diff --git a/pyproject.toml b/pyproject.toml
index 47b2f37..7bb2df0 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -20,10 +20,10 @@ dependencies = [
     "boto3",
     "boto3-stubs[s3]",
     "pydantic-settings>=2.0",
-    "pydantic>=2.7,<2.9",
+    "pydantic>=2.10",
     "pymongo==4.3.3",
     "dask==2023.5.0",
-    "aind-data-schema==1.0.0",
+    "aind-data-schema==1.2.0",
     "aind-codeocean-api==0.5.0",
 ]
 
diff --git a/src/aind_data_asset_indexer/__init__.py b/src/aind_data_asset_indexer/__init__.py
index 9dd0800..24dc33a 100644
--- a/src/aind_data_asset_indexer/__init__.py
+++ b/src/aind_data_asset_indexer/__init__.py
@@ -1,3 +1,3 @@
 """Package"""
 
-__version__ = "0.12.0"
+__version__ = "0.13.0"
diff --git a/src/aind_data_asset_indexer/aind_bucket_indexer.py b/src/aind_data_asset_indexer/aind_bucket_indexer.py
index eb08449..48899a4 100644
--- a/src/aind_data_asset_indexer/aind_bucket_indexer.py
+++ b/src/aind_data_asset_indexer/aind_bucket_indexer.py
@@ -11,6 +11,7 @@
 
 import boto3
 import dask.bag as dask_bag
+from aind_data_schema.base import is_dict_corrupt
 from mypy_boto3_s3 import S3Client
 from mypy_boto3_s3.type_defs import CopySourceTypeDef
 from pymongo import MongoClient
@@ -30,7 +31,6 @@
     get_dict_of_file_info,
     get_s3_bucket_and_prefix,
     get_s3_location,
-    is_dict_corrupt,
     is_prefix_valid,
     is_record_location_valid,
     iterate_through_top_level,
@@ -215,15 +215,15 @@ def _resolve_schema_information(
           The fields in the DocDb record that will require updating.
         """
         docdb_record_fields_to_update = dict()
-        for core_schema_file_name in core_schema_file_names:
-            field_name = core_schema_file_name.replace(".json", "")
+        for (
+            field_name,
+            core_schema_file_name,
+        ) in core_schema_file_names.items():
             is_in_record = docdb_record.get(field_name) is not None
             is_in_root = (
                 core_schema_info_in_root.get(core_schema_file_name) is not None
             )
-            is_in_copy_subdir = (
-                core_schema_file_name in list_of_schemas_in_copy_subdir
-            )
+            is_in_copy_subdir = field_name in list_of_schemas_in_copy_subdir
             # To avoid copying and pasting the same arguments, we'll keep it
             # them in a dict
             common_kwargs = {
@@ -580,8 +580,9 @@ def _process_prefix(
                         collection = db[
                             self.job_settings.doc_db_collection_name
                         ]
-                        if "_id" in json_contents:
-                            # TODO: check is_dict_corrupt(json_contents)
+                        if "_id" in json_contents and not is_dict_corrupt(
+                            json_contents
+                        ):
                             logging.info(
                                 f"Adding record to docdb for: {location}"
                             )
@@ -602,6 +603,10 @@ def _process_prefix(
                                     self.job_settings.copy_original_md_subdir
                                 ),
                             )
+                        elif "_id" in json_contents:
+                            logging.warning(
+                                f"Metadata record for {location} is corrupt!"
+                            )
                         else:
                             logging.warning(
                                 f"Metadata record for {location} "
diff --git a/src/aind_data_asset_indexer/utils.py b/src/aind_data_asset_indexer/utils.py
index e0a7870..16f5ac1 100644
--- a/src/aind_data_asset_indexer/utils.py
+++ b/src/aind_data_asset_indexer/utils.py
@@ -11,8 +11,12 @@
 
 from aind_codeocean_api.codeocean import CodeOceanClient
 from aind_data_schema.core.data_description import DataLevel, DataRegex
-from aind_data_schema.core.metadata import ExternalPlatforms, Metadata
-from aind_data_schema.utils.json_writer import SchemaWriter
+from aind_data_schema.core.metadata import CORE_FILES as CORE_SCHEMAS
+from aind_data_schema.core.metadata import (
+    ExternalPlatforms,
+    Metadata,
+    create_metadata_json,
+)
 from botocore.exceptions import ClientError
 from mypy_boto3_s3 import S3Client
 from mypy_boto3_s3.type_defs import (
@@ -23,12 +27,9 @@
 
 metadata_filename = Metadata.default_filename()
 
-# TODO: This would be better if it was available in aind-data-schema
-core_schema_file_names = [
-    s.default_filename()
-    for s in SchemaWriter.get_schemas()
-    if s.default_filename() != metadata_filename
-]
+core_schema_file_names = {
+    field_name: f"{field_name}.json" for field_name in CORE_SCHEMAS
+}
 
 
 def create_object_key(prefix: str, filename: str) -> str:
@@ -328,11 +329,10 @@ def does_s3_metadata_copy_exist(
         Bucket=bucket, Prefix=copy_prefix, Delimiter="/"
     )
     if "Contents" in response:
-        core_schemas = [s.replace(".json", "") for s in core_schema_file_names]
         pattern = re.escape(copy_prefix) + r"([a-zA-Z0-9_]+)\.\d{8}\.json$"
         for obj in response["Contents"]:
             m = re.match(pattern, obj["Key"])
-            if m is not None and m.group(1) in core_schemas:
+            if m is not None and m.group(1) in CORE_SCHEMAS:
                 return True
     return False
 
@@ -359,8 +359,8 @@ def list_metadata_copies(
     Returns
     -------
     List[str]
-      A list of the core schemas in the copy_subdir without timestamp, e..g,
-      ["subject.json", "procedures.json", "processing.json"]
+      A list of the core schemas in the copy_subdir without timestamp, e.g,
+      ["subject", "procedures", "processing"]
     """
     # Use trailing slash and delimiter to get top-level objects in copy_subdir
     copy_prefix = create_object_key(prefix, copy_subdir.strip("/") + "/")
@@ -369,12 +369,11 @@ def list_metadata_copies(
     )
     files = []
     if "Contents" in response:
-        core_schemas = [s.replace(".json", "") for s in core_schema_file_names]
         pattern = re.escape(copy_prefix) + r"([a-zA-Z0-9_]+)\.\d{8}\.json$"
         for obj in response["Contents"]:
             m = re.match(pattern, obj["Key"])
-            if m is not None and m.group(1) in core_schemas:
-                files.append(f"{m.group(1)}.json")
+            if m is not None and m.group(1) in CORE_SCHEMAS:
+                files.append(m.group(1))
     return files
 
 
@@ -440,12 +439,10 @@ def get_dict_of_core_schema_file_info(
       ...
       }
     """
-    key_map = dict(
-        [
-            (create_object_key(prefix=prefix, filename=s), s)
-            for s in core_schema_file_names
-        ]
-    )
+    key_map = {
+        create_object_key(prefix=prefix, filename=file_name): file_name
+        for file_name in core_schema_file_names.values()
+    }
     file_info = get_dict_of_file_info(
         s3_client=s3_client, bucket=bucket, keys=list(key_map.keys())
     )
@@ -491,32 +488,6 @@ def iterate_through_top_level(
         ]
 
 
-def is_dict_corrupt(input_dict: dict) -> bool:
-    """
-    Checks that all the keys, included nested keys, don't contain '$' or '.'
-
-    Parameters
-    ----------
-    input_dict : dict
-
-    Returns
-    -------
-    bool
-      True if input_dict is not a dict, or if nested dictionary keys contain
-      forbidden characters. False otherwise.
-
-    """
-    if not isinstance(input_dict, dict):
-        return True
-    for key, value in input_dict.items():
-        if "$" in key or "." in key:
-            return True
-        elif isinstance(value, dict):
-            if is_dict_corrupt(value):
-                return True
-    return False
-
-
 def download_json_file_from_s3(
     s3_client: S3Client, bucket: str, object_key: str
 ) -> Optional[dict]:
@@ -578,44 +549,34 @@ def build_metadata_record_from_prefix(
       there are issues with Metadata construction.
 
