweb.html
-
-    Args:
-        path:
-            The path to the data file (gzip-compressed).
-        format:
-            The type of object to load the data set into.
-    Returns:
-        The loaded MSWeb data.
-    """
-    ds = _load_ms_dataset(path)
-    match format:
-        case "collection":
-            return ds.interactions("visit").item_lists()
-        case "dataset":
-            return ds
-        case _:  # pragma: nocover
-            raise ValueError(f"invalid format: {format}")
+import warnings
 
+from .sources.msweb import load_ms_web
 
-def _load_ms_dataset(path: Path) -> Dataset:
-    item_ids = []
-    item_titles = []
-    item_urls = []
-    session_votes = []
-    cur_session = None
-    _log.info("opening MSWeb file", path=str(path))
-    with xopen(path, "rt") as data:
-        reader = csv.reader(data)
-        for row in reader:
-            code = row[0]
-            match code:
-                case "A":
-                    _c, vid, _n, title, url = row
-                    item_ids.append(int(vid))
-                    item_titles.append(title)
-                    item_urls.append(url)
-                case "C":
-                    _c, _sname, sid = row
-                    cur_session = int(sid)
-                case "V":
-                    _c, vid, _n = row
-                    session_votes.append({"session_id": cur_session, "item_id": int(vid)})
+__all__ = ["load_ms_web"]
 
-    dsb = DatasetBuilder("ms-web")
-    dsb.add_entities("item", item_ids)
-    dsb.add_scalar_attribute("item", "title", item_ids, item_titles)
-    dsb.add_scalar_attribute("item", "url", item_ids, item_urls)
-    dsb.add_entity_class("session")
-    votes = pa.Table.from_pylist(session_votes)
-    dsb.add_interactions(
-        "visit",
-        votes,
-        entities=["session", "item"],
-        missing="insert",
-        default=True,
-        allow_repeats=False,
-    )
-    return dsb.build()
+warnings.warn(
+    "lenskit.data.msweb deprecated, use lenskit.data or lenskit.data.sources",
+    DeprecationWarning,
+)
diff --git a/src/lenskit/data/sources/msweb.py b/src/lenskit/data/sources/msweb.py
new file mode 100644
index 000000000..e8408b921
--- /dev/null
+++ b/src/lenskit/data/sources/msweb.py
@@ -0,0 +1,106 @@
+# This file is part of LensKit.
+# Copyright (C) 2018-2023 Boise State University.
+# Copyright (C) 2023-2026 Drexel University.
+# Licensed under the MIT license, see LICENSE.md for details.
+# SPDX-License-Identifier: MIT
+
+"""
+Support for the MSWeb datasets.
+"""
+
+import csv
+from pathlib import Path
+from typing import Literal, overload
+
+import pyarrow as pa
+from xopen import xopen
+
+from lenskit.logging import get_logger
+
+from .._builder import DatasetBuilder
+from .._collection import ItemListCollection
+from .._dataset import Dataset
+
+_log = get_logger(__name__)
+
+
+@overload
+def load_ms_web(path: Path, format: Literal["dataset"] = "dataset") -> Dataset: ...
+@overload
+def load_ms_web(path: Path, format: Literal["collection"]) -> ItemListCollection: ...
+@overload
+def load_ms_web(
+    path: Path, format: Literal["dataset", "collection"] = "dataset"
+) -> Dataset | ItemListCollection: ...
+def load_ms_web(
+    path: Path, format: Literal["dataset", "collection"] = "dataset"
+) -> Dataset | ItemListCollection:
+    """
+    Load the MSWeb data set.
+
+    The Microsoft Anonymous Web data set was published by
+    :cite:t:`breeseEmpiricalAnalysisPredictive1998`, and is available from the
+    `UCI repository`_.
+
+    This function can load the data either as a :class:`Dataset` (useful for
+    training) or as an :class:`ItemListCollection` (for evaluation).
+
+    .. _UCI repository: https://kdd.ics.uci.edu/databases/msweb/msweb.html
+
+    Args:
+        path:
+            The path to the data file (gzip-compressed).
+        format:
+            The type of object to load the data set into.
+    Returns:
+        The loaded MSWeb data.
+    """
+    ds = _load_ms_dataset(path)
+    match format:
+        case "collection":
+            return ds.interactions("visit").item_lists()
+        case "dataset":
+            return ds
+        case _:  # pragma: nocover
+            raise ValueError(f"invalid format: {format}")
+
+
+def _load_ms_dataset(path: Path) -> Dataset:
+    item_ids = []
+    item_titles = []
+    item_urls = []
+    session_votes = []
+    cur_session = None
+    _log.info("opening MSWeb file", path=str(path))
+    with xopen(path, "rt") as data:
+        reader = csv.reader(data)
+        for row in reader:
+            code = row[0]
+            match code:
+                case "A":
+                    _c, vid, _n, title, url = row
+                    item_ids.append(int(vid))
+                    item_titles.append(title)
+                    item_urls.append(url)
+                case "C":
+                    _c, _sname, sid = row
+                    cur_session = int(sid)
+                case "V":
+                    _c, vid, _n = row
+                    session_votes.append({"session_id": cur_session, "item_id": int(vid)})
+
+    dsb = DatasetBuilder("ms-web")
+    dsb.add_entities("item", item_ids)
+    dsb.add_scalar_attribute("item", "title", item_ids, item_titles)
+    dsb.add_scalar_attribute("item", "url", item_ids, item_urls)
+    dsb.add_entity_class("session")
+    votes = pa.Table.from_pylist(session_votes)
+    dsb.add_interactions(
+        "visit",
+        votes,
+        entities=["session", "item"],
+        missing="insert",
+        default=True,
+        allow_repeats=False,
+    )
+    return dsb.build()
diff --git a/src/lenskit/data/sources/steam.py b/src/lenskit/data/sources/steam.py
new file mode 100644
index 000000000..aa034954b
--- /dev/null
+++ b/src/lenskit/data/sources/steam.py
@@ -0,0 +1,185 @@
+# This file is part of LensKit.
