input and analysis via UI working

app.py

@@ -2,169 +2,177 @@ import os
 import yaml
 import json
 from pathlib import Path
-from compliance_analysis import check_overall_compliance
-
-# if __name__ == "__main__":
-#     demo.launch()
-
 import streamlit as st
-import yaml
-from pathlib import Path
-import pandas as pd
-
-
-def load_data(files):
-    cards = []
-    for file in files:
-        content = file.read().decode("utf-8")
-        if Path(file.name).name == "project_cc.yaml":
-            project_cc_yaml = yaml.safe_load(content)
-            data = project_cc_yaml
-            card_type = "project"
-            cards.append((card_type, data))
-        if Path(file.name).name == "data_cc.yaml":
-            data_cc_yaml = yaml.safe_load(content)
-            data = data_cc_yaml
-            card_type = "data"
-            cards.append((card_type, data))
-        if Path(file.name).name == "model_cc.yaml":
-            model_cc_yaml = yaml.safe_load(content)
-            data = model_cc_yaml
-            card_type = "model"
-            cards.append((card_type, data))
-    return cards
-
-# def process_files(files):
-#     results = []
-#     for file in files:
-#         content = file.read().decode("utf-8")
-#         if Path(file.name).name == "project_cc.yaml":
-#             project_cc_yaml = yaml.safe_load(content)
-#             if project_cc_yaml:
-#                 msg = run_compliance_analysis_on_project(project_cc_yaml)
-#                 results.append(msg)            
-#     return results
-
-# def process_files(data):
-#     results = []
-#     msg = run_compliance_analysis_on_project(yaml.safe_load(data))
-#     results.append(msg)            
-#     return results
-
-# def extract_properties(data):
-        
-#     flattened_data = []
-
-#     for category, items in data.items():
-#         for item, attributes in items.items():
-#             flattened_data.append({
-#                 "Category": category,
-#                 "Item": item,
-#                 "Verbose": attributes["verbose"],
-#                 "Value": attributes["value"]
-#             })
-#     df = pd.DataFrame(flattened_data)
-    
-#     return df
-
-def gather_cards(files):
-    cards = {}
-    cards['project_file'] = ''
-    cards['data_files'] = []
-    cards['model_files'] = []
-    for file in files:
-        file_path = os.path.join('/tmp', file.name)        
-        with open(file_path, 'wb') as f:
-            f.write(file.getbuffer())
-        with open(file_path, 'r') as file_path:
-            content = yaml.safe_load(file_path.read())            
-            if content['card_type'] == 'project':
-                cards['project_file'] = file_path.name
-            if content['card_type'] == "data":
-                cards['data_files'].append(file_path.name)
-            if content['card_type'] == "model":
-                cards['model_files'].append(file_path.name)
-    return cards
+from compliance_analysis import check_overall_compliance_ui
 
 def compliance_analysis(cards):
-    results = []
-    dispositive_variables = check_overall_compliance(cards)
-    results.append(dispositive_variables)#['msg'])
-    return results
+    dispositive_variables = check_overall_compliance_ui(cards)
+    return dispositive_variables
+
+def load_yaml(file_path):
+    with open(file_path, 'r') as file:
+        return yaml.safe_load(file)
 
+def format_card_label(card):
+    return card[0]
+    
 # Streamlit app
-# st.set_page_config(page_title="AI", layout="wide")
-# st.markdown(
-#     """
-#     <style>
-#     [data-testid="stSidebar"][aria-expanded="true"] > div:first-child{
-#         width: 600px;
-#     }
-#     [data-testid="stSidebar"][aria-expanded="false"] > div:first-child{
-#         width: 600px;
-#         margin-left: -400px;
-#     }
+st.set_page_config(page_title="AI", layout="wide")
+st.markdown(
+    """
+    <style>
+    [data-testid="stSidebar"][aria-expanded="true"] > div:first-child{
+        width: 600px;
+    }
+    [data-testid="stSidebar"][aria-expanded="false"] > div:first-child{
+        width: 600px;
+        margin-left: -400px;
+    }
      
-#     """,
-#     unsafe_allow_html=True,
-# )
+    """,
+    unsafe_allow_html=True,
+)
 
 st.title("AI")
 
 uploaded_files = st.file_uploader("Upload YAML Files", type="yaml", accept_multiple_files=True)
 # project_files = st.file_uploader("Upload Project Files", type="yaml", accept_multiple_files=True)
 
+cards = {"project_file": None, "data_files": [], "model_files": []}
+
 if uploaded_files:
 
-    cards = load_data(uploaded_files)
-    for card in cards:
-        
-        data = card[1]
-    
-        if data != None:    
+    for uploaded_file in uploaded_files:
+        cc = load_yaml(uploaded_file.name)
+        card_type = cc['card_details'].get('card_type', '').lower()
+        if card_type == 'project':
+            cards["project_file"] = cc
+        elif card_type == 'data':
+            cards["data_files"].append((cc['card_details']['card_label'], cc))
+        elif card_type == 'model':
+            cards["model_files"].append((cc['card_details']['card_label'], cc))
 
-            st.title("Compliance Checkboxes")
-            st.title(f"{card[0]}")
+project_col, data_col, model_col = st.columns(3)
 
-            for section, items in data.items():
-                if section != 'card_type':
+with project_col:
+    st.title("Project CC")
+    
+    if cards["project_file"]:
+        project_cc = cards["project_file"]
+   
+        for section, items in project_cc.items():
+            if section != 'card_details':
+                st.header(section.replace('_', ' ').title())  # section header
+                for key, details in items.items():
+                    if 'verbose' in details and 'value' in details:
+                        st.subheader(key.replace('_', ' ').title())  # section header
+                        # details['value'] = st.checkbox(details['verbose'], value=details['value'])
+                        if isinstance(details['value'], str):
+                            details['value'] = st.text_input(details['verbose'], value=details['value'])
+                        elif isinstance(details['value'], bool):
+                            details['value'] = st.checkbox(details['verbose'], value=details['value'])                        
+                    if 'verbose' not in details and 'value' not in details:
+                        st.subheader(key.replace('_', ' ').title())  # section header
+                        for key, details in details.items():
+                            st.subheader(key.replace('_', ' ').title())  # section header
+                            details['value'] = st.checkbox(details['verbose'], value=details['value'])
+                        st.divider()
+                st.divider()
+        # st.write("Updated Data:", project_cc)
+                
+        updated_project_cc = yaml.dump(project_cc, sort_keys=False)
+        
+        st.download_button(
+            label=f"Download Updated Project CC as YAML",
+            data=updated_project_cc,
+            file_name="updated_project.yaml",
+            mime="text/yaml"
+        )  
+
+with data_col:
+
+    st.title("Data CC")
+    if cards['data_files']:
+        # selected_data_file = st.selectbox("Select a Data CC", cards['data_files'], format_func=format_card_label)
+        # data_cc = selected_data_file[1]
+        for card in cards['data_files']:
+            data_cc = card[1]
+            st.title(f"{card[0]}")
+            for section, items in data_cc.items():
+                if section != 'card_details':
+                    st.header(section.replace('_', ' ').title())  # section header
+                    for key, details in items.items():
+                        if 'verbose' in details and 'value' in details:
+                            st.subheader(key.replace('_', ' ').title())  # section header
+                            # details['value'] = st.checkbox(details['verbose'], value=details['value'])
+                            if isinstance(details['value'], str):
+                                details['value'] = st.text_input(details['verbose'], value=details['value'], key=f"data_{card[0]}_{key}")
+                            elif isinstance(details['value'], bool):                                
+                                details['value'] = st.checkbox(details['verbose'], value=details['value'], key=f"data_{card[0]}_{details}_{key}")                        
+                        if 'verbose' not in details and 'value' not in details:
+                            st.subheader(key.replace('_', ' ').title())  # section header
+                            for key, details in details.items():
+                                st.subheader(key.replace('_', ' ').title())  # section header
+                                details['value'] = st.checkbox(details['verbose'], value=details['value'], key=f"data_{card[0]}_{details}_{key}")
+                            st.divider()
+                    st.divider()
+            # st.write("Updated Data:", data_cc)
+        
+            data_cc_yaml_data = yaml.dump(data_cc, sort_keys=False)
+
+            st.download_button(
+                label=f"Download Updated {card[0]} CC as YAML",
+                data=data_cc_yaml_data,
+                file_name="updated_data.yaml",
+                mime="text/yaml"
+            )
+
+with model_col:
+            
+    st.title("Model CC")
+    if cards['model_files']:
+        # selected_data_file = st.selectbox("Select a Modle CC", cards['model_files'], format_func=format_card_label)
+        # model_cc = selected_data_file[1]
+        for card in cards['model_files']:
+            model_cc = card[1]
+            st.title(f"{card[0]}")        
+            for section, items in model_cc.items():
+                if section != 'card_details':
                     st.header(section.replace('_', ' ').title())  # section header
                     for key, details in items.items():
                         if 'verbose' in details and 'value' in details:
                             st.subheader(key.replace('_', ' ').title())  # section header
                             # details['value'] = st.checkbox(details['verbose'], value=details['value'])
                             if isinstance(details['value'], str):
-                                details['value'] = st.text_input(details['verbose'], value=details['value'])
+                                details['value'] = st.text_input(details['verbose'], value=details['value'], key=f"model_{card[0]}_{key}")
                             elif isinstance(details['value'], bool):
-                                details['value'] = st.checkbox(details['verbose'], value=details['value'])                        
+                                details['value'] = st.checkbox(details['verbose'], value=details['value'], key=f"model_{card[0]}_{details}_{key}")                        
                         if 'verbose' not in details and 'value' not in details:
                             st.subheader(key.replace('_', ' ').title())  # section header
                             for key, details in details.items():
                                 st.subheader(key.replace('_', ' ').title())  # section header
-                                details['value'] = st.checkbox(details['verbose'], value=details['value'])
-                            # st.divider()
-                    # st.divider()
-            # st.write("Updated Data:", data)
-           
-            yaml_data = yaml.dump(data, sort_keys=False)
-
-            # st.download_button(
-            #     label=f"Download Updated Data as YAML{card[0]}",
-            #     data=yaml_data,
-            #     file_name="updated_data.yaml",
-            #     mime="text/yaml"
-            # )
-
-            # json_data = json.dumps(data, indent=2)
-            # st.download_button(
-            #     label="Download Updated Data as JSON",
-            #     data=json_data,
-            #     file_name="updated_data.json",
-            #     mime="application/json"
-            # )   
-
-    cards = gather_cards(uploaded_files)    
-    if st.button(f"Run Analysis"):
-        results = compliance_analysis(cards)    
-        # st.text_area("Analysis Results", value=json.dumps(results, indent=4), height=600)
-        st.write("Analysis Results", results)
+                                details['value'] = st.checkbox(details['verbose'], value=details['value'], key=f"model_{card[0]}_{details}_{key}")
+                            st.divider()
+                    st.divider()
+            # st.write("Updated Data:", model_cc)
+        
+            model_cc_yaml_data = yaml.dump(model_cc, sort_keys=False)
+
+            st.download_button(
+                label=f"Download Updated {card[0]} CC as YAML",
+                data=model_cc_yaml_data,
+                file_name="updated_model.yaml",
+                mime="text/yaml"
+            )
+
+# # #         # json_data = json.dumps(data, indent=2)
+# # #         # st.download_button(
+# # #         #     label="Download Updated Data as JSON",
+# # #         #     data=json_data,
+# # #         #     file_name="updated_data.json",
+# # #         #     mime="application/json"
+# # #         # )   
+
+if st.button(f"Run Analysis"):
+    results = compliance_analysis(cards)
+    st.write("Analysis Results", results)

compliance_analysis.py

@@ -1,36 +1,86 @@
 import yaml
-from utils import set_operator_role_and_location, set_eu_market_status, check_within_scope_cc, check_within_scope_act, check_prohibited
+from utils import set_operator_role_and_location, set_eu_market_status, check_within_scope_act, check_prohibited
 
 # TODO tells the user where the compliance analysis failed
 # TODO cite article from yaml file as explanation
 
-def check_overall_compliance(cards):
-    
+def check_overall_compliance_ui(cards):
+   
+    project_cc = cards['project_file']
+
     dispositive_variables = {
     "ai_project_type": {
-        "ai_system": False,
-        "gpai_model": True,
-        "high_risk_ai_system": True,
+        "ai_system": project_cc['ai_system']['ai_system']['value'],
+        "gpai_model": project_cc['gpai_model']['gpai_model']['value'],
+        "high_risk_ai_system": False,
         "gpai_model_systemic_risk": False
     },
     "operator_details": {
-        "provider": False,
-        "eu_located": False,
-        "output_used": False
+        "provider": project_cc['operator_details']['provider']['value'],
+        "eu_located": project_cc['operator_details']['eu_located']['value'],
+        "output_used": project_cc['operator_details']['output_used']['value']
     },
     "eu_market_status": {
-        "placed_on_market": False,
-        "put_into_service": False
+        "placed_on_market": project_cc['eu_market_status']['placed_on_market']['value'],
+        "put_into_service": project_cc['eu_market_status']['put_into_service']['value']
     },
-    "intended_purposes": [],
+    "project_intended_purposes": [],
     "project_cc_pass": False,
     "data_cc_pass": False,
     "model_cc_pass": False,
     "msg": []
     }
-    
+   
+    # check intended purposes 
+    for card in cards['data_files']:
+        data_cc = card[1]
+        dispositive_variables = check_intended_purpose(dispositive_variables, project_cc, data_cc)
+        
+    for card in cards['model_files']:
+        model_cc = card[1]
+        dispositive_variables = check_intended_purpose(dispositive_variables, project_cc, model_cc)
+   
+    # for each model_cc and data_cc - run analysis with ref to project_cc
+    dispositive_variables = run_compliance_analysis_on_project(dispositive_variables, project_cc)
+
+    for card in cards['data_files']:
+        data_cc = card[1]
+        dispositive_variables = run_compliance_analysis_on_data(dispositive_variables, data_cc)
+            
+    for card in cards['model_files']:
+        model_cc = card[1]
+        dispositive_variables = run_compliance_analysis_on_model(dispositive_variables, model_cc)
+
+    return dispositive_variables
+
+def check_overall_compliance(cards):
+   
     with open(cards['project_file'], 'r') as project_filepath:
+        print(project_filepath)
         project_cc = yaml.safe_load(project_filepath.read())
+
+    dispositive_variables = {
+    "ai_project_type": {
+        "ai_system": project_cc['ai_system']['ai_system']['value'],
+        "gpai_model": project_cc['gpai_model']['gpai_model']['value'],
+        "high_risk_ai_system": False,
+        "gpai_model_systemic_risk": False
+    },
+    "operator_details": {
+        "provider": project_cc['operator_details']['provider']['value'],
+        "eu_located": project_cc['operator_details']['eu_located']['value'],
+        "output_used": project_cc['operator_details']['output_used']['value']
+    },
+    "eu_market_status": {
+        "placed_on_market": project_cc['eu_market_status']['placed_on_market']['value'],
+        "put_into_service": project_cc['eu_market_status']['put_into_service']['value']
+    },
+    "project_intended_purposes": [],
+    "project_cc_pass": False,
+    "data_cc_pass": False,
+    "model_cc_pass": False,
+    "msg": []
+    }
    
     # check intended purposes 
     for card in cards['data_files']:
@@ -92,21 +142,23 @@ def run_compliance_analysis_on_project(dispositive_variables, project_cc_yaml):
     dispositive_variables = set_eu_market_status(dispositive_variables, project_cc_yaml)
 
     # Check if project is within scope of the Compliance Cards project. If not, inform user.
-    if check_within_scope_cc(dispositive_variables, project_cc_yaml):
+    if project_cc_yaml['operator_details']['provider']['value'] == True:
         dispositive_variables['msg'].append("Project is within the scope of the Compliance Cards system. Let's continue...") 
     else: 
         dispositive_variables['msg'].append("Project is not within the scope of the initial version of the Compliance Cards system.")
+        return dispositive_variables
     
     # Check if the project is within scope of the Act. If it's not, the analysis is over.
     if check_within_scope_act(dispositive_variables, project_cc_yaml):
         dispositive_variables['msg'].append("Project is within the scope of Act. Let's continue...") 
     else: 
         dispositive_variables['msg'].append("Project is not within the scope of what is regulated by the Act.")
+        return dispositive_variables
 
     # Check for prohibited practices. If any exist, the analysis is over.
     if check_prohibited(project_cc_yaml) == True: 
-        print("Project contains prohibited practices and is therefore non-compliant.")
         dispositive_variables['msg'].append("Project is non-compliant due to a prohibited practice.")
+        return dispositive_variables
     else: 
         print("Project does not contain prohibited practies. Let's continue...")
 
@@ -223,7 +275,7 @@ def check_intended_purpose(dispositive_variables, project_cc, other_cc):
     
     # For each Data CC, put the intended uses in a set and then make sure the Project's intended use is in the set
    
-    if other_cc['card_type'] == 'data':
+    if other_cc['card_details']['card_type'] == 'data':
         data_cc = other_cc        
         for key in data_cc['intended_purpose']:
             if data_cc['intended_purpose'][f'{key}']['value']:
@@ -235,7 +287,7 @@ def check_intended_purpose(dispositive_variables, project_cc, other_cc):
 
     # Now do the exact same thing for all models
 
-    if other_cc['card_type'] == 'model':
+    if other_cc['card_details']['card_type'] == 'model':
         model_cc = other_cc        
         for key in model_cc['intended_purpose']:
             if model_cc['intended_purpose'][f'{key}']['value']:
@@ -245,7 +297,7 @@ def check_intended_purpose(dispositive_variables, project_cc, other_cc):
             if purpose not in model_intended_purposes:
                 dispositive_variables['msg'].append(f"You are not compliant because {purpose} is not a valid purpose for the model")
 
-    dispositive_variables['intended_purposes'] = project_intended_purposes
+    dispositive_variables['project_intended_purposes'] = project_intended_purposes
 
     return dispositive_variables
 

data_cc 02.yaml

@@ -0,0 +1,228 @@
+card_details: 
+  card_type: "data" # "project", "data" or "model"
+  card_label: "data_02"
+
+# Metadata related to intended purpose(s) of data 
+
+intended_purpose:
+  safety_component: 
+    article: 'Art. 6(1)(a)'
+    verbose: 'This dataset is appropriate to use for AI projects involving product safety components'
+    value: !!bool true 
+  product_regulated_machinery: 
+    article: 'Art. 6(1)(b); Annex I'
+    verbose: 'This dataset is appropriate to use for AI projects involving products covered by Directive 2006/42/EC of the European Parliament and of the Council of 17 May 2006 on machinery, and amending Directive 95/16/EC (OJ L 157, 9.6.2006, p. 24) [as repealed by the Machinery Regulation]'
+    value: !!bool false 
+  product_regulated_toy: 
+    article: 'Art. 6(1)(b); Annex I'
+    verbose: 'This dataset is appropriate to use for AI projects involving products covered by Directive 2009/48/EC of the European Parliament and of the Council of 18 June 2009 on the safety of toys (OJ L 170, 30.6.2009, p. 1)'
+    value: !!bool false 
+  product_regulated_watercraft: 
+    article: 'Art. 6(1)(b); Annex I'
+    verbose: 'This dataset is appropriate to use for AI projects involving products covered by Directive 2013/53/EU of the European Parliament and of the Council of 20 November 2013 on recreational craft and personal watercraft and repealing Directive 94/25/EC (OJ L 354, 28.12.2013, p. 90)'
+    value: !!bool false 
+  biometric_categorization: 
+    article: 'Art. 6(2); Annex III(1)(b)'
+    verbose: 'This dataset is appropriate to use for AI projects involving biometric categorisation, according to sensitive or protected attributes or characteristics based on the inference of those attributes or characteristics'
+    value: !!bool false 
+  emotion_recognition: 
+    article: 'Art. 6(2); Annex III(1)(c)'
+    verbose: 'This dataset is appropriate to use for AI projects involving emotion recognition'
+    value: !!bool true 
+  critical_infrastructure: 
+    article: 'Art. 6(2); Annex III(2)'
+    verbose: 'This dataset is appropriate to use for AI projects involving safety components in the management and operation of critical digital infrastructure, road traffic, or in the supply of water, gas, heating or electricity'
+    value: !!bool true 
+  admission: 
+    article: 'Art. 6(2); Annex III(3)(a)'
+    verbose: 'This dataset is appropriate to use for AI projects involving the determination of access or admission or to assigning natural persons to educational and vocational training institutions at all levels'
+    value: !!bool false 
+  recruitment: 
+    article: 'Art. 6(2); Annex III(4)(a)'
+    verbose: 'This dataset is appropriate to use for AI projects involving the recruitment or selection of natural persons, in particular to place targeted job advertisements, to analyse and filter job applications, and to evaluate candidates'
+    value: !!bool false 
+  public_assistance: 
+    article: 'Art. 6(2); Annex III(5)(a)'
+    verbose: 'This dataset is appropriate to use for AI projects intended to be used by public authorities or on behalf of public authorities to evaluate the eligibility of natural persons for essential public assistance benefits and services, including healthcare services, as well as to grant, reduce, revoke, or reclaim such benefits and services'
+    value: !!bool false 
+  victim_assessment: 
+    article: 'Art. 6(2); Annex III(6)(a)'
+    verbose: 'This dataset is appropriate to use for AI projects intended to be used by or on behalf of law enforcement authorities, or by Union institutions, bodies, offices or agencies in support of law enforcement authorities or on their behalf to assess the risk of a natural person becoming the victim of criminal offences'
+    value: !!bool false 
+  polygraph: 
+    article: 'Art. 6(2); Annex III(7)(a)'
+    verbose: 'This dataset is appropriate to use for AI projects intended to be used by or on behalf of competent public authorities or by Union institutions, bodies, offices or agencies as polygraphs or similar tools'
+    value: !!bool false 
+  judicial: 
+    article: 'Art. 6(2); Annex III(8)(a)' 
+    verbose: 'This dataset is appropriate to use for AI projects intended to be used by a judicial authority or on their behalf to assist a judicial authority in researching and interpreting facts and the law and in applying the law to a concrete set of facts, or to be used in a similar way in alternative dispute resolution'
+    value: !!bool false 
+
+# Metadata related to data-related requirements for high-risk AI systems
+
+high_risk_ai_system_requirements:
+# data governance
+  data_and_data_governance_data_governance: 
+    article: 'Art. 10(1)-(2)'
+    verbose: 'The dataset was subject to data governance and management practices appropriate to the intended use case'
+    value: !!bool false
+  data_and_data_governance_design_choices:  
+    article: 'Art. 10(2)(a)'
+    verbose: 'The dataset has been subject to data governance and management practices as regards its relevant design choices'
+    value: !!bool false
+  data_and_data_governance_data_origin: 
+    article: 'Art. 10(2)(b)'
+    verbose: 'The dataset has been subject to data governance and management practices as regards its data collection processes and the origin of data, and in the case of personal data, the original purpose of the data collection'
+    value: !!bool false
+  data_and_data_governance_data_preparation: 
+    article: 'Art. 10(2)(c)'
+    verbose: 'The dataset has been subject to data governance and management practices as regards its data-preparation processing operations, such as annotation, labelling, cleaning, updating, enrichment and aggregation' 
+    value: !!bool false
+  data_and_data_governance_data_assumptions: 
+    article: 'Art. 10(2)(d)'
+    verbose: 'The dataset has been subject to data governance and management practices as regards its formulation of assumptions, in particular with respect to the information that the data are supposed to measure and represent'
+    value: !!bool false
+  data_and_data_governance_data_quantity: 
+    article: 'Art. 10(2)(e)'
+    verbose: 'The dataset has been subject to data governance and management practices that include an assessment of the availability, quantity and suitability of the data sets that are needed'
+    value: !!bool false
+  data_and_data_governance_ata_bias_examination: 
+    article: 'Art. 10(2)(f)'
+    verbose: 'The dataset has been subject to data governance and management practices that include an examination of possible biases that are likely to affect the health and safety of persons, have a negative impact on fundamental rights or lead to discrimination prohibited under Union law, especially where data outputs influence inputs for future operations' 
+    value: !!bool false
+  data_and_data_governance_data_and_data_governance_data_bias_mitigation: 
+    article: 'Art. 10(2)(g)'
+    verbose: 'The dataset has been subject to data governance and management practices that include appropriate measures to detect, prevent and mitigate possible biases that are likely to affect the health and safety of persons, have a negative impact on fundamental rights or lead to discrimination prohibited under Union law, especially where data outputs influence inputs for future operations'
+    value: !!bool true
+  data_and_data_governance_data_compliance: 
+    article: 'Art. 10(2)(h)'
+    verbose: 'The dataset has been subject to data governance and management practices that include identification of relevant data gaps or shortcomings that prevent compliance with this Regulation, and how those gaps and shortcomings can be addressed'
+    value: !!bool false
+ #   data_characteristics   
+  data_and_data_governance_data_relevance: 
+    article: 'Art. 10(3); Rec. 67'
+    verbose: 'Training data is relevant' 
+    value: !!bool false
+  data_and_data_governance_data_representativity: 
+    article: 'Art. 10(3); Rec. 67'
+    verbose: 'Training data is sufficiently representative'
+    value: !!bool false
+  data_and_data_governance_data_errors: 
+    article: 'Art. 10(3); Rec. 67'
+    verbose: 'Training data is, to the best extent possible, free of errors'
+    value: !!bool false
+  data_and_data_governance_data_completeness: 
+    article: 'Art. 10(3); Rec. 67'
+    verbose: 'Training data is complete in view of the intended purpose'
+    value: !!bool false
+  data_and_data_governance_statistical_properties: 
+    article: 'Art. 10(3)'
+    verbose: 'Training data possesses the appropriate statistical properties, including, where applicable, as regards the people in relation to whom it is intended to be used'
+    value: !!bool false
+  data_and_data_governance_contextual: 
+    article: 'Art. 10(4)'
+    verbose: 'Training data takes into account, to the extent required by the intended purpose, the characteristics or elements that are particular to the specific geographical, contextual, behavioural or functional setting within which it is intended to be used'
+    value: !!bool false
+  # special_categories_of_personal_data:
+  data_and_data_governance_personal_data_necessary: 
+    article: 'Art. 10(5)'
+    verbose: 'Where special categories of personal data have been used to ensure the detection and correction of possible biases that are likely to affect the health and safety of persons, have a negative impact on fundamental rights or lead to discrimination prohibited under Union law, especially where data outputs influence inputs for future operations, the use of this data was strictly necessary'
+    value: !!bool false
+  data_and_data_governance_personal_data_safeguards: 
+    article: 'Art. 10(5)'
+    verbose: 'Where special categories of personal data have been used to ensure the detection and correction of possible biases that are likely to affect the health and safety of persons, have a negative impact on fundamental rights or lead to discrimination prohibited under Union law, especially where data outputs influence inputs for future operations, the use complied with appropriate safeguards for the fundamental rights and freedoms of natural persons'
+    value: !!bool false
+  data_and_data_governance_personal_data_gdpr: 
+    article: 'Art. 10(5)'
+    verbose: 'Where special categories of personal data have been used to ensure the detection and correction of possible biases that are likely to affect the health and safety of persons, have a negative impact on fundamental rights or lead to discrimination prohibited under Union law, especially where data outputs influence inputs for future operations, the use of this data satisfied the provisions set out in Regulations (EU) 2016/679 and (EU) 2018/1725 and Directive (EU) 2016/680'
+    value: !!bool false
+  data_and_data_governance_personal_data_other_options: 
+    article: 'Art. 10(5)(a)'
+    verbose: 'Where special categories of personal data have been used to ensure the detection and correction of possible biases that are likely to affect the health and safety of persons, have a negative impact on fundamental rights or lead to discrimination prohibited under Union law, especially where data outputs influence inputs for future operations, the bias detection and correction was not effectively fulfilled by processing other data, including synthetic or anonymised data'
+    value: !!bool false
+  data_and_data_governance_personal_data_limitations: 
+    article: 'Art. 10(5)(b)'
+    verbose: 'Where special categories of personal data have been used to ensure the detection and correction of possible biases that are likely to affect the health and safety of persons, have a negative impact on fundamental rights or lead to discrimination prohibited under Union law, especially where data outputs influence inputs for future operations, the special categories of personal data were not subject to technical limitations on the re-use of the personal data, and state-of-the-art security and privacy-preserving measures, including pseudonymisation'
+    value: !!bool false
+  data_and_data_governance_personal_data_controls: 
+    article: 'Art. 10(5)(c)'
+    verbose: 'Where special categories of personal data have been used to ensure the detection and correction of possible biases that are likely to affect the health and safety of persons, have a negative impact on fundamental rights or lead to discrimination prohibited under Union law, especially where data outputs influence inputs for future operations, the special categories of personal data were subject to measures to ensure that the personal data processed are secured, protected, subject to suitable safeguards, including strict controls and documentation of the access, to avoid misuse and ensure that only authorised persons have access to those personal data with appropriate confidentiality obligations'
+    value: !!bool false
+  data_and_data_governance_personal_data_access: 
+    article: 'Art. 10(5)(d)'
+    verbose: 'Where special categories of personal data have been used to ensure the detection and correction of possible biases that are likely to affect the health and safety of persons, have a negative impact on fundamental rights or lead to discrimination prohibited under Union law, especially where data outputs influence inputs for future operations, the special categories of personal data were not to be transmitted, transferred or otherwise accessed by other parties'
+    value: !!bool false
+  data_and_data_governance_personal_data_deletion: 
+    article: 'Art. 10(5)(e)'
+    verbose: 'Where special categories of personal data have been used to ensure the detection and correction of possible biases that are likely to affect the health and safety of persons, have a negative impact on fundamental rights or lead to discrimination prohibited under Union law, especially where data outputs influence inputs for future operations, the special categories of personal data were deleted once the bias was corrected or the personal data reached the end of its retention period (whichever came first)'
+    value: !!bool false
+  data_and_data_governance_personal_data_necessary_105f: 
+    article: 'Art. 10(5)(f)'
+    verbose: 'Where special categories of personal data have been used to ensure the detection and correction of possible biases that are likely to affect the health and safety of persons, have a negative impact on fundamental rights or lead to discrimination prohibited under Union law, especially where data outputs influence inputs for future operations, the records of processing activities pursuant to Regulations (EU) 2016/679 and (EU) 2018/1725 and Directive (EU) 2016/680 include the reasons why the processing of special categories of personal data was strictly necessary to detect and correct biases, and why that objective could not be achieved by processing other data'
+    value: !!bool false
+  # technical_documentation:  
+  technical_documentation_general_description: 
+    article: 'Art. 11; Annex IV(2)(d)'
+    verbose: 'Dataset carries technical documention, such as a dataseet, including a general description of the dataset.'
+    value: !!bool false
+  technical_documentation_provenance: 
+    article: 'Art. 11; Annex IV(2)(d)'
+    verbose: 'Dataset carries technical documention, such as a dataseet, including information about its provenance' 
+    value: !!bool false
+  technical_documentation_scope: 
+    article: 'Art. 11; Annex IV(2)(d)'
+    verbose: 'Dataset carries technical documention, such as a dataseet, including information about scope and main characteristics' 
+    value: !!bool false
+  technical_documentation_origins: 
+    article: 'Art. 11; Annex IV(2)(d)' 
+    verbose: 'Dataset carries technical documention, such as a dataseet, including information about how the data was obtained and selected'
+    value: !!bool false
+  technical_documentation_labelling: 
+    article: 'Art. 11; Annex IV(2)(d)'
+    verbose: 'Dataset carries technical documention, such as a dataseet, including information about labelling procedures (e.g. for supervised learning)'
+    value: !!bool false
+  technical_documentation_cleaning: 
+    article: 'Art. 11; Annex IV(2)(d)' 
+    verbose: 'Dataset carries technical documention, such as a dataseet, including information about data cleaning methodologies (e.g. outliers detection)'
+    value: !!bool false
+  technical_documentation_cybersecurity:  
+    article: 'Art. 11; Annex IV(2)(h)'
+    verbose: 'Cybersecurity measures were put in place as regards the data (e.g., scanning for data poisoning)'
+    value: !!bool false
+    
+  transparency_and_provision_of_information_to_deployers: 
+    article: '# Art. 13(3)(b)(vi)'
+    verbose: 'Dataset is accompanied by instructions for use that convery relevant information about it, taking into account its intended purpose'
+    value: !!bool false
+  quality_management_system: 
+    article: 'Art. 17(1)(f)'
+    verbose: 'Datset was subject to a quality management system that is documented in a systematic and orderly manner in the form of written policies, procedures and instructions, and includes a description of the systems and procedures for data management, including data acquisition, data collection, data analysis, data labelling, data storage, data filtration, data mining, data aggregation, data retention and any other operation regarding the data'
+    value: !!bool false
+
+# Metadata related to data-related requirements for GPAI models 
+
+gpai_model_requirements: 
+  data_type: 
+    article: 'Art. 53(1); Annex XI(2)(c)'
+    verbose: 'Documentation for the dataset is available that contains the type of data'
+    value: !!bool false
+  data_provenance: 
+    article: 'Art. 53(1); Annex XI(2)(c)'
+    verbose: 'Documentation for the dataset is available that contains the provenance of data'
+    value: !!bool false 
+  data_curation:
+    article: 'Art. 53(1); Annex XI(2)(c)'
+    verbose: 'Documentation for the dataset is available that contains the curation methodologies (e.g. cleaning, filtering, etc.)'
+    value: !!bool false 
+  data_number: 
+    article: 'Art. 53(1); Annex XI(2)(c)'
+    verbose: 'Documentation for the dataset is available that contains the number of data points'
+    value: !!bool false 
+  data_scope: 
+    article: 'Art. 53(1); Annex XI(2)(c)'
+    verbose: 'Documentation for the dataset is available that contains the number of data scope and main characteristics'
+    value: !!bool false 
+  data_origin:
+    article: 'Art. 53(1); Annex XI(2)(c)'
+    verbose: 'Documentation for the dataset is available that contains information on how the data was obtained and selected as well as all other measures to detect the unsuitability of data sources and methods to detect identifiable biases'
+    value: !!bool false 

data_cc.yaml

@@ -1,4 +1,6 @@
-card_type: "data" # "project", "data" or "model"
+card_details: 
+  card_type: "data" # "project", "data" or "model"
+  card_label: "data_01"
 
 # Metadata related to intended purpose(s) of data 
 

model_cc 02.yaml

@@ -0,0 +1,313 @@
+card_details: 
+  card_type: "model" # "project", "data" or "model"
+  card_label: "model_02"
+
+# Metadata related to intended purpose(s) of model 
+
+intended_purpose:
+  safety_component: 
+    article: 'Art. 6(1)(a)'
+    verbose: 'This model is appropriate to use for AI projects involving product safety components'
+    value: !!bool false 
+  product_regulated_machinery: 
+    article: 'Art. 6(1)(b); Annex I'
+    verbose: 'This model is appropriate to use for AI projects involving products covered by Directive 2006/42/EC of the European Parliament and of the Council of 17 May 2006 on machinery, and amending Directive 95/16/EC (OJ L 157, 9.6.2006, p. 24) [as repealed by the Machinery Regulation]'
+    value: !!bool false 
+  product_regulated_toy: 
+    article: 'Art. 6(1)(b); Annex I'
+    verbose: 'This model is appropriate to use for AI projects involving products covered by Directive 2009/48/EC of the European Parliament and of the Council of 18 June 2009 on the safety of toys (OJ L 170, 30.6.2009, p. 1)'
+    value: !!bool false 
+  product_regulated_watercraft: 
+    article: 'Art. 6(1)(b); Annex I'
+    verbose: 'This model is appropriate to use for AI projects involving products covered by Directive 2013/53/EU of the European Parliament and of the Council of 20 November 2013 on recreational craft and personal watercraft and repealing Directive 94/25/EC (OJ L 354, 28.12.2013, p. 90)'
+    value: !!bool false 
+  biometric_categorization: 
+    article: 'Art. 6(2); Annex III(1)(b)'
+    verbose: 'This model is appropriate to use for AI projects involving biometric categorisation, according to sensitive or protected attributes or characteristics based on the inference of those attributes or characteristics'
+    value: !!bool false 
+  emotion_recognition: 
+    article: 'Art. 6(2); Annex III(1)(c)'
+    verbose: 'This model is appropriate to use for AI projects involving emotion recognition'
+    value: !!bool true 
+  critical_infrastructure: 
+    article: 'Art. 6(2); Annex III(2)'
+    verbose: 'This model is appropriate to use for AI projects involving safety components in the management and operation of critical digital infrastructure, road traffic, or in the supply of water, gas, heating or electricity'
+    value: !!bool true 
+  admission: 
+    article: 'Art. 6(2); Annex III(3)(a)'
+    verbose: 'This model is appropriate to use for AI projects involving the determination of access or admission or to assigning natural persons to educational and vocational training institutions at all levels'
+    value: !!bool false 
+  recruitment: 
+    article: 'Art. 6(2); Annex III(4)(a)'
+    verbose: 'This model is appropriate to use for AI projects involving the recruitment or selection of natural persons, in particular to place targeted job advertisements, to analyse and filter job applications, and to evaluate candidates'
+    value: !!bool false 
+  public_assistance: 
+    article: 'Art. 6(2); Annex III(5)(a)'
+    verbose: 'This model is appropriate to use for AI projects intended to be used by public authorities or on behalf of public authorities to evaluate the eligibility of natural persons for essential public assistance benefits and services, including healthcare services, as well as to grant, reduce, revoke, or reclaim such benefits and services'
+    value: !!bool false 
+  victim_assessment: 
+    article: 'Art. 6(2); Annex III(6)(a)'
+    verbose: 'This model is appropriate to use for AI projects intended to be used by or on behalf of law enforcement authorities, or by Union institutions, bodies, offices or agencies in support of law enforcement authorities or on their behalf to assess the risk of a natural person becoming the victim of criminal offences'
+    value: !!bool false 
+  polygraph: 
+    article: 'Art. 6(2); Annex III(7)(a)'
+    verbose: 'This model is appropriate to use for AI projects intended to be used by or on behalf of competent public authorities or by Union institutions, bodies, offices or agencies as polygraphs or similar tools'
+    value: !!bool false 
+  judicial: 
+    article: 'Art. 6(2); Annex III(8)(a)'
+    verbose: 'This model is appropriate to use for AI projects intended to be used by a judicial authority or on their behalf to assist a judicial authority in researching and interpreting facts and the law and in applying the law to a concrete set of facts, or to be used in a similar way in alternative dispute resolution'
+    value: !!bool false 
+
+# Metadata that will help us determine if the model itself is a GPAI and, therefore, must satisfy the requirements of GPAI models
+
+classification_of_gpai_models:
+  high_impact_capabilities: 
+    article: 'Art. 51(1)(a)'
+    verbose: 'The model has high impact capabilities evaluated on the basis of appropriate technical tools and methodologies, including indicators and benchmarks'
+    value: !!bool false
+  flops: 
+    article: 'Art. 51(2)'
+    verbose: 'The cumulative compute used for training the model, as measured in floating point operations (FLOPs), was greater than 10^25.'
+    value: !!bool false
+
+# Metadata related to model-related requirements for high-risk AI systems
+
+high_risk_ai_system_requirements:
+  risk_management_system_general:
+    article: 'Art. 9(2)'
+    verbose: 'A risk management system has been planned, run, reviewed, and updated throughout the model lifecycle' 
+    value: !!bool false 
+  risk_management_system_foreseeable_risks: 
+    article: 'Art. 9(2)(a)'
+    verbose: 'The risk management system that was established, implemented, documented and maintained througout the model lifecycle included the identification and analysis of any known or reasonably foreseeable risks the model can pose to health or safety when used for intended purpose'
+    value: !!bool false
+  risk_management_system_evaluation: 
+    article: 'Art. 9(2)(b)'
+    verbose: 'The risk management system that was established, implemented, documented and maintained througout the model lifecycle included the estimation and evaluation of risks when model used for intended purpose'
+    value: !!bool false
+  risk_management_system_misuse: 
+    article: 'Art. 9(2)(b)'
+    verbose: 'The risk management system that was established, implemented, documented and maintained througout the model lifecycle included the estimation and evaluation of risks when model used under conditions of reasonably foreseeable misuse' 
+    value: !!bool false
+  risk_management_system_testing_performance: 
+    article: 'Art. 9(6)'
+    verbose: 'The risk management system that was established, implemented, documented and maintained througout the model lifecycle included testing to ensure model performs consistently for intended purpose'
+    value: !!bool false
+  risk_management_system_testing_compliance: 
+    article: 'Art. 9(6)'
+    verbose: 'The risk management system that was established, implemented, documented and maintained througout the model lifecycle included testing to ensure model complies with Act'
+    value: !!bool false
+  risk_management_system_testing_benchmark: 
+    article: 'Art. 9(8)'
+    verbose: 'The risk management system that was established, implemented, documented and maintained througout the model lifecycle included testing against prior defined metrics appropriate to intended purpose'
+    value: !!bool false
+  risk_management_system_testing_probabilistic:  
+    article: 'Art. 9(8)'
+    verbose: 'The risk management system that was established, implemented, documented and maintained througout the model lifecycle included testing against probabilistic thresholds appropriate to intended purpose'
+    value: !!bool false
+  technical_documentation_pre_trained_elements: 
+    article: 'Art. 11; Annex IV(2)(a)'
+    verbose: 'Model has technical documentation that describes pre-trained elements of model provided by third parties and how used, integrated or modified'
+    value: !!bool false 
+  technical_documentation_logic: 
+    article: 'Art. 11; Annex IV(2)(b)'
+    verbose: 'Model has technical documentation that describes general logic of model'
+    value: !!bool false
+  technical_documentation_design_choices: 
+    article: 'Art. 11; Annex IV(2)(b)'
+    verbose: 'Model has technical documentation that describes key design choices including rationale and assumptions made, including with regard to persons or groups on which model intended to be used'
+    value: !!bool false
+  technical_documentation_classification_choices: 
+    article: 'Art. 11; Annex IV(2)(b)'
+    verbose: 'Model has technical documentation that describes main classification choices'
+    value: !!bool false
+  technical_documentation_parameters: 
+    article: 'Art. 11; Annex IV(2)(b)'
+    verbose: 'Model has technical documentation that describes what model is designed to optimise for and relevance of its different parameters'
+    value: !!bool false
+  technical_documentation_expected_output: 
+    article: 'Art. 11; Annex IV(2)(b)'
+    verbose: 'Model has technical documentation that the expected output and output quality of the system'
+    value: !!bool false
+  technical_documentation_act_compliance: 
+    article: 'Art. 11; Annex IV(2)'
+    verbose: 'Model has technical documentation that describes decisions about any possible trade-off made regarding the technical solutions adopted to comply with the requirements set out in Title III, Chapter 2'
+    value: !!bool false
+  technical_documentation_human_oversight: 
+    article: 'Art. 11; Annex IV(2)(e)'
+    verbose: 'Model has technical documentation that describes an assessment of the human oversight measures needed in accordance with Article 14, including an assessment of the technical measures needed to facilitate the interpretation of the outputs of AI systems by the deployers, in accordance with Articles 13(3)(d)'
+    value: !!bool false
+  technical_documentation_validation: 
+    article: 'Art. 11; Annex IV(2)(g)'
+    verbose: 'Model has technical documentation that describes validation and testing procedures used, including information about the validation and testing data used and their main characteristics; metrics used to measure accuracy, robustness and compliance with other relevant requirements set out in Title III, Chapter 2 as well as potentially discriminatory impacts; test logs and all test reports dated and signed by the responsible persons, including with regard to predetermined changes as referred to under point (f)' 
+    value: !!bool false
+  technical_documentation_cybersecurity: 
+    article: 'Art. 11; Annex IV(2)(h)'
+    verbose: 'Model has technical documentation that describes cybersecurity measures put in place'
+    value: !!bool false
+  transparency_to_deployers_intended_purpose: 
+    article: 'Art. 13(3)(b)(i)'
+    verbose: 'Model is accompanied by instructions for use that include the characteristics, capabilities, performance limitations, and intended purpose of the model'
+    value: !!bool false
+  transparency_to_deployers_metrics: 
+    article: 'Art. 13(3)(b)(ii)'
+    verbose: 'Model is accompanied by instructions for use that include the level of accuracy, including its metrics, robustness and cybersecurity against which the model has been tested and validated and which can be expected, and any known and foreseeable circumstances that may have an impact on that expected level of accuracy, robustness and cybersecurity'
+    value: !!bool false
+  transparency_to_deployers_foreseeable_misuse: 
+    article: 'Art. 13(3)(b)(iii)'
+    verbose: 'Model is accompanied by instructions for use that include any known or foreseeable circumstance, related to the use of the model in accordance with its intended purpose or under conditions of reasonably foreseeable misuse, which may lead to risks to the health and safety or fundamental rights referred to in Article 9(2)' 
+    value: !!bool false
+  transparency_to_deployers_explainability:  
+    article: 'Art. 13(3)(b)(iv)'
+    verbose: 'Model is accompanied by instructions for use that include technical capabilities and characteristics of the model to provide information that is relevant to explain its output' 
+    value: !!bool false
+  transparency_to_deployers_specific_groups: 
+    article: 'Art. 13(3)(b)(v)'
+    verbose: 'Model is accompanied by instructions for use that include performance regarding specific persons or groups of persons on which the model is intended to be used'
+    value: !!bool false
+  transparency_to_deployers_data: 
+    article: 'Art. 13(3)(b)(vi)'
+    verbose: 'Model is accompanied by instructions for use that include specifications for the input data, or any other relevant information in terms of the training, validation and testing data sets used, taking into account the intended purpose of the model'
+    value: !!bool false
+  transparency_to_deployers_interpretability: 
+    article: 'Art. 13(3)(b)(vii)'
+    verbose: 'Model is accompanied by instructions for use that include information to enable deployers to interpret the output of the model and use it appropriately'
+    value: !!bool false   
+  transparency_to_deployers_human_oversight: 
+    article: 'Art. 13(3)(d)'
+    verbose: 'Model is accompanied by instructions for use that include human oversight measures, including the technical measures put in place to facilitate the interpretation of the outputs of model by the deployers' 
+    value: !!bool false
+  transparency_to_deployers_hardware: 
+    article: 'Art. 13(3)(e)'
+    verbose: 'Model is accompanied by instructions for use that include computational and hardware resources needed, the expected lifetime of the model and any necessary maintenance and care measures, including their frequency, to ensure the proper functioning of that model, including as regards software updates'
+    value: !!bool false
+  accuracy_robustness_cybersecurity_accuracy:  # These need to be cleaned up and to match/compliment project cc
+    article: 'Art. 15(1)'
+    verbose: 'Model is designed and developed to achieve appropriate level of accuracy'
+    value: !!bool false
+  accuracy_robustness_cybersecurity_robustiness: 
+    article: 'Art. 15(1)'
+    verbose: 'Model is designed and developed to achieve appropriate level of robustness'
+    value: !!bool false
+  accuracy_robustness_cybersecurity_cybersecurity:  
+    article: 'Art. 15(1)'
+    verbose: 'Model is designed and developed to achieve appropriate level of cybersecurity'
+    value: !!bool false
+  accuracy_robustness_cybersecurity_accuracy_metrics: 
+    article: 'Art. 15(2)'
+    verbose: 'Use of relevant accuracy metrics'
+    value: !!bool false
+  accuracy_robustness_cybersecurity_fault_resilience: 
+    article: 'Art. 15(4)'
+    verbose: 'Maximum possible resilience regarding errors, faults or inconsistencies that may occur within the system or the environment in which the system operates, in particular due to their interaction with natural persons or other systems. Technical and organisational measures shall be taken towards this regard'
+    value: !!bool false
+  accuracy_robustness_cybersecurity_attacks: 
+    article: 'Art. 15(5)'
+    verbose: 'Measures were taken to prevent, detect, respond to, resolve and control for model poisoning attacks, adversarial examples or model evasion attacks (attacks using inputs designed to cause the model to make a mistake), and confidentiality attacks or model flaws'
+    value: !!bool false
+  quality_management_system:
+    article: 'Art. 17(1)(d)'
+    verbose: 'Examination, test and validation procedures to be carried out before, during and after the development of the high-risk AI system, and the frequency with which they have to be carried out'
+    value: !!bool false
+
+# Metadata related to model-related requirements for GPAI models 
+
+gpai_model_requirements:
+  task:  
+    article: 'Art. 53; Annex XI(1)(1)(a)'
+    verbose: 'The tasks that the model is intended to perform and the type and nature of AI systems in which it can be integrated'
+    value: !!bool false
+  acceptable_use: 
+    article: 'Art. 53; Annex XI(1)(1)(b)'
+    verbose: 'Acceptable use policies applicable'
+    value: !!bool false
+  release_date: 
+    article: 'Art. 53; Annex XI(1)(1)(c)'
+    verbose: 'The date of release and methods of distribution'
+    value: !!bool false
+  architecture: 
+    article: 'Art. 53; Annex XI(1)(1)(d)'
+    verbose: 'The architecture and number of parameters'
+    value: !!bool false
+  input_output_modality: 
+    article: 'Art. 53; Annex XI(1)(1)(e)'
+    verbos: 'Modality (e.g. text, image) and format of inputs and outputs'
+    value: !!bool false
+  license: 
+    article: 'Art. 53; Annex XI(1)(1)(f)'
+    verbose: 'The license'
+    value: !!bool false
+  training: 
+    article: 'Art. 53; Annex XI(1)(2)(b)'
+    verbose: 'Training methodologies and techniques'
+    value: !!bool false
+  design_choices: 
+    article: 'Art. 53; Annex XI(1)(2)(b)'
+    verbose: 'Key design choices including the rationale and assumptions made'
+    value: !!bool false
+  optimized_for:  
+    article: 'Art. 53; Annex XI(1)(2)(b)'
+    verbose: 'What the model is designed to optimise for'
+    value: !!bool false
+  parameters: 
+    article: 'Art. 53; Annex XI(1)(2)(b)'
+    verbose: 'The relevance of the different parameters, as applicable'
+    value: !!bool false
+  data_type: 
+    article: 'Art. 53; Annex XI(1)(2)(c)'
+    verbose: 'Information on the data used for training, testing and validation: type of data' 
+    value: !!bool false
+  data_provenance: 
+    article: 'Art. 53; Annex XI(1)(2)(c)'
+    verbose: 'Information on the data used for training, testing and validation: provenance of data'
+    value: !!bool false
+  data_curation: 
+    article: 'Art. 53; Annex XI(1)(2)(c)'
+    verbose: 'Information on the data used for training: curation methodologies (e.g. cleaning, filtering etc)'
+    value: !!bool false
+  data_number: 
+    article: 'Art. 53; Annex XI(1)(2)(c)'
+    verbose: 'Information on the data used for training: the number of data points'
+    value: !!bool false
+  data_characteristics: 
+    article: 'Art. 53; Annex XI(1)(2)(c)'
+    verbose: 'Information on the data used for training: data points scope and main characteristics applicable'
+    value: !!bool false
+  data_origin: 
+    article: 'Art. 53; Annex XI(1)(2)(c)'
+    verbose: 'Information on the data used for training: how the data was obtained and selected'
+    value: !!bool false
+  data_bias: 
+    article: 'Art. 53; Annex XI(1)(2)(c)'
+    verbose: 'Information on the data used for training: all other measures to detect the unsuitability of data sources and methods to detect identifiable biases, where applicable'
+    value: !!bool false
+  computation: 
+    article: 'Art. 53; Annex XI(1)(2)(d)'
+    verbose: 'The computational resources used to train the model (e.g. number of floating point operations – FLOPs), training time, and other relevant details related to the training'
+    value: !!bool false
+  energy_consumption: 
+    article: 'Art. 53; Annex XI(1)(2)(e)'
+    verbose: 'Known or estimated energy consumption of the model; in case not known, this could be based on information about computational resources used'
+    value: !!bool false
+  evaluation: 
+    article: 'Art. 53; Annex XI(2)(1)'
+    verbose: 'Detailed description of the evaluation strategies, including evaluation results, on the basis of available public evaluation protocols and tools or otherwise of other evaluation methodologies. Evaluation strategies shall include evaluation criteria, metrics and the methodology on the identification of limitations'
+    value: !!bool false
+  adversarial_testing: 
+    article: 'Art. 53; Annex XI(2)(2)'
+    verbose: 'Where applicable, detailed description of the measures put in place for the purpose of conducting internal and/or external adversarial testing (e.g. red teaming), model adaptations, including alignment and fine-tuning'
+    value: !!bool false
+
+gpai_model_with_systemic_risk_requirements:
+  evaluation: 
+    article: 'Art. 55(1)(a)'
+    verbose: 'Perform model evaluation in accordance with standardised protocols and tools reflecting the state of the art, including conducting and documenting adversarial testing of the model with a view to identify and mitigate systemic risk'
+    value: !!bool false
+  systematic_risk:  
+    article: 'Art. 55(1)(b)'
+    verbose: 'Assess and mitigate possible systemic risks at Union level, including their sources, that may stem from the development'
+    value: !!bool false
+  cybersecurity: 
+    article: 'Art. 55(1)(d)'
+    verbose: 'Ensure an adequate level of cybersecurity protection for the GPAI model with systemic risk and the physical infrastructure of the mode'
+    value: !!bool false

