From 8662e64e4627a9e23247e96d757947b99a0a7efd Mon Sep 17 00:00:00 2001
From: Alessio Buccino <alejoe9187@gmail.com>
Date: Thu, 24 Sep 2026 14:37:39 +0200
Subject: [PATCH 01/15] wip

---
 src/spikeinterface/core/basesorting.py     |  2 +
 src/spikeinterface/core/binaryfolder.py    |  4 +-
 src/spikeinterface/core/core_tools.py      |  4 +-
 src/spikeinterface/core/sortinganalyzer.py | 77 ++++++++--------------
 src/spikeinterface/core/sortingfolder.py   | 15 +++--
 src/spikeinterface/core/zarrextractors.py  | 23 +++++--
 6 files changed, 65 insertions(+), 60 deletions(-)

diff --git a/src/spikeinterface/core/basesorting.py b/src/spikeinterface/core/basesorting.py
index 1e136f2dff..93a249bf93 100644
--- a/src/spikeinterface/core/basesorting.py
+++ b/src/spikeinterface/core/basesorting.py
@@ -535,6 +535,8 @@ def save(self, format="numpy_folder", **save_kwargs):
             * "numpy_folder" format:
                 - folder : str or Path
                     The folder where the files will be saved.
+                - mmap_mode : str or None, default: None
+                    The memory-mapping mode to use when saving numpy files. If None, no memory mapping is used.
                 - overwrite : bool, default: False
                     If True, existing files in the folder will be overwritten.
             * "zarr" format:
diff --git a/src/spikeinterface/core/binaryfolder.py b/src/spikeinterface/core/binaryfolder.py
index c0090719ca..c3c4e07cb8 100644
--- a/src/spikeinterface/core/binaryfolder.py
+++ b/src/spikeinterface/core/binaryfolder.py
@@ -15,7 +15,7 @@
     make_paths_absolute,
     load_properties_from_folder,
     save_properties_to_folder,
-    save_extractor_provenance,
+    save_provenance_to_folder,
     save_annotations_to_folder,
     load_annotations_from_folder,
 )
@@ -160,7 +160,7 @@ def write_recording(
         )
 
         save_properties_to_folder(folder_path / "properties", recording)
-        save_extractor_provenance(folder_path, recording)
+        save_provenance_to_folder(folder_path, recording, relative_to=folder_path)
         # new in version 0.105.0, before that annotations were handle by "si_folder.json" file
         save_annotations_to_folder(folder_path, recording)
 
diff --git a/src/spikeinterface/core/core_tools.py b/src/spikeinterface/core/core_tools.py
index b5ee518208..25e1da5e93 100644
--- a/src/spikeinterface/core/core_tools.py
+++ b/src/spikeinterface/core/core_tools.py
@@ -934,11 +934,11 @@ def load_annotations_from_folder(folder: str | Path, extractor: "BaseExtractor")
                 extractor._annotations.update(annotations)
 
 
-def save_extractor_provenance(folder: str | Path, extractor: "BaseExtractor"):
+def save_provenance_to_folder(folder: str | Path, extractor: "BaseExtractor", relative_to: str | Path | None = None):
     folder = Path(folder)
     if extractor.check_serializability("json"):
         provenance_file_path = folder / f"provenance.json"
-        extractor.dump_to_json(file_path=provenance_file_path, relative_to=folder)
+        extractor.dump_to_json(file_path=provenance_file_path, relative_to=relative_to)
     elif extractor.check_serializability("pickle"):
         provenance_file = folder / f"provenance.pkl"
         extractor.dump_to_pickle(provenance_file, relative_to=folder)
diff --git a/src/spikeinterface/core/sortinganalyzer.py b/src/spikeinterface/core/sortinganalyzer.py
index 953f75259d..62d84dd465 100644
--- a/src/spikeinterface/core/sortinganalyzer.py
+++ b/src/spikeinterface/core/sortinganalyzer.py
@@ -714,7 +714,6 @@ def create_binary_folder(
         info_file = folder / "spikeinterface_info.json"
         settings_file = folder / "settings.json"
         sorting_folder = folder / "sorting"
-        sorting_provenance_file = folder / "sorting_provenance.json"
         sparsity_file = folder / "sparsity_mask.npy"
         recording_provenance_file = folder / "recording"  # .json (default) or .pickle (if not json-serializable)
         rec_attributes_file = recording_info_folder / "recording_attributes.json"
@@ -731,17 +730,7 @@ def create_binary_folder(
             json.dump(check_json(settings), f, indent=4)
 
         # Save the sorting output
-        sorting = sorting.save(folder=sorting_folder)
-
-        # Dump sorting provenance
-        if sorting.check_serializability("json"):
-            sorting.dump(sorting_provenance_file, relative_to=folder)
-        elif sorting.check_serializability("pickle"):
-            sorting.dump(sorting_provenance_file.with_suffix(".pickle"), relative_to=folder)
-        else:
-            warnings.warn(
-                "The sorting provenance is not serializable! The sorting provenance link will be lost for future load"
-            )
+        _ = sorting.save(folder=sorting_folder, relative_to=folder)
 
         # Save sparsity
         if sparsity is not None:
@@ -1071,27 +1060,9 @@ def create_zarr(
         settings = {"return_in_uV": return_in_uV, "peak_sign": peak_sign, "peak_mode": peak_mode}
         zarr_root.attrs["settings"] = check_json(settings)
 
