diff --git a/chlorophyll/chl_climatology_and_fill.py b/chlorophyll/chl_climatology_and_fill.py
index ecd645ee..1930de9d 100644
--- a/chlorophyll/chl_climatology_and_fill.py
+++ b/chlorophyll/chl_climatology_and_fill.py
@@ -70,18 +70,6 @@ def main():
     input_directory = os.path.abspath(args.input_directory)
     output_filename = os.path.abspath(args.output_filename)
 
-    this_file = os.path.normpath(__file__)
-
-    # Add some info about how the file was generated
-    runcmd = (
-        f"python3 {os.path.basename(this_file)} --input-directory={input_directory} "
-        f"--output-filename={output_filename}"
-    )
-
-    history_attrs = {
-        "history": get_provenance_metadata(this_file, runcmd),
-    }
-
     # Load the input data and compute the monthly climatology
     input_files = sorted(glob.glob(f"{input_directory}/*.nc"))
 
@@ -160,7 +148,7 @@ def main():
     chl.time.attrs["long_name"] = "Time"
     chl.time.attrs["standard_name"] = "time"
     chl.time.attrs["axis"] = "T"
-    chl.attrs |= history_attrs
+    chl.attrs |= get_provenance_metadata(input_files)
     comp = dict(zlib=True, complevel=4)
     encoding = {var: comp for var in chl.data_vars}
     # Time coords should be double type according for CF conventions
diff --git a/data_stream_xml_generation/generate_xml_datm_era5.py b/data_stream_xml_generation/generate_xml_datm_era5.py
index ea279f20..4f6b0f9b 100644
--- a/data_stream_xml_generation/generate_xml_datm_era5.py
+++ b/data_stream_xml_generation/generate_xml_datm_era5.py
@@ -85,9 +85,7 @@
 root = Element("file", id="stream", version="2.0")
 
 # Obtain metadata
-this_file = sys.argv[0]
-runcmd = " ".join(sys.argv)
-metadata_info = get_provenance_metadata(this_file, runcmd)
+metadata_info = get_provenance_metadata()
 
 # Add metadata
 metadata = SubElement(root, "metadata")
@@ -95,7 +93,7 @@
 SubElement(metadata, "date_generated").text = datetime.now().strftime(
     "%Y-%m-%d %H:%M:%S"
 )
-SubElement(metadata, "history").text = metadata_info
+SubElement(metadata, "history").text = metadata_info["history"]
 
 # Generate stream info elements with changing years
 for stream_name, era5_prefix, datavar_pairs, mapalgo, offset_seconds in STREAM_SPECS:
diff --git a/data_stream_xml_generation/generate_xml_datm_jra55.py b/data_stream_xml_generation/generate_xml_datm_jra55.py
index 91339653..19c1f4d0 100644
--- a/data_stream_xml_generation/generate_xml_datm_jra55.py
+++ b/data_stream_xml_generation/generate_xml_datm_jra55.py
@@ -61,9 +61,7 @@
 root = Element("file", id="stream", version="2.0")
 
 # Obtain metadata
-this_file = sys.argv[0]
-runcmd = " ".join(sys.argv)
-metadata_info = get_provenance_metadata(this_file, runcmd)
+metadata_info = get_provenance_metadata()
 
 # Add metadata
 metadata = SubElement(root, "metadata")
@@ -71,7 +69,7 @@
 SubElement(metadata, "date_generated").text = datetime.now().strftime(
     "%Y-%m-%d %H:%M:%S"
 )
-SubElement(metadata, "history").text = metadata_info
+SubElement(metadata, "history").text = metadata_info["history"]
 
 # Define the stream info names and corresponding var names
 stream_info_names = [*STREAMS_AVE, *STREAMS_PT]
diff --git a/data_stream_xml_generation/generate_xml_drof_jra55.py b/data_stream_xml_generation/generate_xml_drof_jra55.py
index 455a6253..5b331a74 100644
--- a/data_stream_xml_generation/generate_xml_drof_jra55.py
+++ b/data_stream_xml_generation/generate_xml_drof_jra55.py
@@ -42,9 +42,7 @@
 root = Element("file", id="stream", version="2.0")
 
 # Obtain metadata
-this_file = sys.argv[0]
-runcmd = " ".join(sys.argv)
-metadata_info = get_provenance_metadata(this_file, runcmd)
+metadata_info = get_provenance_metadata()
 
 # Add metadata
 metadata = SubElement(root, "metadata")
@@ -52,7 +50,7 @@
 SubElement(metadata, "date_generated").text = datetime.now().strftime(
     "%Y-%m-%d %H:%M:%S"
 )
-SubElement(metadata, "history").text = metadata_info
+SubElement(metadata, "history").text = metadata_info["history"]
 
 # Define the stream info names and corresponding var names
 stream_info_data = [
diff --git a/external_tidal_generation/generate_bottom_roughness_intermediate_woa.py b/external_tidal_generation/generate_bottom_roughness_intermediate_woa.py
index 9523d1e7..0de8ef8d 100644
--- a/external_tidal_generation/generate_bottom_roughness_intermediate_woa.py
+++ b/external_tidal_generation/generate_bottom_roughness_intermediate_woa.py
@@ -135,7 +135,7 @@
 
 path_root = Path(__file__).parents[1]
 sys.path.append(str(path_root))
-from scripts_common import get_provenance_metadata, md5sum
+from scripts_common import get_provenance_metadata
 
 
 def coriolis_f(lat: xr.DataArray) -> xr.DataArray:
@@ -838,30 +838,14 @@ def main():
         )
 
