diff --git a/entries/yoochoose/__init__.py b/entries/yoochoose/__init__.py
index 4b392ce..37fac72 100644
--- a/entries/yoochoose/__init__.py
+++ b/entries/yoochoose/__init__.py
@@ -43,7 +43,7 @@ url = ['https://recsys.acm.org/recsys15/challenge/',
        'https://s3-eu-west-1.amazonaws.com/yc-rdata/yoochoose-data.7z']
 citation = [('D. Ben-Shimon, A. Tsikinovsky, M. Friedmann, B. Shapira, L. Rokach, J. Hoerle, "RecSys Challenge 2015 and the YOOCHOOSE Dataset." Proceedings of the 9th ACM Conference on Recommender Systems, 357-358 (2015)',
              'https://doi.org/10.1145/2792838.2798723')]
-icon_hash = None
+date_added = '2026-10-28'
 upstream_license = ('CC BY-NC-ND 4.0', 'https://creativecommons.org/licenses/by-nc-nd/4.0/')
 upstream_prefix = 'https://s3-eu-west-1.amazonaws.com/yc-rdata'
 files = [(('yoochoose-data.7z:yoochoose-clicks.dat',

diff --git a/entries/yoochoose/__init__.py b/entries/yoochoose/__init__.py
index 4b7a6ac..4b392ce 100644
--- a/entries/yoochoose/__init__.py
+++ b/entries/yoochoose/__init__.py
@@ -29,15 +29,15 @@ A directed edge from a session to an item is a click on the item during the sess
 
 The network has the following properties:
 
-- `is_session`: whether the node is a session (otherwise it is an item).
-- `id`: the identifier of the session or item.
-- Edge `time`: the time of the click or purchase, as Unix time (with milliseconds).
-- Edge `buy`: whether the edge is a purchase (otherwise it is a click).
-- Edge `test`: whether the session is one of the test sessions of the challenge.
-- Edge `category` (clicks): the context of the click: 0 if missing, 1 to 12 for one of the categories of the shop, or the 8-10 digit identifier of a brand (-1 for special offers, and for purchases).
-- Edge `special_offer` (clicks): whether the item was clicked in the context of a special offer or promotion.
-- Edge `price` (purchases): the price of the item (modified by the source; -1 for clicks; 0 for 610,030 of the 1,150,753 purchases, whose price and quantity are not given).
-- Edge `quantity` (purchases): the number of items bought (-1 for clicks; 0 where not given)."""
+- (Node) `is_session`: whether the node is a session (otherwise it is an item).
+- (Node) `id`: the identifier of the session or item.
+- (Edge) `time`: the time of the click or purchase, as Unix time (with milliseconds).
+- (Edge) `buy`: whether the edge is a purchase (otherwise it is a click).
+- (Edge) `test`: whether the session is one of the test sessions of the challenge.
+- (Edge) `category` (clicks): the context of the click: 0 if missing, 1 to 12 for one of the categories of the shop, or the 8-10 digit identifier of a brand (-1 for special offers, and for purchases).
+- (Edge) `special_offer` (clicks): whether the item was clicked in the context of a special offer or promotion.
+- (Edge) `price` (purchases): the price of the item (modified by the source; -1 for clicks; 0 for 610,030 of the 1,150,753 purchases, whose price and quantity are not given).
+- (Edge) `quantity` (purchases): the number of items bought (-1 for clicks; 0 where not given)."""
 tags = ['Economic', 'Commerce', 'Bipartite', 'Multigraph', 'Timestamps', 'Metadata']
 url = ['https://recsys.acm.org/recsys15/challenge/',
        'https://s3-eu-west-1.amazonaws.com/yc-rdata/yoochoose-data.7z']

diff --git a/entries/yoochoose/__init__.py b/entries/yoochoose/__init__.py
new file mode 100644
index 0000000..4b7a6ac
--- /dev/null
+++ b/entries/yoochoose/__init__.py
@@ -0,0 +1,141 @@
+#! /usr/bin/env python
+# -*- coding: utf-8 -*-
+#
+# Copyright (C) 2026 Tiago de Paula Peixoto <tiago@skewed.de>
+#
+# This program is free software: you can redistribute it and/or modify it under
+# the terms of the GNU Affero General Public License as published by the Free
+# Software Foundation, either version 3 of the License, or (at your option) any
+# later version.