-        # Save the sorting output
-        add_sorting_to_zarr_group(sorting, sorting_group, **saving_options)
-
-        # Dump sorting provenance
         relative_to = None if is_remote else folder
-        sort_dict = sorting.to_dict(relative_to=relative_to, recursive=True)
-        if sorting.check_serializability("json"):
-            _write_object_array(zarr_root, "sorting_provenance", check_json(sort_dict), codec="json")
-        elif sorting.check_serializability("pickle"):
-            try:
-                _write_object_array(zarr_root, "sorting_provenance", sort_dict, codec="pickle")
-            except:
-                warnings.warn(
-                    "Failed to serialize sorting provenance with Pickle Codec! "
-                    "The sorting provenance link will be lost for future load"
-                )
-        else:
-            warnings.warn(
-                "The sorting provenance is not serializable! "
-                "The sorting provenance link will be lost for future load"
-            )
+        # Save the sorting output
+        add_sorting_to_zarr_group(sorting, sorting_group, relative_to=folder, **saving_options)
 
         # Save sparsity
         if sparsity is not None:
@@ -1135,7 +1106,7 @@ def create_zarr(
 
         # Create SortingAnalyzer
         sorting_analyzer = SortingAnalyzer(
-            sorting=NumpySorting.from_sorting(sorting, with_metadata=True, copy_spike_vector=True),
+            sorting=sorting,
             recording=recording,
             rec_attributes={**rec_attributes_to_save, "probegroup": probegroup},
             format="zarr",
@@ -2006,9 +1977,12 @@ def merge_units(
 
             mergeable_unit_groups = []
             unmergeable_unit_groups = []
-            for merge_unit_group, mergeable in zip(merge_unit_groups, mergeable.values()):
+            new_unit_ids_mergeable = [] if new_unit_ids is not None else None
+            for i, (merge_unit_group, mergeable) in enumerate(zip(merge_unit_groups, mergeable.values())):
                 if mergeable:
                     mergeable_unit_groups.append(merge_unit_group)
+                    if new_unit_ids_mergeable is not None:
+                        new_unit_ids_mergeable.append(new_unit_ids[i])
                 else:
                     unmergeable_unit_groups.append(merge_unit_group)
 
@@ -2021,9 +1995,14 @@ def merge_units(
                     warnings.warn(warning_message)
         else:
             mergeable_unit_groups = merge_unit_groups
+            new_unit_ids_mergeable = new_unit_ids
+
+        if len(mergeable_unit_groups) == 0:
+            warnings.warn("No mergeable unit groups found.")
+            return self if not return_new_unit_ids else (self, [])
 
         new_unit_ids = generate_unit_ids_for_merge_group(
-            self.unit_ids, mergeable_unit_groups, new_unit_ids, new_id_strategy
+            self.unit_ids, mergeable_unit_groups, new_unit_ids_mergeable, new_id_strategy
         )
         all_unit_ids = _get_ids_after_merging(self.unit_ids, mergeable_unit_groups, new_unit_ids=new_unit_ids)
 
@@ -2175,34 +2154,36 @@ def get_sorting_provenance(self):
         """
         from .loading import load
 
+        sorting_provenance = None
         if self.format == "memory":
             # the original sorting provenance is not kept in that case
-            sorting_provenance = None
-
+            pass
         elif self.format == "binary_folder":
             for type in ("json", "pickle"):
-                filename = self.folder / f"sorting_provenance.{type}"
+                filename = self.folder / "sorting" / f"provenance.{type}"
                 sorting_provenance = None
+                if not filename.is_file():
+                    # Legacy location
+                    filename = self.folder / "sorting_provenance.json"
+                # try-except here is because it's not required to be able
+                # to load the sorting provenance, as the user might have deleted
+                # the original sorting folder
                 if filename.is_file():
-                    # try-except here is because it's not required to be able
-                    # to load the sorting provenance, as the user might have deleted
-                    # the original sorting folder
                     try:
                         sorting_provenance = load(filename, base_folder=self.folder)
                         break
                     except:
                         pass
-                        # sorting_provenance = None
-
         elif self.format == "zarr":
             zarr_root = self._get_zarr_root(mode="r")
             sorting_provenance = None
-            if "sorting_provenance" in zarr_root.keys():
-                # try-except here is because it's not required to be able
-                # to load the sorting provenance, as the user might have deleted
-                # the original sorting folder
-                try:
+            sort_dict = zarr_root["sorting"].attrs.get("provenance", None)
+            if sort_dict is None:
+                # Legacy
+                if "sorting_provenance" in zarr_root.keys():
                     sort_dict = zarr_root["sorting_provenance"][0]
+            if sort_dict is not None:
+                try:
                     sorting_provenance = load(sort_dict, base_folder=self.folder)
                 except:
                     pass
diff --git a/src/spikeinterface/core/sortingfolder.py b/src/spikeinterface/core/sortingfolder.py
index 3a068e0384..fefe5c1229 100644
--- a/src/spikeinterface/core/sortingfolder.py
+++ b/src/spikeinterface/core/sortingfolder.py
@@ -15,7 +15,7 @@
     save_properties_to_folder,
     save_annotations_to_folder,
     load_annotations_from_folder,
-    save_extractor_provenance,
+    save_provenance_to_folder,
 )
 