+# Copyright (C) 2018-2023 Boise State University.
+# Copyright (C) 2023-2026 Drexel University.
+# Licensed under the MIT license, see LICENSE.md for details.
+# SPDX-License-Identifier: MIT
+
+"""
+Support for importing `Steam data`_.
+
+.. _Steam data: https://cseweb.ucsd.edu/~jmcauley/datasets.html#steam_data
+"""
+
+import sys
+from collections.abc import Generator
+from itertools import batched
+from pathlib import Path
+from typing import Any
+
+import numpy as np
+import pyarrow as pa
+import pyarrow.compute as pc
+from xopen import xopen
+
+from lenskit._accel import data as _accel_data
+from lenskit.data import Dataset, DatasetBuilder
+from lenskit.diagnostics import DataError
+from lenskit.logging import get_logger
+
+_log = get_logger(__name__)
+
+BATCH_SIZE = 10_000
+AU_USERS_ITEMS_SCHEMA = pa.schema(
+    {
+        "user_id": pa.string(),
+        "items_count": pa.int32(),
+        "steam_id": pa.string(),
+        "user_url": pa.string(),
+        "items": pa.list_(
+            pa.struct(
+                [
+                    pa.field("item_id", pa.string()),
+                    pa.field("item_name", pa.string()),
+                    pa.field("playtime_2weeks", pa.float32()),
+                    pa.field("playtime_forever", pa.float32()),
+                ]
+            )
+        ),
+    }
+)
+
+
+def load_steam(*files: Path, reviews: bool = False) -> Dataset:
+    """
+    Load a `Steam dataset`_ from Julian McAuley's group at UCSD.
+
+    .. _Steam dataset: https://cseweb.ucsd.edu/~jmcauley/datasets.html#steam_data
+
+    .. note::
+
+        This function uses filenames to detect which version of the data to
+        load, so the files should be named exactly as they are from McAuley's
+        download site, optionally recompressed.
+
+    Args:
+        files:
+            Input files to read, in any order.  Can only load one version of
+            the data at a time (Australian or full).
+        reviews:
+            Set to ``True`` to include review text in the loaded dataset.
+    """
+    au_interactions = None
+    au_reviews = None
+    all_games = None
+    all_reviews = None
+
+    # autodetect our file(s)
+    for file in files:
+        name = file.name
+        if name.startswith("australian_user_reviews.json"):
+            au_reviews = file
+        elif name.startswith("australian_users_items.json"):
+            au_interactions = file
+        elif name.startswith("steam_games.json"):
+            all_games = file
+        elif name.startswith("steam_reviews.json"):
+            all_reviews = file
+
+    if au_interactions is not None:
+        _log.debug("looking for Australian subset interactions")
+        if all_reviews is not None or all_games is not None:
+            _log.error("cannot specify both Australian and overall input files")
+            raise DataError("invalid combination of Steam input files")
+
+        return _load_au_steam(au_interactions, au_reviews if reviews else None)
+
+    elif all_reviews is not None:
+        _log.debug("looking for full-data inteactions")
+        if au_reviews is not None:
+            _log.error("cannot specify both Australian and overall input files")
+            raise DataError("invalid combination of Steam input files")
+
+        return _load_all_steam(all_games, all_reviews, include_reviews=reviews)
+    else:
+        _log.error("must supply one of australian_users_items or steam_reviews")
+        raise DataError("no Steam interactions provided")
+
+
+def _load_au_steam(interactions: Path, reviews: Path | None) -> Dataset:
+    dsb = DatasetBuilder()
+
+    ui_data = _read_table(interactions, AU_USERS_ITEMS_SCHEMA)
+
+    _log.debug("de-duplicating Steam data", rows=ui_data.num_rows)
+    _uq_ids, uq_rows = np.unique(ui_data.column("steam_id"), return_index=True, sorted=False)
+    uq_rows = pa.array(uq_rows)
+    ui_data = ui_data.take(uq_rows)
+
+    _log.info("loaded Steam data", users=ui_data.num_rows)
+
+    items = ui_data.column("items")
+
+    _log.debug("loading items")
+    ii_flat_chunks = [c.flatten() for c in items.chunks]
+    ii_tbl: pa.Table = pa.table(
+        {
+            "item_id": pa.chunked_array(c.field("item_id") for c in ii_flat_chunks),
+            "item_name": pa.chunked_array(c.field("item_name") for c in ii_flat_chunks),
+        }
+    )
+    item_info: pa.Table = ii_tbl.group_by("item_id").aggregate([("item_name", "distinct")])
+    item_info = item_info.append_column(
+        "title", pc.list_element(item_info.column("item_name_distinct"), 0)
+    ).drop_columns("item_name_distinct")
+    item_info = item_info.filter(item_info.column("item_id").is_valid())
+    _log.debug("item schema: %s", item_info.schema)
+    _log.info("adding items", count=item_info.num_rows)
+    dsb.add_entities("item", item_info.column("item_id"))
+    dsb.add_scalar_attribute("item", "title", item_info)
+
+    _log.info("adding users", count=ui_data.num_rows)
+    users = ui_data.select(["steam_id", "user_id"]).rename_columns(["user_id", "username"])
+    dsb.add_entities("user", users)
+
+    _log.info("adding user-item interactions")
+    # TODO: make DSB work better with CSR-shaped data
+
+    return dsb.build()
+
+
+def _load_all_steam(games: Path | None, reviews: Path, *, include_reviews: bool) -> Dataset:
+    raise NotImplementedError()
+
+
+def _read_table(path: Path, schema: pa.Schema | None = None) -> pa.Table:
+    _log.debug("reading table from loose JSON", file=str(path))
+    tbl = pa.Table.from_batches(_decode_chunks(path, schema))
+    _log.debug("finished reading table", rows=tbl.num_rows, file=str(path))
+    return tbl
+
+
+def _decode_chunks(path: Path, schema: pa.Schema | None = None) -> Generator[pa.RecordBatch]:
+    for chunk in batched(_decode_steam(path), BATCH_SIZE):
+        batch = pa.RecordBatch.from_pylist(chunk, schema)
+        if schema is None:
+            schema = batch.schema
+        yield batch
+
+
+def _decode_steam(path: Path) -> Generator[dict[str, Any]]:
+    """
+    Decode a stream of malformed JSON.
+    """
+    with xopen(path, "rt") as stream:
+        for line in stream:
+            yield _accel_data.pyon_loads(line)
+
+
+def _preview_file(path: str | Path):
+    path = Path(path)
+    batch = next(_decode_chunks(path))
+    print(batch.schema)
+
+
+if __name__ == "__main__":
+    _preview_file(sys.argv[1])
diff --git a/src/lenskit/testing/_msweb.py b/src/lenskit/testing/_msweb.py
index ea2f078df..9737676e2 100644
--- a/src/lenskit/testing/_msweb.py
+++ b/src/lenskit/testing/_msweb.py
@@ -8,7 +8,7 @@
 
 from pytest import fixture, skip
 
-from lenskit.data.msweb import load_ms_web
+from lenskit.data.sources.msweb import load_ms_web
 from lenskit.splitting import TTSplit
 
 MSWEB_TRAIN = Path("data/anonymous-msweb.data.gz")
diff --git a/tests/cli/count-tests.pl b/tests/cli/count-tests.pl
index b40030bc9..b040da6c2 100755
--- a/tests/cli/count-tests.pl
+++ b/tests/cli/count-tests.pl
@@ -8,7 +8,7 @@
 print STDERR "counting tests\n" if $verbose;
 
 while (<>) {
-    if (m/^(run-(lenskit|python|command)|require)\b/) {
+    if (m/^\s*(run-(lenskit|python|command)|require)\b/) {
         print STDERR "test: $_" if $verbose;
         $test_count += 1;
     }
diff --git a/tests/cli/test-data-convert.sh b/tests/cli/test-data-convert.sh
index 08d4281d0..2538e2a54 100644
--- a/tests/cli/test-data-convert.sh
+++ b/tests/cli/test-data-convert.sh
@@ -4,3 +4,11 @@ require -f "$TEST_WORK/ml-data/schema.json"
 
 name="$(jq -r .name "$TEST_WORK/ml-data/schema.json")"
 require "$name" = ml-latest-small
+
+if [[ -f data/australian_users_items.json.gz ]]; then
+    run-lenskit data convert --steam data/australian_users_items.json.gz "$TEST_WORK/steam-au-data"
+    require -d "$TEST_WORK/steam-au-data"
+    require -f "$TEST_WORK/steam-au-data/schema.json"
+else
+    skip 3
+fi
diff --git a/uv.lock b/uv.lock
index 5cfdaee3a..b32775cb3 100644
--- a/uv.lock
+++ b/uv.lock
@@ -3248,45 +3248,45 @@ wheels = [
 
 [[package]]
 name = "pyarrow"
-version = "23.0.1"
-source = { registry = "https://pypi.org/simple" }
-sdist = { url = "https://files.pythonhosted.org/packages/88/22/134986a4cc224d593c1afde5494d18ff629393d74cc2eddb176669f234a4/pyarrow-23.0.1.tar.gz", hash = "sha256:b8c5873e33440b2bc2f4a79d2b47017a89c5a24116c055625e6f2ee50523f019", size = 1167336, upload-time = "2026-02-16T10:14:12.39Z" }
-wheels = [
-    { url = "https://files.pythonhosted.org/packages/9a/4b/4166bb5abbfe6f750fc60ad337c43ecf61340fa52ab386da6e8dbf9e63c4/pyarrow-23.0.1-cp312-cp312-macosx_12_0_arm64.whl", hash = "sha256:f4b0dbfa124c0bb161f8b5ebb40f1a680b70279aa0c9901d44a2b5a20806039f", size = 34214575, upload-time = "2026-02-16T10:09:56.225Z" },
-    { url = "https://files.pythonhosted.org/packages/e1/da/3f941e3734ac8088ea588b53e860baeddac8323ea40ce22e3d0baa865cc9/pyarrow-23.0.1-cp312-cp312-macosx_12_0_x86_64.whl", hash = "sha256:7707d2b6673f7de054e2e83d59f9e805939038eebe1763fe811ee8fa5c0cd1a7", size = 35832540, upload-time = "2026-02-16T10:10:03.428Z" },
-    { url = "https://files.pythonhosted.org/packages/88/7c/3d841c366620e906d54430817531b877ba646310296df42ef697308c2705/pyarrow-23.0.1-cp312-cp312-manylinux_2_28_aarch64.whl", hash = "sha256:86ff03fb9f1a320266e0de855dee4b17da6794c595d207f89bba40d16b5c78b9", size = 44470940, upload-time = "2026-02-16T10:10:10.704Z" },
-    { url = "https://files.pythonhosted.org/packages/2c/a5/da83046273d990f256cb79796a190bbf7ec999269705ddc609403f8c6b06/pyarrow-23.0.1-cp312-cp312-manylinux_2_28_x86_64.whl", hash = "sha256:813d99f31275919c383aab17f0f455a04f5a429c261cc411b1e9a8f5e4aaaa05", size = 47586063, upload-time = "2026-02-16T10:10:17.95Z" },
-    { url = "https://files.pythonhosted.org/packages/5b/3c/b7d2ebcff47a514f47f9da1e74b7949138c58cfeb108cdd4ee62f43f0cf3/pyarrow-23.0.1-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:bf5842f960cddd2ef757d486041d57c96483efc295a8c4a0e20e704cbbf39c67", size = 48173045, upload-time = "2026-02-16T10:10:25.363Z" },
-    { url = "https://files.pythonhosted.org/packages/43/b2/b40961262213beaba6acfc88698eb773dfce32ecdf34d19291db94c2bd73/pyarrow-23.0.1-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:564baf97c858ecc03ec01a41062e8f4698abc3e6e2acd79c01c2e97880a19730", size = 50621741, upload-time = "2026-02-16T10:10:33.477Z" },