         # Add provenance metadata and MD5 hashes for input files.
-        this_file = os.path.normpath(__file__)
-        runcmd = (
-            f"mpirun -n $PBS_NCPUS python3 {os.path.basename(this_file)} "
-            f"--woa_temp_file={args.woa_temp_file} "
-            f"--woa_salt_file={args.woa_salt_file} "
-            f"--synbath_file={args.synbath_file} "
-            f"--chunk-lat={args.chunk_lat} "
-            f"--chunk-lon={args.chunk_lon} "
-            f"--nradial={args.nradial} "
-            f"--ntheta={args.ntheta} "
-            f"--earth-radius={args.earth_radius} "
-            f"--omega={args.omega} "
-            f"--print-every={args.print_every} "
-            f"--woa-intermediate-file={args.woa_intermediate_file} "
-        )
-
-        history = get_provenance_metadata(this_file, runcmd)
-        global_attrs = {"history": history}
-        file_hashes = [
-            f"{args.woa_temp_file} (md5 hash: {md5sum(args.woa_temp_file)})",
-            f"{args.woa_salt_file} (md5 hash: {md5sum(args.woa_salt_file)})",
-            f"{args.synbath_file} (md5 hash: {md5sum(args.synbath_file)})",
+        runcmd = f"mpirun -n $PBS_NCPUS python3 {' '.join(sys.argv)} "
+        input_files = [
+            args.woa_temp_file,
+            args.woa_salt_file,
+            args.synbath_file,
         ]
-        global_attrs["inputFile"] = ", ".join(file_hashes)
+        global_attrs = get_provenance_metadata(input_files, runcmd)
+
         ds_woa_output.attrs.update(global_attrs)
 
         ds_woa_output.to_netcdf(args.woa_intermediate_file)
diff --git a/external_tidal_generation/generate_bottom_roughness_polyfit.py b/external_tidal_generation/generate_bottom_roughness_polyfit.py
index 8dfc0e4a..e75c5574 100644
--- a/external_tidal_generation/generate_bottom_roughness_polyfit.py
+++ b/external_tidal_generation/generate_bottom_roughness_polyfit.py
@@ -39,7 +39,7 @@
 path_root = Path(__file__).parents[1]
 sys.path.append(str(path_root))
 
-from scripts_common import get_provenance_metadata, md5sum
+from scripts_common import get_provenance_metadata
 from mesh_generation.generate_mesh import mom6_mask_detection
 
 
@@ -383,25 +383,10 @@ def main():
         )
 
         # Add provenance metadata and MD5 hashes for input files.
-        this_file = os.path.normpath(__file__)
-        runcmd = (
-            f"mpirun -n $PBS_NCPUS python3 {os.path.basename(this_file)} "
-            f"--high-res-topo-file={args.high_res_topo_file} "
-            f"--hgrid-file={args.hgrid_file} "
-            f"--topog-file={args.topog_file} "
-            f"--chunk-lat={args.chunk_lat} "
-            f"--chunk-lon={args.chunk_lon} "
-            f"--output={args.output}"
-        )
+        runcmd = f"mpirun -n $PBS_NCPUS python3 {' '.join(sys.argv)} "
+        input_files = [args.high_res_topo_file, args.hgrid_file, args.topog_file]
+        global_attrs = get_provenance_metadata(input_files, runcmd)
 
-        history = get_provenance_metadata(this_file, runcmd)
-        global_attrs = {"history": history}
-        file_hashes = [
-            f"{args.high_res_topo_file} (md5 hash: {md5sum(args.high_res_topo_file)})",
-            f"{args.hgrid_file} (md5 hash: {md5sum(args.hgrid_file)})",
-            f"{args.topog_file} (md5 hash: {md5sum(args.topog_file)})",
-        ]
-        global_attrs["inputFile"] = ", ".join(file_hashes)
         h2_out.attrs.update(global_attrs)
 
         h2_out.to_netcdf(args.output)
diff --git a/external_tidal_generation/generate_bottom_roughness_regrid.py b/external_tidal_generation/generate_bottom_roughness_regrid.py
index 567ee1e0..0bb985b7 100644
--- a/external_tidal_generation/generate_bottom_roughness_regrid.py
+++ b/external_tidal_generation/generate_bottom_roughness_regrid.py
@@ -53,7 +53,7 @@
 
 path_root = Path(__file__).parents[1]
 sys.path.append(str(path_root))
-from scripts_common import get_provenance_metadata, md5sum
+from scripts_common import get_provenance_metadata
 from mesh_generation.generate_mesh import mom6_mask_detection
 
 
@@ -396,26 +396,8 @@ def main():
     print("Regridding done!")
 
     # Add provenance metadata and MD5 hashes for input files.
-    this_file = os.path.normpath(__file__)
-    runcmd = (
-        f"python3 {os.path.basename(this_file)} "
-        f"--topog_file={args.topog_file} "
-        f"--hgrid_file={args.hgrid_file} "
-        f"--woa_intermediate_file={args.woa_intermediate_file} "
-        f"--output_file={args.output_file} "
-        f"--method={args.method} "
-        f"--periodic_regrid={args.periodic_regrid} "
-        f"--periodic_lon_laplace={args.periodic_lon_laplace}"
-    )
-
-    history = get_provenance_metadata(this_file, runcmd)
-    global_attrs = {"history": history}
-    file_hashes = [
-        f"{args.hgrid_file} (md5 hash: {md5sum(args.hgrid_file)})",
-        f"{args.topog_file} (md5 hash: {md5sum(args.topog_file)})",
-        f"{args.woa_intermediate_file} (md5 hash: {md5sum(args.woa_intermediate_file)})",
-    ]
-    global_attrs["inputFile"] = ", ".join(file_hashes)
+    input_files = [args.hgrid_file, args.topog_file, args.woa_intermediate_file]
+    global_attrs = get_provenance_metadata(input_files)
     regrid_depth_var.attrs.update(global_attrs)
 
     output_path = Path(args.output_file)
diff --git a/external_tidal_generation/generate_tide_amplitude.py b/external_tidal_generation/generate_tide_amplitude.py
index a707f4d9..f3b021f4 100644
--- a/external_tidal_generation/generate_tide_amplitude.py
+++ b/external_tidal_generation/generate_tide_amplitude.py
@@ -38,7 +38,7 @@
 path_root = Path(__file__).parents[1]
 sys.path.append(str(path_root))
 
-from scripts_common import get_provenance_metadata, md5sum
+from scripts_common import get_provenance_metadata
 from mesh_generation.generate_mesh import mom6_mask_detection
 
 PRIMARY_CONSTITUENTS = ["m2", "s2", "n2", "k2", "k1", "o1", "p1", "q1"]
@@ -277,25 +277,8 @@ def main():
     tideamp = tideamp.rename({"x": "xh", "y": "yh"})
 
     # Add provenance metadata and MD5 hashes for input files.
-    this_file = os.path.normpath(__file__)
-    runcmd = (
-        f"python3 {os.path.basename(this_file)} "
-        f"--hgrid-file={args.hgrid_file} "
-        f"--topog-file={args.topog_file} "
-        f"--method={args.method} "
-        f"--data-path={args.data_path} "
-        f"--output={args.output} "
-    )
-
-    history = get_provenance_metadata(this_file, runcmd)
-    global_attrs = {"history": history}
-
-    # add md5 hashes for input files
-    file_hashes = [
-        f"{args.hgrid_file} (md5 hash: {md5sum(args.hgrid_file)})",
-        f"{args.topog_file} (md5 hash: {md5sum(args.topog_file)})",
-    ]
-    global_attrs["inputFile"] = ", ".join(file_hashes)
+    input_files = [args.hgrid_file, args.topog_file]
+    global_attrs = get_provenance_metadata(input_files)
     tideamp.attrs.update(global_attrs)
 
     tideamp.to_netcdf(args.output, unlimited_dims=["time"])
diff --git a/grid_generation/generate_vertical_grid.py b/grid_generation/generate_vertical_grid.py
index a310728f..76cff9ea 100644
--- a/grid_generation/generate_vertical_grid.py
+++ b/grid_generation/generate_vertical_grid.py
@@ -38,7 +38,7 @@
 path_root = Path(__file__).parents[1]
 sys.path.append(str(path_root))
 
-from scripts_common import get_provenance_metadata, md5sum
+from scripts_common import get_provenance_metadata
 
 # Define a small constant to initialize the iteration and prevent numerical issues
 epsilon = 0.001
@@ -91,18 +91,8 @@ def generate_vertical_grid(H, dzd, min_dz, depfac, output_filename):
         : len(real_prop_z)
     ]  # Trim the spacing values to match the adjusted depth levels
 
-    this_file = os.path.normpath(__file__)
-
-    # Add some info about how the file was generated
-    runcmd = (
-        f"python3 {os.path.basename(this_file)} --H={H} --depfac={depfac} "
-        f"--dzd={dzd} "
-        f"--min_dz={min_dz} "
-        f"--output={output_filename} "
-    )
-
     # Write to NetCDF file
-    write_netcdf_file(output_filename, real_prop_z, this_file, runcmd)
+    write_netcdf_file(output_filename, real_prop_z)
 
     print(
         f"SUCCESS! A vertical grid with {len(real_prop_z) - 1} levels has been generated. "
@@ -111,7 +101,7 @@ def generate_vertical_grid(H, dzd, min_dz, depfac, output_filename):
     )
 
 
-def write_netcdf_file(output_filename, real_prop_z, this_file, runcmd):
+def write_netcdf_file(output_filename, real_prop_z):
     """Function to write vertical grid data to a NetCDF file."""
     # Convert to float32 (single precision) to ensure values are exactly representable in single precision,
     # then convert back to float64 (double precision) for storage in NetCDF.
@@ -125,7 +115,7 @@ def write_netcdf_file(output_filename, real_prop_z, this_file, runcmd):
     zeta.standard_name = "depth"
     zeta.long_name = "vertical grid depth at top and bottom of each cell"
     eddyfile.variables["zeta"][:] = real_prop_z_float64
-    eddyfile.setncatts({"history": get_provenance_metadata(this_file, runcmd)})
+    eddyfile.setncatts(get_provenance_metadata())  # Obtain metadata
     eddyfile.close()
 
 
diff --git a/make_ryf/make_ryf.py b/make_ryf/make_ryf.py
index b86d1a44..8ffaada3 100644
--- a/make_ryf/make_ryf.py
+++ b/make_ryf/make_ryf.py
@@ -38,7 +38,7 @@
 path_root = Path(__file__).parents[1]
 sys.path.append(str(path_root))
 
-from scripts_common import get_provenance_metadata, md5sum
+from scripts_common import get_provenance_metadata
 
 FILLVALUE = 1e20
 # compression settings to use
@@ -113,7 +113,7 @@
     ds = {}
 
     for var in variables:
-        ryf_files = str()
+        input_files = []
         print(var)
         for y in (year1, year2):
             if source_data == "jra55v1p4" or source_data == "jra55v1p6":
@@ -147,7 +147,7 @@
             print("Loading {} for {}".format(files[0], y))
             ds[y] = xarray.open_dataset(files[0], decode_coords=False)
             # save info for metadata
-            ryf_files += f"{files[0]} (md5 hash: {md5sum(files[0])}, )"
+            input_files.append(files[0])
         # Make a copy of the second year without time_bnds
         ryf = ds[baseyear].drop_vars("time_bnds")
         ryf.encoding = ds[baseyear].encoding
@@ -205,10 +205,7 @@
         )
 
         # Add some info about how the file was generated
-        this_file = os.path.normpath(__file__)
-        runcmd = f"python3 {os.path.basename(this_file)}"
-        ryf.attrs |= {"RYF_creation": get_provenance_metadata(this_file, runcmd)}
-        ryf.attrs |= {"RYF_inputFiles": ryf_files}
+        ryf.attrs |= get_provenance_metadata(input_files)
 
         outfile = "RYF.{}.{}_{}.nc".format(var, year1, year2)
         print("Writing ", outfile)
diff --git a/mesh_generation/generate_mesh.py b/mesh_generation/generate_mesh.py
index d312f445..511d3b78 100755
--- a/mesh_generation/generate_mesh.py
+++ b/mesh_generation/generate_mesh.py
@@ -43,7 +43,7 @@
 path_root = Path(__file__).parents[1]
 sys.path.append(str(path_root))
 
-from scripts_common import get_provenance_metadata, md5sum
+from scripts_common import get_provenance_metadata
 
 EARTH_R = 6.37122e6
 
@@ -126,7 +126,7 @@ def __init__(
 
         self.mesh = None
 
-    def create_mesh(self, wrap_lons=True, global_attrs=None):
+    def create_mesh(self, wrap_lons=True):
         """
         Create the mesh as an xarray Dataset
 
@@ -134,8 +134,6 @@ def create_mesh(self, wrap_lons=True, global_attrs=None):
         ----------
         wrap_lons: boolean, optional
             If True, wrap longitude values into the range between 0 and 360
-        global_attrs: dict
-            Global attributes to the mesh object
         """
 
         if wrap_lons:
@@ -205,15 +203,7 @@ def create_mesh(self, wrap_lons=True, global_attrs=None):
             "timeGenerated": f"{datetime.now()}",
             "created_by": f"{os.environ.get('USER')}",
         }
-        if self.inputs:
-            file_hashes = []
-            for input in self.inputs:
-                file_hashes.append(f"{input} (md5 hash: {md5sum(input)})")
-            ds.attrs["inputFile"] = ", ".join(file_hashes)
-
-        # add git info to history
-        if global_attrs:
-            ds.attrs |= global_attrs
+        ds.attrs |= get_provenance_metadata(input_files=self.inputs)
 
         self.mesh = ds
 
@@ -589,29 +579,6 @@ def main():
     if topog_filename:
         topog_filename = os.path.abspath(topog_filename)
 
-    this_file = os.path.normpath(__file__)
-
-    # Add some info about how the file was generated
-    runcmd = (
-        f"python3 {os.path.basename(this_file)} --grid-type={grid_type} --grid-filename={grid_filename} "
-        f"--mesh-filename={mesh_filename}"
-    )
-    if topog_filename:
-        runcmd += f" --topog-filename={topog_filename}"
-        if minimum_depth:
-            runcmd += f" --minimum-depth={minimum_depth}"
-        if masking_depth:
-            runcmd += f" --masking-depth={masking_depth}"
-    runcmd += f" --wrap-lons={wrap_lons}"
-    if lon_name:
-        runcmd += f" --lon-name={lon_name}"
-    if lat_name:
-        runcmd += f" --lat-name={lat_name}"
-    if area_name:
-        runcmd += f" --area-name={area_name}"
-
-    global_attrs = {"history": get_provenance_metadata(this_file, runcmd)}
-
     mesh = gridtype_dispatch[grid_type](
         grid_filename,
         topog_filename,
@@ -622,9 +589,7 @@ def main():
         masking_depth,
     )
 
-    mesh.create_mesh(wrap_lons=wrap_lons, global_attrs=global_attrs).write(
-        mesh_filename
-    )
+    mesh.create_mesh(wrap_lons=wrap_lons).write(mesh_filename)
 
 
 if __name__ == "__main__":
diff --git a/mesh_generation/generate_rof_weights.py b/mesh_generation/generate_rof_weights.py
index 88c63401..935859ea 100755
--- a/mesh_generation/generate_rof_weights.py
+++ b/mesh_generation/generate_rof_weights.py
@@ -42,13 +42,13 @@
 
 path_root = Path(__file__).parents[1]
 sys.path.append(str(path_root))
-from scripts_common import get_provenance_metadata, md5sum
+from scripts_common import get_provenance_metadata
 
 TEMP_WEIGHTS_F = "temp_weights.nc"
 COMP_ENCODING = {"complevel": 1, "compression": "zlib"}  # compression settings to use
 
 
-def drof_remapping_weights(mesh_filename, weights_filename, nx, ny, global_attrs=None):
+def drof_remapping_weights(mesh_filename, weights_filename, nx, ny):
     # We need to generate remapping weights for use in the mediator, such that the overall volume of runoff is conserved
     # and no runoff is mapped onto land cells. Inside the mediator, the grid doesn't change as we run the mediator with
     # the ocean grid (the DROF component does the remapping from JRA grid to mediator grid). Therefore we use the
@@ -139,12 +139,10 @@ def drof_remapping_weights(mesh_filename, weights_filename, nx, ny, global_attrs
     # add global attributes
     weights_ds.attrs = {
         "gridType": "unstructured mesh",
-        "inputFile": f"{mesh_filename} (md5 hash: {md5sum(mesh_filename)})",
     }
 
     # add git info to history
-    if global_attrs:
-        weights_ds.attrs |= global_attrs
+    weights_ds.attrs |= get_provenance_metadata([mesh_filename])
 
     # save (compressed)
     encoding = {}
@@ -188,19 +186,8 @@ def main():
     )
 
     args = parser.parse_args()
-    mesh_filename = os.path.abspath(args.mesh_filename)
-    weights_filename = os.path.abspath(args.weights_filename)
 
-    this_file = os.path.normpath(__file__)
-
-    # Add some info about how the file was generated
-    runcmd = f"python3 {os.path.basename(this_file)} --mesh_filename={mesh_filename} --nx={args.nx} --ny={args.ny} --weights_filename={weights_filename} "
-
-    global_attrs = {"history": get_provenance_metadata(this_file, runcmd)}
-
-    drof_remapping_weights(
-        mesh_filename, weights_filename, args.nx, args.ny, global_attrs
-    )
+    drof_remapping_weights(args.mesh_filename, args.weights_filename, args.nx, args.ny)
 
     return True
 
diff --git a/payu_config/postscript/build_intake_ds.py b/payu_config/postscript/build_intake_ds.py
index ac4c7595..268de232 100644
--- a/payu_config/postscript/build_intake_ds.py
+++ b/payu_config/postscript/build_intake_ds.py
@@ -19,7 +19,7 @@
 path_root = Path(__file__).parents[2]
 sys.path.append(str(path_root))
 
-from scripts_common import get_provenance_metadata, md5sum
+from scripts_common import get_provenance_metadata
 
 METADATA_FILENAME = "metadata.yaml"
 UUID_FIELD = "experiment_uuid"
@@ -39,18 +39,12 @@ def description():
         warn(f"{METADATA_FILENAME} not found in config folder")
         uuid = False
 
-    # Check git status of this .py file
-    this_file = os.path.normpath(__file__)
-
-    runcmd = f"python3 {os.path.basename(this_file)}"
-
-    # Get string "Created using $file: $command"
-    provenance = get_provenance_metadata(this_file, runcmd)
+    provenance = get_provenance_metadata()
 
     if uuid:
-        description = f"intake-esm datastore for experiment {uuid}, in folder {os.getcwd()}. {provenance}. (md5 hash: {md5sum(this_file)})"
+        description = f"intake-esm datastore for experiment {uuid}, in folder {os.getcwd()}. {provenance['history']}."
     else:
-        description = f"intake-esm datastore for experiment in folder {os.getcwd()}. {provenance}. (md5 hash: {md5sum(this_file)})"
+        description = f"intake-esm datastore for experiment in folder {os.getcwd()}. {provenance['history']}."
 
     return description
 
diff --git a/payu_config/postscript/concat_ice_daily.py b/payu_config/postscript/concat_ice_daily.py
index 28ee6bd3..50e9bbd9 100644
--- a/payu_config/postscript/concat_ice_daily.py
+++ b/payu_config/postscript/concat_ice_daily.py
@@ -29,7 +29,7 @@
 
 path_root = Path(__file__).parents[2]
 sys.path.append(str(path_root))
-from scripts_common import get_provenance_metadata, md5sum
+from scripts_common import get_provenance_metadata
 
 CICE_DAILY_FN = "access-om3.cice.1day.mean.????-??-??.nc"
 MONTHLY_STUB_FN = "access-om3.cice.1day.mean."
@@ -134,9 +134,7 @@ def __init__(self, directory=None, assume_gadi=True):
         del daily_ds.attrs["comment3"]
 
         # Add some info about how the file was generated
-        this_file = os.path.normpath(__file__)
-        runcmd = f"python3 {os.path.basename(this_file)} --directory={os.path.abspath(directory)}"
-        daily_ds.attrs["postprocessing"] = get_provenance_metadata(this_file, runcmd)
+        daily_ds.attrs |= get_provenance_metadata()
 
         self.directory = directory
         self.daily_ds = daily_ds
diff --git a/regrid_common.py b/regrid_common.py
index dbb01ab7..9343ee09 100644
--- a/regrid_common.py
+++ b/regrid_common.py
@@ -15,7 +15,7 @@
 import scipy.sparse as sp
 import scipy.sparse.linalg as spla
 
-from scripts_common import md5sum
+from scripts_common import get_provenance_input_files
 
 
 def _guess_longitude_name(ds):
@@ -119,19 +119,6 @@ def parse_cli(self):
         if self.mask_filename:
             self.mask_filename = os.path.abspath(self.mask_filename)
 
-        # some info about how the file was generated
-
-        runcmd_args = f"--hgrid-filename={self.hgrid_filename} --output-filename={self.output_filename}"
-
-        if self.mask_filename:
-            runcmd_args += f" --mask-filename={self.mask_filename}"
-        if self.lon_name:
-            runcmd_args += f" --lon-name={self.lon_name}"
-        if self.lat_name:
-            runcmd_args += f" --lat-name={self.lat_name}"
-
-        self.runcmd_args = runcmd_args
-
     ## NOTE: it's implied that forcing_filename is set outside this class
 
     def open_datasets(self):
@@ -229,17 +216,12 @@ def save_output(self):
         forcing_regrid = self.forcing_regrid
 