model_cc.yaml

@@ -1,4 +1,6 @@
-card_type: "model" # "project", "data" or "model"
+card_details: 
+  card_type: "model" # "project", "data" or "model"
+  card_label: "model_01"
 
 # Metadata related to intended purpose(s) of model 
 

project_cc.yaml

@@ -1,6 +1,8 @@
 
 # Information related to high-level characteristics of AI project, including the role of the operator, their location, and where the output is used
-card_type: "project" # "project", "data" or "model"
+card_details: 
+  card_type: "project" # "project", "data" or "model"
+  card_label: "project"
   
 # TODO potentially add scenarios that get the provider off the hook per Article 25 
 

run.py

@@ -2,7 +2,7 @@ import yaml
 import json
 from pathlib import Path
 import pandas as pd
-from compliance_analysis import check_overall_compliance
+from src.compliance_analysis import check_overall_compliance
 
 pd.set_option('display.max_columns', None)  
 pd.set_option('display.max_rows', None)

utils.py

@@ -31,16 +31,6 @@ def set_eu_market_status(dispositive_variables, project_cc_yaml):
         
     return dispositive_variables
 
-
-def check_within_scope_cc(dispositive_variables, project_cc_yaml):
-
-    # Check that the person filling out the form (the operator) is in fact a provider;
-    if project_cc_yaml['operator_details']['provider']['value']:        
-        return True
-    else:
-        print("The initial versiton of the Compliance Cards System is for provider-side compliance analyses only.")
-        return False
-
 def check_within_scope_act(dispositive_variables, project_cc_yaml):
 
     # Check that the project is within the scope of the Act