     """
-    file_keys = [
-        create_object_key(prefix=prefix, filename=file_name)
-        for file_name in core_schema_file_names
-    ]
-    s3_file_responses = get_dict_of_file_info(
-        s3_client=s3_client, bucket=bucket, keys=file_keys
+    core_files_infos = get_dict_of_core_schema_file_info(
+        s3_client=s3_client, bucket=bucket, prefix=prefix
     )
     record_name = prefix.strip("/") if optional_name is None else optional_name
     try:
-        metadata_dict = {
-            "name": record_name,
-            "location": get_s3_location(bucket=bucket, prefix=prefix),
-        }
-        if optional_created is not None:
-            metadata_dict["created"] = optional_created
-        if optional_external_links is not None:
-            metadata_dict["external_links"] = optional_external_links
-        for object_key, response_data in s3_file_responses.items():
+        core_jsons = dict()
+        for field_name, file_name in core_schema_file_names.items():
+            response_data = core_files_infos.get(file_name)
             if response_data is not None:
-                field_name = object_key.split("/")[-1].replace(".json", "")
+                object_key = create_object_key(prefix, file_name)
                 json_contents = download_json_file_from_s3(
                     s3_client=s3_client, bucket=bucket, object_key=object_key
                 )
                 if json_contents is not None:
-                    is_corrupt = is_dict_corrupt(input_dict=json_contents)
-                    if not is_corrupt:
-                        metadata_dict[field_name] = json_contents
-        # TODO: We should handle constructing the Metadata file in a better way
-        #  in aind-data-schema. By using model_validate, a lot of info from the
-        #  original files get removed. For now, we can use model_construct
-        #  until a better method is implemented in aind-data-schema. This will
-        #  mark all the initial files as metadata_status=Unknown
-        metadata_dict = Metadata.model_construct(
-            **metadata_dict
-        ).model_dump_json(warnings=False, by_alias=True)
+                    core_jsons[field_name] = json_contents
+        # Construct Metadata file using core schema jsons
+        # Validation and de/serialization are handled in aind-data-schema
+        metadata_dict = create_metadata_json(
+            name=record_name,
+            location=get_s3_location(bucket=bucket, prefix=prefix),
+            core_jsons=core_jsons,
+            optional_created=optional_created,
+            optional_external_links=optional_external_links,
+        )
+        metadata_str = json.dumps(metadata_dict)
     except Exception:
-        metadata_dict = None
-    return metadata_dict
+        metadata_str = None
+    return metadata_str
 