         # Info about input data used
-        file_hashes = [
-            f"{self.forcing_filename} (md5 hash: {md5sum(self.forcing_filename)})",
-            f"{self.hgrid_filename} (md5 hash: {md5sum(self.hgrid_filename)})",
-        ]
+        input_files = [self.forcing_filename, self.hgrid_filename]
         if self.mask_filename:
-            file_hashes.append(
-                f"{self.mask_filename} (md5 hash: {md5sum(self.mask_filename)})"
-            )
+            input_files.append(self.mask_filename)
 
         global_attrs = {
-            "inputFile": ", ".join(file_hashes),
+            "inputFile": get_provenance_input_files(input_files),
         }
         forcing_regrid.attrs = forcing_regrid.attrs | global_attrs
 
diff --git a/restart_modifications/apply_bathy_mom_restarts.py b/restart_modifications/apply_bathy_mom_restarts.py
index f8fa41f4..3e56faac 100644
--- a/restart_modifications/apply_bathy_mom_restarts.py
+++ b/restart_modifications/apply_bathy_mom_restarts.py
@@ -45,14 +45,14 @@
 
 
 def copy_data(args):
-    in_f, out_f, runcmd, this_f, template_f = args
+    in_f, out_f, template_f = args
     print(f"\n[INFO] Processing:\n  OLD: {in_f}\n  OUT: {out_f}")
     try:
         with nc.Dataset(in_f) as in_fp, nc.Dataset(out_f, "r+") as out_fp:
             # Add metadata
             out_fp.setncattr("title", "Updated restart file with new bathymetry mask")
             out_fp.setncattr("source", "Generated by fix_mom6_restarts.py")
-            out_fp.setncattr("history", get_provenance_metadata(this_f, runcmd))
+            out_fp.setncatts(get_provenance_metadata())
             out_fp.setncattr(
                 "template_file",
                 f"{os.path.abspath(template_f)} (md5 hash: {md5sum(template_f)})",
@@ -145,9 +145,6 @@ def main():
         print(f"[COPY] {tf} -> {out_f}")
         shutil.copy(tf, out_f)
 
-    this_file = os.path.normpath(__file__)
-    runcmd = f"python3 {os.path.basename(this_file)} --template_dir {args.template_dir} --old_dir {args.old_dir} --output_dir {args.output_dir} --template_prefix {args.template_prefix} --old_prefix {args.old_prefix} --nprocs {args.nprocs}"
-
     print("[INFO] Starting update of variables...")
     # update each restart file on a different proc
     pool = mp.Pool(args.nprocs)
@@ -156,8 +153,6 @@ def main():
         zip(
             old_files,
             output_files,
-            [runcmd] * len(old_files),
-            [this_file] * len(old_files),
             template_files,
         ),
     )
diff --git a/restart_modifications/remask_cpl_restart.py b/restart_modifications/remask_cpl_restart.py
index 0419bd1c..80acfd58 100644
--- a/restart_modifications/remask_cpl_restart.py
+++ b/restart_modifications/remask_cpl_restart.py
@@ -157,21 +157,12 @@ def main():
         unmask_file(f, mask, missing_value, skip_vars=skip_vars)
         apply_mask_file(f, mask, skip_vars=skip_vars)
 
-        this_file = os.path.normpath(__file__)
-        runcmd = (
-            f"python3 {os.path.basename(this_file)} "
-            f"--input_file {args.input_file} "
-            f"--output_file {args.output_file} "
-            f"--mask_file {args.mask_file} "
-            f"--mask_var {args.mask_var}"
-        )
-
         # Add metadata
         f.setncattr(
             "title",
             "Coupler restart fields updated with land mask of modified bathymetry",
         )
-        f.setncattr("history", get_provenance_metadata(this_file, runcmd))
+        f.setncatts(get_provenance_metadata())
         f.setncattr(
             "mask_file",
             f"{os.path.abspath(args.mask_file)} (md5 hash: {md5sum(args.mask_file)})",
diff --git a/rof_pattern_generation/generate_rofi_pattern.py b/rof_pattern_generation/generate_rofi_pattern.py
index 04f0dbba..41a00976 100755
--- a/rof_pattern_generation/generate_rofi_pattern.py
+++ b/rof_pattern_generation/generate_rofi_pattern.py
@@ -40,7 +40,7 @@
 sys.path.append(str(path_root))
 
 from regrid_common import Regrid_Common
-from scripts_common import get_provenance_metadata, md5sum
+from scripts_common import get_provenance_metadata
 from mesh_generation.generate_mesh import mom6_mask_detection
 
 # in a climatology, with 365 day calendar, whats the day of the middle of each month
@@ -179,31 +179,20 @@ def main():
         "units": "days since 0001-01-01 00:00:00",
     }
 
-    # Add some info about how the file was generated
-    this_file = os.path.normpath(__file__)
-
-    runcmd = (
-        f"python3 {os.path.basename(this_file)} --topog-file={regrid.args.topog_file} "
-        f"{regrid.runcmd_args}"
-    )
-
     # Info about input data used
-    file_hashes = [
-        f"{AQ_MELT_PATTERN} (md5 hash: {md5sum(AQ_MELT_PATTERN)})",
-        f"{GL_MELT_PATTERN} (md5 hash: {md5sum(GL_MELT_PATTERN)})",
-        f"{regrid.hgrid_filename} (md5 hash: {md5sum(regrid.hgrid_filename)})",
-        f"{regrid.args.topog_file} (md5 hash: {md5sum(regrid.args.topog_file)})",
+    input_files = [
+        AQ_MELT_PATTERN,
+        GL_MELT_PATTERN,
+        regrid.hgrid_filename,
+        regrid.args.topog_file,
     ]
     if regrid.mask_filename:
-        file_hashes.append(
-            f"{regrid.mask_filename} (md5 hash: {md5sum(regrid.mask_filename)})"
-        )
+        input_files.append(regrid.mask_filename)
 