 
@@ -61,7 +61,13 @@ def __init__(self, folder_path, mmap_mode: str | None = None):
         self._kwargs = dict(folder_path=str(folder_path.absolute()), mmap_mode=mmap_mode)
 
     @staticmethod
-    def write_sorting(sorting, folder_path, overwrite: bool = False):
+    def write_sorting(
+        sorting,
+        folder_path,
+        overwrite: bool = False,
+        mmap_mode: str | None = None,
+        relative_to: str | Path | None = None,
+    ):
         # the folder can already exists but not contaning numpysorting_info.json
         folder_path = Path(folder_path)
         if folder_path.is_dir():
@@ -81,14 +87,15 @@ def write_sorting(sorting, folder_path, overwrite: bool = False):
         np.save(folder_path / "spikes.npy", sorting.to_spike_vector())
 
         save_properties_to_folder(folder_path / "properties", sorting)
-        save_extractor_provenance(folder_path, sorting)
+        relative_to = folder_path if relative_to is None else relative_to
+        save_provenance_to_folder(folder_path, sorting, relative_to=relative_to)
         # new in version 0.105.0, before that annotations were handle by "si_folder.json" file
         save_annotations_to_folder(folder_path, sorting)
 
         # Create the si_folder file to make the load() easier until version 0.105.0
         # All properties, annotations, and probe information are already saved in the folder,
         # so we don't need to include them in the si_folder.json
-        cached = NumpyFolderSorting(folder_path=folder_path)
+        cached = NumpyFolderSorting(folder_path=folder_path, mmap_mode=mmap_mode)
         si_folder_path = folder_path / f"si_folder.json"
         cached.dump_to_json(
             file_path=si_folder_path,
diff --git a/src/spikeinterface/core/zarrextractors.py b/src/spikeinterface/core/zarrextractors.py
index 448dbd94a7..27451bda2a 100644
--- a/src/spikeinterface/core/zarrextractors.py
+++ b/src/spikeinterface/core/zarrextractors.py
@@ -559,6 +559,7 @@ def write_sorting(
         folder_path: str | Path,
         overwrite: bool = False,
         storage_options: dict | None = None,
+        relative_to: str | Path | None = None,
         **kwargs,
     ):
         """
@@ -567,7 +568,7 @@ def write_sorting(
         folder_path = create_zarr_path_for_write(folder_path, overwrite=overwrite)
         zarr_root = zarr.open(str(folder_path), mode="w", storage_options=storage_options)
         zarr_root.attrs["zarr_class_info"] = retrieve_importing_provenance(ZarrSortingExtractor)
-        add_sorting_to_zarr_group(sorting, zarr_root, **kwargs)
+        add_sorting_to_zarr_group(sorting, zarr_root, relative_to=relative_to, **kwargs)
         return ZarrSortingExtractor(folder_path, storage_options=storage_options)
 
 
@@ -734,7 +735,9 @@ def add_properties_and_annotations(zarr_group: zarr.Group, recording_or_sorting:
     zarr_group.attrs["annotations"] = check_json(recording_or_sorting._annotations)
 
 
-def add_sorting_to_zarr_group(sorting: BaseSorting, zarr_group: zarr.Group, **kwargs):
+def add_sorting_to_zarr_group(
+    sorting: BaseSorting, zarr_group: zarr.Group, relative_to: str | Path | None = None, **kwargs
+):
     """
     Add a sorting extractor to a zarr group.
 
@@ -749,6 +752,11 @@ def add_sorting_to_zarr_group(sorting: BaseSorting, zarr_group: zarr.Group, **kw
     """
     from numcodecs import Delta
 
+    if sorting.check_serializability("json"):
+        zarr_group.attrs["provenance"] = check_json(sorting.to_dict(recursive=True, relative_to=relative_to))
+    else:
+        zarr_group.attrs["provenance"] = None
+
     num_segments = sorting.get_num_segments()
     zarr_group.attrs["sampling_frequency"] = float(sorting.sampling_frequency)
     zarr_group.attrs["num_segments"] = int(num_segments)
@@ -777,11 +785,18 @@ def add_sorting_to_zarr_group(sorting: BaseSorting, zarr_group: zarr.Group, **kw
     add_properties_and_annotations(zarr_group, sorting)
 
 
-def add_recording_to_zarr_group(recording: BaseRecording, zarr_group: zarr.Group, verbose=False, dtype=None, **kwargs):
+def add_recording_to_zarr_group(
+    recording: BaseRecording,
+    zarr_group: zarr.Group,
+    verbose=False,
+    dtype=None,
+    relative_to: str | Path | None = None,
+    **kwargs,
+):
     zarr_kwargs, job_kwargs = split_job_kwargs(kwargs)
 
     if recording.check_serializability("json"):
-        zarr_group.attrs["provenance"] = check_json(recording.to_dict(recursive=True))
+        zarr_group.attrs["provenance"] = check_json(recording.to_dict(recursive=True, relative_to=relative_to))
     else:
         zarr_group.attrs["provenance"] = None
 

From 3962ffbd06d04b37805cde4da953a4f3fbbe6163 Mon Sep 17 00:00:00 2001
From: Alessio Buccino <alejoe9187@gmail.com>
Date: Thu, 24 Sep 2026 14:39:07 +0200
Subject: [PATCH 02/15] revert merge changes