 
 def cond_copy_then_sync_core_json_files(
@@ -705,17 +666,13 @@ def copy_core_json_files(
     """
     tgt_copy_subdir = copy_original_md_subdir.strip("/")
     tgt_copy_prefix = create_object_key(prefix, tgt_copy_subdir)
-    core_files_keys = [
-        create_object_key(prefix=prefix, filename=s)
-        for s in core_schema_file_names
-    ]
-    core_files_infos = get_dict_of_file_info(
-        s3_client=s3_client, bucket=bucket, keys=core_files_keys
+    core_files_infos = get_dict_of_core_schema_file_info(
+        s3_client=s3_client, bucket=bucket, prefix=prefix
     )
-    for file_name in core_schema_file_names:
+    for file_name in core_schema_file_names.values():
         source = create_object_key(prefix, file_name)
         source_location = get_s3_location(bucket=bucket, prefix=source)
-        source_file_info = core_files_infos[source]
+        source_file_info = core_files_infos[file_name]
         if source_file_info is not None:
             date_stamp = source_file_info["last_modified"].strftime("%Y%m%d")
             target = create_object_key(
@@ -766,16 +723,11 @@ def sync_core_json_files(
     None
     """
     md_record_json = json.loads(metadata_json)
-    core_files_keys = [
-        create_object_key(prefix=prefix, filename=s)
-        for s in core_schema_file_names
-    ]
-    core_files_infos = get_dict_of_file_info(
-        s3_client=s3_client, bucket=bucket, keys=core_files_keys
+    core_files_infos = get_dict_of_core_schema_file_info(
+        s3_client=s3_client, bucket=bucket, prefix=prefix
     )
-    for file_name in core_schema_file_names:
+    for field_name, file_name in core_schema_file_names.items():
         object_key = create_object_key(prefix, file_name)
-        field_name = file_name.replace(".json", "")
         location = get_s3_location(bucket=bucket, prefix=object_key)
         if (
             field_name in md_record_json
@@ -785,7 +737,7 @@ def sync_core_json_files(
             field_contents_str = json.dumps(field_contents)
             # Core schema jsons are created if they don't already exist.
             # Otherwise, they are only updated if their contents are outdated.
-            if core_files_infos[object_key] is None:
+            if core_files_infos[file_name] is None:
                 logging.info(f"Uploading new {field_name} to {location}")
                 response = upload_json_str_to_s3(
                     bucket=bucket,
@@ -795,7 +747,7 @@ def sync_core_json_files(
                 )
                 logging.debug(response)
             else:
-                s3_object_hash = core_files_infos[object_key]["e_tag"].strip(
+                s3_object_hash = core_files_infos[file_name]["e_tag"].strip(
                     '"'
                 )
                 core_field_md5_hash = compute_md5_hash(field_contents_str)
@@ -818,7 +770,7 @@ def sync_core_json_files(
         else:
             # If a core field is None but the core json exists,
             # delete the core json.
-            if core_files_infos[object_key] is not None:
+            if core_files_infos[file_name] is not None:
                 logging.info(
                     f"{field_name} not found in metadata.nd.json for "
                     f"{prefix} but {location} exists! Deleting."
diff --git a/tests/resources/utils/example_metadata.nd.json b/tests/resources/utils/example_metadata.nd.json
index 96d9124..fa1a36f 100644
--- a/tests/resources/utils/example_metadata.nd.json
+++ b/tests/resources/utils/example_metadata.nd.json
@@ -4,114 +4,139 @@
    "created": "2024-05-13T22:01:56.035469",
    "data_description": null,
    "describedBy": "https://raw.githubusercontent.com/AllenNeuralDynamics/aind-data-schema/main/src/aind_data_schema/core/metadata.py",
-   "external_links": [],
+   "external_links": {},
    "instrument": null,
    "last_modified": "2024-05-13T22:01:56.035475",
    "location": "s3://aind-ephys-data-dev-u5u0i5/ecephys_642478_2023-01-17_13-56-29",
-   "metadata_status": "Unknown",
+   "metadata_status": "Valid",
    "name": "ecephys_642478_2023-01-17_13-56-29",
    "procedures": null,
    "processing": {
-      "data_processes": [
-         {
-            "code_url": "https://github.com/AllenNeuralDynamics/aind-data-transfer",
-            "end_date_time": "2023-01-20T19:13:36.434644+00:00",
-            "input_location": "\\\\allen\\programs\\aind\\workgroups\\ephys\\data\\ephys\\642478_2023-01-17_13-56-29",
-            "name": "Ephys preprocessing",
-            "notes": null,
-            "output_location": "s3://aind-ephys-data/ecephys_642478_2023-01-17_13-56-29",
-            "parameters": {
-               "aws_secret_names": {
-                  "code_ocean_api_token_name": "codeocean-api-token",
-                  "region": "us-west-2",
-                  "video_encryption_password": "video_encryption_password"
-               },
-               "clip_data_job": {
-                  "clip_kwargs": {}
-               },
-               "compress_data_job": {
-                  "compressor": {
-                     "compressor_name": "wavpack",
-                     "kwargs": {
-                        "level": 3
+      "analyses": [],
+      "describedBy": "https://raw.githubusercontent.com/AllenNeuralDynamics/aind-data-schema/main/src/aind_data_schema/core/processing.py",
+      "notes": null,
+      "processing_pipeline": {
+         "data_processes": [
+            {
+               "code_url": "https://github.com/AllenNeuralDynamics/aind-data-transfer",
+               "code_version": null,
+               "end_date_time": "2023-01-20T19:13:36.434644Z",
+               "input_location": "\\\\allen\\programs\\aind\\workgroups\\ephys\\data\\ephys\\642478_2023-01-17_13-56-29",
+               "name": "Ephys preprocessing",
+               "notes": null,
+               "output_location": "s3://aind-ephys-data/ecephys_642478_2023-01-17_13-56-29",
+               "outputs": {},
+               "parameters": {
+                  "aws_secret_names": {
+                     "code_ocean_api_token_name": "codeocean-api-token",
+                     "region": "us-west-2",
+                     "video_encryption_password": "video_encryption_password"
+                  },
+                  "clip_data_job": {
+                     "clip_kwargs": {}
+                  },
+                  "compress_data_job": {
+                     "compressor": {
+                        "compressor_name": "wavpack",
+                        "kwargs": {
+                           "level": 3
+                        }
+                     },
+                     "format_kwargs": {},
+                     "scale_params": {},
+                     "write_kwargs": {
+                        "chunk_duration": "1s",
+                        "n_jobs": 24,
+                        "progress_bar": true
                      }
                   },
-                  "format_kwargs": {},
-                  "scale_params": {},
-                  "write_kwargs": {
-                     "chunk_duration": "1s",
-                     "n_jobs": 24,
-                     "progress_bar": true
+                  "data": {
+                     "name": "openephys"
+                  },
+                  "endpoints": {
+                     "code_repo_location": "https://github.com/AllenNeuralDynamics/aind-data-transfer",
+                     "codeocean_domain": "https://codeocean.allenneuraldynamics.org",
+                     "dest_data_dir": "ecephys_642478_2023-01-17_13-56-29",
+                     "gcp_prefix": "ecephys_642478_2023-01-17_13-56-29",
+                     "metadata_service_url": "http://aind-metadata-service",
+                     "raw_data_dir": "\\\\allen\\programs\\aind\\workgroups\\ephys\\data\\ephys\\642478_2023-01-17_13-56-29",
+                     "s3_bucket": "aind-ephys-data",
+                     "s3_prefix": "ecephys_642478_2023-01-17_13-56-29"
+                  },
+                  "jobs": {
+                     "attach_metadata": true,
+                     "clip": true,
+                     "compress": true,
+                     "trigger_codeocean_job": true,
+                     "upload_to_gcp": false,
+                     "upload_to_s3": true
+                  },
+                  "logging": {
+                     "level": "INFO"
+                  },
+                  "trigger_codeocean_job": {
+                     "bucket": "aind-ephys-data",
+                     "capsule_id": "648473aa-791e-4372-bd25-205cc587ec56",
+                     "job_type": "openephys",
+                     "prefix": "ecephys_642478_2023-01-17_13-56-29"
+                  },
+                  "upload_data_job": {
+                     "dryrun": false
                   }
                },
-               "data": {
-                  "name": "openephys"
-               },
-               "endpoints": {
-                  "code_repo_location": "https://github.com/AllenNeuralDynamics/aind-data-transfer",
-                  "codeocean_domain": "https://codeocean.allenneuraldynamics.org",
-                  "dest_data_dir": "ecephys_642478_2023-01-17_13-56-29",
-                  "gcp_prefix": "ecephys_642478_2023-01-17_13-56-29",
-                  "metadata_service_url": "http://aind-metadata-service",
-                  "raw_data_dir": "\\\\allen\\programs\\aind\\workgroups\\ephys\\data\\ephys\\642478_2023-01-17_13-56-29",
-                  "s3_bucket": "aind-ephys-data",
-                  "s3_prefix": "ecephys_642478_2023-01-17_13-56-29"
-               },
-               "jobs": {
-                  "attach_metadata": true,
-                  "clip": true,
-                  "compress": true,
-                  "trigger_codeocean_job": true,
-                  "upload_to_gcp": false,
-                  "upload_to_s3": true
-               },
-               "logging": {
-                  "level": "INFO"
