config_gise.yaml

# Temporal Reasoning Audio Dataset Pipeline Configuration
##uniform distributuon for clip duration
##not mixing datasets 

##count
##pick dataset -> pick class -> pick audio clip -> get duration -> concatenate clips to reach target duration -> modulo to get num clips -> inserting silences randomly based on remainder

##duration
##amplitude based filtering -> normalize -> threshold based selection
##gap between audio clips - x2/1.5 the shorter one -> add as param
##different clips of the same class can be contatenated to reach target duration
##consecutive ordering only
##based on n unique sources and total clips we can have -> shortest and longest duration calculation

##reject datapoint if same target audio clip cannot be repeated to maintain the gap - arg
##sample different clip from the same class -> check if different clips can be used to fill the gap - arg

##amplitude filtered durations in metadata csv

##get_max_clip_num_to_be_joined()
##pick dataset -> pick class -> pick audio clip -> get duration -> concatenate clips to reach target duration -> modulo to get num clips -> inserting silences randomly based on remainder

##ensure_silence_between_clips()
##silence should always be there between two clips

##order
##repeat target clips 
##second and second last - modify question types

##volume
##amplitude average loudness for a audio clip -> repetitions but same clip(argument) -> different volume levels based on dB levels

##add crossfade

##trimming - threshold separately for each audio clip - normalize 1 and 0 - get threshold -> trim -> concatenate
##leftmost and rightmost silence trimming
##buffer for trimming - cutting early and cutting a bit late to avoid cutting important parts 
##periodicity affect

##volume - trim and get average loudness -> normalize -> adjust volume levels 

##number of clips per samples to avoid silence 


# ESC-50 Dataset paths (each clip is 5 seconds)
esc50:  
  audio_path: "/home/debarpanb1/TREA_2.0/ESC-50-master/audio"
  metadata_path: "/home/debarpanb1/TREA_2.0/ESC-50-master/meta/esc50.csv"

# Generic dataset source. When present, pipeline tasks use this instead of ESC-50.
dataset_source:
  name: "GISE_preprocessed_duration"
  audio_path: "/home/debarpanb1/TREA_2.0/GISE_preprocessed_duration/isolated_events"
  metadata_path: "/home/debarpanb1/TREA_2.0/GISE_preprocessed_duration/gise_metadata_kept_0p5_10s.csv"
  preprocessed_path: "/home/debarpanb1/TREA_2.0/GISE_preprocessed_duration"
  category_col: "class"
  filename_col: "file_name"
  classid_col: "classID"
  fullpath_col: "clean_audio_path"
  duration_col: "duration"

# Synthetic silence audio for concatenation
synthetic_silence:
  path: "/home/debarpanb1/TREA_2.0/synthetic_silences"
  
# Output configuration
output:
  base_path: "/home/debarpanb1/TREA_2.0/pipeline/dataset_gise"
# Dataset class-subset configuration
# Use this to create datasets (train/val/test) from a persistent subset
# of classes (e.g. use 40 of 50 classes for in-distribution splits and
# optionally create an OOD test set using all 50 classes).
dataset:
  use_class_subset: false                # if false, use all available classes
  num_classes_subset: 40                # number of classes to use for train/val/test
  subset_persist_path: "/home/debarpanb1/TREA_2.0/class_subset.json"
  subset_seed: 42                       # RNG seed when sampling the subset (persisted)

# Audio generation parameters
audio:
  # Duration range for each GENERATED clip (in seconds)
  # Original ESC-50 clips are 5s and will be concatenated to create clips in this range
  min_clip_duration: 20.0     # Minimum duration for each generated clip
  max_clip_duration: 60.0     # Maximum duration for each generated clip
  
  # Crossfade and silence
  crossfade_duration: 500    # Crossfade between audio and silence (milliseconds) for smooth transitions
  silence_duration: 1000     # Default silence between clips (milliseconds)
  min_silence_duration: 100  # Minimum silence ALWAYS inserted between clips (milliseconds)
  max_extra_silence_per_gap: 500  # Maximum extra silence per gap when distributing remainder
  crossfade_within_source: 50  # Small crossfade within same-source repetitions (count task)
  with_silence: true         # Add silence between clips
  # Duration (seconds) of individual source clips (ESC-50 are 5s by default).
  # Used to compute how many source clips are concatenated to reach a target
  # generated clip duration. Change only if your source clips differ.
  source_clip_duration: 6.5
  
  # Audio normalization
  normalize: false
  normalize_target_dBFS: -20.0

# Random seed for reproducibility
random_seed: 42

# LLM for question generation (local Llama 3.1 8B)
llm:
  enabled: false  # Set to true to use LLM for question generation

# Task-specific configurations
tasks:
  count:
    enabled: true
    # Total duration for ALL samples in this task combined (in hours)
    # Pipeline will calculate number of samples based on min/max clip durations
    task_duration_size: 1.0  # hours
    
    # Maximum unique sound sources per sample (single number)
    # Actual number will be subsampled from max(1, max_clips-3) to min(max_clips, max_clips_per_sample)
    max_clips_per_sample: 10
    
    # Ordering mode for repeated clips of same source:
    # "random": Clips are shuffled randomly (A B A C B A C...) - tests recognition of recurring sounds
    # "consecutive": Same-source clips grouped together (AAA BBB CCC) - easier, just count blocks
    ordering_mode: "random"
    
    # Question types: unique_count (how many distinct sounds) and
    # occurrence_count (how many times does a specific sound occur)
    question_types: ["unique_count", "occurrence_count"]
    
    # Question templates for MCQ (organized by question type)
    mcq_questions:
      unique_count:
        - "What is the number of distinct sound sources in the audio file?"
        - "How many different types of sounds can be identified in this recording?"
        - "How many unique types of sound are present in this audio?"
        - "Identify the count of different sound sources in this clip."
        - "What is the total number of unique sounds heard in this audio?"
        - "How many distinct sound categories are there in this audio file?"
        - "Determine the number of unique sound sources in this recording."
        - "How many separate sound sources are included in the audio?"
        - "What is the total number of unique sound types in this audio?"
        - "How many different sound sources can be heard in this clip?"
      occurrence_count:
        - "How many times does {target_sound} occur in the audio?"
        - "How many separate occurrences of {target_sound} are heard in this recording?"
        - "What is the number of times {target_sound} appears in the audio?"
        - "How many {target_sound} events are present in the clip?"
    # Question templates for open-text (organized by question type)
    open_text_questions:
      unique_count:
        - "How many distinct sound sources are present in the audio?"
        - "Count the number of unique sounds in this recording."
        - "What is the total count of different sound categories heard?"
        - "Identify and count all unique sound types in the clip."
      occurrence_count:
        - "How many times is {target_sound} heard?"
        - "Count the number of {target_sound} occurrences in the audio."
        - "How many separate {target_sound} events are present?"
    
  duration:
    enabled: true
    # Total duration for ALL samples in this task combined (in hours)
    task_duration_size: 1.0  # hours
    
    # Number of unique sound sources per sample (can be single int or list)
    # Single int (e.g., 15): randomly samples from 1 to 15 (like count/order tasks)
    # List (e.g., [2,3,4]): randomly picks from the list
    # The script will automatically generate repetition patterns to create
    # shortest/longest variations based on the target clip duration
    num_unique_sources: 10
    
    # Ordering: only keep "consecutive" so repeated segments of the same
    # source remain grouped together, ensuring that multiple consecutive
    # clips of the same audio yield the longest duration unambiguously.
    ordering_methods: ["consecutive"]
    
    # =====================================================
    # Amplitude-based filtering parameters (preprocessing)
    # =====================================================
    # RELATIVE dB threshold below peak to consider as silence
    # For each clip: silence_threshold = clip_peak_dB + amplitude_threshold_db
    # Example: If clip peak is -5 dB and threshold is -20, silence threshold = -25 dB
    # Based on ESC-50 analysis: -20 dB gives ~60% effective duration (good balance)
    # More aggressive (removes more silence): -15 dB
    # More conservative (keeps more sound): -25 dB
    amplitude_threshold_db: -20.0
    
    # Minimum duration of sound region to keep (milliseconds)
    # Filters out very short transient noise spikes
    # ESC-50 is curated, so 20-30ms is sufficient
    min_sound_duration_ms: 25
    