---
 src/spikeinterface/core/sortinganalyzer.py | 12 ++----------
 1 file changed, 2 insertions(+), 10 deletions(-)

diff --git a/src/spikeinterface/core/sortinganalyzer.py b/src/spikeinterface/core/sortinganalyzer.py
index 62d84dd465..fab0a2451e 100644
--- a/src/spikeinterface/core/sortinganalyzer.py
+++ b/src/spikeinterface/core/sortinganalyzer.py
@@ -1977,12 +1977,9 @@ def merge_units(
 
             mergeable_unit_groups = []
             unmergeable_unit_groups = []
-            new_unit_ids_mergeable = [] if new_unit_ids is not None else None
-            for i, (merge_unit_group, mergeable) in enumerate(zip(merge_unit_groups, mergeable.values())):
+            for merge_unit_group, mergeable in zip(merge_unit_groups, mergeable.values()):
                 if mergeable:
                     mergeable_unit_groups.append(merge_unit_group)
-                    if new_unit_ids_mergeable is not None:
-                        new_unit_ids_mergeable.append(new_unit_ids[i])
                 else:
                     unmergeable_unit_groups.append(merge_unit_group)
 
@@ -1995,14 +1992,9 @@ def merge_units(
                     warnings.warn(warning_message)
         else:
             mergeable_unit_groups = merge_unit_groups
-            new_unit_ids_mergeable = new_unit_ids
-
-        if len(mergeable_unit_groups) == 0:
-            warnings.warn("No mergeable unit groups found.")
-            return self if not return_new_unit_ids else (self, [])
 
         new_unit_ids = generate_unit_ids_for_merge_group(
-            self.unit_ids, mergeable_unit_groups, new_unit_ids_mergeable, new_id_strategy
+            self.unit_ids, mergeable_unit_groups, new_unit_ids, new_id_strategy
         )
         all_unit_ids = _get_ids_after_merging(self.unit_ids, mergeable_unit_groups, new_unit_ids=new_unit_ids)
 

From 5be6690562ce61f9baefea21bfbbb973080b6839 Mon Sep 17 00:00:00 2001
From: Alessio Buccino <alejoe9187@gmail.com>
Date: Thu, 24 Sep 2026 14:54:58 +0200
Subject: [PATCH 03/15] fix: add warnigns in zarr when provenance is not JSON
 serializable

---
 src/spikeinterface/core/zarrextractors.py | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/src/spikeinterface/core/zarrextractors.py b/src/spikeinterface/core/zarrextractors.py
index 27451bda2a..1ad57db992 100644
--- a/src/spikeinterface/core/zarrextractors.py
+++ b/src/spikeinterface/core/zarrextractors.py
@@ -755,6 +755,9 @@ def add_sorting_to_zarr_group(
     if sorting.check_serializability("json"):
         zarr_group.attrs["provenance"] = check_json(sorting.to_dict(recursive=True, relative_to=relative_to))
     else:
+        warnings.warn(
+            "The sorting provenance is not serializable! " "The sorting provenance link will be lost for future load"
+        )
         zarr_group.attrs["provenance"] = None
 
     num_segments = sorting.get_num_segments()
@@ -798,6 +801,10 @@ def add_recording_to_zarr_group(
     if recording.check_serializability("json"):
         zarr_group.attrs["provenance"] = check_json(recording.to_dict(recursive=True, relative_to=relative_to))
     else:
+        warnings.warn(
+            "The recording provenance is not serializable! "
+            "The recording provenance link will be lost for future load"
+        )
         zarr_group.attrs["provenance"] = None
 
     # save data (done the subclass)

From df58f4679d75db4467a49892fbbe76a4f7037f5c Mon Sep 17 00:00:00 2001
From: Alessio Buccino <alejoe9187@gmail.com>
Date: Fri, 25 Sep 2026 14:57:24 +0200
Subject: [PATCH 04/15] fix: add copy method to ZarrSpikeVector

---
 src/spikeinterface/core/zarrextractors.py | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/src/spikeinterface/core/zarrextractors.py b/src/spikeinterface/core/zarrextractors.py
index 1ad57db992..ea4d0d2566 100644
--- a/src/spikeinterface/core/zarrextractors.py
+++ b/src/spikeinterface/core/zarrextractors.py
@@ -453,6 +453,9 @@ def __array__(self, dtype=None):
             arr["segment_index"][s0:s1] = seg_idx
         return arr if dtype is None else arr.astype(dtype)
 
+    def copy(self):
+        return np.copy(np.asarray(self))
+
 
 class ZarrSortingExtractor(BaseSorting):
     """

From 87b4ef4b24f648a2fd4c8d981d096cdbe7d31fa7 Mon Sep 17 00:00:00 2001
From: Alessio Buccino <alejoe9187@gmail.com>
Date: Mon, 28 Sep 2026 12:45:16 +0200
Subject: [PATCH 05/15] fix: use cached sorting and make NumpySorting not
 pickle-serializable