-               },
-               "trigger_codeocean_job": {
-                  "bucket": "aind-ephys-data",
-                  "capsule_id": "648473aa-791e-4372-bd25-205cc587ec56",
-                  "job_type": "openephys",
-                  "prefix": "ecephys_642478_2023-01-17_13-56-29"
-               },
-               "upload_data_job": {
-                  "dryrun": false
-               }
-            },
-            "start_date_time": "2023-01-20T19:06:02.945386+00:00",
-            "version": "0.2.9"
-         }
-      ],
-      "describedBy": "https://raw.githubusercontent.com/AllenNeuralDynamics/aind-data-schema/main/src/aind_data_schema/processing.py",
-      "pipeline_url": null,
-      "pipeline_version": null,
-      "schema_version": "0.1.0"
+               "resources": null,
+               "software_version": "0.2.9",
+               "start_date_time": "2023-01-20T19:06:02.945386Z"
+            }
+         ],
+         "note": null,
+         "pipeline_url": null,
+         "pipeline_version": null,
+         "processor_full_name": "service"
+      },
+      "schema_version": "1.1.3"
    },
    "quality_control": null,
    "rig": null,
-   "schema_version": "1.0.0",
+   "schema_version": "1.1.1",
    "session": null,
    "subject": {
+      "alleles": [],
       "background_strain": null,
-      "breeding_group": "Chat-IRES-Cre-neo",
+      "breeding_info": {
+         "breeding_group": "Chat-IRES-Cre-neo",
+         "maternal_genotype": "Chat-IRES-Cre-neo/Chat-IRES-Cre-neo",
+         "maternal_id": "624133",
+         "paternal_genotype": "Chat-IRES-Cre-neo/Chat-IRES-Cre-neo",
+         "paternal_id": "624115"
+      },
       "date_of_birth": "2022-07-16",
-      "describedBy": "https://raw.githubusercontent.com/AllenNeuralDynamics/aind-data-schema/main/site-packages/aind_data_schema/subject.py",
+      "describedBy": "https://raw.githubusercontent.com/AllenNeuralDynamics/aind-data-schema/main/src/aind_data_schema/core/subject.py",
       "genotype": "Chat-IRES-Cre-neo/Chat-IRES-Cre-neo",
-      "home_cage_enrichment": null,
-      "light_cycle": null,
-      "maternal_genotype": "Chat-IRES-Cre-neo/Chat-IRES-Cre-neo",
-      "maternal_id": "624133",
-      "mgi_allele_ids": null,
+      "housing": null,
       "notes": null,
-      "paternal_genotype": "Chat-IRES-Cre-neo/Chat-IRES-Cre-neo",
-      "paternal_id": "624115",
       "restrictions": null,
       "rrid": null,
-      "schema_version": "0.2.2",
+      "schema_version": "1.0.0",
       "sex": "Male",
-      "source": null,
-      "species": "Mus musculus",
+      "source": {
+         "abbreviation": "AI",
+         "name": "Allen Institute",
+         "registry": {
+            "abbreviation": "ROR",
+            "name": "Research Organization Registry"
+         },
+         "registry_identifier": "03cpe7c52"
+      },
+      "species": {
+         "name": "Mus musculus",
+         "registry": {
+            "abbreviation": "NCBI",
+            "name": "National Center for Biotechnology Information"
+         },
+         "registry_identifier": "NCBI:txid10090"
+      },
       "subject_id": "642478",
-      "wellness_reports": null
+      "wellness_reports": []
    }
 }
\ No newline at end of file
diff --git a/tests/resources/utils/example_metadata1.nd.json b/tests/resources/utils/example_metadata1.nd.json
index 798da14..b9588de 100644
--- a/tests/resources/utils/example_metadata1.nd.json
+++ b/tests/resources/utils/example_metadata1.nd.json
@@ -52,7 +52,7 @@
       "subject_id": "567890"
    },
    "describedBy": "https://raw.githubusercontent.com/AllenNeuralDynamics/aind-data-schema/main/src/aind_data_schema/core/metadata.py",
-   "external_links": [],
+   "external_links": {},
    "instrument": null,
    "last_modified": "2024-05-15T17:41:26.697535",
    "location": "s3://aind-ephys-data-dev-u5u0i5/ecephys_567890_2000-01-01_04-00-00",
@@ -97,7 +97,7 @@
    },
    "quality_control": null,
    "rig": null,
-   "schema_version": "1.0.0",
+   "schema_version": "1.1.1",
    "session": null,
    "subject": {
       "background_strain": null,
diff --git a/tests/resources/utils/example_metadata2.nd.json b/tests/resources/utils/example_metadata2.nd.json
index 6f7b08f..e03a770 100644
--- a/tests/resources/utils/example_metadata2.nd.json
+++ b/tests/resources/utils/example_metadata2.nd.json
@@ -52,7 +52,7 @@
       "subject_id": "655019"
    },
    "describedBy": "https://raw.githubusercontent.com/AllenNeuralDynamics/aind-data-schema/main/src/aind_data_schema/core/metadata.py",
-   "external_links": [],
+   "external_links": {},
    "instrument": null,
    "last_modified": "2024-05-15T17:41:30.131278",
    "location": "s3://aind-ephys-data-dev-u5u0i5/ecephys_655019_2000-01-01_01-01-02",
@@ -175,7 +175,7 @@
    },
    "quality_control": null,
    "rig": null,
-   "schema_version": "1.0.0",
+   "schema_version": "1.1.1",
    "session": null,
    "subject": {
       "background_strain": null,
diff --git a/tests/resources/utils/processing.json b/tests/resources/utils/processing.json
index dc67940..319fe2c 100644
--- a/tests/resources/utils/processing.json
+++ b/tests/resources/utils/processing.json
@@ -1,76 +1,85 @@
 {
-    "describedBy": "https://raw.githubusercontent.com/AllenNeuralDynamics/aind-data-schema/main/src/aind_data_schema/processing.py",
-    "schema_version": "0.1.0",
-    "pipeline_version": null,
-    "pipeline_url": null,
-    "data_processes": [
-        {
+   "describedBy": "https://raw.githubusercontent.com/AllenNeuralDynamics/aind-data-schema/main/src/aind_data_schema/core/processing.py",
+   "schema_version": "1.1.3",
+   "processing_pipeline": {
+      "data_processes": [
+         {
             "name": "Ephys preprocessing",
-            "version": "0.2.9",
-            "start_date_time": "2023-01-20T19:06:02.945386+00:00",
-            "end_date_time": "2023-01-20T19:13:36.434644+00:00",
+            "software_version": "0.2.9",
+            "start_date_time": "2023-01-20T19:06:02.945386Z",
+            "end_date_time": "2023-01-20T19:13:36.434644Z",
             "input_location": "\\\\allen\\programs\\aind\\workgroups\\ephys\\data\\ephys\\642478_2023-01-17_13-56-29",
             "output_location": "s3://aind-ephys-data/ecephys_642478_2023-01-17_13-56-29",
             "code_url": "https://github.com/AllenNeuralDynamics/aind-data-transfer",
+            "code_version": null,
             "parameters": {
-                "endpoints": {
-                    "raw_data_dir": "\\\\allen\\programs\\aind\\workgroups\\ephys\\data\\ephys\\642478_2023-01-17_13-56-29",
-                    "dest_data_dir": "ecephys_642478_2023-01-17_13-56-29",
-                    "s3_bucket": "aind-ephys-data",
-                    "s3_prefix": "ecephys_642478_2023-01-17_13-56-29",
-                    "gcp_prefix": "ecephys_642478_2023-01-17_13-56-29",
-                    "codeocean_domain": "https://codeocean.allenneuraldynamics.org",
-                    "code_repo_location": "https://github.com/AllenNeuralDynamics/aind-data-transfer",
-                    "metadata_service_url": "http://aind-metadata-service"
-                },
-                "aws_secret_names": {
-                    "region": "us-west-2",
-                    "video_encryption_password": "video_encryption_password",
-                    "code_ocean_api_token_name": "codeocean-api-token"
-                },
-                "jobs": {
-                    "clip": true,
-                    "compress": true,
-                    "attach_metadata": true,
-                    "upload_to_s3": true,
-                    "upload_to_gcp": false,
-                    "trigger_codeocean_job": true
-                },
-                "data": {
-                    "name": "openephys"
-                },
-                "clip_data_job": {
-                    "clip_kwargs": {}
-                },
-                "compress_data_job": {
-                    "write_kwargs": {
-                        "n_jobs": 24,
-                        "chunk_duration": "1s",
-                        "progress_bar": true
-                    },
-                    "format_kwargs": {},
-                    "compressor": {
-                        "compressor_name": "wavpack",
-                        "kwargs": {
-                            "level": 3
-                        }
-                    },
-                    "scale_params": {}
-                },
-                "upload_data_job": {
-                    "dryrun": false
-                },
-                "trigger_codeocean_job": {
-                    "capsule_id": "648473aa-791e-4372-bd25-205cc587ec56",
-                    "job_type": "openephys",
-                    "bucket": "aind-ephys-data",
-                    "prefix": "ecephys_642478_2023-01-17_13-56-29"
-                },
-                "logging": {
-                    "level": "INFO"
-                }
+               "endpoints": {
+                  "raw_data_dir": "\\\\allen\\programs\\aind\\workgroups\\ephys\\data\\ephys\\642478_2023-01-17_13-56-29",
+                  "dest_data_dir": "ecephys_642478_2023-01-17_13-56-29",
+                  "s3_bucket": "aind-ephys-data",
+                  "s3_prefix": "ecephys_642478_2023-01-17_13-56-29",
+                  "gcp_prefix": "ecephys_642478_2023-01-17_13-56-29",
+                  "codeocean_domain": "https://codeocean.allenneuraldynamics.org",
+                  "code_repo_location": "https://github.com/AllenNeuralDynamics/aind-data-transfer",
+                  "metadata_service_url": "http://aind-metadata-service"
+               },
+               "aws_secret_names": {
+                  "region": "us-west-2",
+                  "video_encryption_password": "video_encryption_password",
+                  "code_ocean_api_token_name": "codeocean-api-token"
+               },
+               "jobs": {
+                  "clip": true,
