[SCHEMA] BEP028 - BIDS-Prov

src/schema/objects/entities.yaml

@@ -229,6 +229,14 @@ processing:
     exploited.
   type: string
   format: label
+prov:
+  name: prov
+  display_name: Provenance group
+  description: |
+    A grouping of provenance records.
+    Defining multiple provenance records groups is appropriate when several processings have been performed on data.
+  type: string
+  format: label
 reconstruction:
   name: rec
   display_name: Reconstruction

src/schema/objects/files.yaml

@@ -102,6 +102,13 @@ code:
     (for example the one used to generate the derivatives from the raw data).
     See the [Code section](SPEC_ROOT/modality-agnostic-files.md#code)
     for more information.
+prov:
+  display_name: Provenance Records
+  file_type: directory
+  description: |
+    A directory in which to store provenance metadata.
+    See the [Provenance section](SPEC_ROOT/modality-agnostic-files.md#provenance)
+    for more information.
 derivatives:
   display_name: Derivative data
   file_type: directory

src/schema/objects/metadata.yaml

@@ -1281,6 +1281,32 @@ GeneratedBy:
           URI:
             type: string
             format: uri
+GeneratedBy:
+  name: GeneratedBy
+  display_name: Generated By
+  description: |
+    Specify the provenance of a file in the dataset, referencing the Id
+    of the Activity (or Activities) responsible for its creation.
+  anyOf:
+    - type: string
+      format: uri
+    - type: array
+      items:
+        type: string
+        format: uri
+GeneratedByProv:
+  name: GeneratedByProv
+  display_name: Generated By Prov
+  description: |
+    Specify the provenance of the dataset, referencing the Id
+    of the Activity (or Activities) responsible for its creation.
+  anyOf:
+    - type: string
+      format: uri
+    - type: array
+      items:
+        type: string
+        format: uri
 GeneticLevel:
   name: GeneticLevel
   display_name: Genetic Level
@@ -3292,6 +3318,19 @@ ShortChannelCount:
     The number of short channels. 0 indicates no short channels.
   type: integer
   minimum: 0
+SidecarGeneratedBy:
+  name: SidecarGeneratedBy
+  display_name: Sidecar Generated By
+  description: |
+    Specify the provenance of a sidecar JSON,
+    referencing the Id of the Activity (or Activities) responsible for its creation.
+  anyOf:
+    - type: string
+      format: uri
+    - type: array
+      items:
+        type: string
+        format: uri
 SinglesRate:
   name: SinglesRate
   display_name: Singles Rate

src/schema/objects/suffixes.yaml

@@ -502,6 +502,18 @@ VFA:
     Depending on the provided metadata fields and the sequence type,
     data may be eligible for DESPOT1, DESPOT2 and their variants
     ([Deoni et al. 2005](https://doi.org/10.1002/mrm.20314)).
+act:
+  value: act
+  display_name: Provenance Activity Records
+  description: |
+    Provenance Activity records for a group of provenance.
+    Activities represent the transformations that have been applied to the data.
+all:
+  value: all
+  display_name: Provenance Records
+  description: |
+    All types of provenance records (Activity, Entity, Environment, Software)
+    for a group of provenance.
 angio:
   value: angio
   display_name: Angiogram
@@ -528,6 +540,11 @@ asllabeling:
     A deidentified screenshot of the planning of the labeling slab/plane
     with respect to the imaging slab or slices.
     This screenshot is based on DICOM macro C.8.13.5.14.
+base:
+  value: base
+  display_name: Base for Provenance Records
+  description: |
+    Base fields for provenance records of a group of provenance.
 beh:
   value: beh
   display_name: Behavioral recording
@@ -612,6 +629,18 @@ electrodes:
   display_name: Electrodes
   description: |
     File that gives the location of (i)EEG electrodes.
+ent:
+  value: ent
+  display_name: Provenance Entity Records
+  description: |
+    Provenance Entity records for a group of provenance.
+    Entities are inputs and outputs of Activities.
+env:
+  value: env
+  display_name: Provenance Environment Records
+  description: |
+    Provenance Environment records for a group of provenance.
+    Environments specify the software environment in which the provenance record was obtained.
 epi:
   value: epi
   display_name: EPI
@@ -817,6 +846,12 @@ probseg:
     A probabilistic segmentation.
 