-    { url = "https://files.pythonhosted.org/packages/f6/70/1fdda42d65b28b078e93d75d371b2185a61da89dda4def8ba6ba41ebdeb4/pyarrow-23.0.1-cp312-cp312-win_amd64.whl", hash = "sha256:07deae7783782ac7250989a7b2ecde9b3c343a643f82e8a4df03d93b633006f0", size = 27620678, upload-time = "2026-02-16T10:10:39.31Z" },
-    { url = "https://files.pythonhosted.org/packages/47/10/2cbe4c6f0fb83d2de37249567373d64327a5e4d8db72f486db42875b08f6/pyarrow-23.0.1-cp313-cp313-macosx_12_0_arm64.whl", hash = "sha256:6b8fda694640b00e8af3c824f99f789e836720aa8c9379fb435d4c4953a756b8", size = 34210066, upload-time = "2026-02-16T10:10:45.487Z" },
-    { url = "https://files.pythonhosted.org/packages/cb/4f/679fa7e84dadbaca7a65f7cdba8d6c83febbd93ca12fa4adf40ba3b6362b/pyarrow-23.0.1-cp313-cp313-macosx_12_0_x86_64.whl", hash = "sha256:8ff51b1addc469b9444b7c6f3548e19dc931b172ab234e995a60aea9f6e6025f", size = 35825526, upload-time = "2026-02-16T10:10:52.266Z" },
-    { url = "https://files.pythonhosted.org/packages/f9/63/d2747d930882c9d661e9398eefc54f15696547b8983aaaf11d4a2e8b5426/pyarrow-23.0.1-cp313-cp313-manylinux_2_28_aarch64.whl", hash = "sha256:71c5be5cbf1e1cb6169d2a0980850bccb558ddc9b747b6206435313c47c37677", size = 44473279, upload-time = "2026-02-16T10:11:01.557Z" },
-    { url = "https://files.pythonhosted.org/packages/b3/93/10a48b5e238de6d562a411af6467e71e7aedbc9b87f8d3a35f1560ae30fb/pyarrow-23.0.1-cp313-cp313-manylinux_2_28_x86_64.whl", hash = "sha256:9b6f4f17b43bc39d56fec96e53fe89d94bac3eb134137964371b45352d40d0c2", size = 47585798, upload-time = "2026-02-16T10:11:09.401Z" },
-    { url = "https://files.pythonhosted.org/packages/5c/20/476943001c54ef078dbf9542280e22741219a184a0632862bca4feccd666/pyarrow-23.0.1-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:9fc13fc6c403d1337acab46a2c4346ca6c9dec5780c3c697cf8abfd5e19b6b37", size = 48179446, upload-time = "2026-02-16T10:11:17.781Z" },
-    { url = "https://files.pythonhosted.org/packages/4b/b6/5dd0c47b335fcd8edba9bfab78ad961bd0fd55ebe53468cc393f45e0be60/pyarrow-23.0.1-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:5c16ed4f53247fa3ffb12a14d236de4213a4415d127fe9cebed33d51671113e2", size = 50623972, upload-time = "2026-02-16T10:11:26.185Z" },
-    { url = "https://files.pythonhosted.org/packages/d5/09/a532297c9591a727d67760e2e756b83905dd89adb365a7f6e9c72578bcc1/pyarrow-23.0.1-cp313-cp313-win_amd64.whl", hash = "sha256:cecfb12ef629cf6be0b1887f9f86463b0dd3dc3195ae6224e74006be4736035a", size = 27540749, upload-time = "2026-02-16T10:12:23.297Z" },
-    { url = "https://files.pythonhosted.org/packages/a5/8e/38749c4b1303e6ae76b3c80618f84861ae0c55dd3c2273842ea6f8258233/pyarrow-23.0.1-cp313-cp313t-macosx_12_0_arm64.whl", hash = "sha256:29f7f7419a0e30264ea261fdc0e5fe63ce5a6095003db2945d7cd78df391a7e1", size = 34471544, upload-time = "2026-02-16T10:11:32.535Z" },
-    { url = "https://files.pythonhosted.org/packages/a3/73/f237b2bc8c669212f842bcfd842b04fc8d936bfc9d471630569132dc920d/pyarrow-23.0.1-cp313-cp313t-macosx_12_0_x86_64.whl", hash = "sha256:33d648dc25b51fd8055c19e4261e813dfc4d2427f068bcecc8b53d01b81b0500", size = 35949911, upload-time = "2026-02-16T10:11:39.813Z" },
-    { url = "https://files.pythonhosted.org/packages/0c/86/b912195eee0903b5611bf596833def7d146ab2d301afeb4b722c57ffc966/pyarrow-23.0.1-cp313-cp313t-manylinux_2_28_aarch64.whl", hash = "sha256:cd395abf8f91c673dd3589cadc8cc1ee4e8674fa61b2e923c8dd215d9c7d1f41", size = 44520337, upload-time = "2026-02-16T10:11:47.764Z" },
-    { url = "https://files.pythonhosted.org/packages/69/c2/f2a717fb824f62d0be952ea724b4f6f9372a17eed6f704b5c9526f12f2f1/pyarrow-23.0.1-cp313-cp313t-manylinux_2_28_x86_64.whl", hash = "sha256:00be9576d970c31defb5c32eb72ef585bf600ef6d0a82d5eccaae96639cf9d07", size = 47548944, upload-time = "2026-02-16T10:11:56.607Z" },
-    { url = "https://files.pythonhosted.org/packages/84/a7/90007d476b9f0dc308e3bc57b832d004f848fd6c0da601375d20d92d1519/pyarrow-23.0.1-cp313-cp313t-musllinux_1_2_aarch64.whl", hash = "sha256:c2139549494445609f35a5cda4eb94e2c9e4d704ce60a095b342f82460c73a83", size = 48236269, upload-time = "2026-02-16T10:12:04.47Z" },