+                  "compress": true,
+                  "attach_metadata": true,
+                  "upload_to_s3": true,
+                  "upload_to_gcp": false,
+                  "trigger_codeocean_job": true
+               },
+               "data": {
+                  "name": "openephys"
+               },
+               "clip_data_job": {
+                  "clip_kwargs": {}
+               },
+               "compress_data_job": {
+                  "write_kwargs": {
+                     "n_jobs": 24,
+                     "chunk_duration": "1s",
+                     "progress_bar": true
+                  },
+                  "format_kwargs": {},
+                  "compressor": {
+                     "compressor_name": "wavpack",
+                     "kwargs": {
+                        "level": 3
+                     }
+                  },
+                  "scale_params": {}
+               },
+               "upload_data_job": {
+                  "dryrun": false
+               },
+               "trigger_codeocean_job": {
+                  "capsule_id": "648473aa-791e-4372-bd25-205cc587ec56",
+                  "job_type": "openephys",
+                  "bucket": "aind-ephys-data",
+                  "prefix": "ecephys_642478_2023-01-17_13-56-29"
+               },
+               "logging": {
+                  "level": "INFO"
+               }
             },
-            "notes": null
-        }
-    ]
+            "outputs": {},
+            "notes": null,
+            "resources": null
+         }
+      ],
+      "processor_full_name": "service",
+      "pipeline_version": null,
+      "pipeline_url": null,
+      "note": null
+   },
+   "analyses": [],
+   "notes": null
 }
\ No newline at end of file
diff --git a/tests/resources/utils/subject.json b/tests/resources/utils/subject.json
index af1e7a9..30bf2ce 100644
--- a/tests/resources/utils/subject.json
+++ b/tests/resources/utils/subject.json
@@ -1,23 +1,39 @@
 {
-    "describedBy": "https://raw.githubusercontent.com/AllenNeuralDynamics/aind-data-schema/main/site-packages/aind_data_schema/subject.py",
-    "schema_version": "0.2.2",
-    "species": "Mus musculus",
-    "subject_id": "642478",
-    "sex": "Male",
-    "date_of_birth": "2022-07-16",
-    "genotype": "Chat-IRES-Cre-neo/Chat-IRES-Cre-neo",
-    "mgi_allele_ids": null,
-    "background_strain": null,
-    "source": null,
-    "rrid": null,
-    "restrictions": null,
-    "breeding_group": "Chat-IRES-Cre-neo",
-    "maternal_id": "624133",
-    "maternal_genotype": "Chat-IRES-Cre-neo/Chat-IRES-Cre-neo",
-    "paternal_id": "624115",
-    "paternal_genotype": "Chat-IRES-Cre-neo/Chat-IRES-Cre-neo",
-    "light_cycle": null,
-    "home_cage_enrichment": null,
-    "wellness_reports": null,
-    "notes": null
+   "describedBy": "https://raw.githubusercontent.com/AllenNeuralDynamics/aind-data-schema/main/src/aind_data_schema/core/subject.py",
+   "schema_version": "1.0.0",
+   "subject_id": "642478",
+   "sex": "Male",
+   "date_of_birth": "2022-07-16",
+   "genotype": "Chat-IRES-Cre-neo/Chat-IRES-Cre-neo",
+   "species": {
+      "name": "Mus musculus",
+      "registry": {
+         "name": "National Center for Biotechnology Information",
+         "abbreviation": "NCBI"
+      },
+      "registry_identifier": "NCBI:txid10090"
+   },
+   "alleles": [],
+   "background_strain": null,
+   "breeding_info": {
+      "breeding_group": "Chat-IRES-Cre-neo",
+      "maternal_id": "624133",
+      "maternal_genotype": "Chat-IRES-Cre-neo/Chat-IRES-Cre-neo",
+      "paternal_id": "624115",
+      "paternal_genotype": "Chat-IRES-Cre-neo/Chat-IRES-Cre-neo"
+   },
+   "source": {
+      "name": "Allen Institute",
+      "abbreviation": "AI",
+      "registry": {
+         "name": "Research Organization Registry",
+         "abbreviation": "ROR"
+      },
+      "registry_identifier": "03cpe7c52"
+   },
+   "rrid": null,
+   "restrictions": null,
+   "wellness_reports": [],
+   "housing": null,
+   "notes": null
 }
\ No newline at end of file
diff --git a/tests/test_aind_bucket_indexer.py b/tests/test_aind_bucket_indexer.py
index 2528a6d..631fd1e 100644
--- a/tests/test_aind_bucket_indexer.py
+++ b/tests/test_aind_bucket_indexer.py
@@ -70,7 +70,7 @@ def test_write_root_file_with_record_info_same_hash(
                     "last_modified": datetime(
                         2024, 5, 15, 17, 41, 28, tzinfo=timezone.utc
                     ),
-                    "e_tag": '"275d922d2a1e547f2e0f35b5cc54f493"',
+                    "e_tag": '"a0f1022e3b4a8bc60e63e3677171f784"',
                     "version_id": "version_id",
                 },
                 prefix="ecephys_642478_2023-01-17_13-56-29",
@@ -201,7 +201,7 @@ def test_copy_file_from_root_to_subdir(
     )
     @patch(
         "aind_data_asset_indexer.aind_bucket_indexer.core_schema_file_names",
-        ["subject.json"],
+        {"subject": "subject.json"},
     )  # Mocking this to limit for loop to one iteration
     def test_resolve_schema_information_case_1(
         self,
@@ -229,7 +229,7 @@ def test_resolve_schema_information_case_1(
             prefix="ecephys_642478_2023-01-17_13-56-29",
             s3_client=mock_s3_client,
             core_schema_info_in_root=core_schema_info_in_root,
-            list_of_schemas_in_copy_subdir=["subject.json"],
+            list_of_schemas_in_copy_subdir=["subject"],
             docdb_record=self.example_md_record,
         )
         self.assertEqual(dict(), docdb_fields_to_update)
@@ -260,7 +260,7 @@ def test_resolve_schema_information_case_1(
     )
     @patch(
         "aind_data_asset_indexer.aind_bucket_indexer.core_schema_file_names",
-        ["subject.json"],
+        {"subject": "subject.json"},
     )  # Mocking this to limit for loop to one iteration
     def test_resolve_schema_information_case_2(
         self,
@@ -326,7 +326,7 @@ def test_resolve_schema_information_case_2(
     )
     @patch(
         "aind_data_asset_indexer.aind_bucket_indexer.core_schema_file_names",
-        ["subject.json"],
+        {"subject": "subject.json"},
     )  # Mocking this to limit for loop to one iteration
     def test_resolve_schema_information_case_3(
         self,
@@ -346,7 +346,7 @@ def test_resolve_schema_information_case_3(
             prefix="ecephys_642478_2023-01-17_13-56-29",
             s3_client=mock_s3_client,
             core_schema_info_in_root=core_schema_info_in_root,
-            list_of_schemas_in_copy_subdir=["subject.json"],
+            list_of_schemas_in_copy_subdir=["subject"],
             docdb_record=self.example_md_record,
         )
         self.assertEqual(dict(), docdb_fields_to_update)
@@ -378,7 +378,7 @@ def test_resolve_schema_information_case_3(
     @patch("aind_data_asset_indexer.aind_bucket_indexer.get_dict_of_file_info")
     @patch(
         "aind_data_asset_indexer.aind_bucket_indexer.core_schema_file_names",
-        ["subject.json"],
+        {"subject": "subject.json"},
     )  # Mocking this to limit for loop to one iteration
     def test_resolve_schema_information_case_4(
         self,
@@ -454,7 +454,7 @@ def test_resolve_schema_information_case_4(
     )
     @patch(
         "aind_data_asset_indexer.aind_bucket_indexer.core_schema_file_names",
-        ["subject.json"],
+        {"subject": "subject.json"},
     )  # Mocking this to limit for loop to one iteration
     def test_resolve_schema_information_case_5(
         self,
@@ -485,7 +485,7 @@ def test_resolve_schema_information_case_5(
                     prefix="ecephys_642478_2023-01-17_13-56-29",
                     s3_client=mock_s3_client,
                     core_schema_info_in_root=core_schema_info_in_root,
-                    list_of_schemas_in_copy_subdir=["subject.json"],
+                    list_of_schemas_in_copy_subdir=["subject"],
                     docdb_record=dict(),
                 )
             )
@@ -516,7 +516,7 @@ def test_resolve_schema_information_case_5(
     )
     @patch(
         "aind_data_asset_indexer.aind_bucket_indexer.core_schema_file_names",
-        ["subject.json"],
+        {"subject": "subject.json"},
     )  # Mocking this to limit for loop to one iteration
     def test_resolve_schema_information_case_6(
         self,
@@ -579,7 +579,7 @@ def test_resolve_schema_information_case_6(
     )
     @patch(
         "aind_data_asset_indexer.aind_bucket_indexer.core_schema_file_names",
-        ["subject.json"],
+        {"subject": "subject.json"},
     )  # Mocking this to limit for loop to one iteration
     def test_resolve_schema_information_case_6_corrupt_download(
         self,
@@ -652,7 +652,7 @@ def test_resolve_schema_information_case_6_corrupt_download(
     )
     @patch(
         "aind_data_asset_indexer.aind_bucket_indexer.core_schema_file_names",
-        ["subject.json"],
+        {"subject": "subject.json"},
     )  # Mocking this to limit for loop to one iteration
     def test_resolve_schema_information_case_7(
         self,
@@ -674,7 +674,7 @@ def test_resolve_schema_information_case_7(
                     prefix="ecephys_642478_2023-01-17_13-56-29",
                     s3_client=mock_s3_client,
                     core_schema_info_in_root=core_schema_info_in_root,
-                    list_of_schemas_in_copy_subdir=["subject.json"],
+                    list_of_schemas_in_copy_subdir=["subject"],
                     docdb_record=dict(),
                 )
             )
@@ -704,7 +704,7 @@ def test_resolve_schema_information_case_7(
     )
     @patch(
         "aind_data_asset_indexer.aind_bucket_indexer.core_schema_file_names",
-        ["subject.json"],
+        {"subject": "subject.json"},
     )  # Mocking this to limit for loop to one iteration
     def test_resolve_schema_information_case_8(
         self,
@@ -1315,6 +1315,62 @@ def test_process_prefix_no_record_yes_file_good_file(
         )
         mock_upload_metadata_json_str_to_s3.assert_not_called()
 
