From 26ddf93fccf127c6f000a34ee4a987d9e05894c8 Mon Sep 17 00:00:00 2001
From: Niels Pardon <par@zurich.ibm.com>
Date: Tue, 17 Mar 2026 09:32:59 +0100
Subject: [PATCH 01/11] fix(extensions)!: change distribution option to enum
 arg for std_dev and variance

BREAKING CHANGE: changes the function signature of existing functions std_dev and variance

Signed-off-by: Niels Pardon <par@zurich.ibm.com>
---
 extensions/functions_arithmetic.yaml | 16 ++++----
 tests/cases/arithmetic/std_dev.test  | 53 ++++++++++++++++++++++++
 tests/cases/arithmetic/variance.test | 61 ++++++++++++++++++++++++++++
 tests/coverage/nodes.py              | 23 ++++++++++-
 4 files changed, 143 insertions(+), 10 deletions(-)
 create mode 100644 tests/cases/arithmetic/std_dev.test
 create mode 100644 tests/cases/arithmetic/variance.test

diff --git a/extensions/functions_arithmetic.yaml b/extensions/functions_arithmetic.yaml
index 8746f0392..7f03eed96 100644
--- a/extensions/functions_arithmetic.yaml
+++ b/extensions/functions_arithmetic.yaml
@@ -1395,21 +1395,21 @@ aggregate_functions:
       - args:
           - name: x
             value: fp32
+          - name: distribution
+            options: [ SAMPLE, POPULATION]
         options:
           rounding:
             values: [ TIE_TO_EVEN, TIE_AWAY_FROM_ZERO, TRUNCATE, CEILING, FLOOR ]
-          distribution:
-            values: [ SAMPLE, POPULATION]
         nullability: DECLARED_OUTPUT
         return: fp32?
       - args:
           - name: x
             value: fp64
+          - name: distribution
+            options: [ SAMPLE, POPULATION]
         options:
           rounding:
             values: [ TIE_TO_EVEN, TIE_AWAY_FROM_ZERO, TRUNCATE, CEILING, FLOOR ]
-          distribution:
-            values: [ SAMPLE, POPULATION]
         nullability: DECLARED_OUTPUT
         return: fp64?
   - name: "variance"
@@ -1418,21 +1418,21 @@ aggregate_functions:
       - args:
           - name: x
             value: fp32
+          - name: distribution
+            options: [ SAMPLE, POPULATION]
         options:
           rounding:
             values: [ TIE_TO_EVEN, TIE_AWAY_FROM_ZERO, TRUNCATE, CEILING, FLOOR ]
-          distribution:
-            values: [ SAMPLE, POPULATION]
         nullability: DECLARED_OUTPUT
         return: fp32?
       - args:
           - name: x
             value: fp64
+          - name: distribution
+            options: [ SAMPLE, POPULATION]
         options:
           rounding:
             values: [ TIE_TO_EVEN, TIE_AWAY_FROM_ZERO, TRUNCATE, CEILING, FLOOR ]
-          distribution:
-            values: [ SAMPLE, POPULATION]
         nullability: DECLARED_OUTPUT
         return: fp64?
   - name: "corr"
diff --git a/tests/cases/arithmetic/std_dev.test b/tests/cases/arithmetic/std_dev.test
new file mode 100644
index 000000000..076fb36c6
--- /dev/null
+++ b/tests/cases/arithmetic/std_dev.test
@@ -0,0 +1,53 @@
+### SUBSTRAIT_AGGREGATE_TEST: v1.0
+### SUBSTRAIT_INCLUDE: '/extensions/functions_arithmetic.yaml'
+
+# basic: Basic examples without any special cases
+((1.0, 2.0, 3.0, 4.0, 5.0)) std_dev(col0::fp32, SAMPLE::enum) = 1.5811388::fp32
+((1.0, 2.0, 3.0, 4.0, 5.0)) std_dev(col0::fp64, SAMPLE::enum) = 1.5811388300841898::fp64
+((1.0, 2.0, 3.0, 4.0, 5.0)) std_dev(col0::fp32, POPULATION::enum) = 1.4142135::fp32
+((1.0, 2.0, 3.0, 4.0, 5.0)) std_dev(col0::fp64, POPULATION::enum) = 1.4142135623730951::fp64
+
+# uniform_values: Standard deviation of uniform values
+((5.0, 5.0, 5.0, 5.0)) std_dev(col0::fp32, SAMPLE::enum) = 0.0::fp32
+((5.0, 5.0, 5.0, 5.0)) std_dev(col0::fp64, POPULATION::enum) = 0.0::fp64
+
+# single_value: Standard deviation with single value
+((42.0)) std_dev(col0::fp32, SAMPLE::enum) = Null::fp32
+((42.0)) std_dev(col0::fp64, POPULATION::enum) = 0.0::fp64
+
+# negative_values: Standard deviation with negative values
+((-5.0, -3.0, -1.0, 1.0, 3.0, 5.0)) std_dev(col0::fp32, SAMPLE::enum) = 3.8944404::fp32
+((-5.0, -3.0, -1.0, 1.0, 3.0, 5.0)) std_dev(col0::fp64, SAMPLE::enum) = 3.8944404818493075::fp64
+((-10.0, -5.0, 0.0, 5.0, 10.0)) std_dev(col0::fp32, POPULATION::enum) = 7.0710678::fp32
+((-10.0, -5.0, 0.0, 5.0, 10.0)) std_dev(col0::fp64, POPULATION::enum) = 7.0710678118654755::fp64
+
+# decimal_precision: Standard deviation with decimal values
+((1.5, 2.5, 3.5, 4.5, 5.5)) std_dev(col0::fp32, SAMPLE::enum) = 1.5811388::fp32
+((1.5, 2.5, 3.5, 4.5, 5.5)) std_dev(col0::fp64, SAMPLE::enum) = 1.5811388300841898::fp64
+((0.1, 0.2, 0.3, 0.4, 0.5)) std_dev(col0::fp64, POPULATION::enum) = 0.14142135623730953::fp64
+
+# large_values: Standard deviation with large values
+((1000.0, 2000.0, 3000.0, 4000.0, 5000.0)) std_dev(col0::fp32, SAMPLE::enum) = 1581.1388::fp32
+((1000.0, 2000.0, 3000.0, 4000.0, 5000.0)) std_dev(col0::fp64, SAMPLE::enum) = 1581.1388300841898::fp64
+
+# small_values: Standard deviation with small values
+((0.001, 0.002, 0.003, 0.004, 0.005)) std_dev(col0::fp64, SAMPLE::enum) = 0.0015811388300841896::fp64
+((0.001, 0.002, 0.003, 0.004, 0.005)) std_dev(col0::fp64, POPULATION::enum) = 0.0014142135623730951::fp64
+
+# null_handling: Examples with null as input or output
+((Null, Null, Null)) std_dev(col0::fp32, SAMPLE::enum) = Null::fp32
+(()) std_dev(col0::fp32, SAMPLE::enum) = Null::fp32
+((1.0, Null, 3.0, Null, 5.0)) std_dev(col0::fp32, SAMPLE::enum) = 2.0::fp32
+((1.0, Null, 3.0, Null, 5.0)) std_dev(col0::fp64, POPULATION::enum) = 1.632993161855452::fp64
+
+# rounding: Examples with different rounding modes
+((1.1, 2.2, 3.3, 4.4, 5.5)) std_dev(col0::fp32, SAMPLE::enum) [rounding:TIE_TO_EVEN] = 1.7406897::fp32
+((1.1, 2.2, 3.3, 4.4, 5.5)) std_dev(col0::fp64, SAMPLE::enum) [rounding:TRUNCATE] = 1.7406897166664838::fp64
+
+# two_values: Standard deviation with two values
+((10.0, 20.0)) std_dev(col0::fp32, SAMPLE::enum) = 7.071068::fp32
+((10.0, 20.0)) std_dev(col0::fp64, POPULATION::enum) = 5.0::fp64
+
+# mixed_range: Standard deviation with mixed range values
+((0.0, 100.0, 50.0, 25.0, 75.0)) std_dev(col0::fp32, SAMPLE::enum) = 41.010193::fp32
+((0.0, 100.0, 50.0, 25.0, 75.0)) std_dev(col0::fp64, POPULATION::enum) = 36.66060555964672::fp64
\ No newline at end of file
diff --git a/tests/cases/arithmetic/variance.test b/tests/cases/arithmetic/variance.test
new file mode 100644
index 000000000..47fac986a
--- /dev/null
+++ b/tests/cases/arithmetic/variance.test
@@ -0,0 +1,61 @@
+### SUBSTRAIT_AGGREGATE_TEST: v1.0
+### SUBSTRAIT_INCLUDE: '/extensions/functions_arithmetic.yaml'
+
+# basic: Basic examples without any special cases
+((1.0, 2.0, 3.0, 4.0, 5.0)) variance(col0::fp32, SAMPLE::enum) = 2.5::fp32
+((1.0, 2.0, 3.0, 4.0, 5.0)) variance(col0::fp64, SAMPLE::enum) = 2.5::fp64
+((1.0, 2.0, 3.0, 4.0, 5.0)) variance(col0::fp32, POPULATION::enum) = 2.0::fp32
+((1.0, 2.0, 3.0, 4.0, 5.0)) variance(col0::fp64, POPULATION::enum) = 2.0::fp64
+
+# uniform_values: Variance of uniform values
+((5.0, 5.0, 5.0, 5.0)) variance(col0::fp32, SAMPLE::enum) = 0.0::fp32
+((5.0, 5.0, 5.0, 5.0)) variance(col0::fp64, POPULATION::enum) = 0.0::fp64
+
+# single_value: Variance with single value
+((42.0)) variance(col0::fp32, SAMPLE::enum) = Null::fp32
+((42.0)) variance(col0::fp64, POPULATION::enum) = 0.0::fp64
+
+# negative_values: Variance with negative values
+((-5.0, -3.0, -1.0, 1.0, 3.0, 5.0)) variance(col0::fp32, SAMPLE::enum) = 15.166667::fp32
+((-5.0, -3.0, -1.0, 1.0, 3.0, 5.0)) variance(col0::fp64, SAMPLE::enum) = 15.166666666666666::fp64
+((-10.0, -5.0, 0.0, 5.0, 10.0)) variance(col0::fp32, POPULATION::enum) = 50.0::fp32
+((-10.0, -5.0, 0.0, 5.0, 10.0)) variance(col0::fp64, POPULATION::enum) = 50.0::fp64
+
+# decimal_precision: Variance with decimal values
+((1.5, 2.5, 3.5, 4.5, 5.5)) variance(col0::fp32, SAMPLE::enum) = 2.5::fp32
+((1.5, 2.5, 3.5, 4.5, 5.5)) variance(col0::fp64, SAMPLE::enum) = 2.5::fp64
+((0.1, 0.2, 0.3, 0.4, 0.5)) variance(col0::fp64, POPULATION::enum) = 0.020000000000000004::fp64
+
+# large_values: Variance with large values
+((1000.0, 2000.0, 3000.0, 4000.0, 5000.0)) variance(col0::fp32, SAMPLE::enum) = 2500000.0::fp32
+((1000.0, 2000.0, 3000.0, 4000.0, 5000.0)) variance(col0::fp64, SAMPLE::enum) = 2500000.0::fp64
+
+# small_values: Variance with small values
+((0.001, 0.002, 0.003, 0.004, 0.005)) variance(col0::fp64, SAMPLE::enum) = 0.0000025::fp64
+((0.001, 0.002, 0.003, 0.004, 0.005)) variance(col0::fp64, POPULATION::enum) = 0.000002::fp64
+
+# null_handling: Examples with null as input or output
+((Null, Null, Null)) variance(col0::fp32, SAMPLE::enum) = Null::fp32
+(()) variance(col0::fp32, SAMPLE::enum) = Null::fp32
+((1.0, Null, 3.0, Null, 5.0)) variance(col0::fp32, SAMPLE::enum) = 4.0::fp32
+((1.0, Null, 3.0, Null, 5.0)) variance(col0::fp64, POPULATION::enum) = 2.666666666666667::fp64
+
+# rounding: Examples with different rounding modes
+((1.1, 2.2, 3.3, 4.4, 5.5)) variance(col0::fp32, SAMPLE::enum) [rounding:TIE_TO_EVEN] = 3.03::fp32
+((1.1, 2.2, 3.3, 4.4, 5.5)) variance(col0::fp64, SAMPLE::enum) [rounding:TRUNCATE] = 3.0299999999999994::fp64
+
+# two_values: Variance with two values
+((10.0, 20.0)) variance(col0::fp32, SAMPLE::enum) = 50.0::fp32
+((10.0, 20.0)) variance(col0::fp64, POPULATION::enum) = 25.0::fp64
+
+# mixed_range: Variance with mixed range values
+((0.0, 100.0, 50.0, 25.0, 75.0)) variance(col0::fp32, SAMPLE::enum) = 1681.25::fp32
+((0.0, 100.0, 50.0, 25.0, 75.0)) variance(col0::fp64, POPULATION::enum) = 1345.0::fp64
+
+# zero_mean: Variance with values around zero
+((-2.0, -1.0, 0.0, 1.0, 2.0)) variance(col0::fp32, SAMPLE::enum) = 2.5::fp32
+((-2.0, -1.0, 0.0, 1.0, 2.0)) variance(col0::fp64, POPULATION::enum) = 2.0::fp64
+
+# three_values: Variance with three values
+((10.0, 20.0, 30.0)) variance(col0::fp32, SAMPLE::enum) = 100.0::fp32
+((10.0, 20.0, 30.0)) variance(col0::fp64, POPULATION::enum) = 66.66666666666667::fp64
\ No newline at end of file
diff --git a/tests/coverage/nodes.py b/tests/coverage/nodes.py
index bee4be838..d1151bd31 100644
--- a/tests/coverage/nodes.py
+++ b/tests/coverage/nodes.py
@@ -85,10 +85,29 @@ def is_return_type_error(self):
         return isinstance(self.result, SubstraitError)
 
     def get_arg_types(self):
-        return [arg.get_base_type() for arg in self.args]
+        types = []
+        for arg in self.args:
+            if isinstance(arg, CaseLiteral):
+                types.append(arg.get_base_type())
+            elif isinstance(arg, AggregateArgument):
+                # For aggregate arguments, use column_type if available, otherwise extract from scalar_value
+                if arg.column_type:
+                    types.append(arg.column_type)
+                elif arg.scalar_value:
+                    types.append(arg.scalar_value.get_base_type())
+        return types
 
     def get_signature(self):
-        return f"{self.func_name}({', '.join([arg.type for arg in self.args])}) = {self.get_return_type()}"
+        arg_types = []
+        for arg in self.args:
+            if isinstance(arg, CaseLiteral):
+                arg_types.append(arg.type)
+            elif isinstance(arg, AggregateArgument):
+                if arg.column_type:
+                    arg_types.append(arg.column_type)
+                elif arg.scalar_value:
+                    arg_types.append(arg.scalar_value.type)
+        return f"{self.func_name}({', '.join(arg_types)}) = {self.get_return_type()}"
 
 
 @dataclass

From 9b5f945bcd8c93a9cf9e46658eff08b1087e2b15 Mon Sep 17 00:00:00 2001
From: Niels Pardon <par@zurich.ibm.com>
Date: Thu, 19 Mar 2026 08:54:34 +0100
Subject: [PATCH 02/11] fix: add deprecated flag and deprecate old sigs

Signed-off-by: Niels Pardon <par@zurich.ibm.com>
---
 extensions/functions_arithmetic.yaml | 44 ++++++++++++++++++++++++++
 text/simple_extensions_schema.yaml   | 47 ++++++++++++++++++++++++++++
 2 files changed, 91 insertions(+)

diff --git a/extensions/functions_arithmetic.yaml b/extensions/functions_arithmetic.yaml
index 7f03eed96..f442fb123 100644
--- a/extensions/functions_arithmetic.yaml
+++ b/extensions/functions_arithmetic.yaml
@@ -1392,6 +1392,17 @@ aggregate_functions:
   - name: "std_dev"
     description: Calculates standard-deviation for a set of values.
     impls:
+      - deprecated: true
+        args:
+          - name: x
+            value: fp32
+        options:
+          rounding:
+            values: [ TIE_TO_EVEN, TIE_AWAY_FROM_ZERO, TRUNCATE, CEILING, FLOOR ]
+          distribution:
+            values: [ SAMPLE, POPULATION]
+        nullability: DECLARED_OUTPUT
+        return: fp32?
       - args:
           - name: x
             value: fp32
@@ -1402,6 +1413,17 @@ aggregate_functions:
             values: [ TIE_TO_EVEN, TIE_AWAY_FROM_ZERO, TRUNCATE, CEILING, FLOOR ]
         nullability: DECLARED_OUTPUT
         return: fp32?
+      - deprecated: true
+        args:
+          - name: x
+            value: fp64
+        options:
+          distribution:
+            values: [ SAMPLE, POPULATION]
+          rounding:
+            values: [ TIE_TO_EVEN, TIE_AWAY_FROM_ZERO, TRUNCATE, CEILING, FLOOR ]
+        nullability: DECLARED_OUTPUT
+        return: fp64?
       - args:
           - name: x
             value: fp64
@@ -1415,6 +1437,17 @@ aggregate_functions:
   - name: "variance"
     description: Calculates variance for a set of values.
     impls:
+      - deprecated: true
+        args:
+          - name: x
+            value: fp32
+        options:
+          distribution:
+            values: [ SAMPLE, POPULATION]
+          rounding:
+            values: [ TIE_TO_EVEN, TIE_AWAY_FROM_ZERO, TRUNCATE, CEILING, FLOOR ]
+        nullability: DECLARED_OUTPUT
+        return: fp32?
       - args:
           - name: x
             value: fp32
@@ -1425,6 +1458,17 @@ aggregate_functions:
             values: [ TIE_TO_EVEN, TIE_AWAY_FROM_ZERO, TRUNCATE, CEILING, FLOOR ]
         nullability: DECLARED_OUTPUT
         return: fp32?
+      - deprecated: true
+        args:
+          - name: x
+            value: fp64
+        options:
+          distribution:
+            values: [ SAMPLE, POPULATION]
+          rounding:
+            values: [ TIE_TO_EVEN, TIE_AWAY_FROM_ZERO, TRUNCATE, CEILING, FLOOR ]
+        nullability: DECLARED_OUTPUT
+        return: fp64?
       - args:
           - name: x
             value: fp64
diff --git a/text/simple_extensions_schema.yaml b/text/simple_extensions_schema.yaml
index dd737246d..44db6bf6a 100644
--- a/text/simple_extensions_schema.yaml
+++ b/text/simple_extensions_schema.yaml
@@ -41,6 +41,11 @@ properties:
           $ref: "#/$defs/type_param_defs"
         variadic: # when set, last parameter may be specified one or more times
           type: boolean
+        deprecated:
+          type: boolean
+          description: >-
+            true if this type has been deprecated, otherwise false (default)
+          default: false
   type_variations:
     type: array
     minItems: 1
@@ -60,6 +65,12 @@ properties:
         functions:
           type: string
           enum: [INHERITS, SEPARATE]
+        deprecated:
+          type: boolean
+          description: >-
+            true if this type variation has been deprecated,
+            otherwise false (default)
+          default: false
   scalar_functions:
     type: array
     items:
@@ -273,6 +284,18 @@ $defs:
               $ref: "#/$defs/returnValue"
             implementation:
               $ref: "#/$defs/implementation"
+            deprecated:
+              type: boolean
+              description: >-
+                true if this scalar function signature has been deprecated,
+                otherwise false (default)
+              default: false
+      deprecated:
+        type: boolean
+        description: >-
+          true if this scalar function has been deprecated,
+          otherwise false (default)
+        default: false
   aggregateFunction:
     type: object
     additionalProperties: false
@@ -322,6 +345,18 @@ $defs:
               $ref: "#/$defs/maxset"
             decomposable:
               $ref: "#/$defs/decomposable"
+            deprecated:
+              type: boolean
+              description: >-
+                true if this aggregate function signature has been deprecated,
+                otherwise false (default)
+              default: false
+      deprecated:
+        type: boolean
+        description: >-
+          true if this aggregate function has been deprecated,
+          otherwise false (default)
+        default: false
   windowFunction:
     type: object
     additionalProperties: false
@@ -374,3 +409,15 @@ $defs:
             window_type:
               type: string
               enum: [STREAMING, PARTITION]
+            deprecated:
+              type: boolean
+              description: >-
+                true if this window function signature has been deprecated,
+                otherwise false (default)
+              default: false
+      deprecated:
+        type: boolean
+        description: >-
+          true if this window function has been deprecated,
+          otherwise false (default)
+        default: false

From eed9e419a5a06126969dcc779a255c70d3547dd4 Mon Sep 17 00:00:00 2001
From: Niels Pardon <par@zurich.ibm.com>
Date: Thu, 19 Mar 2026 10:07:32 +0100
Subject: [PATCH 03/11] doc: add deprecated field to docs

Signed-off-by: Niels Pardon <par@zurich.ibm.com>
---
 site/docs/expressions/scalar_functions.md | 1 +
 1 file changed, 1 insertion(+)

diff --git a/site/docs/expressions/scalar_functions.md b/site/docs/expressions/scalar_functions.md
index 212a32df8..6d6dd7410 100644
--- a/site/docs/expressions/scalar_functions.md
+++ b/site/docs/expressions/scalar_functions.md
@@ -12,6 +12,7 @@ A function is a scalar function if that function takes in values from a single r
 | Nullability Handling | Describes how nullability of input arguments maps to nullability of output arguments. Three options are: `MIRROR`, `DECLARED_OUTPUT` and `DISCRETE`. More details about nullability handling are listed below.                                                                                                                                                                                        | Optional, defaults to `MIRROR` |
 | Description            | Additional description of function for implementers or users. Should be written human-readable to allow exposure to end users. Can be specified at the function level and/or on individual implementations to document overload-specific behavior.                                                                                                                         | Optional                            |
 | Return Value | The output type of the expression.  Return types can be expressed as a fully-defined type or a type expression. See below for more on type expressions.                                                                                                                                                                                                                                               | Required                            |
+| deprecated | Indicates whether this function or function signature has been deprecated. | Optional, defaults to false |
 | Implementation Map     | A map of implementation locations for one or more implementations of the given function. Each key is a function implementation type. Implementation types include examples such as: AthenaArrowLambda, TrinoV361Jar, ArrowCppKernelEnum, GandivaEnum, LinkedIn Transport Jar, etc. [Definition TBD]. Implementation type has one or more properties associated with retrieval of that implementation. | Optional                            |
 
 

From 02dd601fd020425de2a130436e0db8c8708a4342 Mon Sep 17 00:00:00 2001
From: Niels Pardon <par@zurich.ibm.com>
Date: Fri, 20 Mar 2026 20:24:12 +0100
Subject: [PATCH 04/11] fix: use new deprecation mechanism

Signed-off-by: Niels Pardon <par@zurich.ibm.com>
---
 extensions/functions_arithmetic.yaml      |  8 +++-
 site/docs/expressions/scalar_functions.md |  1 -
 text/simple_extensions_schema.yaml        | 47 -----------------------
 3 files changed, 6 insertions(+), 50 deletions(-)

diff --git a/extensions/functions_arithmetic.yaml b/extensions/functions_arithmetic.yaml
index f442fb123..1cd189ce3 100644
--- a/extensions/functions_arithmetic.yaml
+++ b/extensions/functions_arithmetic.yaml
@@ -1392,7 +1392,9 @@ aggregate_functions:
   - name: "std_dev"
     description: Calculates standard-deviation for a set of values.
     impls:
-      - deprecated: true
+      - deprecated:
+          since: "0.86.0"
+          reason: Use implementation with distribution enum argument instead.
         args:
           - name: x
             value: fp32
@@ -1413,7 +1415,9 @@ aggregate_functions:
             values: [ TIE_TO_EVEN, TIE_AWAY_FROM_ZERO, TRUNCATE, CEILING, FLOOR ]
         nullability: DECLARED_OUTPUT
         return: fp32?
-      - deprecated: true
+      - deprecated:
+          since: "0.86.0"
+          reason: Use implementation with distribution enum argument instead.
         args:
           - name: x
             value: fp64
diff --git a/site/docs/expressions/scalar_functions.md b/site/docs/expressions/scalar_functions.md
index 6d6dd7410..212a32df8 100644
--- a/site/docs/expressions/scalar_functions.md
+++ b/site/docs/expressions/scalar_functions.md
@@ -12,7 +12,6 @@ A function is a scalar function if that function takes in values from a single r
 | Nullability Handling | Describes how nullability of input arguments maps to nullability of output arguments. Three options are: `MIRROR`, `DECLARED_OUTPUT` and `DISCRETE`. More details about nullability handling are listed below.                                                                                                                                                                                        | Optional, defaults to `MIRROR` |
 | Description            | Additional description of function for implementers or users. Should be written human-readable to allow exposure to end users. Can be specified at the function level and/or on individual implementations to document overload-specific behavior.                                                                                                                         | Optional                            |
 | Return Value | The output type of the expression.  Return types can be expressed as a fully-defined type or a type expression. See below for more on type expressions.                                                                                                                                                                                                                                               | Required                            |
-| deprecated | Indicates whether this function or function signature has been deprecated. | Optional, defaults to false |
 | Implementation Map     | A map of implementation locations for one or more implementations of the given function. Each key is a function implementation type. Implementation types include examples such as: AthenaArrowLambda, TrinoV361Jar, ArrowCppKernelEnum, GandivaEnum, LinkedIn Transport Jar, etc. [Definition TBD]. Implementation type has one or more properties associated with retrieval of that implementation. | Optional                            |
 