-    { url = "https://files.pythonhosted.org/packages/b0/3f/b16fab3e77709856eb6ac328ce35f57a6d4a18462c7ca5186ef31b45e0e0/pyarrow-23.0.1-cp313-cp313t-musllinux_1_2_x86_64.whl", hash = "sha256:7044b442f184d84e2351e5084600f0d7343d6117aabcbc1ac78eb1ae11eb4125", size = 50604794, upload-time = "2026-02-16T10:12:11.797Z" },
-    { url = "https://files.pythonhosted.org/packages/e9/a1/22df0620a9fac31d68397a75465c344e83c3dfe521f7612aea33e27ab6c0/pyarrow-23.0.1-cp313-cp313t-win_amd64.whl", hash = "sha256:a35581e856a2fafa12f3f54fce4331862b1cfb0bef5758347a858a4aa9d6bae8", size = 27660642, upload-time = "2026-02-16T10:12:17.746Z" },
-    { url = "https://files.pythonhosted.org/packages/8d/1b/6da9a89583ce7b23ac611f183ae4843cd3a6cf54f079549b0e8c14031e73/pyarrow-23.0.1-cp314-cp314-macosx_12_0_arm64.whl", hash = "sha256:5df1161da23636a70838099d4aaa65142777185cc0cdba4037a18cee7d8db9ca", size = 34238755, upload-time = "2026-02-16T10:12:32.819Z" },
-    { url = "https://files.pythonhosted.org/packages/ae/b5/d58a241fbe324dbaeb8df07be6af8752c846192d78d2272e551098f74e88/pyarrow-23.0.1-cp314-cp314-macosx_12_0_x86_64.whl", hash = "sha256:fa8e51cb04b9f8c9c5ace6bab63af9a1f88d35c0d6cbf53e8c17c098552285e1", size = 35847826, upload-time = "2026-02-16T10:12:38.949Z" },
-    { url = "https://files.pythonhosted.org/packages/54/a5/8cbc83f04aba433ca7b331b38f39e000efd9f0c7ce47128670e737542996/pyarrow-23.0.1-cp314-cp314-manylinux_2_28_aarch64.whl", hash = "sha256:0b95a3994f015be13c63148fef8832e8a23938128c185ee951c98908a696e0eb", size = 44536859, upload-time = "2026-02-16T10:12:45.467Z" },
-    { url = "https://files.pythonhosted.org/packages/36/2e/c0f017c405fcdc252dbccafbe05e36b0d0eb1ea9a958f081e01c6972927f/pyarrow-23.0.1-cp314-cp314-manylinux_2_28_x86_64.whl", hash = "sha256:4982d71350b1a6e5cfe1af742c53dfb759b11ce14141870d05d9e540d13bc5d1", size = 47614443, upload-time = "2026-02-16T10:12:55.525Z" },
-    { url = "https://files.pythonhosted.org/packages/af/6b/2314a78057912f5627afa13ba43809d9d653e6630859618b0fd81a4e0759/pyarrow-23.0.1-cp314-cp314-musllinux_1_2_aarch64.whl", hash = "sha256:c250248f1fe266db627921c89b47b7c06fee0489ad95b04d50353537d74d6886", size = 48232991, upload-time = "2026-02-16T10:13:04.729Z" },
-    { url = "https://files.pythonhosted.org/packages/40/f2/1bcb1d3be3460832ef3370d621142216e15a2c7c62602a4ea19ec240dd64/pyarrow-23.0.1-cp314-cp314-musllinux_1_2_x86_64.whl", hash = "sha256:5f4763b83c11c16e5f4c15601ba6dfa849e20723b46aa2617cb4bffe8768479f", size = 50645077, upload-time = "2026-02-16T10:13:14.147Z" },
-    { url = "https://files.pythonhosted.org/packages/eb/3f/b1da7b61cd66566a4d4c8383d376c606d1c34a906c3f1cb35c479f59d1aa/pyarrow-23.0.1-cp314-cp314-win_amd64.whl", hash = "sha256:3a4c85ef66c134161987c17b147d6bffdca4566f9a4c1d81a0a01cdf08414ea5", size = 28234271, upload-time = "2026-02-16T10:14:09.397Z" },
-    { url = "https://files.pythonhosted.org/packages/b5/78/07f67434e910a0f7323269be7bfbf58699bd0c1d080b18a1ab49ba943fe8/pyarrow-23.0.1-cp314-cp314t-macosx_12_0_arm64.whl", hash = "sha256:17cd28e906c18af486a499422740298c52d7c6795344ea5002a7720b4eadf16d", size = 34488692, upload-time = "2026-02-16T10:13:21.541Z" },
-    { url = "https://files.pythonhosted.org/packages/50/76/34cf7ae93ece1f740a04910d9f7e80ba166b9b4ab9596a953e9e62b90fe1/pyarrow-23.0.1-cp314-cp314t-macosx_12_0_x86_64.whl", hash = "sha256:76e823d0e86b4fb5e1cf4a58d293036e678b5a4b03539be933d3b31f9406859f", size = 35964383, upload-time = "2026-02-16T10:13:28.63Z" },
-    { url = "https://files.pythonhosted.org/packages/46/90/459b827238936d4244214be7c684e1b366a63f8c78c380807ae25ed92199/pyarrow-23.0.1-cp314-cp314t-manylinux_2_28_aarch64.whl", hash = "sha256:a62e1899e3078bf65943078b3ad2a6ddcacf2373bc06379aac61b1e548a75814", size = 44538119, upload-time = "2026-02-16T10:13:35.506Z" },
-    { url = "https://files.pythonhosted.org/packages/28/a1/93a71ae5881e99d1f9de1d4554a87be37da11cd6b152239fb5bd924fdc64/pyarrow-23.0.1-cp314-cp314t-manylinux_2_28_x86_64.whl", hash = "sha256:df088e8f640c9fae3b1f495b3c64755c4e719091caf250f3a74d095ddf3c836d", size = 47571199, upload-time = "2026-02-16T10:13:42.504Z" },