+    @patch(
+        "aind_data_asset_indexer.aind_bucket_indexer."
+        "upload_metadata_json_str_to_s3"
+    )
+    @patch(
+        "aind_data_asset_indexer.aind_bucket_indexer."
+        "cond_copy_then_sync_core_json_files"
+    )
+    @patch("aind_data_asset_indexer.aind_bucket_indexer.is_dict_corrupt")
+    @patch(
+        "aind_data_asset_indexer.aind_bucket_indexer."
+        "download_json_file_from_s3"
+    )
+    @patch("aind_data_asset_indexer.aind_bucket_indexer.does_s3_object_exist")
+    @patch("aind_data_asset_indexer.aind_bucket_indexer.MongoClient")
+    @patch("boto3.client")
+    def test_process_prefix_no_record_yes_file_corrupt_file(
+        self,
+        mock_s3_client: MagicMock,
+        mock_docdb_client: MagicMock,
+        mock_does_s3_object_exist: MagicMock,
+        mock_download_json_file_from_s3: MagicMock,
+        mock_is_dict_corrupt: MagicMock,
+        mock_cond_copy_then_sync_core_json_files: MagicMock,
+        mock_upload_metadata_json_str_to_s3: MagicMock,
+    ):
+        """Tests _process_prefix method when there is no record in DocDb,
+        there is and there is metadata.nd.json file in S3, and the file can
+        be serialized to json, but its contents are corrupt."""
+        mock_db = MagicMock()
+        mock_docdb_client.__getitem__.return_value = mock_db
+        mock_collection = MagicMock()
+        mock_db.__getitem__.return_value = mock_collection
+
+        mock_does_s3_object_exist.return_value = True
+        mocked_downloaded_record = deepcopy(self.example_md_record)
+        mock_download_json_file_from_s3.return_value = mocked_downloaded_record
+        mock_is_dict_corrupt.return_value = True
+
+        location_to_id_map = dict()
+        with self.assertLogs(level="DEBUG") as captured:
+            self.basic_job._process_prefix(
+                s3_prefix="ecephys_642478_2023-01-17_13-56-29",
+                docdb_client=mock_docdb_client,
+                s3_client=mock_s3_client,
+                location_to_id_map=location_to_id_map,
+            )
+        expected_log_messages = [
+            "WARNING:root:Metadata record for s3://aind-ephys-data-dev-u5u0i5/"
+            "ecephys_642478_2023-01-17_13-56-29 is corrupt!"
+        ]
+        self.assertEqual(expected_log_messages, captured.output)
+        mock_collection.assert_not_called()
+        mock_cond_copy_then_sync_core_json_files.assert_not_called()
+        mock_upload_metadata_json_str_to_s3.assert_not_called()
+
     @patch(
         "aind_data_asset_indexer.aind_bucket_indexer."
         "upload_metadata_json_str_to_s3"
diff --git a/tests/test_codeocean_bucket_indexer.py b/tests/test_codeocean_bucket_indexer.py
index 1b7b944..5b2f2cc 100644
--- a/tests/test_codeocean_bucket_indexer.py
+++ b/tests/test_codeocean_bucket_indexer.py
@@ -73,16 +73,17 @@ def setUpClass(cls) -> None:
                 },
             },
         ]
+        # corresponds to cls.example_codeocean_records[1]
         cls.example_dict_of_file_info = {
-            "ecephys_642478_2023-01-17_13-56-29/acquisition.json": None,
-            "ecephys_642478_2023-01-17_13-56-29/data_description.json": None,
-            "ecephys_642478_2023-01-17_13-56-29/instrument.json": None,
-            "ecephys_642478_2023-01-17_13-56-29/procedures.json": None,
-            "ecephys_642478_2023-01-17_13-56-29/processing.json": None,
-            "ecephys_642478_2023-01-17_13-56-29/quality_control.json": None,
-            "ecephys_642478_2023-01-17_13-56-29/rig.json": None,
-            "ecephys_642478_2023-01-17_13-56-29/session.json": None,
-            "ecephys_642478_2023-01-17_13-56-29/subject.json": None,
+            "666666cc-66cc-6c66-666c-6c66c6666666/acquisition.json": None,
+            "666666cc-66cc-6c66-666c-6c66c6666666/data_description.json": None,
+            "666666cc-66cc-6c66-666c-6c66c6666666/instrument.json": None,
+            "666666cc-66cc-6c66-666c-6c66c6666666/procedures.json": None,
+            "666666cc-66cc-6c66-666c-6c66c6666666/processing.json": None,
+            "666666cc-66cc-6c66-666c-6c66c6666666/quality_control.json": None,
+            "666666cc-66cc-6c66-666c-6c66c6666666/rig.json": None,
+            "666666cc-66cc-6c66-666c-6c66c6666666/session.json": None,
+            "666666cc-66cc-6c66-666c-6c66c6666666/subject.json": None,
         }
         cls.example_docdb_records = [
             {
@@ -358,7 +359,7 @@ def test_process_codeocean_record(
             ],
         )
 