    # =====================================================
    # Adaptive threshold strategy
    # =====================================================
    # "peak_relative": threshold = peak_dB + amplitude_threshold_db (fixed offset from peak)
    #   - Simple but not adaptive to actual noise levels
    # "noise_floor": threshold = percentile(dB, N) + delta_dB (RECOMMENDED)
    #   - Fully adaptive per-clip based on its own noise floor
    #   - Each clip analyzed independently - no fixed dB values needed
    #   - Better for diverse audio with varying noise levels
    threshold_strategy: "noise_floor"
    
    # Noise floor estimation percentile (used when threshold_strategy = noise_floor)
    # Lower percentile = more conservative estimate of background noise
    # 5 = use 5th percentile of dB values as noise floor estimate (better for sparse sounds)
    noise_floor_percentile: 2.0
    
    # Delta above noise floor (dB) to set as threshold
    # This is relative to EACH clip's own noise floor, not a fixed dB value
    # 8dB above the clip's noise floor works well for most ESC-50 clips
    # Higher = more conservative (keeps more), Lower = more aggressive (removes more)
    noise_floor_delta_db: 5.0
    
    # Path to preprocessed ESC-50 data (effective durations + trimmed audio)
    preprocessed_data_path: "/home/debarpanb1/TREA_2.0/GISE_preprocessed_duration"
    
    # =====================================================
    # Duration gap multipliers
    # =====================================================
    # For LONGEST questions: target_effective >= max_background × multiplier_longest
    multiplier_longest: 1.5
    # For SHORTEST questions: target_effective <= min_background × multiplier_shortest
    # Using 0.75 instead of 0.5 for smaller gaps (easier to distinguish)
    multiplier_shortest: 0.75
    
    # Minimum effective duration per source (seconds)
    # Clips with less than this duration are harder to distinguish
    min_effective_duration_per_source: 1.0
    
    # =====================================================
    # Fallback/rejection options
    # =====================================================
    # Reject sample if duration gap cannot be satisfied
    reject_if_gap_not_met: true
    # Try different clips from same class if one clip isn't enough
    sample_different_clips_same_class: true
    
    # Question types
    question_types: ["shortest", "longest", "pairwise_longer", "pairwise_shorter"]
    # MCQ questions
    mcq_questions:
      shortest: "Which of the following sounds is heard for the shortest duration?"
      longest: "Which of the following sounds is heard for the longest duration?"
      pairwise_longer: "Between {sound1} and {sound2}, which sound lasts longer?"
      pairwise_shorter: "Between {sound1} and {sound2}, which sound is heard for a shorter duration?"
    # Open-text questions
    open_text_questions:
      shortest: "Which sound is heard for the shortest duration in the audio?"
      longest: "Which sound is heard for the longest duration in the audio?"
      pairwise_longer: "Which lasts longer, {sound1} or {sound2}?"
      pairwise_shorter: "Which is shorter, {sound1} or {sound2}?"
    
  order:
    enabled: true
    # Total duration for ALL samples in this task combined (in hours)
    task_duration_size: 1.0  # hours
    
    # Maximum clips to join per sample (minimum 2 for ordering)
    # Actual number will be subsampled from max(2, max_clips-3) to min(max_clips, max_clips_per_sample)
    max_clips_per_sample: 10
    
    # Whether to allow repeating clips from the same source category
    # If true: sequence could be [dog, dog, cat, bird] (same clip repeated)
    # If false: sequence is always unique sources
    allow_source_repetition: false
    
    # Minimum clips needed for "second" and "second_last" questions
    # Set to 4 to ensure second and second_last refer to different positions
    # (with 3 clips, both would refer to middle clip at position 1)
    min_clips_for_second_questions: 3
    
    # Question types: "first", "last", "after", "before", "second", "second_last"
    # "second" and "second_last" only generated when n_clips >= min_clips_for_second_questions
    question_types: ["first", "last", "after", "before", "second", "second_last"]
    
    # MCQ question templates
    mcq_questions:
      first: "Which sound appears first in the audio clip?"
      last: "Which sound appears last in the audio clip?"
      after: "Which sound comes after {sound1}?"
      before: "Which sound comes before {sound2}?"
      second: "Which sound appears second in the audio clip?"
      second_last: "Which sound appears second to last in the audio clip?"
    # Open-text question templates
    open_text_questions:
      first: "What is the first sound you hear in the audio?"
      last: "What is the last sound you hear in the audio?"
      after: "What sound comes after {sound1}?"
      before: "What sound comes before {sound2}?"
      second: "What is the second sound you hear in the audio?"
      second_last: "What sound is second to last in the audio?"
      sequence: "List the sounds in the order they appear in the audio."
    
  volume:
    enabled: true
    # Total duration for ALL samples in this task combined (in hours)
    task_duration_size: 1.0  # hours
    
    # Maximum clips with different volumes per sample
    # Actual number will be subsampled from max(2, max_clips-3) to min(max_clips, max_clips_per_sample)
    max_clips_per_sample: 10
    
    # =====================================================
    # Normalization settings (CRITICAL for volume comparison)
    # =====================================================
    # All clips are FIRST normalized to baseline, THEN volume adjusted
    # This ensures volume differences are controlled and comparable
    normalize_to_baseline: true
    baseline_dBFS: -20.0  # Normalize all clips to this level first (used if use_lufs=false)
    
    # =====================================================
    # LUFS (Perceived Loudness) Settings
    # =====================================================
    # LUFS (Loudness Units Full Scale) measures PERCEIVED loudness
    # Unlike dBFS which only measures RMS amplitude, LUFS accounts for
    # human hearing sensitivity to different frequencies (K-weighting)
    # 
    # IMPORTANT: For volume comparison task, we DISABLE LUFS normalization!
    # LUFS makes everything the same perceived loudness, defeating the purpose.
    # Instead, we normalize to a baseline dBFS then apply LARGE volume adjustments.
    use_lufs: false               # DISABLED for audible volume differences
    baseline_lufs: -23.0          # EBU R128 standard (not used when use_lufs=false)
    
    # =====================================================
    # Volume gap multipliers (similar to duration task)
    # =====================================================
    # For MAX_LOUDNESS questions: target_loudness >= second_loudest × multiplier_max
    # Multiplier 2.5 = ~8dB difference = clearly audible
    # Multiplier 4.0 = ~12dB difference = very obvious (4x perceived loudness)
    multiplier_max_loudness: 4.0
    
    # For MIN_LOUDNESS questions: target_loudness <= second_softest × multiplier_min
    # Multiplier 0.25 = ~12dB quieter = clearly distinguishable
    multiplier_min_loudness: 0.25
    
    # Reject sample if loudness gap cannot be satisfied
    reject_if_gap_not_met: true
    
    # =====================================================
    # Source clip options
    # =====================================================
    # If true: same clip can be repeated at different volumes
    # If false: always use different source clips (default behavior)
    use_same_clip_different_volumes: false
    
    # If use_same_clip_different_volumes is true, how many repetitions per source?
    # Can be a single int or list for variety
    repetitions_per_source: [2, 3, 4]
    
    # Question types: "max_loudness", "min_loudness", "pairwise_louder", "pairwise_softer"
    question_types: ["max_loudness", "min_loudness", "pairwise_louder", "pairwise_softer"]
    
    # MCQ questions
    mcq_questions:
      max_loudness: "Which sound has the maximum loudness in the audio?"
      min_loudness: "Which sound has the minimum loudness in the audio?"
      pairwise_louder: "Between {sound1} and {sound2}, which sound is louder?"
      pairwise_softer: "Between {sound1} and {sound2}, which sound is softer?"
    # Open-text questions
    open_text_questions:
      max_loudness: "Identify the sound with maximum loudness in the audio clip."
      min_loudness: "Identify the sound with minimum loudness in the audio clip."
      pairwise_louder: "Which is louder, {sound1} or {sound2}?"
      pairwise_softer: "Which is softer, {sound1} or {sound2}?"
      order_volume: "List the sounds in order from maximum to minimum loudness."

  # =============================================================
  # NEW TASKS: silence_gap, overlap, during_contains
  # =============================================================
  
  silence_gap:
    enabled: true
    task_duration_size: 1.0  # hours
    
    # Clips per sample: need at least 3 clips to have 2+ gaps to compare
    min_clips_per_sample: 3
    max_clips_per_sample: 10
    
    # =====================================================
    # Silence gap control
    # =====================================================
    # Range for individual gap durations (milliseconds)
    min_gap_duration_ms: 500
    max_gap_duration_ms: 3000
    
    # Multiplier constraint: longest gap >= shortest gap × gap_multiplier
    # 2.0 = longest silence must be at least 2× the shortest
    gap_multiplier: 2.0
    