-    { url = "https://files.pythonhosted.org/packages/88/a3/d2c462d4ef313521eaf2eff04d204ac60775263f1fb08c374b543f79f610/pyarrow-23.0.1-cp314-cp314t-musllinux_1_2_aarch64.whl", hash = "sha256:46718a220d64677c93bc243af1d44b55998255427588e400677d7192671845c7", size = 48259435, upload-time = "2026-02-16T10:13:49.226Z" },
-    { url = "https://files.pythonhosted.org/packages/cc/f1/11a544b8c3d38a759eb3fbb022039117fd633e9a7b19e4841cc3da091915/pyarrow-23.0.1-cp314-cp314t-musllinux_1_2_x86_64.whl", hash = "sha256:a09f3876e87f48bc2f13583ab551f0379e5dfb83210391e68ace404181a20690", size = 50629149, upload-time = "2026-02-16T10:13:57.238Z" },
-    { url = "https://files.pythonhosted.org/packages/50/f2/c0e76a0b451ffdf0cf788932e182758eb7558953f4f27f1aff8e2518b653/pyarrow-23.0.1-cp314-cp314t-win_amd64.whl", hash = "sha256:527e8d899f14bd15b740cd5a54ad56b7f98044955373a17179d5956ddb93d9ce", size = 28365807, upload-time = "2026-02-16T10:14:03.892Z" },
+version = "24.0.0"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/91/13/13e1069b351bdc3881266e11147ffccf687505dbb0ea74036237f5d454a5/pyarrow-24.0.0.tar.gz", hash = "sha256:85fe721a14dd823aca09127acbb06c3ca723efbd436c004f16bca601b04dcc83", size = 1180261, upload-time = "2026-04-21T10:51:25.837Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/b4/a9/9686d9f07837f91f775e8932659192e02c74f9d8920524b480b85212cc68/pyarrow-24.0.0-cp312-cp312-macosx_12_0_arm64.whl", hash = "sha256:6233c9ed9ab9d1db47de57d9753256d9dcffbf42db341576099f0fd9f6bf4810", size = 34981559, upload-time = "2026-04-21T10:47:22.17Z" },
+    { url = "https://files.pythonhosted.org/packages/80/b6/0ddf0e9b6ead3474ab087ae598c76b031fc45532bf6a63f3a553440fb258/pyarrow-24.0.0-cp312-cp312-macosx_12_0_x86_64.whl", hash = "sha256:f7616236ec1bc2b15bfdec22a71ab38851c86f8f05ff64f379e1278cf20c634a", size = 36663654, upload-time = "2026-04-21T10:47:28.315Z" },
+    { url = "https://files.pythonhosted.org/packages/7c/3b/926382efe8ce27ba729071d3566ade6dfb86bdf112f366000196b2f5780a/pyarrow-24.0.0-cp312-cp312-manylinux_2_28_aarch64.whl", hash = "sha256:1617043b99bd33e5318ae18eb2919af09c71322ef1ca46566cdafc6e6712fb66", size = 45679394, upload-time = "2026-04-21T10:47:34.821Z" },
+    { url = "https://files.pythonhosted.org/packages/b3/7a/829f7d9dfd37c207206081d6dad474d81dde29952401f07f2ba507814818/pyarrow-24.0.0-cp312-cp312-manylinux_2_28_x86_64.whl", hash = "sha256:6165461f55ef6314f026de6638d661188e3455d3ec49834556a0ebbdbace18bb", size = 48863122, upload-time = "2026-04-21T10:47:42.056Z" },
+    { url = "https://files.pythonhosted.org/packages/5f/e8/f88ce625fe8babaae64e8db2d417c7653adb3019b08aae85c5ed787dc816/pyarrow-24.0.0-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:3b13dedfe76a0ad2d1d859b0811b53827a4e9d93a0bcb05cf59333ab4980cc7e", size = 49376032, upload-time = "2026-04-21T10:47:48.967Z" },
+    { url = "https://files.pythonhosted.org/packages/36/7a/82c363caa145fff88fb475da50d3bf52bb024f61917be5424c3392eaf878/pyarrow-24.0.0-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:25ea65d868eb04015cd18e6df2fbe98f07e5bda2abefabcb88fce39a947716f6", size = 51929490, upload-time = "2026-04-21T10:47:55.981Z" },
+    { url = "https://files.pythonhosted.org/packages/66/1c/e3e72c8014ad2743ca64a701652c733cc5cbcee15c0463a32a8c55518d9e/pyarrow-24.0.0-cp312-cp312-win_amd64.whl", hash = "sha256:295f0a7f2e242dabd513737cf076007dc5b2d59237e3eca37b05c0c6446f3826", size = 27355660, upload-time = "2026-04-21T10:48:01.718Z" },
+    { url = "https://files.pythonhosted.org/packages/6f/d3/a1abf004482026ddc17f4503db227787fa3cfe41ec5091ff20e4fea55e57/pyarrow-24.0.0-cp313-cp313-macosx_12_0_arm64.whl", hash = "sha256:02b001b3ed4723caa44f6cd1af2d5c86aa2cf9971dacc2ffa55b21237713dfba", size = 34976759, upload-time = "2026-04-21T10:48:07.258Z" },
+    { url = "https://files.pythonhosted.org/packages/4f/4a/34f0a36d28a2dd32225301b79daad44e243dc1a2bb77d43b60749be255c4/pyarrow-24.0.0-cp313-cp313-macosx_12_0_x86_64.whl", hash = "sha256:04920d6a71aabd08a0417709efce97d45ea8e6fb733d9ca9ecffb13c67839f68", size = 36658471, upload-time = "2026-04-21T10:48:13.347Z" },