 
diff --git a/text/simple_extensions_schema.yaml b/text/simple_extensions_schema.yaml
index 44db6bf6a..dd737246d 100644
--- a/text/simple_extensions_schema.yaml
+++ b/text/simple_extensions_schema.yaml
@@ -41,11 +41,6 @@ properties:
           $ref: "#/$defs/type_param_defs"
         variadic: # when set, last parameter may be specified one or more times
           type: boolean
-        deprecated:
-          type: boolean
-          description: >-
-            true if this type has been deprecated, otherwise false (default)
-          default: false
   type_variations:
     type: array
     minItems: 1
@@ -65,12 +60,6 @@ properties:
         functions:
           type: string
           enum: [INHERITS, SEPARATE]
-        deprecated:
-          type: boolean
-          description: >-
-            true if this type variation has been deprecated,
-            otherwise false (default)
-          default: false
   scalar_functions:
     type: array
     items:
@@ -284,18 +273,6 @@ $defs:
               $ref: "#/$defs/returnValue"
             implementation:
               $ref: "#/$defs/implementation"
-            deprecated:
-              type: boolean
-              description: >-
-                true if this scalar function signature has been deprecated,
-                otherwise false (default)
-              default: false
-      deprecated:
-        type: boolean
-        description: >-
-          true if this scalar function has been deprecated,
-          otherwise false (default)
-        default: false
   aggregateFunction:
     type: object
     additionalProperties: false
@@ -345,18 +322,6 @@ $defs:
               $ref: "#/$defs/maxset"
             decomposable:
               $ref: "#/$defs/decomposable"
-            deprecated:
-              type: boolean
-              description: >-
-                true if this aggregate function signature has been deprecated,
-                otherwise false (default)
-              default: false
-      deprecated:
-        type: boolean
-        description: >-
-          true if this aggregate function has been deprecated,
-          otherwise false (default)
-        default: false
   windowFunction:
     type: object
     additionalProperties: false
@@ -409,15 +374,3 @@ $defs:
             window_type:
               type: string
               enum: [STREAMING, PARTITION]
-            deprecated:
-              type: boolean
-              description: >-
-                true if this window function signature has been deprecated,
-                otherwise false (default)
-              default: false
-      deprecated:
-        type: boolean
-        description: >-
-          true if this window function has been deprecated,
-          otherwise false (default)
-        default: false

From 8e570e20a3ee2df4fe6f61bd86b4ebaee890223b Mon Sep 17 00:00:00 2001
From: Niels Pardon <par@zurich.ibm.com>
Date: Fri, 20 Mar 2026 20:30:50 +0100
Subject: [PATCH 05/11] fix: also change variance function to new deprecation

Signed-off-by: Niels Pardon <par@zurich.ibm.com>
---
 extensions/functions_arithmetic.yaml | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/extensions/functions_arithmetic.yaml b/extensions/functions_arithmetic.yaml
index 1cd189ce3..ec5f762fb 100644
--- a/extensions/functions_arithmetic.yaml
+++ b/extensions/functions_arithmetic.yaml
@@ -1441,7 +1441,9 @@ aggregate_functions:
   - name: "variance"
     description: Calculates variance for a set of values.
     impls:
-      - deprecated: true
+      - deprecated:
+          since: "0.86.0"
+          reason: Use implementation with distribution enum argument instead.
         args:
           - name: x
             value: fp32
@@ -1462,7 +1464,9 @@ aggregate_functions:
             values: [ TIE_TO_EVEN, TIE_AWAY_FROM_ZERO, TRUNCATE, CEILING, FLOOR ]
         nullability: DECLARED_OUTPUT
         return: fp32?
-      - deprecated: true
+      - deprecated:
+          since: "0.86.0"
+          reason: Use implementation with distribution enum argument instead.
         args:
           - name: x
             value: fp64

From 1330e33a596e48a45eac1676178bbf7f6ee19a17 Mon Sep 17 00:00:00 2001
From: Niels Pardon <par@zurich.ibm.com>
Date: Fri, 20 Mar 2026 20:41:09 +0100
Subject: [PATCH 06/11] fix: test case nullability

Signed-off-by: Niels Pardon <par@zurich.ibm.com>
---
 tests/cases/arithmetic/std_dev.test  | 58 ++++++++++++------------
 tests/cases/arithmetic/variance.test | 66 ++++++++++++++--------------
 2 files changed, 62 insertions(+), 62 deletions(-)

diff --git a/tests/cases/arithmetic/std_dev.test b/tests/cases/arithmetic/std_dev.test
index 076fb36c6..2a5310651 100644
--- a/tests/cases/arithmetic/std_dev.test
+++ b/tests/cases/arithmetic/std_dev.test
@@ -2,52 +2,52 @@
 ### SUBSTRAIT_INCLUDE: '/extensions/functions_arithmetic.yaml'
 
 # basic: Basic examples without any special cases
-((1.0, 2.0, 3.0, 4.0, 5.0)) std_dev(col0::fp32, SAMPLE::enum) = 1.5811388::fp32
-((1.0, 2.0, 3.0, 4.0, 5.0)) std_dev(col0::fp64, SAMPLE::enum) = 1.5811388300841898::fp64
-((1.0, 2.0, 3.0, 4.0, 5.0)) std_dev(col0::fp32, POPULATION::enum) = 1.4142135::fp32
-((1.0, 2.0, 3.0, 4.0, 5.0)) std_dev(col0::fp64, POPULATION::enum) = 1.4142135623730951::fp64
+((1.0, 2.0, 3.0, 4.0, 5.0)) std_dev(col0::fp32, SAMPLE::enum) = 1.5811388::fp32?
+((1.0, 2.0, 3.0, 4.0, 5.0)) std_dev(col0::fp64, SAMPLE::enum) = 1.5811388300841898::fp64?
+((1.0, 2.0, 3.0, 4.0, 5.0)) std_dev(col0::fp32, POPULATION::enum) = 1.4142135::fp32?
+((1.0, 2.0, 3.0, 4.0, 5.0)) std_dev(col0::fp64, POPULATION::enum) = 1.4142135623730951::fp64?
 
 # uniform_values: Standard deviation of uniform values
-((5.0, 5.0, 5.0, 5.0)) std_dev(col0::fp32, SAMPLE::enum) = 0.0::fp32
-((5.0, 5.0, 5.0, 5.0)) std_dev(col0::fp64, POPULATION::enum) = 0.0::fp64
+((5.0, 5.0, 5.0, 5.0)) std_dev(col0::fp32, SAMPLE::enum) = 0.0::fp32?
+((5.0, 5.0, 5.0, 5.0)) std_dev(col0::fp64, POPULATION::enum) = 0.0::fp64?
 
 # single_value: Standard deviation with single value
-((42.0)) std_dev(col0::fp32, SAMPLE::enum) = Null::fp32
-((42.0)) std_dev(col0::fp64, POPULATION::enum) = 0.0::fp64
+((42.0)) std_dev(col0::fp32, SAMPLE::enum) = Null::fp32?
+((42.0)) std_dev(col0::fp64, POPULATION::enum) = 0.0::fp64?
 
 # negative_values: Standard deviation with negative values
-((-5.0, -3.0, -1.0, 1.0, 3.0, 5.0)) std_dev(col0::fp32, SAMPLE::enum) = 3.8944404::fp32
-((-5.0, -3.0, -1.0, 1.0, 3.0, 5.0)) std_dev(col0::fp64, SAMPLE::enum) = 3.8944404818493075::fp64
-((-10.0, -5.0, 0.0, 5.0, 10.0)) std_dev(col0::fp32, POPULATION::enum) = 7.0710678::fp32
-((-10.0, -5.0, 0.0, 5.0, 10.0)) std_dev(col0::fp64, POPULATION::enum) = 7.0710678118654755::fp64
+((-5.0, -3.0, -1.0, 1.0, 3.0, 5.0)) std_dev(col0::fp32, SAMPLE::enum) = 3.8944404::fp32?
+((-5.0, -3.0, -1.0, 1.0, 3.0, 5.0)) std_dev(col0::fp64, SAMPLE::enum) = 3.8944404818493075::fp64?
+((-10.0, -5.0, 0.0, 5.0, 10.0)) std_dev(col0::fp32, POPULATION::enum) = 7.0710678::fp32?
+((-10.0, -5.0, 0.0, 5.0, 10.0)) std_dev(col0::fp64, POPULATION::enum) = 7.0710678118654755::fp64?
 
 # decimal_precision: Standard deviation with decimal values
-((1.5, 2.5, 3.5, 4.5, 5.5)) std_dev(col0::fp32, SAMPLE::enum) = 1.5811388::fp32
-((1.5, 2.5, 3.5, 4.5, 5.5)) std_dev(col0::fp64, SAMPLE::enum) = 1.5811388300841898::fp64
-((0.1, 0.2, 0.3, 0.4, 0.5)) std_dev(col0::fp64, POPULATION::enum) = 0.14142135623730953::fp64
+((1.5, 2.5, 3.5, 4.5, 5.5)) std_dev(col0::fp32, SAMPLE::enum) = 1.5811388::fp32?
+((1.5, 2.5, 3.5, 4.5, 5.5)) std_dev(col0::fp64, SAMPLE::enum) = 1.5811388300841898::fp64?
+((0.1, 0.2, 0.3, 0.4, 0.5)) std_dev(col0::fp64, POPULATION::enum) = 0.14142135623730953::fp64?
 
 # large_values: Standard deviation with large values
-((1000.0, 2000.0, 3000.0, 4000.0, 5000.0)) std_dev(col0::fp32, SAMPLE::enum) = 1581.1388::fp32
-((1000.0, 2000.0, 3000.0, 4000.0, 5000.0)) std_dev(col0::fp64, SAMPLE::enum) = 1581.1388300841898::fp64
+((1000.0, 2000.0, 3000.0, 4000.0, 5000.0)) std_dev(col0::fp32, SAMPLE::enum) = 1581.1388::fp32?
+((1000.0, 2000.0, 3000.0, 4000.0, 5000.0)) std_dev(col0::fp64, SAMPLE::enum) = 1581.1388300841898::fp64?
 
 # small_values: Standard deviation with small values
-((0.001, 0.002, 0.003, 0.004, 0.005)) std_dev(col0::fp64, SAMPLE::enum) = 0.0015811388300841896::fp64
-((0.001, 0.002, 0.003, 0.004, 0.005)) std_dev(col0::fp64, POPULATION::enum) = 0.0014142135623730951::fp64
+((0.001, 0.002, 0.003, 0.004, 0.005)) std_dev(col0::fp64, SAMPLE::enum) = 0.0015811388300841896::fp64?
+((0.001, 0.002, 0.003, 0.004, 0.005)) std_dev(col0::fp64, POPULATION::enum) = 0.0014142135623730951::fp64?
 
 # null_handling: Examples with null as input or output
-((Null, Null, Null)) std_dev(col0::fp32, SAMPLE::enum) = Null::fp32
-(()) std_dev(col0::fp32, SAMPLE::enum) = Null::fp32
-((1.0, Null, 3.0, Null, 5.0)) std_dev(col0::fp32, SAMPLE::enum) = 2.0::fp32
-((1.0, Null, 3.0, Null, 5.0)) std_dev(col0::fp64, POPULATION::enum) = 1.632993161855452::fp64
+((Null, Null, Null)) std_dev(col0::fp32?, SAMPLE::enum) = Null::fp32?
+(()) std_dev(col0::fp32, SAMPLE::enum) = Null::fp32?
+((1.0, Null, 3.0, Null, 5.0)) std_dev(col0::fp32?, SAMPLE::enum) = 2.0::fp32?
+((1.0, Null, 3.0, Null, 5.0)) std_dev(col0::fp64?, POPULATION::enum) = 1.632993161855452::fp64?
 
 # rounding: Examples with different rounding modes
-((1.1, 2.2, 3.3, 4.4, 5.5)) std_dev(col0::fp32, SAMPLE::enum) [rounding:TIE_TO_EVEN] = 1.7406897::fp32
-((1.1, 2.2, 3.3, 4.4, 5.5)) std_dev(col0::fp64, SAMPLE::enum) [rounding:TRUNCATE] = 1.7406897166664838::fp64
+((1.1, 2.2, 3.3, 4.4, 5.5)) std_dev(col0::fp32, SAMPLE::enum) [rounding:TIE_TO_EVEN] = 1.7406897::fp32?
+((1.1, 2.2, 3.3, 4.4, 5.5)) std_dev(col0::fp64, SAMPLE::enum) [rounding:TRUNCATE] = 1.7406897166664838::fp64?
 
 # two_values: Standard deviation with two values
-((10.0, 20.0)) std_dev(col0::fp32, SAMPLE::enum) = 7.071068::fp32
-((10.0, 20.0)) std_dev(col0::fp64, POPULATION::enum) = 5.0::fp64
+((10.0, 20.0)) std_dev(col0::fp32, SAMPLE::enum) = 7.071068::fp32?
+((10.0, 20.0)) std_dev(col0::fp64, POPULATION::enum) = 5.0::fp64?
 
 # mixed_range: Standard deviation with mixed range values
-((0.0, 100.0, 50.0, 25.0, 75.0)) std_dev(col0::fp32, SAMPLE::enum) = 41.010193::fp32
-((0.0, 100.0, 50.0, 25.0, 75.0)) std_dev(col0::fp64, POPULATION::enum) = 36.66060555964672::fp64
\ No newline at end of file
+((0.0, 100.0, 50.0, 25.0, 75.0)) std_dev(col0::fp32, SAMPLE::enum) = 41.010193::fp32?
+((0.0, 100.0, 50.0, 25.0, 75.0)) std_dev(col0::fp64, POPULATION::enum) = 36.66060555964672::fp64?
diff --git a/tests/cases/arithmetic/variance.test b/tests/cases/arithmetic/variance.test
index 47fac986a..49f5ed063 100644
--- a/tests/cases/arithmetic/variance.test
+++ b/tests/cases/arithmetic/variance.test
@@ -2,60 +2,60 @@
 ### SUBSTRAIT_INCLUDE: '/extensions/functions_arithmetic.yaml'
 
 # basic: Basic examples without any special cases
-((1.0, 2.0, 3.0, 4.0, 5.0)) variance(col0::fp32, SAMPLE::enum) = 2.5::fp32
-((1.0, 2.0, 3.0, 4.0, 5.0)) variance(col0::fp64, SAMPLE::enum) = 2.5::fp64
-((1.0, 2.0, 3.0, 4.0, 5.0)) variance(col0::fp32, POPULATION::enum) = 2.0::fp32
-((1.0, 2.0, 3.0, 4.0, 5.0)) variance(col0::fp64, POPULATION::enum) = 2.0::fp64
+((1.0, 2.0, 3.0, 4.0, 5.0)) variance(col0::fp32, SAMPLE::enum) = 2.5::fp32?
+((1.0, 2.0, 3.0, 4.0, 5.0)) variance(col0::fp64, SAMPLE::enum) = 2.5::fp64?
+((1.0, 2.0, 3.0, 4.0, 5.0)) variance(col0::fp32, POPULATION::enum) = 2.0::fp32?
+((1.0, 2.0, 3.0, 4.0, 5.0)) variance(col0::fp64, POPULATION::enum) = 2.0::fp64?
 
 # uniform_values: Variance of uniform values
-((5.0, 5.0, 5.0, 5.0)) variance(col0::fp32, SAMPLE::enum) = 0.0::fp32
-((5.0, 5.0, 5.0, 5.0)) variance(col0::fp64, POPULATION::enum) = 0.0::fp64
+((5.0, 5.0, 5.0, 5.0)) variance(col0::fp32, SAMPLE::enum) = 0.0::fp32?
+((5.0, 5.0, 5.0, 5.0)) variance(col0::fp64, POPULATION::enum) = 0.0::fp64?
 
 # single_value: Variance with single value
-((42.0)) variance(col0::fp32, SAMPLE::enum) = Null::fp32
-((42.0)) variance(col0::fp64, POPULATION::enum) = 0.0::fp64
+((42.0)) variance(col0::fp32, SAMPLE::enum) = Null::fp32?
+((42.0)) variance(col0::fp64, POPULATION::enum) = 0.0::fp64?
 
 # negative_values: Variance with negative values
-((-5.0, -3.0, -1.0, 1.0, 3.0, 5.0)) variance(col0::fp32, SAMPLE::enum) = 15.166667::fp32
-((-5.0, -3.0, -1.0, 1.0, 3.0, 5.0)) variance(col0::fp64, SAMPLE::enum) = 15.166666666666666::fp64
-((-10.0, -5.0, 0.0, 5.0, 10.0)) variance(col0::fp32, POPULATION::enum) = 50.0::fp32
-((-10.0, -5.0, 0.0, 5.0, 10.0)) variance(col0::fp64, POPULATION::enum) = 50.0::fp64
+((-5.0, -3.0, -1.0, 1.0, 3.0, 5.0)) variance(col0::fp32, SAMPLE::enum) = 15.166667::fp32?
+((-5.0, -3.0, -1.0, 1.0, 3.0, 5.0)) variance(col0::fp64, SAMPLE::enum) = 15.166666666666666::fp64?
+((-10.0, -5.0, 0.0, 5.0, 10.0)) variance(col0::fp32, POPULATION::enum) = 50.0::fp32?
+((-10.0, -5.0, 0.0, 5.0, 10.0)) variance(col0::fp64, POPULATION::enum) = 50.0::fp64?
 
 # decimal_precision: Variance with decimal values
-((1.5, 2.5, 3.5, 4.5, 5.5)) variance(col0::fp32, SAMPLE::enum) = 2.5::fp32
-((1.5, 2.5, 3.5, 4.5, 5.5)) variance(col0::fp64, SAMPLE::enum) = 2.5::fp64
-((0.1, 0.2, 0.3, 0.4, 0.5)) variance(col0::fp64, POPULATION::enum) = 0.020000000000000004::fp64
+((1.5, 2.5, 3.5, 4.5, 5.5)) variance(col0::fp32, SAMPLE::enum) = 2.5::fp32?
+((1.5, 2.5, 3.5, 4.5, 5.5)) variance(col0::fp64, SAMPLE::enum) = 2.5::fp64?
+((0.1, 0.2, 0.3, 0.4, 0.5)) variance(col0::fp64, POPULATION::enum) = 0.020000000000000004::fp64?
 
 # large_values: Variance with large values
-((1000.0, 2000.0, 3000.0, 4000.0, 5000.0)) variance(col0::fp32, SAMPLE::enum) = 2500000.0::fp32
-((1000.0, 2000.0, 3000.0, 4000.0, 5000.0)) variance(col0::fp64, SAMPLE::enum) = 2500000.0::fp64
+((1000.0, 2000.0, 3000.0, 4000.0, 5000.0)) variance(col0::fp32, SAMPLE::enum) = 2500000.0::fp32?
+((1000.0, 2000.0, 3000.0, 4000.0, 5000.0)) variance(col0::fp64, SAMPLE::enum) = 2500000.0::fp64?
 
 # small_values: Variance with small values
-((0.001, 0.002, 0.003, 0.004, 0.005)) variance(col0::fp64, SAMPLE::enum) = 0.0000025::fp64
-((0.001, 0.002, 0.003, 0.004, 0.005)) variance(col0::fp64, POPULATION::enum) = 0.000002::fp64
+((0.001, 0.002, 0.003, 0.004, 0.005)) variance(col0::fp64, SAMPLE::enum) = 0.0000025::fp64?
+((0.001, 0.002, 0.003, 0.004, 0.005)) variance(col0::fp64, POPULATION::enum) = 0.000002::fp64?
 
 # null_handling: Examples with null as input or output
-((Null, Null, Null)) variance(col0::fp32, SAMPLE::enum) = Null::fp32
-(()) variance(col0::fp32, SAMPLE::enum) = Null::fp32
-((1.0, Null, 3.0, Null, 5.0)) variance(col0::fp32, SAMPLE::enum) = 4.0::fp32
-((1.0, Null, 3.0, Null, 5.0)) variance(col0::fp64, POPULATION::enum) = 2.666666666666667::fp64
+((Null, Null, Null)) variance(col0::fp32?, SAMPLE::enum) = Null::fp32?
+(()) variance(col0::fp32, SAMPLE::enum) = Null::fp32?
+((1.0, Null, 3.0, Null, 5.0)) variance(col0::fp32?, SAMPLE::enum) = 4.0::fp32?
+((1.0, Null, 3.0, Null, 5.0)) variance(col0::fp64?, POPULATION::enum) = 2.666666666666667::fp64?
 
 # rounding: Examples with different rounding modes
-((1.1, 2.2, 3.3, 4.4, 5.5)) variance(col0::fp32, SAMPLE::enum) [rounding:TIE_TO_EVEN] = 3.03::fp32
-((1.1, 2.2, 3.3, 4.4, 5.5)) variance(col0::fp64, SAMPLE::enum) [rounding:TRUNCATE] = 3.0299999999999994::fp64
+((1.1, 2.2, 3.3, 4.4, 5.5)) variance(col0::fp32, SAMPLE::enum) [rounding:TIE_TO_EVEN] = 3.03::fp32?
+((1.1, 2.2, 3.3, 4.4, 5.5)) variance(col0::fp64, SAMPLE::enum) [rounding:TRUNCATE] = 3.0299999999999994::fp64?
 
 # two_values: Variance with two values
-((10.0, 20.0)) variance(col0::fp32, SAMPLE::enum) = 50.0::fp32
-((10.0, 20.0)) variance(col0::fp64, POPULATION::enum) = 25.0::fp64
+((10.0, 20.0)) variance(col0::fp32, SAMPLE::enum) = 50.0::fp32?
+((10.0, 20.0)) variance(col0::fp64, POPULATION::enum) = 25.0::fp64?
 
 # mixed_range: Variance with mixed range values
-((0.0, 100.0, 50.0, 25.0, 75.0)) variance(col0::fp32, SAMPLE::enum) = 1681.25::fp32
-((0.0, 100.0, 50.0, 25.0, 75.0)) variance(col0::fp64, POPULATION::enum) = 1345.0::fp64
+((0.0, 100.0, 50.0, 25.0, 75.0)) variance(col0::fp32, SAMPLE::enum) = 1681.25::fp32?
+((0.0, 100.0, 50.0, 25.0, 75.0)) variance(col0::fp64, POPULATION::enum) = 1345.0::fp64?
 
 # zero_mean: Variance with values around zero
-((-2.0, -1.0, 0.0, 1.0, 2.0)) variance(col0::fp32, SAMPLE::enum) = 2.5::fp32
-((-2.0, -1.0, 0.0, 1.0, 2.0)) variance(col0::fp64, POPULATION::enum) = 2.0::fp64
+((-2.0, -1.0, 0.0, 1.0, 2.0)) variance(col0::fp32, SAMPLE::enum) = 2.5::fp32?
+((-2.0, -1.0, 0.0, 1.0, 2.0)) variance(col0::fp64, POPULATION::enum) = 2.0::fp64?
 
 # three_values: Variance with three values
-((10.0, 20.0, 30.0)) variance(col0::fp32, SAMPLE::enum) = 100.0::fp32
-((10.0, 20.0, 30.0)) variance(col0::fp64, POPULATION::enum) = 66.66666666666667::fp64
\ No newline at end of file
+((10.0, 20.0, 30.0)) variance(col0::fp32, SAMPLE::enum) = 100.0::fp32?
+((10.0, 20.0, 30.0)) variance(col0::fp64, POPULATION::enum) = 66.66666666666667::fp64?