     global_attrs |= {
         "description": "Mankoff 2025 iceberg spreading climatology remapped onto an ACCESS-OM3 grid",
-        "history": get_provenance_metadata(this_file, runcmd),
-        "inputFile": ", ".join(file_hashes),
     }
+    global_attrs |= get_provenance_metadata(input_files)
 
     weights_ds.attrs = weights_ds.attrs | global_attrs
 
diff --git a/scripts_common.py b/scripts_common.py
index 10e7e639..cfe4e2d8 100644
--- a/scripts_common.py
+++ b/scripts_common.py
@@ -7,7 +7,7 @@
 
 
 import subprocess
-import os
+import os, sys
 from warnings import warn
 import io
 import hashlib
@@ -97,15 +97,21 @@ def username(file):
     return name
 
 
-def get_provenance_metadata(file, runcmd):
+def get_provenance_metadata(input_files=None, runcmd=None):
     """
-    Return a string with the provenance of the file being run. Warn if the file is not pushed to the git upstream repository.
+    Return a dictionary with the provenance of the file being run. Warn if the
+    file is not pushed to the git upstream repository.
 
     arguments:
-        file: the path to the file being run
-        runcmd: the command used to run the file (with any arguments)
+        input_files: list of input files being used in the script being run (optional)
+        runcmd: the command used to run the file, with any arguments. Optional -
+            defaults to the python executable + input arguments
     """
 
+    file = os.path.abspath(sys.argv[0])  # script being run
+    if runcmd is None:
+        runcmd = f"{sys.executable} {' '.join(sys.argv)}"
+
     prepend = (
         f"Created by {username(file)} on {datetime.now().strftime('%Y-%m-%d')}, using "
     )
@@ -127,9 +133,14 @@ def get_provenance_metadata(file, runcmd):
         warn(
             f"{file} not under git version control! Add your file to a repository before generating any production output."
         )
-        prepend += f"{file}: "
+        prepend += f"{file} (md5 hash: {md5sum(file)}): "
+
+    attrs = {"history": prepend + runcmd}
 
-    return prepend + runcmd
+    if input_files is not None:
+        attrs["inputFile"] = get_provenance_input_files(input_files)
+
+    return attrs
 
 
 def md5sum(path):
@@ -144,3 +155,13 @@ def md5sum(path):
         for chunk in iter(lambda: fd.read(length), b""):
             md5.update(chunk)
     return md5.hexdigest()
+
+
+def get_provenance_input_files(input_files):
+    """
+    Return a formatted string of provided input files and their md5 hashes
+    """
+    file_hashes = []
+    for input in input_files:
+        file_hashes.append(f"{os.path.abspath(input)} (md5 hash: {md5sum(input)})")
+    return ", ".join(file_hashes)
diff --git a/surface_restoring_generation/make_sfc_restore_from_regridded_woa.py b/surface_restoring_generation/make_sfc_restore_from_regridded_woa.py
index c17e4478..696091fe 100755
--- a/surface_restoring_generation/make_sfc_restore_from_regridded_woa.py
+++ b/surface_restoring_generation/make_sfc_restore_from_regridded_woa.py
@@ -38,7 +38,7 @@
 path_root = Path(__file__).parents[1]
 sys.path.append(str(path_root))
 
-from scripts_common import get_provenance_metadata, md5sum
+from scripts_common import get_provenance_metadata
 
 
 def smooth2d(src):
@@ -93,14 +93,8 @@ def main(input_path, variable_to_smooth, output_file):
 
     out_ds["time"] = out_ds.time.assign_attrs({"modulo": " "})
 
-    this_file = os.path.normpath(__file__)
-    runcmd = f"python3 {os.path.basename(this_file)} --input_path={input_path} --var={variable_to_smooth} --output_file={output_file}"
-    out_ds = out_ds.assign_attrs(
-        {
-            "history": get_provenance_metadata(this_file, runcmd),
-            "input_files": [f"{f}(md5sum:{md5sum(f)})" for f in file_paths],
-        }
-    )
+    # Obtain metadata
+    out_ds = out_ds.assign_attrs(get_provenance_metadata(file_paths))
 
     # Save
     out_ds[variable_to_smooth].encoding.setdefault(
diff --git a/wombat_ic_generation/SFe_climatology.py b/wombat_ic_generation/SFe_climatology.py
index 5a8b6489..f632cacc 100644
--- a/wombat_ic_generation/SFe_climatology.py
+++ b/wombat_ic_generation/SFe_climatology.py
@@ -62,21 +62,11 @@ def main():
     )
 
     args = parser.parse_args()
-    input_filename = os.path.abspath(args.input_filename)
-    output_filename = os.path.abspath(args.output_filename)
+    input_filename = args.input_filename
+    output_filename = args.output_filename
 
-    this_file = os.path.normpath(__file__)
-
-    # Add some info about how the file was generated
-    runcmd = (
-        f"python3 {os.path.basename(this_file)} --input-filename={input_filename} "
-        f"--output-filename={output_filename}"
-    )
-
-    history_attrs = {
-        "history": get_provenance_metadata(this_file, runcmd),
-        "inputFile": f"{input_filename} (md5 hash: {md5sum(input_filename)})",
-    }
+    # Obtain metadata
+    history_attrs = get_provenance_metadata(input_files=[input_filename])
 