+    { url = "https://files.pythonhosted.org/packages/1f/78/543b94712ae8bb1a6023bcc1acf1a740fbff8286747c289cd9468fced2a5/pyarrow-24.0.0-cp313-cp313-manylinux_2_28_aarch64.whl", hash = "sha256:a964266397740257f16f7bb2e4f08a0c81454004beab8ff59dd531b73610e9f2", size = 45675981, upload-time = "2026-04-21T10:48:20.201Z" },
+    { url = "https://files.pythonhosted.org/packages/84/9f/8fb7c222b100d314137fa40ec050de56cd8c6d957d1cfff685ce72f15b17/pyarrow-24.0.0-cp313-cp313-manylinux_2_28_x86_64.whl", hash = "sha256:6f066b179d68c413374294bc1735f68475457c933258df594443bb9d88ddc2a0", size = 48859172, upload-time = "2026-04-21T10:48:27.541Z" },
+    { url = "https://files.pythonhosted.org/packages/a7/d3/1ea72538e6c8b3b475ed78d1049a2c518e655761ea50fe1171fc855fcab7/pyarrow-24.0.0-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:1183baeb14c5f587b1ec52831e665718ce632caab84b7cd6b85fd44f96114495", size = 49385733, upload-time = "2026-04-21T10:48:34.7Z" },
+    { url = "https://files.pythonhosted.org/packages/c3/be/c3d8b06a1ba35f2260f8e1f771abbee7d5e345c0937aab90675706b1690a/pyarrow-24.0.0-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:806f24b4085453c197a5078218d1ee08783ebbba271badd153d1ae22a3ee804f", size = 51934335, upload-time = "2026-04-21T10:48:42.099Z" },
+    { url = "https://files.pythonhosted.org/packages/9c/62/89e07a1e7329d2cde3e3c6994ba0839a24977a2beda8be6005ea3d860b99/pyarrow-24.0.0-cp313-cp313-win_amd64.whl", hash = "sha256:e4505fc6583f7b05ab854934896bcac8253b04ac1171a77dfb73efef92076d91", size = 27271748, upload-time = "2026-04-21T10:49:42.532Z" },
+    { url = "https://files.pythonhosted.org/packages/17/1a/cff3a59f80b5b1658549d46611b67163f65e0664431c076ad728bf9d5af4/pyarrow-24.0.0-cp313-cp313t-macosx_12_0_arm64.whl", hash = "sha256:1a4e45017efbf115032e4475ee876d525e0e36c742214fbe405332480ecd6275", size = 35238554, upload-time = "2026-04-21T10:48:48.526Z" },
+    { url = "https://files.pythonhosted.org/packages/a8/99/cce0f42a327bfef2c420fb6078a3eb834826e5d6697bf3009fe11d2ad051/pyarrow-24.0.0-cp313-cp313t-macosx_12_0_x86_64.whl", hash = "sha256:7986f1fa71cee060ad00758bcc79d3a93bab8559bf978fab9e53472a2e25a17b", size = 36782301, upload-time = "2026-04-21T10:48:55.181Z" },
+    { url = "https://files.pythonhosted.org/packages/2a/66/8e560d5ff6793ca29aca213c53eec0dd482dd46cb93b2819e5aab52e4252/pyarrow-24.0.0-cp313-cp313t-manylinux_2_28_aarch64.whl", hash = "sha256:d3e0b61e8efb24ed38898e5cdc5fffa9124be480008d401a1f8071500494ae42", size = 45721929, upload-time = "2026-04-21T10:49:03.676Z" },
+    { url = "https://files.pythonhosted.org/packages/27/0c/a26e25505d030716e078d9f16eb74973cbf0b33b672884e9f9da1c83b871/pyarrow-24.0.0-cp313-cp313t-manylinux_2_28_x86_64.whl", hash = "sha256:55a3bc1e3df3b5567b7d27ef551b2283f0c68a5e86f1cd56abc569da4f31335b", size = 48825365, upload-time = "2026-04-21T10:49:11.714Z" },
+    { url = "https://files.pythonhosted.org/packages/5f/eb/771f9ecb0c65e73fe9dccdd1717901b9594f08c4515d000c7c62df573811/pyarrow-24.0.0-cp313-cp313t-musllinux_1_2_aarch64.whl", hash = "sha256:641f795b361874ac9da5294f8f443dfdbee355cf2bd9e3b8d97aaac2306b9b37", size = 49451819, upload-time = "2026-04-21T10:49:21.474Z" },
+    { url = "https://files.pythonhosted.org/packages/48/da/61ae89a88732f5a785646f3ec6125dbb640fa98a540eb2b9889caa561403/pyarrow-24.0.0-cp313-cp313t-musllinux_1_2_x86_64.whl", hash = "sha256:8adc8e6ce5fccf5dc707046ae4914fd537def529709cc0d285d37a7f9cd442ca", size = 51909252, upload-time = "2026-04-21T10:49:31.164Z" },
+    { url = "https://files.pythonhosted.org/packages/cb/1a/8dd5cafab7b66573fa91c03d06d213356ad4edd71813aa75e08ce2b3a844/pyarrow-24.0.0-cp313-cp313t-win_amd64.whl", hash = "sha256:9b18371ad2f44044b81a8d23bc2d8a9b6a6226dca775e8e16cfee640473d6c5d", size = 27388127, upload-time = "2026-04-21T10:49:37.334Z" },
+    { url = "https://files.pythonhosted.org/packages/ad/80/d022a34ff05d2cbedd8ccf841fc1f532ecfa9eb5ed1711b56d0e0ea71fc9/pyarrow-24.0.0-cp314-cp314-macosx_12_0_arm64.whl", hash = "sha256:1cc9057f0319e26333b357e17f3c2c022f1a83739b48a88b25bfd5fa2dc18838", size = 35007997, upload-time = "2026-04-21T10:49:48.796Z" },