From b364972e5e94ef7fdafe717c467350f9718db800 Mon Sep 17 00:00:00 2001
From: Niels Pardon <par@zurich.ibm.com>
Date: Mon, 23 Mar 2026 18:51:13 +0100
Subject: [PATCH 07/11] fix: update deprecation version

Signed-off-by: Niels Pardon <par@zurich.ibm.com>
---
 extensions/functions_arithmetic.yaml | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/extensions/functions_arithmetic.yaml b/extensions/functions_arithmetic.yaml
index ec5f762fb..c9a598050 100644
--- a/extensions/functions_arithmetic.yaml
+++ b/extensions/functions_arithmetic.yaml
@@ -1393,7 +1393,7 @@ aggregate_functions:
     description: Calculates standard-deviation for a set of values.
     impls:
       - deprecated:
-          since: "0.86.0"
+          since: "0.87.0"
           reason: Use implementation with distribution enum argument instead.
         args:
           - name: x
@@ -1416,7 +1416,7 @@ aggregate_functions:
         nullability: DECLARED_OUTPUT
         return: fp32?
       - deprecated:
-          since: "0.86.0"
+          since: "0.87.0"
           reason: Use implementation with distribution enum argument instead.
         args:
           - name: x
@@ -1442,7 +1442,7 @@ aggregate_functions:
     description: Calculates variance for a set of values.
     impls:
       - deprecated:
-          since: "0.86.0"
+          since: "0.87.0"
           reason: Use implementation with distribution enum argument instead.
         args:
           - name: x
@@ -1465,7 +1465,7 @@ aggregate_functions:
         nullability: DECLARED_OUTPUT
         return: fp32?
       - deprecated:
-          since: "0.86.0"
+          since: "0.87.0"
           reason: Use implementation with distribution enum argument instead.
         args:
           - name: x

From 6275d2318b2d456014e13a81d14a84c88d202a5b Mon Sep 17 00:00:00 2001
From: Niels Pardon <par@zurich.ibm.com>
Date: Mon, 23 Mar 2026 19:04:26 +0100
Subject: [PATCH 08/11] fix: remove deprecated field

Signed-off-by: Niels Pardon <par@zurich.ibm.com>
---
 extensions/functions_arithmetic.yaml | 20 ++++----------------
 1 file changed, 4 insertions(+), 16 deletions(-)

diff --git a/extensions/functions_arithmetic.yaml b/extensions/functions_arithmetic.yaml
index c9a598050..f261b8b3f 100644
--- a/extensions/functions_arithmetic.yaml
+++ b/extensions/functions_arithmetic.yaml
@@ -1392,10 +1392,7 @@ aggregate_functions:
   - name: "std_dev"
     description: Calculates standard-deviation for a set of values.
     impls:
-      - deprecated:
-          since: "0.87.0"
-          reason: Use implementation with distribution enum argument instead.
-        args:
+      - args:
           - name: x
             value: fp32
         options:
@@ -1415,10 +1412,7 @@ aggregate_functions:
             values: [ TIE_TO_EVEN, TIE_AWAY_FROM_ZERO, TRUNCATE, CEILING, FLOOR ]
         nullability: DECLARED_OUTPUT
         return: fp32?
-      - deprecated:
-          since: "0.87.0"
-          reason: Use implementation with distribution enum argument instead.
-        args:
+      - args:
           - name: x
             value: fp64
         options:
@@ -1441,10 +1435,7 @@ aggregate_functions:
   - name: "variance"
     description: Calculates variance for a set of values.
     impls:
-      - deprecated:
-          since: "0.87.0"
-          reason: Use implementation with distribution enum argument instead.
-        args:
+      - args:
           - name: x
             value: fp32
         options:
@@ -1464,10 +1455,7 @@ aggregate_functions:
             values: [ TIE_TO_EVEN, TIE_AWAY_FROM_ZERO, TRUNCATE, CEILING, FLOOR ]
         nullability: DECLARED_OUTPUT
         return: fp32?
-      - deprecated:
-          since: "0.87.0"
-          reason: Use implementation with distribution enum argument instead.
-        args:
+      - args:
           - name: x
             value: fp64
         options:

From 8175a7300e6bb896a3ac861ef52e5f3a90bd6a80 Mon Sep 17 00:00:00 2001
From: Niels Pardon <par@zurich.ibm.com>
Date: Tue, 24 Mar 2026 09:33:36 +0100
Subject: [PATCH 09/11] fix: reverse argument order

Signed-off-by: Niels Pardon <par@zurich.ibm.com>
---
 extensions/functions_arithmetic.yaml | 16 +++----
 tests/cases/arithmetic/std_dev.test  | 58 ++++++++++++------------
 tests/cases/arithmetic/variance.test | 66 ++++++++++++++--------------
 3 files changed, 70 insertions(+), 70 deletions(-)

diff --git a/extensions/functions_arithmetic.yaml b/extensions/functions_arithmetic.yaml
index f261b8b3f..079f8fa98 100644
--- a/extensions/functions_arithmetic.yaml
+++ b/extensions/functions_arithmetic.yaml
@@ -1403,10 +1403,10 @@ aggregate_functions:
         nullability: DECLARED_OUTPUT
         return: fp32?
       - args:
-          - name: x
-            value: fp32
           - name: distribution
             options: [ SAMPLE, POPULATION]
+          - name: x
+            value: fp32
         options:
           rounding:
             values: [ TIE_TO_EVEN, TIE_AWAY_FROM_ZERO, TRUNCATE, CEILING, FLOOR ]
@@ -1423,10 +1423,10 @@ aggregate_functions:
         nullability: DECLARED_OUTPUT
         return: fp64?
       - args:
-          - name: x
-            value: fp64
           - name: distribution
             options: [ SAMPLE, POPULATION]
+          - name: x
+            value: fp64
         options:
           rounding:
             values: [ TIE_TO_EVEN, TIE_AWAY_FROM_ZERO, TRUNCATE, CEILING, FLOOR ]
@@ -1446,10 +1446,10 @@ aggregate_functions:
         nullability: DECLARED_OUTPUT
         return: fp32?
       - args:
-          - name: x
-            value: fp32
           - name: distribution
             options: [ SAMPLE, POPULATION]
+          - name: x
+            value: fp32
         options:
           rounding:
             values: [ TIE_TO_EVEN, TIE_AWAY_FROM_ZERO, TRUNCATE, CEILING, FLOOR ]
@@ -1466,10 +1466,10 @@ aggregate_functions:
         nullability: DECLARED_OUTPUT
         return: fp64?
       - args:
-          - name: x
-            value: fp64
           - name: distribution
             options: [ SAMPLE, POPULATION]
+          - name: x
+            value: fp64
         options:
           rounding:
             values: [ TIE_TO_EVEN, TIE_AWAY_FROM_ZERO, TRUNCATE, CEILING, FLOOR ]
diff --git a/tests/cases/arithmetic/std_dev.test b/tests/cases/arithmetic/std_dev.test
index 2a5310651..abbd57e35 100644
--- a/tests/cases/arithmetic/std_dev.test
+++ b/tests/cases/arithmetic/std_dev.test
@@ -2,52 +2,52 @@
 ### SUBSTRAIT_INCLUDE: '/extensions/functions_arithmetic.yaml'
 
 # basic: Basic examples without any special cases
-((1.0, 2.0, 3.0, 4.0, 5.0)) std_dev(col0::fp32, SAMPLE::enum) = 1.5811388::fp32?
-((1.0, 2.0, 3.0, 4.0, 5.0)) std_dev(col0::fp64, SAMPLE::enum) = 1.5811388300841898::fp64?
-((1.0, 2.0, 3.0, 4.0, 5.0)) std_dev(col0::fp32, POPULATION::enum) = 1.4142135::fp32?
-((1.0, 2.0, 3.0, 4.0, 5.0)) std_dev(col0::fp64, POPULATION::enum) = 1.4142135623730951::fp64?
+((1.0, 2.0, 3.0, 4.0, 5.0)) std_dev(SAMPLE::enum, col0::fp32) = 1.5811388::fp32?
+((1.0, 2.0, 3.0, 4.0, 5.0)) std_dev(SAMPLE::enum, col0::fp64) = 1.5811388300841898::fp64?
+((1.0, 2.0, 3.0, 4.0, 5.0)) std_dev(POPULATION::enum, col0::fp32) = 1.4142135::fp32?
+((1.0, 2.0, 3.0, 4.0, 5.0)) std_dev(POPULATION::enum, col0::fp64) = 1.4142135623730951::fp64?
 
 # uniform_values: Standard deviation of uniform values
-((5.0, 5.0, 5.0, 5.0)) std_dev(col0::fp32, SAMPLE::enum) = 0.0::fp32?
-((5.0, 5.0, 5.0, 5.0)) std_dev(col0::fp64, POPULATION::enum) = 0.0::fp64?
+((5.0, 5.0, 5.0, 5.0)) std_dev(SAMPLE::enum, col0::fp32) = 0.0::fp32?
+((5.0, 5.0, 5.0, 5.0)) std_dev(POPULATION::enum, col0::fp64) = 0.0::fp64?
 
 # single_value: Standard deviation with single value
-((42.0)) std_dev(col0::fp32, SAMPLE::enum) = Null::fp32?
-((42.0)) std_dev(col0::fp64, POPULATION::enum) = 0.0::fp64?
+((42.0)) std_dev(SAMPLE::enum, col0::fp32) = Null::fp32?
+((42.0)) std_dev(POPULATION::enum, col0::fp64) = 0.0::fp64?
 
 # negative_values: Standard deviation with negative values
-((-5.0, -3.0, -1.0, 1.0, 3.0, 5.0)) std_dev(col0::fp32, SAMPLE::enum) = 3.8944404::fp32?
-((-5.0, -3.0, -1.0, 1.0, 3.0, 5.0)) std_dev(col0::fp64, SAMPLE::enum) = 3.8944404818493075::fp64?
-((-10.0, -5.0, 0.0, 5.0, 10.0)) std_dev(col0::fp32, POPULATION::enum) = 7.0710678::fp32?
-((-10.0, -5.0, 0.0, 5.0, 10.0)) std_dev(col0::fp64, POPULATION::enum) = 7.0710678118654755::fp64?
+((-5.0, -3.0, -1.0, 1.0, 3.0, 5.0)) std_dev(SAMPLE::enum, col0::fp32) = 3.8944404::fp32?
+((-5.0, -3.0, -1.0, 1.0, 3.0, 5.0)) std_dev(SAMPLE::enum, col0::fp64) = 3.8944404818493075::fp64?
+((-10.0, -5.0, 0.0, 5.0, 10.0)) std_dev(POPULATION::enum, col0::fp32) = 7.0710678::fp32?
+((-10.0, -5.0, 0.0, 5.0, 10.0)) std_dev(POPULATION::enum, col0::fp64) = 7.0710678118654755::fp64?
 
 # decimal_precision: Standard deviation with decimal values
-((1.5, 2.5, 3.5, 4.5, 5.5)) std_dev(col0::fp32, SAMPLE::enum) = 1.5811388::fp32?
-((1.5, 2.5, 3.5, 4.5, 5.5)) std_dev(col0::fp64, SAMPLE::enum) = 1.5811388300841898::fp64?
-((0.1, 0.2, 0.3, 0.4, 0.5)) std_dev(col0::fp64, POPULATION::enum) = 0.14142135623730953::fp64?
+((1.5, 2.5, 3.5, 4.5, 5.5)) std_dev(SAMPLE::enum, col0::fp32) = 1.5811388::fp32?
+((1.5, 2.5, 3.5, 4.5, 5.5)) std_dev(SAMPLE::enum, col0::fp64) = 1.5811388300841898::fp64?
+((0.1, 0.2, 0.3, 0.4, 0.5)) std_dev(POPULATION::enum, col0::fp64) = 0.14142135623730953::fp64?
 
 # large_values: Standard deviation with large values
-((1000.0, 2000.0, 3000.0, 4000.0, 5000.0)) std_dev(col0::fp32, SAMPLE::enum) = 1581.1388::fp32?
-((1000.0, 2000.0, 3000.0, 4000.0, 5000.0)) std_dev(col0::fp64, SAMPLE::enum) = 1581.1388300841898::fp64?
+((1000.0, 2000.0, 3000.0, 4000.0, 5000.0)) std_dev(SAMPLE::enum, col0::fp32) = 1581.1388::fp32?
+((1000.0, 2000.0, 3000.0, 4000.0, 5000.0)) std_dev(SAMPLE::enum, col0::fp64) = 1581.1388300841898::fp64?
 
 # small_values: Standard deviation with small values
-((0.001, 0.002, 0.003, 0.004, 0.005)) std_dev(col0::fp64, SAMPLE::enum) = 0.0015811388300841896::fp64?
-((0.001, 0.002, 0.003, 0.004, 0.005)) std_dev(col0::fp64, POPULATION::enum) = 0.0014142135623730951::fp64?
+((0.001, 0.002, 0.003, 0.004, 0.005)) std_dev(SAMPLE::enum, col0::fp64) = 0.0015811388300841896::fp64?
+((0.001, 0.002, 0.003, 0.004, 0.005)) std_dev(POPULATION::enum, col0::fp64) = 0.0014142135623730951::fp64?
 