---
 src/spikeinterface/core/numpyextractors.py |  3 +--
 src/spikeinterface/core/sortinganalyzer.py | 12 ++++++------
 2 files changed, 7 insertions(+), 8 deletions(-)

diff --git a/src/spikeinterface/core/numpyextractors.py b/src/spikeinterface/core/numpyextractors.py
index b58a98eddb..e2c2df6280 100644
--- a/src/spikeinterface/core/numpyextractors.py
+++ b/src/spikeinterface/core/numpyextractors.py
@@ -276,8 +276,7 @@ def __init__(self, spikes, sampling_frequency, unit_ids):
 
         self._serializability["memory"] = True
         self._serializability["json"] = False
-        # theorically this should be False but for simplicity make generators simples we still need this.
-        self._serializability["pickle"] = True
+        self._serializability["pickle"] = False
 
         if spikes.size == 0:
             nseg = 1
diff --git a/src/spikeinterface/core/sortinganalyzer.py b/src/spikeinterface/core/sortinganalyzer.py
index fab0a2451e..59ae9ed7d2 100644
--- a/src/spikeinterface/core/sortinganalyzer.py
+++ b/src/spikeinterface/core/sortinganalyzer.py
@@ -730,7 +730,8 @@ def create_binary_folder(
             json.dump(check_json(settings), f, indent=4)
 
         # Save the sorting output
-        _ = sorting.save(folder=sorting_folder, relative_to=folder)
+        mmap_mode = "r" if lazy else None
+        sorting_cached = sorting.save(folder=sorting_folder, relative_to=folder, mmap_mode=mmap_mode)
 
         # Save sparsity
         if sparsity is not None:
@@ -765,7 +766,7 @@ def create_binary_folder(
 
         # Create SortingAnalyzer
         sorting_analyzer = SortingAnalyzer(
-            sorting=sorting,
+            sorting=sorting_cached,
             recording=recording,
             rec_attributes={**rec_attributes_to_save, "probegroup": probegroup},
             format="binary_folder",
@@ -1031,9 +1032,7 @@ def create_zarr(
         backend_options: dict | None,
         lazy: bool = False,
     ) -> "SortingAnalyzer":
-        # used by create and save_as
-
-        from .zarrextractors import add_sorting_to_zarr_group
+        from .zarrextractors import add_sorting_to_zarr_group, ZarrSortingExtractor
 
         is_remote = is_path_remote(folder)
         if not is_remote:
@@ -1063,6 +1062,7 @@ def create_zarr(
         relative_to = None if is_remote else folder
         # Save the sorting output
         add_sorting_to_zarr_group(sorting, sorting_group, relative_to=folder, **saving_options)
+        sorting_cached = ZarrSortingExtractor(folder / "sorting", lazy_spike_vector=lazy)
 
         # Save sparsity
         if sparsity is not None:
@@ -1106,7 +1106,7 @@ def create_zarr(
 
         # Create SortingAnalyzer
         sorting_analyzer = SortingAnalyzer(
-            sorting=sorting,
+            sorting=sorting_cached,
             recording=recording,
             rec_attributes={**rec_attributes_to_save, "probegroup": probegroup},
             format="zarr",

From 82b894cbc7bd43914cf96b30a4d3b8def6103d3c Mon Sep 17 00:00:00 2001
From: Alessio Buccino <alejoe9187@gmail.com>
Date: Mon, 28 Sep 2026 13:01:09 +0200
Subject: [PATCH 06/15] fix: tests

---
 src/spikeinterface/core/tests/test_sortinganalyzer.py | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/src/spikeinterface/core/tests/test_sortinganalyzer.py b/src/spikeinterface/core/tests/test_sortinganalyzer.py
index 8cc069ce1e..88bbb13c75 100644
--- a/src/spikeinterface/core/tests/test_sortinganalyzer.py
+++ b/src/spikeinterface/core/tests/test_sortinganalyzer.py
@@ -92,6 +92,7 @@ def test_SortingAnalyzer_memory(tmp_path, dataset):
 
 def test_SortingAnalyzer_binary_folder(tmp_path, dataset):
     recording, sorting = dataset
+    recording = recording.save(folder=tmp_path / "recording_binary")
 
     folder = tmp_path / "test_SortingAnalyzer_binary_folder"
     if folder.exists():
@@ -138,6 +139,7 @@ def test_SortingAnalyzer_binary_folder(tmp_path, dataset):
 
 def test_SortingAnalyzer_zarr(tmp_path, dataset):
     recording, sorting = dataset
+    recording = recording.save(folder=tmp_path / "recording_zarr")
 
     folder = tmp_path / "test_SortingAnalyzer_zarr.zarr"
 

From a9fd1ba5b803ec0771b2f8a7be5c9b2e93de51cd Mon Sep 17 00:00:00 2001
From: Alessio Buccino <alejoe9187@gmail.com>
Date: Mon, 28 Sep 2026 14:29:37 +0200
Subject: [PATCH 07/15] fix: preprocessing pipeline tests

---
 src/spikeinterface/preprocessing/tests/test_pipeline.py | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/src/spikeinterface/preprocessing/tests/test_pipeline.py b/src/spikeinterface/preprocessing/tests/test_pipeline.py
index 5f5c298430..4a62bc0088 100644
--- a/src/spikeinterface/preprocessing/tests/test_pipeline.py
+++ b/src/spikeinterface/preprocessing/tests/test_pipeline.py
@@ -169,6 +169,7 @@ def test_loading_provenance(create_cache_folder):
     cache_folder = create_cache_folder / "preprocessed_rec_for_pipeline"
 
     rec, _ = generate_ground_truth_recording(seed=0, num_channels=6)
+    rec = rec.save(folder=cache_folder / "recording_provenance")
     pp_rec = detect_and_remove_bad_channels(
         bandpass_filter(common_reference(rec, operator="average")),
         noisy_channel_threshold=0.3,
@@ -176,9 +177,9 @@ def test_loading_provenance(create_cache_folder):
         # when several run
         seed=2205,
     )
-    pp_rec.save(folder=cache_folder)
+    pp_rec.save(folder=cache_folder / "preprocessed_recording")
 