+#
+# This program is distributed in the hope that it will be useful, but WITHOUT
+# ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS
+# FOR A PARTICULAR PURPOSE.  See the GNU Affero General Public License for more
+# details.
+#
+# You should have received a copy of the GNU Affero General Public License along
+# with this program.  If not, see <http://www.gnu.org/licenses/>.
+
+import pyarrow
+import pyarrow.csv
+import pyarrow.compute as pc
+
+from .. import *
+
+title = "YooChoose e-commerce sessions (RecSys Challenge 2015)"
+description = r"""A bipartite network of the browsing sessions of the customers of a European online retailer and the items they clicked on and bought, released by YooChoose GmbH for the RecSys Challenge 2015 (whose task was to predict which sessions end with a purchase, and which items are bought). The data were collected during six months of 2014 (April to September) by tracking the website of the retailer, whose identity is not disclosed; all numbers (identifiers, prices) were modified by the source to protect the privacy of the users and the retailer.
+
+A directed edge from a session to an item is a click on the item during the session, or a purchase of it (edge property `buy`). The network is a multigraph, since items are often clicked several times in a session. Sessions are not linked to persistent users. It combines the three files of the challenge: the clicks of the training sessions (`yoochoose-clicks.dat`, 33.0 million clicks), the purchases of these sessions (`yoochoose-buys.dat`, 1.15 million purchases; most training sessions have none), and the clicks of the test sessions (`yoochoose-test.dat`, 8.3 million clicks, marked by the edge property `test`), whose purchases are not given.
+
+The network has the following properties:
+
+- `is_session`: whether the node is a session (otherwise it is an item).
+- `id`: the identifier of the session or item.
+- Edge `time`: the time of the click or purchase, as Unix time (with milliseconds).
+- Edge `buy`: whether the edge is a purchase (otherwise it is a click).
+- Edge `test`: whether the session is one of the test sessions of the challenge.
+- Edge `category` (clicks): the context of the click: 0 if missing, 1 to 12 for one of the categories of the shop, or the 8-10 digit identifier of a brand (-1 for special offers, and for purchases).
+- Edge `special_offer` (clicks): whether the item was clicked in the context of a special offer or promotion.
+- Edge `price` (purchases): the price of the item (modified by the source; -1 for clicks; 0 for 610,030 of the 1,150,753 purchases, whose price and quantity are not given).
+- Edge `quantity` (purchases): the number of items bought (-1 for clicks; 0 where not given)."""
+tags = ['Economic', 'Commerce', 'Bipartite', 'Multigraph', 'Timestamps', 'Metadata']
+url = ['https://recsys.acm.org/recsys15/challenge/',
+       'https://s3-eu-west-1.amazonaws.com/yc-rdata/yoochoose-data.7z']
+citation = [('D. Ben-Shimon, A. Tsikinovsky, M. Friedmann, B. Shapira, L. Rokach, J. Hoerle, "RecSys Challenge 2015 and the YOOCHOOSE Dataset." Proceedings of the 9th ACM Conference on Recommender Systems, 357-358 (2015)',
+             'https://doi.org/10.1145/2792838.2798723')]
+icon_hash = None
+upstream_license = ('CC BY-NC-ND 4.0', 'https://creativecommons.org/licenses/by-nc-nd/4.0/')
+upstream_prefix = 'https://s3-eu-west-1.amazonaws.com/yc-rdata'
+files = [(('yoochoose-data.7z:yoochoose-clicks.dat',
+           'yoochoose-data.7z:yoochoose-buys.dat',
+           'yoochoose-data.7z:yoochoose-test.dat'), None, None)]
+
+def fetch_upstream(force=False):
+    return fetch_upstream_files(__name__.split(".")[-1], upstream_prefix, files,
+                                force, check=False)
+
+# For checks only: if set, only (about) this many records of each file are read
+_check_rows = None
+
+def read(name, fname, cols, types):
+    "The table of the CSV file `fname` (without header)."