 # null_handling: Examples with null as input or output
-((Null, Null, Null)) std_dev(col0::fp32?, SAMPLE::enum) = Null::fp32?
-(()) std_dev(col0::fp32, SAMPLE::enum) = Null::fp32?
-((1.0, Null, 3.0, Null, 5.0)) std_dev(col0::fp32?, SAMPLE::enum) = 2.0::fp32?
-((1.0, Null, 3.0, Null, 5.0)) std_dev(col0::fp64?, POPULATION::enum) = 1.632993161855452::fp64?
+((Null, Null, Null)) std_dev(SAMPLE::enum, col0::fp32?) = Null::fp32?
+(()) std_dev(SAMPLE::enum, col0::fp32) = Null::fp32?
+((1.0, Null, 3.0, Null, 5.0)) std_dev(SAMPLE::enum, col0::fp32?) = 2.0::fp32?
+((1.0, Null, 3.0, Null, 5.0)) std_dev(POPULATION::enum, col0::fp64?) = 1.632993161855452::fp64?
 
 # rounding: Examples with different rounding modes
-((1.1, 2.2, 3.3, 4.4, 5.5)) std_dev(col0::fp32, SAMPLE::enum) [rounding:TIE_TO_EVEN] = 1.7406897::fp32?
-((1.1, 2.2, 3.3, 4.4, 5.5)) std_dev(col0::fp64, SAMPLE::enum) [rounding:TRUNCATE] = 1.7406897166664838::fp64?
+((1.1, 2.2, 3.3, 4.4, 5.5)) std_dev(SAMPLE::enum, col0::fp32) [rounding:TIE_TO_EVEN] = 1.7406897::fp32?
+((1.1, 2.2, 3.3, 4.4, 5.5)) std_dev(SAMPLE::enum, col0::fp64) [rounding:TRUNCATE] = 1.7406897166664838::fp64?
 
 # two_values: Standard deviation with two values
-((10.0, 20.0)) std_dev(col0::fp32, SAMPLE::enum) = 7.071068::fp32?
-((10.0, 20.0)) std_dev(col0::fp64, POPULATION::enum) = 5.0::fp64?
+((10.0, 20.0)) std_dev(SAMPLE::enum, col0::fp32) = 7.071068::fp32?
+((10.0, 20.0)) std_dev(POPULATION::enum, col0::fp64) = 5.0::fp64?
 
 # mixed_range: Standard deviation with mixed range values
-((0.0, 100.0, 50.0, 25.0, 75.0)) std_dev(col0::fp32, SAMPLE::enum) = 41.010193::fp32?
-((0.0, 100.0, 50.0, 25.0, 75.0)) std_dev(col0::fp64, POPULATION::enum) = 36.66060555964672::fp64?
+((0.0, 100.0, 50.0, 25.0, 75.0)) std_dev(SAMPLE::enum, col0::fp32) = 41.010193::fp32?
+((0.0, 100.0, 50.0, 25.0, 75.0)) std_dev(POPULATION::enum, col0::fp64) = 36.66060555964672::fp64?
diff --git a/tests/cases/arithmetic/variance.test b/tests/cases/arithmetic/variance.test
index 49f5ed063..d2cc50eef 100644
--- a/tests/cases/arithmetic/variance.test
+++ b/tests/cases/arithmetic/variance.test
@@ -2,60 +2,60 @@
 ### SUBSTRAIT_INCLUDE: '/extensions/functions_arithmetic.yaml'
 
 # basic: Basic examples without any special cases
-((1.0, 2.0, 3.0, 4.0, 5.0)) variance(col0::fp32, SAMPLE::enum) = 2.5::fp32?
-((1.0, 2.0, 3.0, 4.0, 5.0)) variance(col0::fp64, SAMPLE::enum) = 2.5::fp64?
-((1.0, 2.0, 3.0, 4.0, 5.0)) variance(col0::fp32, POPULATION::enum) = 2.0::fp32?
-((1.0, 2.0, 3.0, 4.0, 5.0)) variance(col0::fp64, POPULATION::enum) = 2.0::fp64?
+((1.0, 2.0, 3.0, 4.0, 5.0)) variance(SAMPLE::enum, col0::fp32) = 2.5::fp32?
+((1.0, 2.0, 3.0, 4.0, 5.0)) variance(SAMPLE::enum, col0::fp64) = 2.5::fp64?
+((1.0, 2.0, 3.0, 4.0, 5.0)) variance(POPULATION::enum, col0::fp32) = 2.0::fp32?
+((1.0, 2.0, 3.0, 4.0, 5.0)) variance(POPULATION::enum, col0::fp64) = 2.0::fp64?
 
 # uniform_values: Variance of uniform values
-((5.0, 5.0, 5.0, 5.0)) variance(col0::fp32, SAMPLE::enum) = 0.0::fp32?
-((5.0, 5.0, 5.0, 5.0)) variance(col0::fp64, POPULATION::enum) = 0.0::fp64?
+((5.0, 5.0, 5.0, 5.0)) variance(SAMPLE::enum, col0::fp32) = 0.0::fp32?
+((5.0, 5.0, 5.0, 5.0)) variance(POPULATION::enum, col0::fp64) = 0.0::fp64?
 
 # single_value: Variance with single value
-((42.0)) variance(col0::fp32, SAMPLE::enum) = Null::fp32?
-((42.0)) variance(col0::fp64, POPULATION::enum) = 0.0::fp64?
+((42.0)) variance(SAMPLE::enum, col0::fp32) = Null::fp32?
+((42.0)) variance(POPULATION::enum, col0::fp64) = 0.0::fp64?
 
 # negative_values: Variance with negative values
-((-5.0, -3.0, -1.0, 1.0, 3.0, 5.0)) variance(col0::fp32, SAMPLE::enum) = 15.166667::fp32?
-((-5.0, -3.0, -1.0, 1.0, 3.0, 5.0)) variance(col0::fp64, SAMPLE::enum) = 15.166666666666666::fp64?
-((-10.0, -5.0, 0.0, 5.0, 10.0)) variance(col0::fp32, POPULATION::enum) = 50.0::fp32?
-((-10.0, -5.0, 0.0, 5.0, 10.0)) variance(col0::fp64, POPULATION::enum) = 50.0::fp64?
+((-5.0, -3.0, -1.0, 1.0, 3.0, 5.0)) variance(SAMPLE::enum, col0::fp32) = 15.166667::fp32?
+((-5.0, -3.0, -1.0, 1.0, 3.0, 5.0)) variance(SAMPLE::enum, col0::fp64) = 15.166666666666666::fp64?
+((-10.0, -5.0, 0.0, 5.0, 10.0)) variance(POPULATION::enum, col0::fp32) = 50.0::fp32?
+((-10.0, -5.0, 0.0, 5.0, 10.0)) variance(POPULATION::enum, col0::fp64) = 50.0::fp64?
 
 # decimal_precision: Variance with decimal values
-((1.5, 2.5, 3.5, 4.5, 5.5)) variance(col0::fp32, SAMPLE::enum) = 2.5::fp32?
-((1.5, 2.5, 3.5, 4.5, 5.5)) variance(col0::fp64, SAMPLE::enum) = 2.5::fp64?
-((0.1, 0.2, 0.3, 0.4, 0.5)) variance(col0::fp64, POPULATION::enum) = 0.020000000000000004::fp64?
+((1.5, 2.5, 3.5, 4.5, 5.5)) variance(SAMPLE::enum, col0::fp32) = 2.5::fp32?
+((1.5, 2.5, 3.5, 4.5, 5.5)) variance(SAMPLE::enum, col0::fp64) = 2.5::fp64?
+((0.1, 0.2, 0.3, 0.4, 0.5)) variance(POPULATION::enum, col0::fp64) = 0.020000000000000004::fp64?
 
 # large_values: Variance with large values
-((1000.0, 2000.0, 3000.0, 4000.0, 5000.0)) variance(col0::fp32, SAMPLE::enum) = 2500000.0::fp32?
-((1000.0, 2000.0, 3000.0, 4000.0, 5000.0)) variance(col0::fp64, SAMPLE::enum) = 2500000.0::fp64?
+((1000.0, 2000.0, 3000.0, 4000.0, 5000.0)) variance(SAMPLE::enum, col0::fp32) = 2500000.0::fp32?
+((1000.0, 2000.0, 3000.0, 4000.0, 5000.0)) variance(SAMPLE::enum, col0::fp64) = 2500000.0::fp64?
 
 # small_values: Variance with small values
-((0.001, 0.002, 0.003, 0.004, 0.005)) variance(col0::fp64, SAMPLE::enum) = 0.0000025::fp64?
-((0.001, 0.002, 0.003, 0.004, 0.005)) variance(col0::fp64, POPULATION::enum) = 0.000002::fp64?
+((0.001, 0.002, 0.003, 0.004, 0.005)) variance(SAMPLE::enum, col0::fp64) = 0.0000025::fp64?
+((0.001, 0.002, 0.003, 0.004, 0.005)) variance(POPULATION::enum, col0::fp64) = 0.000002::fp64?
 
 # null_handling: Examples with null as input or output
-((Null, Null, Null)) variance(col0::fp32?, SAMPLE::enum) = Null::fp32?
-(()) variance(col0::fp32, SAMPLE::enum) = Null::fp32?
-((1.0, Null, 3.0, Null, 5.0)) variance(col0::fp32?, SAMPLE::enum) = 4.0::fp32?
-((1.0, Null, 3.0, Null, 5.0)) variance(col0::fp64?, POPULATION::enum) = 2.666666666666667::fp64?
+((Null, Null, Null)) variance(SAMPLE::enum, col0::fp32?) = Null::fp32?
+(()) variance(SAMPLE::enum, col0::fp32) = Null::fp32?
+((1.0, Null, 3.0, Null, 5.0)) variance(SAMPLE::enum, col0::fp32?) = 4.0::fp32?
+((1.0, Null, 3.0, Null, 5.0)) variance(POPULATION::enum, col0::fp64?) = 2.666666666666667::fp64?
 
 # rounding: Examples with different rounding modes
-((1.1, 2.2, 3.3, 4.4, 5.5)) variance(col0::fp32, SAMPLE::enum) [rounding:TIE_TO_EVEN] = 3.03::fp32?
-((1.1, 2.2, 3.3, 4.4, 5.5)) variance(col0::fp64, SAMPLE::enum) [rounding:TRUNCATE] = 3.0299999999999994::fp64?
+((1.1, 2.2, 3.3, 4.4, 5.5)) variance(SAMPLE::enum, col0::fp32) [rounding:TIE_TO_EVEN] = 3.03::fp32?
+((1.1, 2.2, 3.3, 4.4, 5.5)) variance(SAMPLE::enum, col0::fp64) [rounding:TRUNCATE] = 3.0299999999999994::fp64?
 
 # two_values: Variance with two values
-((10.0, 20.0)) variance(col0::fp32, SAMPLE::enum) = 50.0::fp32?
-((10.0, 20.0)) variance(col0::fp64, POPULATION::enum) = 25.0::fp64?
+((10.0, 20.0)) variance(SAMPLE::enum, col0::fp32) = 50.0::fp32?
+((10.0, 20.0)) variance(POPULATION::enum, col0::fp64) = 25.0::fp64?
 
 # mixed_range: Variance with mixed range values
-((0.0, 100.0, 50.0, 25.0, 75.0)) variance(col0::fp32, SAMPLE::enum) = 1681.25::fp32?
-((0.0, 100.0, 50.0, 25.0, 75.0)) variance(col0::fp64, POPULATION::enum) = 1345.0::fp64?
+((0.0, 100.0, 50.0, 25.0, 75.0)) variance(SAMPLE::enum, col0::fp32) = 1681.25::fp32?
+((0.0, 100.0, 50.0, 25.0, 75.0)) variance(POPULATION::enum, col0::fp64) = 1345.0::fp64?
 
 # zero_mean: Variance with values around zero
-((-2.0, -1.0, 0.0, 1.0, 2.0)) variance(col0::fp32, SAMPLE::enum) = 2.5::fp32?
-((-2.0, -1.0, 0.0, 1.0, 2.0)) variance(col0::fp64, POPULATION::enum) = 2.0::fp64?
+((-2.0, -1.0, 0.0, 1.0, 2.0)) variance(SAMPLE::enum, col0::fp32) = 2.5::fp32?
+((-2.0, -1.0, 0.0, 1.0, 2.0)) variance(POPULATION::enum, col0::fp64) = 2.0::fp64?
 