    # Use preprocessed (trimmed) audio to avoid random leading/trailing silences
    preprocessed_data_path: "/home/debarpanb1/TREA_2.0/GISE_preprocessed_duration"
    
    # Question types
    question_types: ["longest_gap", "shortest_gap", "after_gap", "before_gap", "compare_gaps"]
    
    # MCQ questions
    mcq_questions:
      longest_gap: "Which two sounds have the longest silence between them?"
      shortest_gap: "Which two sounds have the shortest silence between them?"
      after_gap: "Which sound occurs after the longest silence?"
      before_gap: "Which sound occurs before the longest silence?"
      compare_gaps: "Which silence is longer: after {sound1} or after {sound2}?"
    # Open-text questions
    open_text_questions:
      longest_gap: "Which two sounds have the longest silence between them?"
      shortest_gap: "Which two sounds have the shortest silence between them?"
      after_gap: "What sound occurs after the longest silence?"
      before_gap: "What sound occurs before the longest silence?"
      compare_gaps: "Which pause is longer, after {sound1} or after {sound2}?"
  
  overlap:
    enabled: true
    task_duration_size: 1.0  # hours
    
    # Number of sounds in each sample (start with 2, configurable)
    num_sounds: 2
    
    # =====================================================
    # Overlap control
    # =====================================================
    # Overlap as a ratio of the shorter clip's duration
    min_overlap_ratio: 0.2   # At least 20% overlap
    max_overlap_ratio: 0.5   # At most 50% overlap
    
    # Question types
    question_types: ["identify_overlap", "overlap_pair", "yes_no_overlap", "starts_before_end"]
    
    # MCQ questions
    mcq_questions:
      identify_overlap: "Which sound overlaps with {anchor_sound}?"
      overlap_pair: "Which two sounds occur at the same time?"
      yes_no_overlap: "Does {sound1} overlap with {sound2}?"
      starts_before_end: "Which sound starts before {anchor_sound} ends?"
    # Open-text questions
    open_text_questions:
      identify_overlap: "Which sound overlaps with {anchor_sound}?"
      overlap_pair: "Which two sounds occur at the same time?"
      yes_no_overlap: "Do {sound1} and {sound2} overlap?"
      starts_before_end: "Which sound starts before {anchor_sound} ends?"
  
  during_contains:
    enabled: true
    task_duration_size: 1.0  # hours
    
    # Number of sounds in each sample (start with 2, configurable)
    num_sounds: 2
    
    # =====================================================
    # Containment control
    # =====================================================
    # Duration of the container sound (seconds)
    # The container is extended by repeating the source clip
    min_container_duration_s: 8.0
    max_container_duration_s: 15.0
    
    # Minimum margin (seconds) between contained sound edges and container edges
    # Ensures the contained sound doesn't start/end right at container boundaries
    min_margin_s: 0.5
    
    # Question types
    question_types: ["during", "contains", "yes_no_during"]
    
    # MCQ questions
    mcq_questions:
      during: "Which sound occurs during {anchor_sound}?"
      contains: "Which longer sound contains {target_sound}?"
      yes_no_during: "Does {target_sound} happen entirely during {anchor_sound}?"
    # Open-text questions
    open_text_questions:
      during: "Which sound occurs during {anchor_sound}?"
      contains: "Which sound contains {target_sound}?"
      yes_no_during: "Does {target_sound} happen entirely during {anchor_sound}?"

  # =====================================================================
  # MULTIHOP TEMPORAL REASONING — SINGULAR TASKS
  # =====================================================================

  conditional_count:
    enabled: true
    task_duration_size: 1.0  # hours
    min_events: 4
    max_events: 8
    question_types: ["count_after", "count_before", "count_between", "count_during", "count_overlap"]
    mcq_questions:
      count_after: "How many {target_sound} sounds occur after {anchor_sound}?"
      count_before: "How many {target_sound} sounds occur before {anchor_sound}?"
      count_between: "How many {target_sound} sounds occur between {sound1} and {sound2}?"
      count_during: "How many {target_sound} sounds occur while {anchor_sound} is playing?"
      count_overlap: "How many sounds overlap with {anchor_sound}?"
    open_text_questions:
      count_after: "How many {target_sound} sounds occur after {anchor_sound}?"
      count_before: "How many {target_sound} sounds occur before {anchor_sound}?"
      count_between: "How many {target_sound} sounds occur between {sound1} and {sound2}?"
      count_during: "How many {target_sound} sounds happen while {anchor_sound} is playing?"
      count_overlap: "How many sounds overlap with {anchor_sound}?"