-    loaded_pp_list = get_preprocessing_list_from_file(cache_folder / "provenance.pkl")
+    loaded_pp_list = get_preprocessing_list_from_file(cache_folder / "preprocessed_recording" / "provenance.json")
 
     pipeline_rec_applying_precomputed_kwargs = apply_preprocessing_pipeline(
         rec,
@@ -204,6 +205,7 @@ def test_loading_from_analyzer(create_cache_folder):
 
     cache_folder = create_cache_folder
     recording, sorting = generate_ground_truth_recording()
+    recording = recording.save(folder=cache_folder / "recording")
 
     preprocessing_dict = {"common_reference": {}, "highpass_filter": {"freq_min": 301.0}}
     pp_recording = apply_preprocessing_pipeline(recording, preprocessing_dict)

From 48d829016da88d8f07845592a6990adbb88d6ae3 Mon Sep 17 00:00:00 2001
From: Alessio Buccino <alejoe9187@gmail.com>
Date: Mon, 28 Sep 2026 14:54:58 +0200
Subject: [PATCH 08/15] fix: postprocessing tests pickle failures

---
 .../postprocessing/tests/test_multi_extensions.py  | 14 ++++++++------
 1 file changed, 8 insertions(+), 6 deletions(-)

diff --git a/src/spikeinterface/postprocessing/tests/test_multi_extensions.py b/src/spikeinterface/postprocessing/tests/test_multi_extensions.py
index 1bb3d383a2..7b53f24f29 100644
--- a/src/spikeinterface/postprocessing/tests/test_multi_extensions.py
+++ b/src/spikeinterface/postprocessing/tests/test_multi_extensions.py
@@ -69,7 +69,7 @@
 }
 
 
-def get_dataset_to_merge():
+def get_dataset_to_merge(cache_folder):
     # generate a dataset with some split units to minimize merge errors
     recording, sorting = generate_ground_truth_recording(
         durations=[30.0],
@@ -81,6 +81,7 @@ def get_dataset_to_merge():
         generate_unit_locations_kwargs=dict(margin_um=10.0, minimum_z=2.0, maximum_z=15.0, minimum_distance=20),
         seed=2205,
     )
+    recording = recording.save(folder=cache_folder / "recording_merge")
 
     # since templates are going to be averaged and this might be a problem for amplitude scaling
     # we select the 3 units with the largest templates to split
@@ -96,7 +97,7 @@ def get_dataset_to_merge():
     return recording, sorting_with_splits, split_unit_ids
 
 
-def get_dataset_to_split():
+def get_dataset_to_split(cache_folder):
     # generate a dataset and return large unit to split to minimize split errors
     recording, sorting = generate_ground_truth_recording(
         durations=[30.0],
@@ -107,6 +108,7 @@ def get_dataset_to_split():
         noise_kwargs=dict(noise_levels=5.0, strategy="tile_pregenerated"),
         seed=2205,
     )
+    recording = recording.save(folder=cache_folder / "recording_split")
 
     # since templates are going to be averaged and this might be a problem for amplitude scaling
     # we select the 3 units with the largest templates to split
@@ -120,13 +122,13 @@ def get_dataset_to_split():
 
 
 @pytest.fixture(scope="module")
-def dataset_to_merge():
-    return get_dataset_to_merge()
+def dataset_to_merge(create_cache_folder):
+    return get_dataset_to_merge(create_cache_folder)
 
 
 @pytest.fixture(scope="module")
-def dataset_to_split():
-    return get_dataset_to_split()
+def dataset_to_split(create_cache_folder):
+    return get_dataset_to_split(create_cache_folder)
 
 
 @pytest.mark.parametrize("lazy", [False, True])

From ae8a94d89d3658afce41a391f36c8ca349bc06cb Mon Sep 17 00:00:00 2001
From: Alessio Buccino <alejoe9187@gmail.com>
Date: Mon, 28 Sep 2026 15:14:15 +0200
Subject: [PATCH 09/15] Apply suggestion from @alejoe91

---
 src/spikeinterface/core/zarrextractors.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/src/spikeinterface/core/zarrextractors.py b/src/spikeinterface/core/zarrextractors.py
index ea4d0d2566..4be7c0d3d6 100644
--- a/src/spikeinterface/core/zarrextractors.py
+++ b/src/spikeinterface/core/zarrextractors.py
@@ -759,7 +759,7 @@ def add_sorting_to_zarr_group(
         zarr_group.attrs["provenance"] = check_json(sorting.to_dict(recursive=True, relative_to=relative_to))
     else:
         warnings.warn(
-            "The sorting provenance is not serializable! " "The sorting provenance link will be lost for future load"
+            "The sorting provenance is not serializable! The sorting provenance link will be lost for future load"
         )
         zarr_group.attrs["provenance"] = None
 

From 9c1f17d8293e06bc814a0ef1c6c2be1d3ebf9111 Mon Sep 17 00:00:00 2001
From: Alessio Buccino <alejoe9187@gmail.com>
Date: Mon, 28 Sep 2026 15:59:35 +0200
Subject: [PATCH 10/15] fix: pickling error in metrics