+    batches = []
+    n = 0
+    with open_upstream_file(name, fname, "rb") as f:
+        reader = pyarrow.csv.open_csv(
+            f, read_options=pyarrow.csv.ReadOptions(column_names=cols,
+                                                    block_size=1 << 26),
+            convert_options=pyarrow.csv.ConvertOptions(column_types=types))
+        for b in reader:
+            if _check_rows is not None and n >= _check_rows:
+                break
+            n += b.num_rows
+            batches.append(b)
+    return pyarrow.Table.from_batches(batches)
+
+def to_time(ts):
+    "Unix time (with milliseconds) of the timestamps 2014-04-07T10:51:09.277Z."
+    t = pc.strptime(pc.utf8_slice_codeunits(ts, 0, 19), format="%Y-%m-%dT%H:%M:%S",
+                    unit="s").cast(pyarrow.int64()).to_numpy()
+    ms = pc.cast(pc.utf8_slice_codeunits(ts, 20, 23), pyarrow.int64()).to_numpy()
+    return t + ms / 1000
+
+@cache_network()
+@coerce_props()
+@annotate()
+def parse(alts=None):
+    name = __name__.split(".")[-1]
+    for fnames, alt, fmt in files:
+        if alts is not None and alt not in alts:
+            continue
+        ctypes = {"session": pyarrow.int64(), "time": pyarrow.string(),
+                  "item": pyarrow.int64(), "category": pyarrow.string()}
+        clicks = read(name, fnames[0], list(ctypes), ctypes)
+        test = read(name, fnames[2], list(ctypes), ctypes)
+        btypes = {"session": pyarrow.int64(), "time": pyarrow.string(),
+                  "item": pyarrow.int64(), "price": pyarrow.int64(),
+                  "quantity": pyarrow.int64()}
+        buys = read(name, fnames[1], list(btypes), btypes)
+
+        parts = [clicks, buys, test]
+        sess = numpy.unique(numpy.concatenate([p["session"].to_numpy() for p in parts]))
+        items = numpy.unique(numpy.concatenate([p["item"].to_numpy() for p in parts]))
+        S = len(sess)
+        g = Graph(directed=True)
+        g.add_vertex(S + len(items))
+        g.vp.is_session = g.new_vp("bool")
+        g.vp.is_session.a[:S] = 1
+        g.vp.id = g.new_vp("int64_t")
+        g.vp.id.a[:S] = sess
+        g.vp.id.a[S:] = items
+
+        time, buy, istest, cat, special, price, qty = [], [], [], [], [], [], []
+        for i, p in enumerate(parts):
+            n = len(p)
+            g.add_edge_list(numpy.column_stack(
+                (numpy.searchsorted(sess, p["session"].to_numpy()),
+                 S + numpy.searchsorted(items, p["item"].to_numpy()))))
+            time.append(to_time(p["time"]))
+            buy.append(numpy.full(n, i == 1))
+            istest.append(numpy.full(n, i == 2))
+            if i == 1:
+                cat.append(numpy.full(n, -1, dtype="int64"))
+                special.append(numpy.zeros(n, dtype="bool"))
+                price.append(p["price"].to_numpy())
+                qty.append(p["quantity"].to_numpy())
+            else:
+                c = p["category"]
+                s = pc.equal(c, "S")
+                special.append(s.to_numpy(zero_copy_only=False))
+                cat.append(pc.cast(pc.if_else(s, "-1", c), pyarrow.int64()).to_numpy())
+                price.append(numpy.full(n, -1, dtype="int64"))
+                qty.append(numpy.full(n, -1, dtype="int64"))
+        del parts, clicks, buys, test
+        g.ep.time = g.new_ep("double", vals=numpy.concatenate(time))
+        g.ep.buy = g.new_ep("bool", vals=numpy.concatenate(buy))
+        g.ep.test = g.new_ep("bool", vals=numpy.concatenate(istest))
+        g.ep.category = g.new_ep("int64_t", vals=numpy.concatenate(cat))
+        g.ep.special_offer = g.new_ep("bool", vals=numpy.concatenate(special))
+        g.ep.price = g.new_ep("int64_t", vals=numpy.concatenate(price))
+        g.ep.quantity = g.new_ep("int64_t", vals=numpy.concatenate(qty))
+        yield alt, g