  conditional_duration:
    enabled: true
    task_duration_size: 1.0  # hours
    min_events: 5
    max_events: 8
    preprocessed_data_path: "/home/debarpanb1/TREA_2.0/GISE_preprocessed_duration"
    question_types: ["longest_after", "shortest_after", "longest_before", "shortest_before", "repeated_compare"]
    mcq_questions:
      longest_after: "Which sound after {anchor_sound} lasts the longest?"
      shortest_after: "Which sound after {anchor_sound} lasts the shortest time?"
      longest_before: "Which sound before {anchor_sound} lasts the longest?"
      shortest_before: "Which sound before {anchor_sound} lasts the shortest time?"
      repeated_compare: "Which {target_sound} occurrence lasts longer: the one before {anchor_sound} or the one after {anchor_sound}?"
    open_text_questions:
      longest_after: "Which sound after {anchor_sound} lasts the longest?"
      shortest_after: "Which sound after {anchor_sound} lasts the shortest?"
      longest_before: "Which sound before {anchor_sound} lasts the longest?"
      shortest_before: "Which sound before {anchor_sound} lasts the shortest?"
      repeated_compare: "Which {target_sound} lasts longer, the one before {anchor_sound} or the one after {anchor_sound}?"

  between_events:
    enabled: true
    task_duration_size: 1.0  # hours
    min_events: 5
    max_events: 8
    question_types: ["identify_between", "count_between", "yes_no_between"]
    mcq_questions:
      identify_between: "Which sound occurs between {sound1} and {sound2}?"
      count_between: "How many sounds occur between {sound1} and {sound2}?"
      yes_no_between: "Is {target_sound} heard between {sound1} and {sound2}?"
    open_text_questions:
      identify_between: "What sound occurs between {sound1} and {sound2}?"
      count_between: "How many sounds occur between {sound1} and {sound2}?"
      yes_no_between: "Is {target_sound} heard between {sound1} and {sound2}?"

  event_density:
    enabled: true
    task_duration_size: 1.0  # hours
    min_events: 6
    max_events: 10
    question_types: ["half_density", "before_after_density", "label_density"]
    mcq_questions:
      half_density: "Which half of the audio contains more sound events?"
      before_after_density: "Are there more sounds before or after {anchor_sound}?"
      label_density: "Which part has more {target_sound} sounds: before {anchor_sound} or after {anchor_sound}?"
    open_text_questions:
      half_density: "Which half of the audio contains more events?"
      before_after_density: "Are there more sounds before or after {anchor_sound}?"
      label_density: "Are there more {target_sound} sounds before or after {anchor_sound}?"

  # =====================================================================
  # MULTIHOP TEMPORAL REASONING — INTER-TASK
  # =====================================================================

  duration_gap:
    enabled: true
    task_duration_size: 1.0  # hours
    min_events: 3
    max_events: 6
    min_gap_ms: 500
    max_gap_ms: 4000
    preprocessed_data_path: "/home/debarpanb1/TREA_2.0/GISE_preprocessed_duration"
    question_types: ["event_vs_after_gap", "event_vs_before_gap", "gap_vs_event"]
    mcq_questions:
      event_vs_after_gap: "Which is longer: {sound1} or the silence after {sound1}?"
      event_vs_before_gap: "Which is longer: {sound1} or the silence before {sound1}?"
      gap_vs_event: "Which lasted longer: the pause between {sound1} and {sound2}, or {sound3}?"
    open_text_questions:
      event_vs_after_gap: "Which is longer, {sound1} or the silence after {sound1}?"
      event_vs_before_gap: "Which is longer, {sound1} or the silence before {sound1}?"
      gap_vs_event: "Was the pause between {sound1} and {sound2} longer than {sound3}?"