-    @patch("aind_data_schema.core.metadata.Metadata.model_construct")
+    @patch("aind_data_asset_indexer.utils.create_metadata_json")
     @patch("aind_data_asset_indexer.codeocean_bucket_indexer.MongoClient")
     @patch("boto3.client")
     @patch("aind_data_asset_indexer.utils.get_dict_of_file_info")
@@ -369,7 +370,7 @@ def test_process_codeocean_record_warning(
         mock_get_dict_of_file_info: MagicMock,
         mock_s3_client: MagicMock,
         mock_docdb_client: MagicMock,
-        mock_model_construct: MagicMock,
+        mock_create_metadata_json: MagicMock,
     ):
         """Tests _process_codeocean_record when there is an issue building the
         record"""
@@ -378,8 +379,10 @@ def test_process_codeocean_record_warning(
             self.example_dict_of_file_info
         )
 
-        # Suppose there is an error using model_construct
-        mock_model_construct.side_effect = Exception("Something went wrong")
+        # Suppose there is an error creating metadata file
+        mock_create_metadata_json.side_effect = Exception(
+            "Something went wrong"
+        )
 
         with self.assertLogs(level="DEBUG") as captured:
             self.basic_job._process_codeocean_record(
diff --git a/tests/test_utils.py b/tests/test_utils.py
index 3b34ad6..c2f41dd 100644
--- a/tests/test_utils.py
+++ b/tests/test_utils.py
@@ -29,7 +29,6 @@
     get_record_from_docdb,
     get_s3_bucket_and_prefix,
     get_s3_location,
-    is_dict_corrupt,
     is_prefix_valid,
     is_record_location_valid,
     iterate_through_top_level,
@@ -145,23 +144,7 @@ def load_json_file(filename: str) -> dict:
     def test_compute_md5_hash(self):
         """Tests compute_md5_hash method"""
         md5_hash = compute_md5_hash(json.dumps(self.example_metadata_nd))
-        self.assertEqual("275d922d2a1e547f2e0f35b5cc54f493", md5_hash)
-
-    def test_is_dict_corrupt(self):
-        """Tests is_dict_corrupt method"""
-        good_contents = {"a": 1, "b": {"c": 2, "d": 3}}
-        bad_contents1 = {"a.1": 1, "b": {"c": 2, "d": 3}}
-        bad_contents2 = {"a": 1, "b": {"c": 2, "$d": 3}}
-        bad_contents3 = {"a": 1, "b": {"c": 2, "d": 3}, "$e": 4}
-        bad_contents4 = {"a": 1, "b": {"c": {"d": 3}, "$e": 4}}
-        bad_contents5 = [{"a": 1}, {"b": {"c": 2, "d": 3}}]
-        self.assertFalse(is_dict_corrupt(good_contents))
-        self.assertTrue(is_dict_corrupt(bad_contents1))
-        self.assertTrue(is_dict_corrupt(bad_contents2))
-        self.assertTrue(is_dict_corrupt(bad_contents3))
-        self.assertTrue(is_dict_corrupt(bad_contents4))
-        # noinspection PyTypeChecker
-        self.assertTrue(is_dict_corrupt(bad_contents5))
+        self.assertEqual("a0f1022e3b4a8bc60e63e3677171f784", md5_hash)
 
     def test_create_object_key(self):
         """Tests create_object_key"""
@@ -480,7 +463,7 @@ def test_list_metadata_copies(self, mock_s3_client: MagicMock):
             copy_subdir="original_metadata",
             s3_client=mock_s3_client,
         )
-        self.assertEqual(["data_description.json", "subject.json"], contents)
+        self.assertEqual(["data_description", "subject"], contents)
 
