name: voice-authenticity
version: "2.0.0"
description: "Voice authenticity detection across real-world degradation conditions with multi-step agentic interaction"
author: "AksharaSharma"
tags:
  - openenv
  - speech
  - fraud-detection
  - audio
  - partial-observability
tasks:
  - name: clean_detection
    difficulty: easy
    description: "Classify real vs synthetic speech from clean audio features"
  - name: compressed_detection
    difficulty: medium
    description: "Classify speech under codec compression degradation"
  - name: adversarial_detection
    difficulty: hard
    description: "Classify adversarially crafted synthetic speech with overlapping distributions"
  - name: streaming_detection
    difficulty: medium_hard
    description: "Streaming detection with step-dependent noise soft-gating"
  - name: phonecall_detection
    difficulty: extreme
    description: "Phone call simulation with heavy codec compression and narrowband degradation"
  - name: realtime_detection
    difficulty: realtime
    description: "Classify at any point after step 2 with time penalty for extra steps. Tests knowing when to stop investigating."
observation_space:
  type: object
  properties:
    features:
      type: array
      description: "48-dim feature vector (zeroed until revealed via actions)"
    visible_features:
      type: object
      description: "Feature groups revealed so far"
    evidence_summary:
      type: string
      description: "Structured summary from analyze_evidence action"
    comparison_result:
      type: object
      description: "Similarity scores to real/fake reference centroids"
    task_name:
      type: string
    step_number:
      type: integer
    difficulty:
      type: string
    available_actions:
      type: array
    actions_taken:
      type: array
action_space:
  type: object
  properties:
    action_type:
      type: string
      enum:
        - request_temporal_features
        - request_spectral_features
        - request_comparison
        - analyze_evidence
        - final_classify
    label:
      type: integer
      description: "0=real, 1=synthetic"
    confidence:
      type: number
      description: "Agent confidence [0.0, 1.0]"
    reasoning:
      type: string
      description: "Explanation of decision"