  temporal_arithmetic:
    enabled: true
    task_duration_size: 1.0  # hours
    min_events: 4
    max_events: 8
    min_gap_ms: 300
    max_gap_ms: 2000
    preprocessed_data_path: "/home/debarpanb1/TREA_2.0/GISE_preprocessed_duration"
    question_types: ["total_label_duration", "label_vs_silence", "combined_duration"]
    mcq_questions:
      total_label_duration: "Which sound lasts longer in total: {sound1} or {sound2}?"
      label_vs_silence: "Which is longer in total: {target_sound} or the total silence?"
      combined_duration: "Which is longer: all {target_sound} sounds combined or the longest silence?"
    open_text_questions:
      total_label_duration: "Which sound lasts longer in total, {sound1} or {sound2}?"
      label_vs_silence: "Which is longer in total, {target_sound} or silence?"
      combined_duration: "Which is longer, all {target_sound} sounds combined or the longest silence?"

  temporal_loudness:
    enabled: true
    task_duration_size: 1.0  # hours
    min_events: 4
    max_events: 8
    # Volume adjustment range for per-event volume (dB)
    volume_range_db: [-12, 6]
    min_volume_diff_db: 3.0
    question_types: ["loudest_after", "softest_after", "loudest_before", "softest_before", "repeated_loudness"]
    mcq_questions:
      loudest_after: "Which sound after {anchor_sound} is the loudest?"
      softest_after: "Which sound after {anchor_sound} is the softest?"
      loudest_before: "Which sound before {anchor_sound} is the loudest?"
      softest_before: "Which sound before {anchor_sound} is the softest?"
      repeated_loudness: "Which occurrence of {target_sound} is the loudest?"
    open_text_questions:
      loudest_after: "Which sound after {anchor_sound} is loudest?"
      softest_after: "Which sound after {anchor_sound} is softest?"
      loudest_before: "Which sound before {anchor_sound} is loudest?"
      softest_before: "Which sound before {anchor_sound} is softest?"
      repeated_loudness: "Which occurrence of {target_sound} is loudest?"

  multi_hop:
    enabled: true
    task_duration_size: 1.0  # hours
    min_events: 5
    max_events: 8
    min_gap_ms: 500
    max_gap_ms: 3000
    # Volume adjustment range for per-event volume (dB)
    volume_range_db: [-10, 6]
    min_volume_diff_db: 4.0
    preprocessed_data_path: "/home/debarpanb1/TREA_2.0/GISE_preprocessed_duration"
    question_types:
      - "after_longest"
      - "before_longest"
      - "after_shortest"
      - "before_loudest"
      - "after_longest_gap"
      - "overlap_after_anchor"
      - "loudest_after_anchor"
      - "longest_before_anchor"
      - "count_before_loudest"
      - "count_after_longest"
    mcq_questions:
      after_longest: "What sound occurs after the longest sound?"
      before_longest: "What sound occurs before the longest sound?"
      after_shortest: "What sound occurs after the shortest sound?"
      before_loudest: "What sound occurs before the loudest sound?"
      after_longest_gap: "Which sound is heard after the longest silence?"
      overlap_after_anchor: "Which sound overlaps with the event that occurs after {anchor_sound}?"
      loudest_after_anchor: "Which sound after {anchor_sound} is the loudest?"
      longest_before_anchor: "Which sound before {anchor_sound} lasts the longest?"
      count_before_loudest: "How many {target_sound} sounds occur before the loudest event?"
      count_after_longest: "How many {target_sound} sounds occur after the longest event?"
    open_text_questions:
      after_longest: "What sound occurs after the longest sound?"
      before_longest: "What sound occurs before the longest sound?"
      after_shortest: "What sound occurs after the shortest sound?"
      before_loudest: "What sound occurs before the loudest sound?"
      after_longest_gap: "Which sound occurs after the longest silence?"
      overlap_after_anchor: "Which sound overlaps with the event that occurs after {anchor_sound}?"
      loudest_after_anchor: "Which sound after {anchor_sound} is loudest?"
      longest_before_anchor: "Which sound before {anchor_sound} lasts the longest?"
      count_before_loudest: "How many {target_sound} sounds occur before the loudest event?"
      count_after_longest: "How many {target_sound} sounds occur after the longest event?"

# MCQ options configuration
mcq:
  num_options: 4
  option_labels: ["A", "B", "C", "D"]
  # Strategy for generating distractor options
  # "present_only": only use sounds present in audio
  # "mixed": mix of present and absent sounds
  # "balanced": balanced distribution
  distractor_strategy: "balanced"

# Logging configuration
logging:
  level: "INFO"  # DEBUG, INFO, WARNING, ERROR, CRITICAL
  log_file: "pipeline.log"
  console_output: true