---
 src/spikeinterface/metrics/conftest.py | 10 ++++++----
 1 file changed, 6 insertions(+), 4 deletions(-)

diff --git a/src/spikeinterface/metrics/conftest.py b/src/spikeinterface/metrics/conftest.py
index aefe2e6cfe..9c495cd36f 100644
--- a/src/spikeinterface/metrics/conftest.py
+++ b/src/spikeinterface/metrics/conftest.py
@@ -8,12 +8,13 @@
 job_kwargs = dict(n_jobs=2, progress_bar=True, chunk_duration="1s")
 
 
-def make_small_analyzer():
+def make_small_analyzer(folder):
     recording, sorting = generate_ground_truth_recording(
         durations=[10.0],
         num_units=10,
         seed=1205,
     )
+    recording = recording.save(folder=folder / "rec_for_small_analyzer", format="binary")
 
     sorting = sorting.select_units(["2", "7", "0"], ["#3", "#9", "#4"])
 
@@ -36,12 +37,12 @@ def make_small_analyzer():
 
 
 @pytest.fixture(scope="module")
-def small_sorting_analyzer():
-    return make_small_analyzer()
+def small_sorting_analyzer(create_cache_folder):
+    return make_small_analyzer(create_cache_folder)
 
 
 @pytest.fixture(scope="module")
-def sorting_analyzer_simple():
+def sorting_analyzer_simple(create_cache_folder):
     # we need high firing rate for amplitude_cutoff
     recording, sorting = generate_ground_truth_recording(
         durations=[
@@ -64,6 +65,7 @@ def sorting_analyzer_simple():
         noise_kwargs=dict(noise_levels=5.0, strategy="tile_pregenerated"),
         seed=1205,
     )
+    recording = recording.save(folder=create_cache_folder / "rec_for_sorting_analyzer_simple", format="binary")
 
     sorting_analyzer = create_sorting_analyzer(sorting, recording, format="memory", sparse=True)
 

From 8645dd0cdb6180056bc08beeb6fdcb26fa2d5a0a Mon Sep 17 00:00:00 2001
From: Alessio Buccino <alejoe9187@gmail.com>
Date: Mon, 28 Sep 2026 17:52:12 +0200
Subject: [PATCH 11/15] fix: tests

---
 src/spikeinterface/sorters/tests/test_runsorter.py         | 7 ++++---
 .../motion/tests/test_motion_interpolation.py              | 3 ++-
 2 files changed, 6 insertions(+), 4 deletions(-)

diff --git a/src/spikeinterface/sorters/tests/test_runsorter.py b/src/spikeinterface/sorters/tests/test_runsorter.py
index 332e6e857e..c07cd94c9b 100644
--- a/src/spikeinterface/sorters/tests/test_runsorter.py
+++ b/src/spikeinterface/sorters/tests/test_runsorter.py
@@ -13,14 +13,15 @@
 ON_GITHUB = bool(os.getenv("GITHUB_ACTIONS"))
 
 
-def _generate_recording():
+def _generate_recording(folder):
     recording, _ = generate_ground_truth_recording(num_channels=8, durations=[10.0], seed=2205)
+    recording = recording.save(folder=folder / "rec_for_generate_recording", format="binary")
     return recording
 
 
 @pytest.fixture(scope="module")
-def generate_recording():
-    return _generate_recording()
+def generate_recording(create_cache_folder):
+    return _generate_recording(create_cache_folder)
 
 
 @pytest.mark.xfail(
diff --git a/src/spikeinterface/sortingcomponents/motion/tests/test_motion_interpolation.py b/src/spikeinterface/sortingcomponents/motion/tests/test_motion_interpolation.py
index 9635bad48b..97558448f4 100644
--- a/src/spikeinterface/sortingcomponents/motion/tests/test_motion_interpolation.py
+++ b/src/spikeinterface/sortingcomponents/motion/tests/test_motion_interpolation.py
@@ -224,7 +224,7 @@ def test_cross_band_interpolation():
     assert np.array_equal(traces_corrected, target)
 
 
-def test_InterpolateMotionRecording():
+def test_InterpolateMotionRecording(create_cache_folder):
     # rec, sorting = make_dataset()
 
     # 2 segments
@@ -244,6 +244,7 @@ def test_InterpolateMotionRecording():
         noise_kwargs=dict(noise_levels=5.0, strategy="on_the_fly"),
         seed=2205,
     )
+    rec = rec.save(folder=create_cache_folder / "rec_for_test_interpolate_motion", format="binary")
 
     motion = make_fake_motion(rec)
 

From 790d530f7642510ff2932474e59ef2c5bdb27368 Mon Sep 17 00:00:00 2001
From: Alessio Buccino <alejoe9187@gmail.com>
Date: Mon, 28 Sep 2026 19:29:26 +0200
Subject: [PATCH 12/15] fix: sorters tests

---
 src/spikeinterface/sorters/tests/test_launcher.py | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/src/spikeinterface/sorters/tests/test_launcher.py b/src/spikeinterface/sorters/tests/test_launcher.py
index 2cd25f119a..96c9b57dcd 100644
--- a/src/spikeinterface/sorters/tests/test_launcher.py
+++ b/src/spikeinterface/sorters/tests/test_launcher.py
@@ -13,10 +13,11 @@
 SORTERS = ["tridesclous2"]
 