     # Load the input data
     ds = xr.open_dataset(input_filename).compute()
diff --git a/wombat_ic_generation/co2_iaf.py b/wombat_ic_generation/co2_iaf.py
index 4e2f2fbf..76ab5255 100644
--- a/wombat_ic_generation/co2_iaf.py
+++ b/wombat_ic_generation/co2_iaf.py
@@ -38,7 +38,7 @@
 path_root = Path(__file__).parents[1]
 sys.path.append(str(path_root))
 
-from scripts_common import get_provenance_metadata, md5sum
+from scripts_common import get_provenance_metadata
 
 xr.set_options(keep_attrs=True)
 
@@ -91,25 +91,9 @@ def main():
     hgrid_filename = os.path.abspath(args.hgrid_filename)
     output_filename = os.path.abspath(args.output_filename)
 
-    this_file = os.path.normpath(__file__)
-
-    # provenance metadata
-    runcmd = (
-        f"python3 {os.path.basename(this_file)} --co2-cmip-filename={co2_cmip_filename} "
-        f"--co2-noaa-filename={co2_noaa_filename} --hgrid-filename={hgrid_filename} "
-        f"--output-filename={output_filename}"
-    )
-
-    file_hashes = [
-        f"{co2_cmip_filename} (md5 hash: {md5sum(co2_cmip_filename)})",
-        f"{co2_noaa_filename} (md5 hash: {md5sum(co2_noaa_filename)})",
-        f"{hgrid_filename} (md5 hash: {md5sum(hgrid_filename)})",
-    ]
-
-    global_attrs = {
-        "history": get_provenance_metadata(this_file, runcmd),
-        "inputFile": ", ".join(file_hashes),
-    }
+    # Obtain metadata
+    input_files = [co2_cmip_filename, co2_noaa_filename, hgrid_filename]
+    global_attrs = get_provenance_metadata(input_files)
 
     # Load the input data
     co2_cmip = xr.open_dataset(co2_cmip_filename, decode_cf=False).compute()
diff --git a/wombat_ic_generation/generate_wombat_ic.py b/wombat_ic_generation/generate_wombat_ic.py
index a156d7be..28ce8e12 100755
--- a/wombat_ic_generation/generate_wombat_ic.py
+++ b/wombat_ic_generation/generate_wombat_ic.py
@@ -75,7 +75,7 @@ def _open_woa_data(file, var, global_attrs, hcoord_int=None, vcoord_int=None):
         "WOA23 (https://www.ncei.noaa.gov/access/world-ocean-atlas-2023/)"
     )
 
-    global_attrs["inputFile"].add(f"{file} (md5 hash: {md5sum(file)})")
+    global_attrs["inputFile"].add(f"{os.path.abspath(file)} (md5 hash: {md5sum(file)})")
 
     return _standardise_coords(da, hcoord_int, vcoord_int)
 
@@ -96,7 +96,7 @@ def _open_glodap_data(file, var, global_attrs, hcoord_int=None, vcoord_int=None)
         "GLODAPv2 mapped data (https://glodap.info/index.php/mapped-data-product/)"
     )
 
-    global_attrs["inputFile"].add(f"{file} (md5 hash: {md5sum(file)})")
+    global_attrs["inputFile"].add(f"{os.path.abspath(file)} (md5 hash: {md5sum(file)})")
 
     return _standardise_coords(da, hcoord_int, vcoord_int)
 
@@ -113,7 +113,7 @@ def _open_huang_data(file, global_attrs, hcoord_int=None, vcoord_int=None):
         "Huang et al 2022 dFe data (https://zenodo.org/records/6994318)"
     )
 
-    global_attrs["inputFile"].add(f"{file} (md5 hash: {md5sum(file)})")
+    global_attrs["inputFile"].add(f"{os.path.abspath(file)} (md5 hash: {md5sum(file)})")
 
     # Extend Latitudes from -90-90
     new_lats = np.concatenate(
@@ -457,18 +457,11 @@ def main():
     wombat_version = args.wombat_version
     output_file = args.output_file
 
-    this_file = os.path.normpath(__file__)
-
-    # Add some info about how the file was generated
-    runcmd = (
-        f"python3 {this_file} --wombat-version={wombat_version} "
-        f"--output-file={os.path.abspath(output_file)}"
-    )
-
     global_attrs = {
-        "history": get_provenance_metadata(this_file, runcmd),
         "inputFile": set(),
     }
+    # Obtain metadata
+    global_attrs |= get_provenance_metadata()
 
     xr.set_options(keep_attrs=True)
     template = _open_woa_data(
diff --git a/wombat_ic_generation/regrid_forcing.py b/wombat_ic_generation/regrid_forcing.py
index 3ec0a5ef..efb4b72b 100644
--- a/wombat_ic_generation/regrid_forcing.py
+++ b/wombat_ic_generation/regrid_forcing.py
@@ -93,19 +93,8 @@ def main():
     forcing_regrid["nx"].encoding |= {"dtype": "float32"}
     forcing_regrid["ny"].encoding |= {"dtype": "float32"}
 
-    # Add some info about how the file was generated
-    this_file = os.path.normpath(__file__)
-
-    runcmd = (
-        f"python3 {os.path.basename(this_file)} --forcing-filename={regrid.forcing_filename} "
-        f"{regrid.runcmd_args}"
-    )
-    if regrid.args.homogenize:
-        runcmd += " --homogenize"
-
-    global_attrs = {
-        "history": get_provenance_metadata(this_file, runcmd),
-    }
+    # Obtain metadata
+    global_attrs = get_provenance_metadata()
 
     forcing_regrid.attrs = forcing_regrid.attrs | global_attrs