     @patch("boto3.client")
     def test_does_s3_metadata_copy_exist_none(self, mock_s3_client: MagicMock):
@@ -717,17 +700,19 @@ def test_build_metadata_record_from_prefix(
             },
         }
         mock_download_json_file.side_effect = [
-            self.example_processing,
             self.example_subject,
+            self.example_processing,
         ]
-        # noinspection PyTypeChecker
-        md = json.loads(
-            build_metadata_record_from_prefix(
-                bucket="aind-ephys-data-dev-u5u0i5",
-                prefix="ecephys_642478_2023-01-17_13-56-29",
-                s3_client=mock_s3_client,
+        # there are some userwarnings when creating Subject from json
+        with self.assertWarns(UserWarning):
+            # noinspection PyTypeChecker
+            md = json.loads(
+                build_metadata_record_from_prefix(
+                    bucket="aind-ephys-data-dev-u5u0i5",
+                    prefix="ecephys_642478_2023-01-17_13-56-29",
+                    s3_client=mock_s3_client,
+                )
             )
-        )
         mock_get_dict_of_file_info.assert_called_once()
         mock_download_json_file.assert_has_calls(
             [
@@ -735,14 +720,14 @@ def test_build_metadata_record_from_prefix(
                     s3_client=mock_s3_client,
                     bucket="aind-ephys-data-dev-u5u0i5",
                     object_key=(
-                        "ecephys_642478_2023-01-17_13-56-29/processing.json"
+                        "ecephys_642478_2023-01-17_13-56-29/subject.json"
                     ),
                 ),
                 call(
                     s3_client=mock_s3_client,
                     bucket="aind-ephys-data-dev-u5u0i5",
                     object_key=(
-                        "ecephys_642478_2023-01-17_13-56-29/subject.json"
+                        "ecephys_642478_2023-01-17_13-56-29/processing.json"
                     ),
                 ),
             ]
@@ -765,15 +750,15 @@ def test_build_metadata_record_from_prefix_with_optional_fields(
         """Tests build_metadata_record_from_prefix method when 'created' and
         'external_links' are provided"""
         mock_get_dict_of_file_info.return_value = {
-            "ecephys_642478_2023-01-17_13-56-29/acquisition.json": None,
-            "ecephys_642478_2023-01-17_13-56-29/data_description.json": None,
-            "ecephys_642478_2023-01-17_13-56-29/instrument.json": None,
-            "ecephys_642478_2023-01-17_13-56-29/procedures.json": None,
-            "ecephys_642478_2023-01-17_13-56-29/processing.json": None,
-            "ecephys_642478_2023-01-17_13-56-29/quality_control.json": None,
-            "ecephys_642478_2023-01-17_13-56-29/rig.json": None,
-            "ecephys_642478_2023-01-17_13-56-29/session.json": None,
-            "ecephys_642478_2023-01-17_13-56-29/subject.json": None,
+            "abc-123/acquisition.json": None,
+            "abc-123/data_description.json": None,
+            "abc-123/instrument.json": None,
+            "abc-123/procedures.json": None,
+            "abc-123/processing.json": None,
+            "abc-123/quality_control.json": None,
+            "abc-123/rig.json": None,
+            "abc-123/session.json": None,
+            "abc-123/subject.json": None,
         }
         # noinspection PyTypeChecker
         md = json.loads(
@@ -793,7 +778,7 @@ def test_build_metadata_record_from_prefix_with_optional_fields(
         self.assertEqual("2020-01-02T03:04:05", md["created"])
         self.assertEqual({"Code Ocean": ["123-456"]}, md["external_links"])
 
-    @patch("aind_data_asset_indexer.utils.Metadata.model_construct")
+    @patch("aind_data_asset_indexer.utils.create_metadata_json")
     @patch("boto3.client")
     @patch("aind_data_asset_indexer.utils.get_dict_of_file_info")
     @patch("aind_data_asset_indexer.utils.download_json_file_from_s3")
@@ -802,7 +787,7 @@ def test_build_metadata_record_from_prefix_error(
         mock_download_json_file: MagicMock,
         mock_get_dict_of_file_info: MagicMock,
         mock_s3_client: MagicMock,
-        mock_metadata_model_construct: MagicMock,
+        mock_create_metadata_json: MagicMock,
     ):
         """Tests build_metadata_record_from_prefix method when there is an
         error when creating the metadata record"""
@@ -830,10 +815,10 @@ def test_build_metadata_record_from_prefix_error(
             },
         }
         mock_download_json_file.side_effect = [
-            self.example_processing,
             self.example_subject,
+            self.example_processing,
         ]
-        mock_metadata_model_construct.side_effect = ValueError(
+        mock_create_metadata_json.side_effect = ValueError(
             "Error creating metadata record"
         )
         # noinspection PyTypeChecker
@@ -849,14 +834,14 @@ def test_build_metadata_record_from_prefix_error(
                     s3_client=mock_s3_client,
                     bucket="aind-ephys-data-dev-u5u0i5",
                     object_key=(
-                        "ecephys_642478_2023-01-17_13-56-29/processing.json"
+                        "ecephys_642478_2023-01-17_13-56-29/subject.json"
                     ),
                 ),
                 call(
                     s3_client=mock_s3_client,
                     bucket="aind-ephys-data-dev-u5u0i5",
                     object_key=(
-                        "ecephys_642478_2023-01-17_13-56-29/subject.json"
+                        "ecephys_642478_2023-01-17_13-56-29/processing.json"
                     ),
                 ),
             ]
@@ -955,7 +940,7 @@ def test_sync_core_json_files(
             f"INFO:root:subject is up-to-date in "
             f"{s3_loc}/subject.json. Skipping.",
         ]
-        self.assertEqual(expected_log_messages, captured.output)
+        self.assertCountEqual(expected_log_messages, captured.output)
         mock_get_dict_of_file_info.assert_called_once()
         # assert that only new or updated core jsons were uploaded to s3
         mock_upload_core_record.assert_has_calls(
@@ -1057,7 +1042,7 @@ def test_cond_copy_then_sync_core_json_files(
             f"s3://{bucket}/{pfx}/subject.json",
             "DEBUG:root:Some Message",
         ]
-        self.assertEqual(expected_output_messages, captured.output)
+        self.assertCountEqual(expected_output_messages, captured.output)
         # assert that an existing /original_metadata folder was detected
         mock_does_s3_metadata_copy_exist.assert_called_once_with(
             bucket=bucket,
@@ -1084,7 +1069,8 @@ def test_cond_copy_then_sync_core_json_files(
                     json_str=json.dumps(self.example_metadata_nd["subject"]),
                     s3_client=mock_s3_client,
                 ),
-            ]
+            ],
+            any_order=True,
         )
         mock_s3_client.delete_object.assert_not_called()
 
@@ -1200,7 +1186,7 @@ def test_cond_copy_then_sync_core_json_files_mismatch(
             f"s3://{bucket}/{pfx}/subject.json",
             "DEBUG:root:Uploaded json",
         ]
-        self.assertEqual(expected_log_messages, captured.output)
+        self.assertCountEqual(expected_log_messages, captured.output)
         # assert that the original core jsons were copied, including
         # corrupt rig.json
         mock_s3_client.copy_object.assert_has_calls(
@@ -1229,7 +1215,8 @@ def test_cond_copy_then_sync_core_json_files_mismatch(
                     },
                     Key=f"{pfx}/original_metadata/subject.20240202.json",
                 ),
-            ]
+            ],
+            any_order=True,
         )
         # assert that only valid core jsons were overwritten
         mock_upload_core_record.assert_has_calls(
@@ -1248,7 +1235,8 @@ def test_cond_copy_then_sync_core_json_files_mismatch(
                     json_str=json.dumps(self.example_metadata_nd["subject"]),
                     s3_client=mock_s3_client,
                 ),
-            ]
+            ],
+            any_order=True,
         )
         # assert the corrupt core json was deleted
         mock_s3_client.delete_object.assert_called_once_with(