+    { url = "https://files.pythonhosted.org/packages/1a/ff/f01485fda6f4e5d441afb8dd5e7681e4db18826c1e271852f5d3957d6a80/pyarrow-24.0.0-cp314-cp314-macosx_12_0_x86_64.whl", hash = "sha256:e6f1278ee4785b6db21229374a1c9e54ec7c549de5d1efc9630b6207de7e170b", size = 36678720, upload-time = "2026-04-21T10:49:55.858Z" },
+    { url = "https://files.pythonhosted.org/packages/9e/c2/2d2d5fea814237923f71b36495211f20b43a1576f9a4d6da7e751a64ec6f/pyarrow-24.0.0-cp314-cp314-manylinux_2_28_aarch64.whl", hash = "sha256:adbbedc55506cbdabb830890444fb856bfb0060c46c6f8026c6c2f2cf86ae795", size = 45741852, upload-time = "2026-04-21T10:50:04.624Z" },
+    { url = "https://files.pythonhosted.org/packages/8e/3a/28ba9c1c1ebdbb5f1b94dfebb46f207e52e6a554b7fe4132540fde29a3a0/pyarrow-24.0.0-cp314-cp314-manylinux_2_28_x86_64.whl", hash = "sha256:ae8a1145af31d903fa9bb166824d7abe9b4681a000b0159c9fb99c11bc11ad26", size = 48889852, upload-time = "2026-04-21T10:50:12.293Z" },
+    { url = "https://files.pythonhosted.org/packages/df/51/4a389acfd31dca009f8fb82d7f510bb4130f2b3a8e18cf00194d0687d8ac/pyarrow-24.0.0-cp314-cp314-musllinux_1_2_aarch64.whl", hash = "sha256:d7027eba1df3b2069e2e8d80f644fa0918b68c46432af3d088ddd390d063ecde", size = 49445207, upload-time = "2026-04-21T10:50:20.677Z" },
+    { url = "https://files.pythonhosted.org/packages/19/4b/0bab2b23d2ae901b1b9a03c0efd4b2d070256f8ce3fc43f6e58c167b2081/pyarrow-24.0.0-cp314-cp314-musllinux_1_2_x86_64.whl", hash = "sha256:e56a1ffe9bf7b727432b89104cc0849c21582949dd7bdcb34f17b2001a351a76", size = 51954117, upload-time = "2026-04-21T10:50:29.14Z" },
+    { url = "https://files.pythonhosted.org/packages/29/88/f4e9145da0417b3d2c12035a8492b35ff4a3dbc653e614fcfb51d9dedb38/pyarrow-24.0.0-cp314-cp314-win_amd64.whl", hash = "sha256:38be1808cdd068605b787e6ca9119b27eb275a0234e50212c3492331680c3b1e", size = 28001155, upload-time = "2026-04-21T10:51:22.337Z" },
+    { url = "https://files.pythonhosted.org/packages/79/4f/46a49a63f43526da895b1a45bbb51d5baf8e4d77159f8528fc3e5490007f/pyarrow-24.0.0-cp314-cp314t-macosx_12_0_arm64.whl", hash = "sha256:418e48ce50a45a6a6c73c454677203a9c75c966cb1e92ca3370959185f197a05", size = 35250387, upload-time = "2026-04-21T10:50:35.552Z" },
+    { url = "https://files.pythonhosted.org/packages/a0/da/d5e0cd5ef00796922404806d5f00325cdadc3441ce2c13fe7115f2df9a64/pyarrow-24.0.0-cp314-cp314t-macosx_12_0_x86_64.whl", hash = "sha256:2f16197705a230a78270cdd4ea8a1d57e86b2fdcbc34a1f6aebc72e65c986f9a", size = 36797102, upload-time = "2026-04-21T10:50:42.417Z" },
+    { url = "https://files.pythonhosted.org/packages/34/c7/5904145b0a593a05236c882933d439b5720f0a145381179063722fbfc123/pyarrow-24.0.0-cp314-cp314t-manylinux_2_28_aarch64.whl", hash = "sha256:fb24ac194bfc5e86839d7dcd52092ee31e5fe6733fe11f5e3b06ef0812b20072", size = 45745118, upload-time = "2026-04-21T10:50:49.324Z" },
+    { url = "https://files.pythonhosted.org/packages/13/d3/cca42fe166d1c6e4d5b80e530b7949104d10e17508a90ae202dac205ce2a/pyarrow-24.0.0-cp314-cp314t-manylinux_2_28_x86_64.whl", hash = "sha256:9700ebd9a51f5895ce75ff4ac4b3c47a7d4b42bc618be8e713e5d56bacf5f931", size = 48844765, upload-time = "2026-04-21T10:50:55.579Z" },
+    { url = "https://files.pythonhosted.org/packages/b0/49/942c3b79878ba928324d1e17c274ed84581db8c0a749b24bcf4cbdf15bd3/pyarrow-24.0.0-cp314-cp314t-musllinux_1_2_aarch64.whl", hash = "sha256:d8ddd2768da81d3ee08cfea9b597f4abb4e8e1dc8ae7e204b608d23a0d3ab699", size = 49471890, upload-time = "2026-04-21T10:51:02.439Z" },
+    { url = "https://files.pythonhosted.org/packages/76/97/ff71431000a75d84135a1ace5ca4ba11726a231a8007bbb320a4c54075d5/pyarrow-24.0.0-cp314-cp314t-musllinux_1_2_x86_64.whl", hash = "sha256:61a3d7eaa97a14768b542f3d284dc6400dd2470d9f080708b13cd46b6ae18136", size = 51932250, upload-time = "2026-04-21T10:51:10.576Z" },
+    { url = "https://files.pythonhosted.org/packages/51/be/6f79d55816d5c22557cf27533543d5d70dfe692adfbee4b99f2760674f38/pyarrow-24.0.0-cp314-cp314t-win_amd64.whl", hash = "sha256:c91d00057f23b8d353039520dc3a6c09d8608164c692e9f59a175a42b2ae0c19", size = 28131282, upload-time = "2026-04-21T10:51:16.815Z" },
 ]
 
 [[package]]