 # three_values: Variance with three values
-((10.0, 20.0, 30.0)) variance(col0::fp32, SAMPLE::enum) = 100.0::fp32?
-((10.0, 20.0, 30.0)) variance(col0::fp64, POPULATION::enum) = 66.66666666666667::fp64?
+((10.0, 20.0, 30.0)) variance(SAMPLE::enum, col0::fp32) = 100.0::fp32?
+((10.0, 20.0, 30.0)) variance(POPULATION::enum, col0::fp64) = 66.66666666666667::fp64?

From 2911777b471ef7e75217e9b6670843e6d65e41bd Mon Sep 17 00:00:00 2001
From: Niels Pardon <par@zurich.ibm.com>
Date: Tue, 17 Mar 2026 13:31:48 +0100
Subject: [PATCH 10/11] feat(extensions): support int arguments with std_dev
 and variance functions

Signed-off-by: Niels Pardon <par@zurich.ibm.com>
---
 extensions/functions_arithmetic.yaml | 80 ++++++++++++++++++++++++++++
 tests/cases/arithmetic/std_dev.test  | 27 ++++++++++
 tests/cases/arithmetic/variance.test | 35 ++++++++++++
 3 files changed, 142 insertions(+)

diff --git a/extensions/functions_arithmetic.yaml b/extensions/functions_arithmetic.yaml
index 079f8fa98..fbeadd78c 100644
--- a/extensions/functions_arithmetic.yaml
+++ b/extensions/functions_arithmetic.yaml
@@ -1432,6 +1432,46 @@ aggregate_functions:
             values: [ TIE_TO_EVEN, TIE_AWAY_FROM_ZERO, TRUNCATE, CEILING, FLOOR ]
         nullability: DECLARED_OUTPUT
         return: fp64?
+      - args:
+          - name: x
+            value: i8
+          - name: distribution
+            options: [ SAMPLE, POPULATION]
+        options:
+          rounding:
+            values: [ TIE_TO_EVEN, TIE_AWAY_FROM_ZERO, TRUNCATE, CEILING, FLOOR ]
+        nullability: DECLARED_OUTPUT
+        return: fp64?
+      - args:
+          - name: x
+            value: i16
+          - name: distribution
+            options: [ SAMPLE, POPULATION]
+        options:
+          rounding:
+            values: [ TIE_TO_EVEN, TIE_AWAY_FROM_ZERO, TRUNCATE, CEILING, FLOOR ]
+        nullability: DECLARED_OUTPUT
+        return: fp64?
+      - args:
+          - name: x
+            value: i32
+          - name: distribution
+            options: [ SAMPLE, POPULATION]
+        options:
+          rounding:
+            values: [ TIE_TO_EVEN, TIE_AWAY_FROM_ZERO, TRUNCATE, CEILING, FLOOR ]
+        nullability: DECLARED_OUTPUT
+        return: fp64?
+      - args:
+          - name: x
+            value: i64
+          - name: distribution
+            options: [ SAMPLE, POPULATION]
+        options:
+          rounding:
+            values: [ TIE_TO_EVEN, TIE_AWAY_FROM_ZERO, TRUNCATE, CEILING, FLOOR ]
+        nullability: DECLARED_OUTPUT
+        return: fp64?
   - name: "variance"
     description: Calculates variance for a set of values.
     impls:
@@ -1475,6 +1515,46 @@ aggregate_functions:
             values: [ TIE_TO_EVEN, TIE_AWAY_FROM_ZERO, TRUNCATE, CEILING, FLOOR ]
         nullability: DECLARED_OUTPUT
         return: fp64?
+      - args:
+          - name: x
+            value: i8
+          - name: distribution
+            options: [ SAMPLE, POPULATION]
+        options:
+          rounding:
+            values: [ TIE_TO_EVEN, TIE_AWAY_FROM_ZERO, TRUNCATE, CEILING, FLOOR ]
+        nullability: DECLARED_OUTPUT
+        return: fp64?
+      - args:
+          - name: x
+            value: i16
+          - name: distribution
+            options: [ SAMPLE, POPULATION]
+        options:
+          rounding:
+            values: [ TIE_TO_EVEN, TIE_AWAY_FROM_ZERO, TRUNCATE, CEILING, FLOOR ]
+        nullability: DECLARED_OUTPUT
+        return: fp64?
+      - args:
+          - name: x
+            value: i32
+          - name: distribution
+            options: [ SAMPLE, POPULATION]
+        options:
+          rounding:
+            values: [ TIE_TO_EVEN, TIE_AWAY_FROM_ZERO, TRUNCATE, CEILING, FLOOR ]
+        nullability: DECLARED_OUTPUT
+        return: fp64?
+      - args:
+          - name: x
+            value: i64
+          - name: distribution
+            options: [ SAMPLE, POPULATION]
+        options:
+          rounding:
+            values: [ TIE_TO_EVEN, TIE_AWAY_FROM_ZERO, TRUNCATE, CEILING, FLOOR ]
+        nullability: DECLARED_OUTPUT
+        return: fp64?
   - name: "corr"
     description: >
       Calculates the value of Pearson's correlation coefficient between `x` and `y`.
diff --git a/tests/cases/arithmetic/std_dev.test b/tests/cases/arithmetic/std_dev.test
index abbd57e35..f951555a6 100644
--- a/tests/cases/arithmetic/std_dev.test
+++ b/tests/cases/arithmetic/std_dev.test
@@ -51,3 +51,30 @@
 # mixed_range: Standard deviation with mixed range values
 ((0.0, 100.0, 50.0, 25.0, 75.0)) std_dev(SAMPLE::enum, col0::fp32) = 41.010193::fp32?
 ((0.0, 100.0, 50.0, 25.0, 75.0)) std_dev(POPULATION::enum, col0::fp64) = 36.66060555964672::fp64?
+
+
+# integer_types: Standard deviation with integer input types returning fp64
+((1, 2, 3, 4, 5)) std_dev(col0::i8, SAMPLE::enum) = 1.5811388300841898::fp64?
+((1, 2, 3, 4, 5)) std_dev(col0::i8, POPULATION::enum) = 1.4142135623730951::fp64?
+((1, 2, 3, 4, 5)) std_dev(col0::i16, SAMPLE::enum) = 1.5811388300841898::fp64?
+((1, 2, 3, 4, 5)) std_dev(col0::i16, POPULATION::enum) = 1.4142135623730951::fp64?
+((1, 2, 3, 4, 5)) std_dev(col0::i32, SAMPLE::enum) = 1.5811388300841898::fp64?
+((1, 2, 3, 4, 5)) std_dev(col0::i32, POPULATION::enum) = 1.4142135623730951::fp64?
+((1, 2, 3, 4, 5)) std_dev(col0::i64, SAMPLE::enum) = 1.5811388300841898::fp64?
+((1, 2, 3, 4, 5)) std_dev(col0::i64, POPULATION::enum) = 1.4142135623730951::fp64?
+
+# integer_negative: Standard deviation with negative integer values
+((-5, -3, -1, 1, 3, 5)) std_dev(col0::i32, SAMPLE::enum) = 3.8944404818493075::fp64?
+((-10, -5, 0, 5, 10)) std_dev(col0::i64, POPULATION::enum) = 7.0710678118654755::fp64?
+
+# integer_uniform: Standard deviation with uniform integer values
+((42, 42, 42, 42)) std_dev(col0::i16, SAMPLE::enum) = 0.0::fp64?
+((100, 100, 100, 100)) std_dev(col0::i32, POPULATION::enum) = 0.0::fp64?
+
+# integer_single: Standard deviation with single integer value
+((7)) std_dev(col0::i8, SAMPLE::enum) = Null::fp64?
+((99)) std_dev(col0::i64, POPULATION::enum) = 0.0::fp64?
+
+# integer_large_values: Standard deviation with large integer values
+((1000, 2000, 3000, 4000, 5000)) std_dev(col0::i32, SAMPLE::enum) = 1581.1388300841898::fp64?
+((100, 200, 300, 400, 500)) std_dev(col0::i64, POPULATION::enum) = 141.4213562373095::fp64?
diff --git a/tests/cases/arithmetic/variance.test b/tests/cases/arithmetic/variance.test
index d2cc50eef..626752cd5 100644
--- a/tests/cases/arithmetic/variance.test
+++ b/tests/cases/arithmetic/variance.test
@@ -59,3 +59,38 @@
 # three_values: Variance with three values
 ((10.0, 20.0, 30.0)) variance(SAMPLE::enum, col0::fp32) = 100.0::fp32?
 ((10.0, 20.0, 30.0)) variance(POPULATION::enum, col0::fp64) = 66.66666666666667::fp64?
+
+
+# integer_types: Variance with integer input types returning fp64
+((1, 2, 3, 4, 5)) variance(col0::i8, SAMPLE::enum) = 2.5::fp64?
+((1, 2, 3, 4, 5)) variance(col0::i8, POPULATION::enum) = 2.0::fp64?
+((1, 2, 3, 4, 5)) variance(col0::i16, SAMPLE::enum) = 2.5::fp64?
+((1, 2, 3, 4, 5)) variance(col0::i16, POPULATION::enum) = 2.0::fp64?
+((1, 2, 3, 4, 5)) variance(col0::i32, SAMPLE::enum) = 2.5::fp64?
+((1, 2, 3, 4, 5)) variance(col0::i32, POPULATION::enum) = 2.0::fp64?
+((1, 2, 3, 4, 5)) variance(col0::i64, SAMPLE::enum) = 2.5::fp64?
+((1, 2, 3, 4, 5)) variance(col0::i64, POPULATION::enum) = 2.0::fp64?
+
+# integer_negative: Variance with negative integer values
+((-5, -3, -1, 1, 3, 5)) variance(col0::i32, SAMPLE::enum) = 15.166666666666666::fp64?
+((-10, -5, 0, 5, 10)) variance(col0::i64, POPULATION::enum) = 50.0::fp64?
+
+# integer_uniform: Variance with uniform integer values
+((42, 42, 42, 42)) variance(col0::i16, SAMPLE::enum) = 0.0::fp64?
+((100, 100, 100, 100)) variance(col0::i32, POPULATION::enum) = 0.0::fp64?
+
+# integer_single: Variance with single integer value
+((7)) variance(col0::i8, SAMPLE::enum) = Null::fp64?
+((99)) variance(col0::i64, POPULATION::enum) = 0.0::fp64?
+
+# integer_large_values: Variance with large integer values
+((1000, 2000, 3000, 4000, 5000)) variance(col0::i32, SAMPLE::enum) = 2500000.0::fp64?
+((100, 200, 300, 400, 500)) variance(col0::i64, POPULATION::enum) = 20000.0::fp64?
+
+# integer_zero_mean: Variance with integer values around zero
+((-2, -1, 0, 1, 2)) variance(col0::i16, SAMPLE::enum) = 2.5::fp64?
+((-2, -1, 0, 1, 2)) variance(col0::i64, POPULATION::enum) = 2.0::fp64?
+
+# integer_three_values: Variance with three integer values
+((10, 20, 30)) variance(col0::i32, SAMPLE::enum) = 100.0::fp64?
+((10, 20, 30)) variance(col0::i8, POPULATION::enum) = 66.66666666666667::fp64?

From a9b2d92f11e39e7f83dfa4ea429ed6c5466e18a3 Mon Sep 17 00:00:00 2001
From: Niels Pardon <par@zurich.ibm.com>
Date: Tue, 24 Mar 2026 09:35:52 +0100
Subject: [PATCH 11/11] fix: reverse argument order

Signed-off-by: Niels Pardon <par@zurich.ibm.com>
---
 extensions/functions_arithmetic.yaml | 32 +++++++++++-----------
 tests/cases/arithmetic/std_dev.test  | 32 +++++++++++-----------
 tests/cases/arithmetic/variance.test | 40 ++++++++++++++--------------
 3 files changed, 52 insertions(+), 52 deletions(-)

diff --git a/extensions/functions_arithmetic.yaml b/extensions/functions_arithmetic.yaml
index fbeadd78c..ae4429a78 100644
--- a/extensions/functions_arithmetic.yaml
+++ b/extensions/functions_arithmetic.yaml
@@ -1433,40 +1433,40 @@ aggregate_functions:
         nullability: DECLARED_OUTPUT
         return: fp64?
       - args:
-          - name: x
-            value: i8
           - name: distribution
             options: [ SAMPLE, POPULATION]
+          - name: x
+            value: i8
         options:
           rounding:
             values: [ TIE_TO_EVEN, TIE_AWAY_FROM_ZERO, TRUNCATE, CEILING, FLOOR ]
         nullability: DECLARED_OUTPUT
         return: fp64?
       - args:
-          - name: x
-            value: i16
           - name: distribution
             options: [ SAMPLE, POPULATION]
+          - name: x
+            value: i16
         options:
           rounding:
             values: [ TIE_TO_EVEN, TIE_AWAY_FROM_ZERO, TRUNCATE, CEILING, FLOOR ]
         nullability: DECLARED_OUTPUT
         return: fp64?
       - args:
-          - name: x
-            value: i32
           - name: distribution
             options: [ SAMPLE, POPULATION]
+          - name: x
+            value: i32
         options:
           rounding:
             values: [ TIE_TO_EVEN, TIE_AWAY_FROM_ZERO, TRUNCATE, CEILING, FLOOR ]
         nullability: DECLARED_OUTPUT
         return: fp64?
       - args:
-          - name: x
-            value: i64
           - name: distribution
             options: [ SAMPLE, POPULATION]
+          - name: x
+            value: i64
         options:
           rounding:
             values: [ TIE_TO_EVEN, TIE_AWAY_FROM_ZERO, TRUNCATE, CEILING, FLOOR ]
@@ -1516,40 +1516,40 @@ aggregate_functions:
         nullability: DECLARED_OUTPUT
         return: fp64?
       - args:
-          - name: x
-            value: i8
           - name: distribution
             options: [ SAMPLE, POPULATION]
+          - name: x
+            value: i8
         options:
           rounding:
             values: [ TIE_TO_EVEN, TIE_AWAY_FROM_ZERO, TRUNCATE, CEILING, FLOOR ]
         nullability: DECLARED_OUTPUT
         return: fp64?
       - args:
-          - name: x
-            value: i16
           - name: distribution
             options: [ SAMPLE, POPULATION]
+          - name: x
+            value: i16
         options:
           rounding:
             values: [ TIE_TO_EVEN, TIE_AWAY_FROM_ZERO, TRUNCATE, CEILING, FLOOR ]
         nullability: DECLARED_OUTPUT
         return: fp64?
       - args:
-          - name: x
-            value: i32
           - name: distribution
             options: [ SAMPLE, POPULATION]
+          - name: x
+            value: i32
         options:
           rounding:
             values: [ TIE_TO_EVEN, TIE_AWAY_FROM_ZERO, TRUNCATE, CEILING, FLOOR ]
         nullability: DECLARED_OUTPUT
         return: fp64?
       - args:
-          - name: x
-            value: i64
           - name: distribution
             options: [ SAMPLE, POPULATION]
+          - name: x
+            value: i64
         options:
           rounding:
             values: [ TIE_TO_EVEN, TIE_AWAY_FROM_ZERO, TRUNCATE, CEILING, FLOOR ]
diff --git a/tests/cases/arithmetic/std_dev.test b/tests/cases/arithmetic/std_dev.test
index f951555a6..d50d86a61 100644
--- a/tests/cases/arithmetic/std_dev.test
+++ b/tests/cases/arithmetic/std_dev.test
@@ -54,27 +54,27 @@
 
 
 # integer_types: Standard deviation with integer input types returning fp64
-((1, 2, 3, 4, 5)) std_dev(col0::i8, SAMPLE::enum) = 1.5811388300841898::fp64?
-((1, 2, 3, 4, 5)) std_dev(col0::i8, POPULATION::enum) = 1.4142135623730951::fp64?
-((1, 2, 3, 4, 5)) std_dev(col0::i16, SAMPLE::enum) = 1.5811388300841898::fp64?
-((1, 2, 3, 4, 5)) std_dev(col0::i16, POPULATION::enum) = 1.4142135623730951::fp64?
-((1, 2, 3, 4, 5)) std_dev(col0::i32, SAMPLE::enum) = 1.5811388300841898::fp64?
-((1, 2, 3, 4, 5)) std_dev(col0::i32, POPULATION::enum) = 1.4142135623730951::fp64?
-((1, 2, 3, 4, 5)) std_dev(col0::i64, SAMPLE::enum) = 1.5811388300841898::fp64?
-((1, 2, 3, 4, 5)) std_dev(col0::i64, POPULATION::enum) = 1.4142135623730951::fp64?
+((1, 2, 3, 4, 5)) std_dev(SAMPLE::enum, col0::i8) = 1.5811388300841898::fp64?
+((1, 2, 3, 4, 5)) std_dev(POPULATION::enum, col0::i8) = 1.4142135623730951::fp64?
+((1, 2, 3, 4, 5)) std_dev(SAMPLE::enum, col0::i16) = 1.5811388300841898::fp64?
+((1, 2, 3, 4, 5)) std_dev(POPULATION::enum, col0::i16) = 1.4142135623730951::fp64?
+((1, 2, 3, 4, 5)) std_dev(SAMPLE::enum, col0::i32) = 1.5811388300841898::fp64?
+((1, 2, 3, 4, 5)) std_dev(POPULATION::enum, col0::i32) = 1.4142135623730951::fp64?
+((1, 2, 3, 4, 5)) std_dev(SAMPLE::enum, col0::i64) = 1.5811388300841898::fp64?
+((1, 2, 3, 4, 5)) std_dev(POPULATION::enum, col0::i64) = 1.4142135623730951::fp64?
 
 # integer_negative: Standard deviation with negative integer values
-((-5, -3, -1, 1, 3, 5)) std_dev(col0::i32, SAMPLE::enum) = 3.8944404818493075::fp64?
-((-10, -5, 0, 5, 10)) std_dev(col0::i64, POPULATION::enum) = 7.0710678118654755::fp64?
+((-5, -3, -1, 1, 3, 5)) std_dev(SAMPLE::enum, col0::i32) = 3.8944404818493075::fp64?
+((-10, -5, 0, 5, 10)) std_dev(POPULATION::enum, col0::i64) = 7.0710678118654755::fp64?
 
 # integer_uniform: Standard deviation with uniform integer values
-((42, 42, 42, 42)) std_dev(col0::i16, SAMPLE::enum) = 0.0::fp64?
-((100, 100, 100, 100)) std_dev(col0::i32, POPULATION::enum) = 0.0::fp64?
+((42, 42, 42, 42)) std_dev(SAMPLE::enum, col0::i16) = 0.0::fp64?
+((100, 100, 100, 100)) std_dev(POPULATION::enum, col0::i32) = 0.0::fp64?
 
 # integer_single: Standard deviation with single integer value
-((7)) std_dev(col0::i8, SAMPLE::enum) = Null::fp64?
-((99)) std_dev(col0::i64, POPULATION::enum) = 0.0::fp64?
+((7)) std_dev(SAMPLE::enum, col0::i8) = Null::fp64?
+((99)) std_dev(POPULATION::enum, col0::i64) = 0.0::fp64?
 
 # integer_large_values: Standard deviation with large integer values
-((1000, 2000, 3000, 4000, 5000)) std_dev(col0::i32, SAMPLE::enum) = 1581.1388300841898::fp64?
-((100, 200, 300, 400, 500)) std_dev(col0::i64, POPULATION::enum) = 141.4213562373095::fp64?
+((1000, 2000, 3000, 4000, 5000)) std_dev(SAMPLE::enum, col0::i32) = 1581.1388300841898::fp64?
+((100, 200, 300, 400, 500)) std_dev(POPULATION::enum, col0::i64) = 141.4213562373095::fp64?
diff --git a/tests/cases/arithmetic/variance.test b/tests/cases/arithmetic/variance.test
index 626752cd5..5a6cc6022 100644
--- a/tests/cases/arithmetic/variance.test
+++ b/tests/cases/arithmetic/variance.test
@@ -62,35 +62,35 @@
 
 
 # integer_types: Variance with integer input types returning fp64
-((1, 2, 3, 4, 5)) variance(col0::i8, SAMPLE::enum) = 2.5::fp64?
-((1, 2, 3, 4, 5)) variance(col0::i8, POPULATION::enum) = 2.0::fp64?
-((1, 2, 3, 4, 5)) variance(col0::i16, SAMPLE::enum) = 2.5::fp64?
-((1, 2, 3, 4, 5)) variance(col0::i16, POPULATION::enum) = 2.0::fp64?
-((1, 2, 3, 4, 5)) variance(col0::i32, SAMPLE::enum) = 2.5::fp64?
-((1, 2, 3, 4, 5)) variance(col0::i32, POPULATION::enum) = 2.0::fp64?
-((1, 2, 3, 4, 5)) variance(col0::i64, SAMPLE::enum) = 2.5::fp64?
-((1, 2, 3, 4, 5)) variance(col0::i64, POPULATION::enum) = 2.0::fp64?
+((1, 2, 3, 4, 5)) variance(SAMPLE::enum, col0::i8) = 2.5::fp64?
+((1, 2, 3, 4, 5)) variance(POPULATION::enum, col0::i8) = 2.0::fp64?
+((1, 2, 3, 4, 5)) variance(SAMPLE::enum, col0::i16) = 2.5::fp64?
+((1, 2, 3, 4, 5)) variance(POPULATION::enum, col0::i16) = 2.0::fp64?
+((1, 2, 3, 4, 5)) variance(SAMPLE::enum, col0::i32) = 2.5::fp64?
+((1, 2, 3, 4, 5)) variance(POPULATION::enum, col0::i32) = 2.0::fp64?
+((1, 2, 3, 4, 5)) variance(SAMPLE::enum, col0::i64) = 2.5::fp64?
+((1, 2, 3, 4, 5)) variance(POPULATION::enum, col0::i64) = 2.0::fp64?
 
 # integer_negative: Variance with negative integer values
-((-5, -3, -1, 1, 3, 5)) variance(col0::i32, SAMPLE::enum) = 15.166666666666666::fp64?
-((-10, -5, 0, 5, 10)) variance(col0::i64, POPULATION::enum) = 50.0::fp64?
+((-5, -3, -1, 1, 3, 5)) variance(SAMPLE::enum, col0::i32) = 15.166666666666666::fp64?
+((-10, -5, 0, 5, 10)) variance(POPULATION::enum, col0::i64) = 50.0::fp64?
 
 # integer_uniform: Variance with uniform integer values
-((42, 42, 42, 42)) variance(col0::i16, SAMPLE::enum) = 0.0::fp64?
-((100, 100, 100, 100)) variance(col0::i32, POPULATION::enum) = 0.0::fp64?
+((42, 42, 42, 42)) variance(SAMPLE::enum, col0::i16) = 0.0::fp64?
+((100, 100, 100, 100)) variance(POPULATION::enum, col0::i32) = 0.0::fp64?
 
 # integer_single: Variance with single integer value
-((7)) variance(col0::i8, SAMPLE::enum) = Null::fp64?
-((99)) variance(col0::i64, POPULATION::enum) = 0.0::fp64?
+((7)) variance(SAMPLE::enum, col0::i8) = Null::fp64?
+((99)) variance(POPULATION::enum, col0::i64) = 0.0::fp64?
 
 # integer_large_values: Variance with large integer values
-((1000, 2000, 3000, 4000, 5000)) variance(col0::i32, SAMPLE::enum) = 2500000.0::fp64?
-((100, 200, 300, 400, 500)) variance(col0::i64, POPULATION::enum) = 20000.0::fp64?
+((1000, 2000, 3000, 4000, 5000)) variance(SAMPLE::enum, col0::i32) = 2500000.0::fp64?
+((100, 200, 300, 400, 500)) variance(POPULATION::enum, col0::i64) = 20000.0::fp64?
 
 # integer_zero_mean: Variance with integer values around zero
-((-2, -1, 0, 1, 2)) variance(col0::i16, SAMPLE::enum) = 2.5::fp64?
-((-2, -1, 0, 1, 2)) variance(col0::i64, POPULATION::enum) = 2.0::fp64?
+((-2, -1, 0, 1, 2)) variance(SAMPLE::enum, col0::i16) = 2.5::fp64?
+((-2, -1, 0, 1, 2)) variance(POPULATION::enum, col0::i64) = 2.0::fp64?
 
 # integer_three_values: Variance with three integer values
-((10, 20, 30)) variance(col0::i32, SAMPLE::enum) = 100.0::fp64?
-((10, 20, 30)) variance(col0::i8, POPULATION::enum) = 66.66666666666667::fp64?
+((10, 20, 30)) variance(SAMPLE::enum, col0::i32) = 100.0::fp64?
+((10, 20, 30)) variance(POPULATION::enum, col0::i8) = 66.66666666666667::fp64?