 
-def create_recordings(NUM_RECORDINGS=2, base_seed=42):
+def create_recordings(folder, NUM_RECORDINGS=2, base_seed=42):
     recordings = []
     for i in range(NUM_RECORDINGS):
         recording, _ = generate_ground_truth_recording(num_channels=8, durations=[10.0], seed=base_seed + i)
+        recording = recording.save(folder=folder / f"rec_for_generate_recording_{i}", format="binary")
 
         if i % 2 == 0:
             recording.set_channel_groups(["0"] * 4 + ["1"] * 4)
@@ -28,7 +29,7 @@ def create_recordings(NUM_RECORDINGS=2, base_seed=42):
 
 def get_job_list(base_folder):
     jobs = []
-    recordings = create_recordings(NUM_RECORDINGS)
+    recordings = create_recordings(base_folder, NUM_RECORDINGS)
     for i, recording in enumerate(recordings):
         for sorter_name in SORTERS:
             kwargs = dict(
@@ -209,7 +210,7 @@ def test_run_sorter_by_property(create_cache_folder):
     if working_folder2.is_dir():
         shutil.rmtree(working_folder2)
 
-    recordings = create_recordings(NUM_RECORDINGS)
+    recordings = create_recordings(create_cache_folder, NUM_RECORDINGS)
 
     rec0 = recordings[0]
     rec0_by = rec0.split_by("group")

From 979698cca07352de14770870500a6f5f57b2ee76 Mon Sep 17 00:00:00 2001
From: Alessio Buccino <alejoe9187@gmail.com>
Date: Tue, 29 Sep 2026 09:32:00 +0200
Subject: [PATCH 13/15] fix: sorters tests

---
 src/spikeinterface/sorters/tests/test_launcher.py | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/src/spikeinterface/sorters/tests/test_launcher.py b/src/spikeinterface/sorters/tests/test_launcher.py
index 96c9b57dcd..6619431866 100644
--- a/src/spikeinterface/sorters/tests/test_launcher.py
+++ b/src/spikeinterface/sorters/tests/test_launcher.py
@@ -16,8 +16,9 @@
 def create_recordings(folder, NUM_RECORDINGS=2, base_seed=42):
     recordings = []
     for i in range(NUM_RECORDINGS):
+
         recording, _ = generate_ground_truth_recording(num_channels=8, durations=[10.0], seed=base_seed + i)
-        recording = recording.save(folder=folder / f"rec_for_generate_recording_{i}", format="binary")
+        recording = recording.save(folder=folder / f"rec_for_generate_recording_{i}", format="binary", overwrite=True)
 
         if i % 2 == 0:
             recording.set_channel_groups(["0"] * 4 + ["1"] * 4)

From 53cbb5007e11986cec37efde912148aff6dbec67 Mon Sep 17 00:00:00 2001
From: Alessio Buccino <alejoe9187@gmail.com>
Date: Tue, 29 Sep 2026 11:34:27 +0200
Subject: [PATCH 14/15] fix: examples

---
 examples/tutorials/core/plot_4_sorting_analyzer.py | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/examples/tutorials/core/plot_4_sorting_analyzer.py b/examples/tutorials/core/plot_4_sorting_analyzer.py
index 7c89088c09..c52426251c 100644
--- a/examples/tutorials/core/plot_4_sorting_analyzer.py
+++ b/examples/tutorials/core/plot_4_sorting_analyzer.py
@@ -33,6 +33,8 @@
 # First let's generate a simulated recording and sorting
 
 recording, sorting = generate_ground_truth_recording()
+# Make the recording JSON serializable, so it can be reloaded later
+recording = recording.save(folder="recording_folder")
 print(recording)
 print(sorting)
 

From dc2a0d6c8e4a5628074c8bd12801338231f0d7a6 Mon Sep 17 00:00:00 2001
From: Alessio Buccino <alejoe9187@gmail.com>
Date: Fri, 2 Oct 2026 16:56:34 +0200
Subject: [PATCH 15/15] fix: remove warnings  if not JSON serializable

Co-authored-by: Alessio Buccino <alejoe9187@gmail.com>
---
 src/spikeinterface/core/zarrextractors.py | 7 -------
 1 file changed, 7 deletions(-)

diff --git a/src/spikeinterface/core/zarrextractors.py b/src/spikeinterface/core/zarrextractors.py
index 4be7c0d3d6..9b88d59b98 100644
--- a/src/spikeinterface/core/zarrextractors.py
+++ b/src/spikeinterface/core/zarrextractors.py
@@ -758,9 +758,6 @@ def add_sorting_to_zarr_group(
     if sorting.check_serializability("json"):
         zarr_group.attrs["provenance"] = check_json(sorting.to_dict(recursive=True, relative_to=relative_to))
     else:
-        warnings.warn(
-            "The sorting provenance is not serializable! The sorting provenance link will be lost for future load"
-        )
         zarr_group.attrs["provenance"] = None
 
     num_segments = sorting.get_num_segments()
@@ -804,10 +801,6 @@ def add_recording_to_zarr_group(
     if recording.check_serializability("json"):
         zarr_group.attrs["provenance"] = check_json(recording.to_dict(recursive=True, relative_to=relative_to))
     else:
-        warnings.warn(
-            "The recording provenance is not serializable! "
-            "The recording provenance link will be lost for future load"
-        )
         zarr_group.attrs["provenance"] = None
 
     # save data (done the subclass)