Merge ""successful preparation means successful execution" guarantee neglects bad operation inputs"
diff --git a/current.txt b/current.txt
index 2aa9ef2..44eebf8 100644
--- a/current.txt
+++ b/current.txt
@@ -574,8 +574,8 @@
 # ABI preserving changes to HALs during Android R
 2410dd02d67786a732d36e80b0f8ccf55086604ef37f9838e2013ff2c571e404 android.hardware.camera.device@3.5::types
 b69a7615c508acf5c5201efd1bfa3262167874fc3594e2db5a3ff93addd8ac75 android.hardware.keymaster@4.0::IKeymasterDevice
-ad431c8de51c07934a068e3043d8dd0537ac4d3158627706628b123f42df48dc android.hardware.neuralnetworks@1.0::IPreparedModel
+eb2fa0c883c2185d514be0b84c179b283753ef0c1b77b45b4f359bd23bba8b75 android.hardware.neuralnetworks@1.0::IPreparedModel
 fb382e986c10b8fbb797a8546e8f9ea6d1107bfe6f3fb7e57f6bbbf1f807a906 android.hardware.neuralnetworks@1.2::IDevice
-aafcc10cf04ab247e86d4582586c71c6b4c2b8c479241ffa7fe37deb659fc942 android.hardware.neuralnetworks@1.2::IPreparedModel
+6c5081dd131eeb7eb02efece2187cd4d7d554197800bb520c92ff874cc238fa6 android.hardware.neuralnetworks@1.2::IPreparedModel
 1a6e2bd289f22931c526b21916910f1d4c436b7acb9556e4243de4ce8e6cc2e4 android.hardware.soundtrigger@2.0::ISoundTriggerHwCallback
 fd65298e1e09e0e3c781ab18305920d757dbe55a3b459ce17814ec5cf6dfee99 android.hardware.wifi@1.0::IWifiP2pIface
diff --git a/neuralnetworks/1.0/IPreparedModel.hal b/neuralnetworks/1.0/IPreparedModel.hal
index 5320050..3dc3202 100644
--- a/neuralnetworks/1.0/IPreparedModel.hal
+++ b/neuralnetworks/1.0/IPreparedModel.hal
@@ -49,11 +49,14 @@
      * must not change the content of any of the data objects corresponding to
      * 'request' inputs.
      *
-     * If the prepared model was prepared from a model wherein all
-     * tensor operands have fully specified dimensions, and the inputs
-     * to the function are valid, then the execution should launch
-     * and complete successfully (ErrorStatus::NONE). There must be
-     * no failure unless the device itself is in a bad state.
+     * If the prepared model was prepared from a model wherein all tensor
+     * operands have fully specified dimensions, and the inputs to the function
+     * are valid, then:
+     * - the execution should launch successfully (ErrorStatus::NONE): There
+     *   must be no failure unless the device itself is in a bad state.
+     * - if at execution time every operation's input operands have legal
+     *   values, the execution should complete successfully (ErrorStatus::NONE):
+     *   There must be no failure unless the device itself is in a bad state.
      *
      * Multiple threads can call the execute function on the same IPreparedModel
      * object concurrently with different requests.
diff --git a/neuralnetworks/1.2/IPreparedModel.hal b/neuralnetworks/1.2/IPreparedModel.hal
index ba16334..f3508fe 100644
--- a/neuralnetworks/1.2/IPreparedModel.hal
+++ b/neuralnetworks/1.2/IPreparedModel.hal
@@ -54,11 +54,14 @@
      * must not change the content of any of the data objects corresponding to
      * 'request' inputs.
      *
-     * If the prepared model was prepared from a model wherein all
-     * tensor operands have fully specified dimensions, and the inputs
-     * to the function are valid, then the execution should launch
-     * and complete successfully (ErrorStatus::NONE). There must be
-     * no failure unless the device itself is in a bad state.
+     * If the prepared model was prepared from a model wherein all tensor
+     * operands have fully specified dimensions, and the inputs to the function
+     * are valid, then:
+     * - the execution should launch successfully (ErrorStatus::NONE): There
+     *   must be no failure unless the device itself is in a bad state.
+     * - if at execution time every operation's input operands have legal
+     *   values, the execution should complete successfully (ErrorStatus::NONE):
+     *   There must be no failure unless the device itself is in a bad state.
      *
      * Any number of calls to the execute, execute_1_2, and executeSynchronously
      * functions, in any combination, may be made concurrently, even on the same
@@ -105,8 +108,9 @@
      *
      * If the prepared model was prepared from a model wherein all tensor
      * operands have fully specified dimensions, and the inputs to the function
-     * are valid, then the execution should complete successfully
-     * (ErrorStatus::NONE). There must be no failure unless the device itself is
+     * are valid, and at execution time every operation's input operands have
+     * legal values, then the execution should complete successfully
+     * (ErrorStatus::NONE): There must be no failure unless the device itself is
      * in a bad state.
      *
      * Any number of calls to the execute, execute_1_2, and executeSynchronously
@@ -145,6 +149,13 @@
      * Configure a Burst object used to execute multiple inferences on a
      * prepared model in rapid succession.
      *
+     * If the prepared model was prepared from a model wherein all tensor
+     * operands have fully specified dimensions, and a valid serialized Request
+     * is sent to the Burst for execution, and at execution time every
+     * operation's input operands have legal values, then the execution should
+     * complete successfully (ErrorStatus::NONE): There must be no failure
+     * unless the device itself is in a bad state.
+     *
      * @param callback A callback object used to retrieve memory resources
      *                 corresponding to a unique identifiers ("slots").
      * @param requestChannel Used by the client to send a serialized Request to