     This suffix may only be used in derivative datasets.
+soft:
+  value: soft
+  display_name: Provenance Software Records
+  description: |
+    Provenance Software records for a group of provenance.
+    The Software specifies the software package with which transformations were applied to the data.
 sbref:
   value: sbref
   display_name: Single-band reference image

src/schema/rules/checks/deprecations.yml

@@ -1,3 +1,4 @@
+---
 AnatomicalLandmarkCoordinateSystemDeprecation:
   issue:
     code: ELEKTA_NEUROMAG_DEPRECATED

src/schema/rules/dataset_metadata.yaml

@@ -16,7 +16,8 @@ dataset_description:
     EthicsApprovals: optional
     ReferencesAndLinks: optional
     DatasetDOI: optional
-    GeneratedBy: recommended
+    GeneratedBy: deprecated
+    GeneratedByProv: recommended
     SourceDatasets: recommended
 
 dataset_authors:
@@ -38,7 +39,8 @@ derivative_description:
     - path == "/dataset_description.json"
     - json.DatasetType == "derivative"
   fields:
-    GeneratedBy: required
+    GeneratedByProv: recommended
+    GeneratedBy: deprecated
 
 dataset_description_with_genetics:
   selectors:

src/schema/rules/directories.yaml

@@ -23,6 +23,7 @@ raw:
       - derivatives
       - logs
       - phenotype
+      - prov
       - sourcedata
       - stimuli
       - subject
@@ -46,6 +47,10 @@ raw:
     name: phenotype
     level: optional
     opaque: false
+  prov:
+    name: prov
+    level: optional
+    opaque: false
   sourcedata:
     name: sourcedata
     level: optional
@@ -72,6 +77,7 @@ raw:
     value: datatype
     level: required
     opaque: false
+    subdirs:
 
 derivative:
   root:
@@ -80,6 +86,7 @@ derivative:
       - derivatives
       - logs
       - phenotype
+      - prov
       - sourcedata
       - stimuli
       - subject
@@ -99,6 +106,10 @@ derivative:
     name: phenotype
     level: optional
     opaque: false
+  prov:
+    name: prov
+    level: optional
+    opaque: false
   sourcedata:
     name: sourcedata
     level: optional

src/schema/rules/entities.yaml

@@ -32,3 +32,4 @@
 - density
 - label
 - description
+- prov

src/schema/rules/files/common/core.yaml

@@ -36,6 +36,9 @@ code:
 derivatives:
   level: optional
   path: derivatives
+prov:
+  level: optional
+  path: prov
 docs:
   level: optional
   path: docs

src/schema/rules/files/common/modality_agnostic.yaml

@@ -0,0 +1,17 @@
+---
+# Files and directories that can be found at any level of a dataset.
+
+# Provenance json files
+provenance:
+  level: optional
+  path: prov/*
+  suffixes:
+    - act
+    - base
+    - ent
+    - env
+    - soft
+  extensions:
+    - .json
+  entities:
+    prov: required

src/schema/rules/files/common/tables.yaml

@@ -5,12 +5,14 @@ participants:
   extensions:
     - .tsv
     - .json
+
 samples:
   level: optional
   stem: samples
   extensions:
     - .tsv
     - .json
+
 scans:
   level: optional
   suffixes:
@@ -21,6 +23,7 @@ scans:
   entities:
     subject: required
     session: optional # session is required if session is present in the dataset.
+
 sessions: # This file may only exist if session is present in the dataset.
   level: optional
   suffixes: