{
  "protocol": {
    "oracle": "Each scene's Option-1 Base-50 audiovisual output",
    "sample_frames": 16,
    "interpretation": "Oracle-relative metrics measure reconstruction adherence; within-option metrics measure low-NFE trajectory consistency."
  },
  "rows_vs_option1_oracle": [
    {
      "scene": "car_drift",
      "option": "option1",
      "variant": "base_25nfe",
      "label": "Base 25",
      "nfe": 25,
      "pixel_mse_mean": 0.03056679293513298,
      "psnr_db_mean": 15.732439994812012,
      "psnr_db_min": 12.823996543884277,
      "ssim_mean": 0.5719250440597534,
      "ssim_min": 0.4391680657863617,
      "motion_delta_cosine": 0.5359526480704533,
      "motion_energy_ratio_right_over_left": 0.9618323445320129,
      "audio_waveform_cosine": 0.8822316165153397,
      "audio_log_spectrum_cosine": 0.947994916404511
    },
    {
      "scene": "car_drift",
      "option": "option1",
      "variant": "base_20nfe",
      "label": "Base 20",
      "nfe": 20,
      "pixel_mse_mean": 0.032744165509939194,
      "psnr_db_mean": 15.172662734985352,
      "psnr_db_min": 12.169617652893066,
      "ssim_mean": 0.503548264503479,
      "ssim_min": 0.4049619436264038,
      "motion_delta_cosine": 0.4906416082088469,
      "motion_energy_ratio_right_over_left": 0.9170500636100769,
      "audio_waveform_cosine": 0.8585309446184185,
      "audio_log_spectrum_cosine": 0.9528011176087328
    },
    {
      "scene": "car_drift",
      "option": "option1",
      "variant": "base_15nfe",
      "label": "Base 15",
      "nfe": 15,
      "pixel_mse_mean": 0.05054790526628494,
      "psnr_db_mean": 13.241310119628906,
      "psnr_db_min": 11.657271385192871,
      "ssim_mean": 0.37954390048980713,
      "ssim_min": 0.2929634153842926,
      "motion_delta_cosine": 0.34453228925194723,
      "motion_energy_ratio_right_over_left": 0.9348943829536438,
      "audio_waveform_cosine": 0.7238307137451927,
      "audio_log_spectrum_cosine": 0.9341013725289196
    },
    {
      "scene": "car_drift",
      "option": "option1",
      "variant": "base_10nfe",
      "label": "Base 10",
      "nfe": 10,
      "pixel_mse_mean": 0.06992176175117493,
      "psnr_db_mean": 12.128948211669922,
      "psnr_db_min": 9.650999069213867,
      "ssim_mean": 0.3444794714450836,
      "ssim_min": 0.24199044704437256,
      "motion_delta_cosine": 0.14387498115439876,
      "motion_energy_ratio_right_over_left": 0.8859903216362,
      "audio_waveform_cosine": 0.6453160079684502,
      "audio_log_spectrum_cosine": 0.9239601351806691
    },
    {
      "scene": "car_drift",
      "option": "option1",
      "variant": "alibaba_pdd_8nfe",
      "label": "Alibaba PDD 8",
      "nfe": 8,
      "pixel_mse_mean": 0.06947905570268631,
      "psnr_db_mean": 11.911153793334961,
      "psnr_db_min": 10.015339851379395,
      "ssim_mean": 0.3805326223373413,
      "ssim_min": 0.2764473855495453,
      "motion_delta_cosine": 0.17248190252643622,
      "motion_energy_ratio_right_over_left": 1.0064672231674194,
      "audio_waveform_cosine": 0.8219916804235595,
      "audio_log_spectrum_cosine": 0.9326200804084621
    },
    {
      "scene": "car_drift",
      "option": "option1",
      "variant": "lightx_turbo_4nfe",
      "label": "LightX2V Turbo 4",
      "nfe": 4,
      "pixel_mse_mean": 0.1075940728187561,
      "psnr_db_mean": 9.963949203491211,
      "psnr_db_min": 8.141242027282715,
      "ssim_mean": 0.2976685166358948,
      "ssim_min": 0.199869766831398,
      "motion_delta_cosine": -0.005563072779646719,
      "motion_energy_ratio_right_over_left": 1.0449739694595337,
      "audio_waveform_cosine": 0.43145609556488423,
      "audio_log_spectrum_cosine": 0.8725122229455431
    },
    {
      "scene": "car_drift",
      "option": "option2",
      "variant": "base_50nfe",
      "label": "Base 50",
      "nfe": 50,
      "pixel_mse_mean": 0.0018456378020346165,
      "psnr_db_mean": 27.504959106445312,
      "psnr_db_min": 25.43390655517578,
      "ssim_mean": 0.8283364772796631,
      "ssim_min": 0.7463627457618713,
      "motion_delta_cosine": 0.979295973753202,
      "motion_energy_ratio_right_over_left": 1.1176725625991821,
      "audio_waveform_cosine": 0.8533491134451852,
      "audio_log_spectrum_cosine": 0.9112426615815274
    },
    {
      "scene": "car_drift",
      "option": "option2",
      "variant": "base_25nfe",
      "label": "Base 25",
      "nfe": 25,
      "pixel_mse_mean": 0.0018153947312384844,
      "psnr_db_mean": 27.618406295776367,
      "psnr_db_min": 25.317176818847656,
      "ssim_mean": 0.8244673013687134,
      "ssim_min": 0.7378547787666321,
      "motion_delta_cosine": 0.9786993043684946,
      "motion_energy_ratio_right_over_left": 1.105544090270996,
      "audio_waveform_cosine": 0.8502329578083399,
      "audio_log_spectrum_cosine": 0.9156973999249244
    },
    {
      "scene": "car_drift",
      "option": "option2",
      "variant": "base_20nfe",
      "label": "Base 20",
      "nfe": 20,
      "pixel_mse_mean": 0.0018132327822968364,
      "psnr_db_mean": 27.650997161865234,
      "psnr_db_min": 25.145877838134766,
      "ssim_mean": 0.8222965598106384,
      "ssim_min": 0.7291641235351562,
      "motion_delta_cosine": 0.9781528287418514,
      "motion_energy_ratio_right_over_left": 1.0984790325164795,
      "audio_waveform_cosine": 0.8472030800684701,
      "audio_log_spectrum_cosine": 0.9166814786784201
    },
    {
      "scene": "car_drift",
      "option": "option2",
      "variant": "base_15nfe",
      "label": "Base 15",
      "nfe": 15,
      "pixel_mse_mean": 0.001822600606828928,
      "psnr_db_mean": 27.655517578125,
      "psnr_db_min": 24.957439422607422,
      "ssim_mean": 0.82127845287323,
      "ssim_min": 0.7270830273628235,
      "motion_delta_cosine": 0.977337635905505,
      "motion_energy_ratio_right_over_left": 1.090334177017212,
      "audio_waveform_cosine": 0.8410354123954369,
      "audio_log_spectrum_cosine": 0.9177918201794234
    },
    {
      "scene": "car_drift",
      "option": "option2",
      "variant": "base_10nfe",
      "label": "Base 10",
      "nfe": 10,
      "pixel_mse_mean": 0.0018679398344829679,
      "psnr_db_mean": 27.57773208618164,
      "psnr_db_min": 24.785552978515625,
      "ssim_mean": 0.81769859790802,
      "ssim_min": 0.7192835211753845,
      "motion_delta_cosine": 0.9759297218253045,
      "motion_energy_ratio_right_over_left": 1.0797978639602661,
      "audio_waveform_cosine": 0.8280527800122176,
      "audio_log_spectrum_cosine": 0.9178043334104539
    },
    {
      "scene": "car_drift",
      "option": "option2",
      "variant": "alibaba_pdd_8nfe",
      "label": "Alibaba PDD 8",
      "nfe": 8,
      "pixel_mse_mean": 0.0019249831093475223,
      "psnr_db_mean": 27.392824172973633,
      "psnr_db_min": 24.780609130859375,
      "ssim_mean": 0.8157745599746704,
      "ssim_min": 0.7228761315345764,
      "motion_delta_cosine": 0.9777372357368557,
      "motion_energy_ratio_right_over_left": 1.1061314344406128,
      "audio_waveform_cosine": 0.8173883730444477,
      "audio_log_spectrum_cosine": 0.9221568279094919
    },
    {
      "scene": "car_drift",
      "option": "option2",
      "variant": "lightx_turbo_4nfe",
      "label": "LightX2V Turbo 4",
      "nfe": 4,
      "pixel_mse_mean": 0.028721371665596962,
      "psnr_db_mean": 17.205333709716797,
      "psnr_db_min": 11.006103515625,
      "ssim_mean": 0.5568569898605347,
      "ssim_min": 0.3531404435634613,
      "motion_delta_cosine": 0.529365240805502,
      "motion_energy_ratio_right_over_left": 1.034543514251709,
      "audio_waveform_cosine": 0.7923379055478821,
      "audio_log_spectrum_cosine": 0.9196274409793617
    },
    {
      "scene": "desert_observatory",
      "option": "option1",
      "variant": "base_25nfe",
      "label": "Base 25",
      "nfe": 25,
      "pixel_mse_mean": 0.0023452909663319588,
      "psnr_db_mean": 26.606433868408203,
      "psnr_db_min": 23.418750762939453,
      "ssim_mean": 0.8262913227081299,
      "ssim_min": 0.7511611580848694,
      "motion_delta_cosine": 0.7195377965148275,
      "motion_energy_ratio_right_over_left": 1.0016645193099976,
      "audio_waveform_cosine": 0.8957697019168636,
      "audio_log_spectrum_cosine": 0.9567942989456991
    },
    {
      "scene": "desert_observatory",
      "option": "option1",
      "variant": "base_20nfe",
      "label": "Base 20",
      "nfe": 20,
      "pixel_mse_mean": 0.002842585789039731,
      "psnr_db_mean": 25.63969612121582,
      "psnr_db_min": 23.40119171142578,
      "ssim_mean": 0.8015527129173279,
      "ssim_min": 0.7456281185150146,
      "motion_delta_cosine": 0.6695841781751989,
      "motion_energy_ratio_right_over_left": 0.9995855093002319,
      "audio_waveform_cosine": 0.8134245865201948,
      "audio_log_spectrum_cosine": 0.943559175713588
    },
    {
      "scene": "desert_observatory",
      "option": "option1",
      "variant": "base_15nfe",
      "label": "Base 15",
      "nfe": 15,
      "pixel_mse_mean": 0.002942632418125868,
      "psnr_db_mean": 25.567264556884766,
      "psnr_db_min": 23.30185890197754,
      "ssim_mean": 0.8057519197463989,
      "ssim_min": 0.7534060478210449,
      "motion_delta_cosine": 0.6220148725642158,
      "motion_energy_ratio_right_over_left": 0.9412403702735901,
      "audio_waveform_cosine": 0.8533099635146477,
      "audio_log_spectrum_cosine": 0.9561662519891593
    },
    {
      "scene": "desert_observatory",
      "option": "option1",
      "variant": "base_10nfe",
      "label": "Base 10",
      "nfe": 10,
      "pixel_mse_mean": 0.0035548892337828875,
      "psnr_db_mean": 24.79360580444336,
      "psnr_db_min": 23.156959533691406,
      "ssim_mean": 0.7818913459777832,
      "ssim_min": 0.7278749942779541,
      "motion_delta_cosine": 0.5418805703456274,
      "motion_energy_ratio_right_over_left": 0.9123114943504333,
      "audio_waveform_cosine": 0.5733368818346539,
      "audio_log_spectrum_cosine": 0.8966554522912287
    },
    {
      "scene": "desert_observatory",
      "option": "option1",
      "variant": "alibaba_pdd_8nfe",
      "label": "Alibaba PDD 8",
      "nfe": 8,
      "pixel_mse_mean": 0.004391529597342014,
      "psnr_db_mean": 23.734195709228516,
      "psnr_db_min": 22.31060028076172,
      "ssim_mean": 0.7553485035896301,
      "ssim_min": 0.7137834429740906,
      "motion_delta_cosine": 0.4781023762085052,
      "motion_energy_ratio_right_over_left": 0.9298186302185059,
      "audio_waveform_cosine": 0.793359173554984,
      "audio_log_spectrum_cosine": 0.9186183045504354
    },
    {
      "scene": "desert_observatory",
      "option": "option1",
      "variant": "lightx_turbo_4nfe",
      "label": "LightX2V Turbo 4",
      "nfe": 4,
      "pixel_mse_mean": 0.024838779121637344,
      "psnr_db_mean": 16.10015106201172,
      "psnr_db_min": 15.291257858276367,
      "ssim_mean": 0.5152208805084229,
      "ssim_min": 0.5025994181632996,
      "motion_delta_cosine": 0.00819057950891805,
      "motion_energy_ratio_right_over_left": 2.091298818588257,
      "audio_waveform_cosine": 0.13763523847236667,
      "audio_log_spectrum_cosine": 0.6530958409092313
    },
    {
      "scene": "desert_observatory",
      "option": "option2",
      "variant": "base_50nfe",
      "label": "Base 50",
      "nfe": 50,
      "pixel_mse_mean": 0.00048004655400291085,
      "psnr_db_mean": 33.23858642578125,
      "psnr_db_min": 31.211864471435547,
      "ssim_mean": 0.9237919449806213,
      "ssim_min": 0.9037051796913147,
      "motion_delta_cosine": 0.9636714794036157,
      "motion_energy_ratio_right_over_left": 1.0937379598617554,
      "audio_waveform_cosine": 0.7327961161235571,
      "audio_log_spectrum_cosine": 0.8944993489090216
    },
    {
      "scene": "desert_observatory",
      "option": "option2",
      "variant": "base_25nfe",
      "label": "Base 25",
      "nfe": 25,
      "pixel_mse_mean": 0.00046897114953026175,
      "psnr_db_mean": 33.348777770996094,
      "psnr_db_min": 31.133220672607422,
      "ssim_mean": 0.9241713285446167,
      "ssim_min": 0.901924192905426,
      "motion_delta_cosine": 0.9637887185547814,
      "motion_energy_ratio_right_over_left": 1.0850186347961426,
      "audio_waveform_cosine": 0.7393157933234848,
      "audio_log_spectrum_cosine": 0.8982141246068063
    },
    {
      "scene": "desert_observatory",
      "option": "option2",
      "variant": "base_20nfe",
      "label": "Base 20",
      "nfe": 20,
      "pixel_mse_mean": 0.00046762090642005205,
      "psnr_db_mean": 33.36248016357422,
      "psnr_db_min": 31.09175682067871,
      "ssim_mean": 0.9234410524368286,
      "ssim_min": 0.8989851474761963,
      "motion_delta_cosine": 0.9631428151146145,
      "motion_energy_ratio_right_over_left": 1.0835517644882202,
      "audio_waveform_cosine": 0.7436985168602224,
      "audio_log_spectrum_cosine": 0.9021690136995468
    },
    {
      "scene": "desert_observatory",
      "option": "option2",
      "variant": "base_15nfe",
      "label": "Base 15",
      "nfe": 15,
      "pixel_mse_mean": 0.000466941564809531,
      "psnr_db_mean": 33.36954879760742,
      "psnr_db_min": 31.11880111694336,
      "ssim_mean": 0.9230095148086548,
      "ssim_min": 0.8996796607971191,
      "motion_delta_cosine": 0.9628628282401892,
      "motion_energy_ratio_right_over_left": 1.078690528869629,
      "audio_waveform_cosine": 0.7369217402304636,
      "audio_log_spectrum_cosine": 0.9050169501281284
    },
    {
      "scene": "desert_observatory",
      "option": "option2",
      "variant": "base_10nfe",
      "label": "Base 10",
      "nfe": 10,
      "pixel_mse_mean": 0.00047420011833310127,
      "psnr_db_mean": 33.30785369873047,
      "psnr_db_min": 31.081966400146484,
      "ssim_mean": 0.9220978617668152,
      "ssim_min": 0.8981773257255554,
      "motion_delta_cosine": 0.9604529537358298,
      "motion_energy_ratio_right_over_left": 1.0647106170654297,
      "audio_waveform_cosine": 0.7012193092915889,
      "audio_log_spectrum_cosine": 0.9025573721676666
    },
    {
      "scene": "desert_observatory",
      "option": "option2",
      "variant": "alibaba_pdd_8nfe",
      "label": "Alibaba PDD 8",
      "nfe": 8,
      "pixel_mse_mean": 0.00047633799840696156,
      "psnr_db_mean": 33.29010009765625,
      "psnr_db_min": 30.849714279174805,
      "ssim_mean": 0.9227285385131836,
      "ssim_min": 0.8962640762329102,
      "motion_delta_cosine": 0.9625017676741647,
      "motion_energy_ratio_right_over_left": 1.0738049745559692,
      "audio_waveform_cosine": 0.6911181622111507,
      "audio_log_spectrum_cosine": 0.9087592076109895
    },
    {
      "scene": "desert_observatory",
      "option": "option2",
      "variant": "lightx_turbo_4nfe",
      "label": "LightX2V Turbo 4",
      "nfe": 4,
      "pixel_mse_mean": 0.023832807317376137,
      "psnr_db_mean": 16.245616912841797,
      "psnr_db_min": 15.570562362670898,
      "ssim_mean": 0.5032937526702881,
      "ssim_min": 0.4805563688278198,
      "motion_delta_cosine": 0.004348951691830817,
      "motion_energy_ratio_right_over_left": 1.715761423110962,
      "audio_waveform_cosine": 0.6817673738662553,
      "audio_log_spectrum_cosine": 0.9217231908580823
    }
  ],
  "rows_vs_own_option_base50": [
    {
      "scene": "car_drift",
      "option": "option1",
      "variant": "base_25nfe",
      "label": "Base 25",
      "nfe": 25,
      "pixel_mse_mean": 0.03056679293513298,
      "psnr_db_mean": 15.732439994812012,
      "psnr_db_min": 12.823996543884277,
      "ssim_mean": 0.5719250440597534,
      "ssim_min": 0.4391680657863617,
      "motion_delta_cosine": 0.5359526480704533,
      "motion_energy_ratio_right_over_left": 0.9618323445320129,
      "audio_waveform_cosine": 0.8822316165153397,
      "audio_log_spectrum_cosine": 0.947994916404511
    },
    {
      "scene": "car_drift",
      "option": "option1",
      "variant": "base_20nfe",
      "label": "Base 20",
      "nfe": 20,
      "pixel_mse_mean": 0.032744165509939194,
      "psnr_db_mean": 15.172662734985352,
      "psnr_db_min": 12.169617652893066,
      "ssim_mean": 0.503548264503479,
      "ssim_min": 0.4049619436264038,
      "motion_delta_cosine": 0.4906416082088469,
      "motion_energy_ratio_right_over_left": 0.9170500636100769,
      "audio_waveform_cosine": 0.8585309446184185,
      "audio_log_spectrum_cosine": 0.9528011176087328
    },
    {
      "scene": "car_drift",
      "option": "option1",
      "variant": "base_15nfe",
      "label": "Base 15",
      "nfe": 15,
      "pixel_mse_mean": 0.05054790526628494,
      "psnr_db_mean": 13.241310119628906,
      "psnr_db_min": 11.657271385192871,
      "ssim_mean": 0.37954390048980713,
      "ssim_min": 0.2929634153842926,
      "motion_delta_cosine": 0.34453228925194723,
      "motion_energy_ratio_right_over_left": 0.9348943829536438,
      "audio_waveform_cosine": 0.7238307137451927,
      "audio_log_spectrum_cosine": 0.9341013725289196
    },
    {
      "scene": "car_drift",
      "option": "option1",
      "variant": "base_10nfe",
      "label": "Base 10",
      "nfe": 10,
      "pixel_mse_mean": 0.06992176175117493,
      "psnr_db_mean": 12.128948211669922,
      "psnr_db_min": 9.650999069213867,
      "ssim_mean": 0.3444794714450836,
      "ssim_min": 0.24199044704437256,
      "motion_delta_cosine": 0.14387498115439876,
      "motion_energy_ratio_right_over_left": 0.8859903216362,
      "audio_waveform_cosine": 0.6453160079684502,
      "audio_log_spectrum_cosine": 0.9239601351806691
    },
    {
      "scene": "car_drift",
      "option": "option1",
      "variant": "alibaba_pdd_8nfe",
      "label": "Alibaba PDD 8",
      "nfe": 8,
      "pixel_mse_mean": 0.06947905570268631,
      "psnr_db_mean": 11.911153793334961,
      "psnr_db_min": 10.015339851379395,
      "ssim_mean": 0.3805326223373413,
      "ssim_min": 0.2764473855495453,
      "motion_delta_cosine": 0.17248190252643622,
      "motion_energy_ratio_right_over_left": 1.0064672231674194,
      "audio_waveform_cosine": 0.8219916804235595,
      "audio_log_spectrum_cosine": 0.9326200804084621
    },
    {
      "scene": "car_drift",
      "option": "option1",
      "variant": "lightx_turbo_4nfe",
      "label": "LightX2V Turbo 4",
      "nfe": 4,
      "pixel_mse_mean": 0.1075940728187561,
      "psnr_db_mean": 9.963949203491211,
      "psnr_db_min": 8.141242027282715,
      "ssim_mean": 0.2976685166358948,
      "ssim_min": 0.199869766831398,
      "motion_delta_cosine": -0.005563072779646719,
      "motion_energy_ratio_right_over_left": 1.0449739694595337,
      "audio_waveform_cosine": 0.43145609556488423,
      "audio_log_spectrum_cosine": 0.8725122229455431
    },
    {
      "scene": "car_drift",
      "option": "option2",
      "variant": "base_25nfe",
      "label": "Base 25",
      "nfe": 25,
      "pixel_mse_mean": 0.0004596885701175779,
      "psnr_db_mean": 33.699249267578125,
      "psnr_db_min": 31.15068817138672,
      "ssim_mean": 0.9435122013092041,
      "ssim_min": 0.9222173094749451,
      "motion_delta_cosine": 0.9940005865329422,
      "motion_energy_ratio_right_over_left": 0.9891484379768372,
      "audio_waveform_cosine": 0.9903262053777798,
      "audio_log_spectrum_cosine": 0.9831404949810343
    },
    {
      "scene": "car_drift",
      "option": "option2",
      "variant": "base_20nfe",
      "label": "Base 20",
      "nfe": 20,
      "pixel_mse_mean": 0.0005940045812167227,
      "psnr_db_mean": 32.64128875732422,
      "psnr_db_min": 29.85171127319336,
      "ssim_mean": 0.9364117383956909,
      "ssim_min": 0.9137483239173889,
      "motion_delta_cosine": 0.992269848395309,
      "motion_energy_ratio_right_over_left": 0.9828271865844727,
      "audio_waveform_cosine": 0.9862774395171119,
      "audio_log_spectrum_cosine": 0.9782006326927905
    },
    {
      "scene": "car_drift",
      "option": "option2",
      "variant": "base_15nfe",
      "label": "Base 15",
      "nfe": 15,
      "pixel_mse_mean": 0.0007716247346252203,
      "psnr_db_mean": 31.56351089477539,
      "psnr_db_min": 28.62004280090332,
      "ssim_mean": 0.9275526404380798,
      "ssim_min": 0.8958634734153748,
      "motion_delta_cosine": 0.9900251102746229,
      "motion_energy_ratio_right_over_left": 0.9755399227142334,
      "audio_waveform_cosine": 0.9776027462816659,
      "audio_log_spectrum_cosine": 0.9722467422520497
    },
    {
      "scene": "car_drift",
      "option": "option2",
      "variant": "base_10nfe",
      "label": "Base 10",
      "nfe": 10,
      "pixel_mse_mean": 0.0009878069395199418,
      "psnr_db_mean": 30.485807418823242,
      "psnr_db_min": 27.616464614868164,
      "ssim_mean": 0.918023943901062,
      "ssim_min": 0.8862035274505615,
      "motion_delta_cosine": 0.9874024002746402,
      "motion_energy_ratio_right_over_left": 0.9661128520965576,
      "audio_waveform_cosine": 0.9613284601609955,
      "audio_log_spectrum_cosine": 0.9632412960242953
    },
    {
      "scene": "car_drift",
      "option": "option2",
      "variant": "alibaba_pdd_8nfe",
      "label": "Alibaba PDD 8",
      "nfe": 8,
      "pixel_mse_mean": 0.0006562302587553859,
      "psnr_db_mean": 32.175018310546875,
      "psnr_db_min": 29.488943099975586,
      "ssim_mean": 0.9347877502441406,
      "ssim_min": 0.9086576104164124,
      "motion_delta_cosine": 0.9916069306148135,
      "motion_energy_ratio_right_over_left": 0.989673912525177,
      "audio_waveform_cosine": 0.8909724437950287,
      "audio_log_spectrum_cosine": 0.939375426309443
    },
    {
      "scene": "car_drift",
      "option": "option2",
      "variant": "lightx_turbo_4nfe",
      "label": "LightX2V Turbo 4",
      "nfe": 4,
      "pixel_mse_mean": 0.03176625818014145,
      "psnr_db_mean": 16.67728614807129,
      "psnr_db_min": 10.655765533447266,
      "ssim_mean": 0.5796858072280884,
      "ssim_min": 0.3674028217792511,
      "motion_delta_cosine": 0.5266651518694025,
      "motion_energy_ratio_right_over_left": 0.9256230592727661,
      "audio_waveform_cosine": 0.8780403690076444,
      "audio_log_spectrum_cosine": 0.9343275306080243
    },
    {
      "scene": "desert_observatory",
      "option": "option1",
      "variant": "base_25nfe",
      "label": "Base 25",
      "nfe": 25,
      "pixel_mse_mean": 0.0023452909663319588,
      "psnr_db_mean": 26.606433868408203,
      "psnr_db_min": 23.418750762939453,
      "ssim_mean": 0.8262913227081299,
      "ssim_min": 0.7511611580848694,
      "motion_delta_cosine": 0.7195377965148275,
      "motion_energy_ratio_right_over_left": 1.0016645193099976,
      "audio_waveform_cosine": 0.8957697019168636,
      "audio_log_spectrum_cosine": 0.9567942989456991
    },
    {
      "scene": "desert_observatory",
      "option": "option1",
      "variant": "base_20nfe",
      "label": "Base 20",
      "nfe": 20,
      "pixel_mse_mean": 0.002842585789039731,
      "psnr_db_mean": 25.63969612121582,
      "psnr_db_min": 23.40119171142578,
      "ssim_mean": 0.8015527129173279,
      "ssim_min": 0.7456281185150146,
      "motion_delta_cosine": 0.6695841781751989,
      "motion_energy_ratio_right_over_left": 0.9995855093002319,
      "audio_waveform_cosine": 0.8134245865201948,
      "audio_log_spectrum_cosine": 0.943559175713588
    },
    {
      "scene": "desert_observatory",
      "option": "option1",
      "variant": "base_15nfe",
      "label": "Base 15",
      "nfe": 15,
      "pixel_mse_mean": 0.002942632418125868,
      "psnr_db_mean": 25.567264556884766,
      "psnr_db_min": 23.30185890197754,
      "ssim_mean": 0.8057519197463989,
      "ssim_min": 0.7534060478210449,
      "motion_delta_cosine": 0.6220148725642158,
      "motion_energy_ratio_right_over_left": 0.9412403702735901,
      "audio_waveform_cosine": 0.8533099635146477,
      "audio_log_spectrum_cosine": 0.9561662519891593
    },
    {
      "scene": "desert_observatory",
      "option": "option1",
      "variant": "base_10nfe",
      "label": "Base 10",
      "nfe": 10,
      "pixel_mse_mean": 0.0035548892337828875,
      "psnr_db_mean": 24.79360580444336,
      "psnr_db_min": 23.156959533691406,
      "ssim_mean": 0.7818913459777832,
      "ssim_min": 0.7278749942779541,
      "motion_delta_cosine": 0.5418805703456274,
      "motion_energy_ratio_right_over_left": 0.9123114943504333,
      "audio_waveform_cosine": 0.5733368818346539,
      "audio_log_spectrum_cosine": 0.8966554522912287
    },
    {
      "scene": "desert_observatory",
      "option": "option1",
      "variant": "alibaba_pdd_8nfe",
      "label": "Alibaba PDD 8",
      "nfe": 8,
      "pixel_mse_mean": 0.004391529597342014,
      "psnr_db_mean": 23.734195709228516,
      "psnr_db_min": 22.31060028076172,
      "ssim_mean": 0.7553485035896301,
      "ssim_min": 0.7137834429740906,
      "motion_delta_cosine": 0.4781023762085052,
      "motion_energy_ratio_right_over_left": 0.9298186302185059,
      "audio_waveform_cosine": 0.793359173554984,
      "audio_log_spectrum_cosine": 0.9186183045504354
    },
    {
      "scene": "desert_observatory",
      "option": "option1",
      "variant": "lightx_turbo_4nfe",
      "label": "LightX2V Turbo 4",
      "nfe": 4,
      "pixel_mse_mean": 0.024838779121637344,
      "psnr_db_mean": 16.10015106201172,
      "psnr_db_min": 15.291257858276367,
      "ssim_mean": 0.5152208805084229,
      "ssim_min": 0.5025994181632996,
      "motion_delta_cosine": 0.00819057950891805,
      "motion_energy_ratio_right_over_left": 2.091298818588257,
      "audio_waveform_cosine": 0.13763523847236667,
      "audio_log_spectrum_cosine": 0.6530958409092313
    },
    {
      "scene": "desert_observatory",
      "option": "option2",
      "variant": "base_25nfe",
      "label": "Base 25",
      "nfe": 25,
      "pixel_mse_mean": 9.585509542375803e-05,
      "psnr_db_mean": 40.20443344116211,
      "psnr_db_min": 39.344425201416016,
      "ssim_mean": 0.969811201095581,
      "ssim_min": 0.9648110270500183,
      "motion_delta_cosine": 0.9881585342313233,
      "motion_energy_ratio_right_over_left": 0.9920279383659363,
      "audio_waveform_cosine": 0.9761036283957878,
      "audio_log_spectrum_cosine": 0.9914665845196144
    },
    {
      "scene": "desert_observatory",
      "option": "option2",
      "variant": "base_20nfe",
      "label": "Base 20",
      "nfe": 20,
      "pixel_mse_mean": 0.00011248183000134304,
      "psnr_db_mean": 39.52902603149414,
      "psnr_db_min": 38.098480224609375,
      "ssim_mean": 0.9672338366508484,
      "ssim_min": 0.9582810401916504,
      "motion_delta_cosine": 0.9860576828276261,
      "motion_energy_ratio_right_over_left": 0.9906867146492004,
      "audio_waveform_cosine": 0.9715660320736218,
      "audio_log_spectrum_cosine": 0.9893321420293751
    },
    {
      "scene": "desert_observatory",
      "option": "option2",
      "variant": "base_15nfe",
      "label": "Base 15",
      "nfe": 15,
      "pixel_mse_mean": 0.00012451267684809864,
      "psnr_db_mean": 39.07453155517578,
      "psnr_db_min": 38.12992858886719,
      "ssim_mean": 0.9658992290496826,
      "ssim_min": 0.9598919749259949,
      "motion_delta_cosine": 0.9853092599688421,
      "motion_energy_ratio_right_over_left": 0.9862421751022339,
      "audio_waveform_cosine": 0.9476482136111682,
      "audio_log_spectrum_cosine": 0.9811335975911727
    },
    {
      "scene": "desert_observatory",
      "option": "option2",
      "variant": "base_10nfe",
      "label": "Base 10",
      "nfe": 10,
      "pixel_mse_mean": 0.00015436706598848104,
      "psnr_db_mean": 38.151222229003906,
      "psnr_db_min": 37.24544143676758,
      "ssim_mean": 0.9628835916519165,
      "ssim_min": 0.9566957354545593,
      "motion_delta_cosine": 0.9824691765110909,
      "motion_energy_ratio_right_over_left": 0.9734604358673096,
      "audio_waveform_cosine": 0.9021341128068574,
      "audio_log_spectrum_cosine": 0.967509431404421
    },
    {
      "scene": "desert_observatory",
      "option": "option2",
      "variant": "alibaba_pdd_8nfe",
      "label": "Alibaba PDD 8",
      "nfe": 8,
      "pixel_mse_mean": 0.000137325405376032,
      "psnr_db_mean": 38.6449089050293,
      "psnr_db_min": 37.59699249267578,
      "ssim_mean": 0.9646050930023193,
      "ssim_min": 0.9583068490028381,
      "motion_delta_cosine": 0.9843310855814316,
      "motion_energy_ratio_right_over_left": 0.9817754030227661,
      "audio_waveform_cosine": 0.8133331287379209,
      "audio_log_spectrum_cosine": 0.9441848137441067
    },
    {
      "scene": "desert_observatory",
      "option": "option2",
      "variant": "lightx_turbo_4nfe",
      "label": "LightX2V Turbo 4",
      "nfe": 4,
      "pixel_mse_mean": 0.025205830112099648,
      "psnr_db_mean": 16.00212860107422,
      "psnr_db_min": 15.339461326599121,
      "ssim_mean": 0.4821704626083374,
      "ssim_min": 0.46132221817970276,
      "motion_delta_cosine": 0.00396359755223561,
      "motion_energy_ratio_right_over_left": 1.5687134265899658,
      "audio_waveform_cosine": 0.7632400083841149,
      "audio_log_spectrum_cosine": 0.914789211241657
    }
  ],
  "paired_option2_minus_option1": [
    {
      "scene": "car_drift",
      "variant": "base_25nfe",
      "label": "Base 25",
      "nfe": 25,
      "option1_psnr_db_mean": 15.732439994812012,
      "option1_ssim_mean": 0.5719250440597534,
      "option1_motion_delta_cosine": 0.5359526480704533,
      "option1_motion_energy_ratio_right_over_left": 0.9618323445320129,
      "option1_audio_waveform_cosine": 0.8822316165153397,
      "option1_audio_log_spectrum_cosine": 0.947994916404511,
      "option2_psnr_db_mean": 27.618406295776367,
      "option2_ssim_mean": 0.8244673013687134,
      "option2_motion_delta_cosine": 0.9786993043684946,
      "option2_motion_energy_ratio_right_over_left": 1.105544090270996,
      "option2_audio_waveform_cosine": 0.8502329578083399,
      "option2_audio_log_spectrum_cosine": 0.9156973999249244,
      "gain_psnr_db_mean": 11.885966300964355,
      "gain_ssim_mean": 0.25254225730895996,
      "gain_motion_delta_cosine": 0.44274665629804133,
      "gain_motion_energy_ratio_right_over_left": 0.14371174573898315,
      "gain_audio_waveform_cosine": -0.031998658706999805,
      "gain_audio_log_spectrum_cosine": -0.03229751647958656
    },
    {
      "scene": "car_drift",
      "variant": "base_20nfe",
      "label": "Base 20",
      "nfe": 20,
      "option1_psnr_db_mean": 15.172662734985352,
      "option1_ssim_mean": 0.503548264503479,
      "option1_motion_delta_cosine": 0.4906416082088469,
      "option1_motion_energy_ratio_right_over_left": 0.9170500636100769,
      "option1_audio_waveform_cosine": 0.8585309446184185,
      "option1_audio_log_spectrum_cosine": 0.9528011176087328,
      "option2_psnr_db_mean": 27.650997161865234,
      "option2_ssim_mean": 0.8222965598106384,
      "option2_motion_delta_cosine": 0.9781528287418514,
      "option2_motion_energy_ratio_right_over_left": 1.0984790325164795,
      "option2_audio_waveform_cosine": 0.8472030800684701,
      "option2_audio_log_spectrum_cosine": 0.9166814786784201,
      "gain_psnr_db_mean": 12.478334426879883,
      "gain_ssim_mean": 0.3187482953071594,
      "gain_motion_delta_cosine": 0.4875112205330045,
      "gain_motion_energy_ratio_right_over_left": 0.1814289689064026,
      "gain_audio_waveform_cosine": -0.011327864549948385,
      "gain_audio_log_spectrum_cosine": -0.03611963893031267
    },
    {
      "scene": "car_drift",
      "variant": "base_15nfe",
      "label": "Base 15",
      "nfe": 15,
      "option1_psnr_db_mean": 13.241310119628906,
      "option1_ssim_mean": 0.37954390048980713,
      "option1_motion_delta_cosine": 0.34453228925194723,
      "option1_motion_energy_ratio_right_over_left": 0.9348943829536438,
      "option1_audio_waveform_cosine": 0.7238307137451927,
      "option1_audio_log_spectrum_cosine": 0.9341013725289196,
      "option2_psnr_db_mean": 27.655517578125,
      "option2_ssim_mean": 0.82127845287323,
      "option2_motion_delta_cosine": 0.977337635905505,
      "option2_motion_energy_ratio_right_over_left": 1.090334177017212,
      "option2_audio_waveform_cosine": 0.8410354123954369,
      "option2_audio_log_spectrum_cosine": 0.9177918201794234,
      "gain_psnr_db_mean": 14.414207458496094,
      "gain_ssim_mean": 0.44173455238342285,
      "gain_motion_delta_cosine": 0.6328053466535578,
      "gain_motion_energy_ratio_right_over_left": 0.15543979406356812,
      "gain_audio_waveform_cosine": 0.11720469865024419,
      "gain_audio_log_spectrum_cosine": -0.01630955234949616
    },
    {
      "scene": "car_drift",
      "variant": "base_10nfe",
      "label": "Base 10",
      "nfe": 10,
      "option1_psnr_db_mean": 12.128948211669922,
      "option1_ssim_mean": 0.3444794714450836,
      "option1_motion_delta_cosine": 0.14387498115439876,
      "option1_motion_energy_ratio_right_over_left": 0.8859903216362,
      "option1_audio_waveform_cosine": 0.6453160079684502,
      "option1_audio_log_spectrum_cosine": 0.9239601351806691,
      "option2_psnr_db_mean": 27.57773208618164,
      "option2_ssim_mean": 0.81769859790802,
      "option2_motion_delta_cosine": 0.9759297218253045,
      "option2_motion_energy_ratio_right_over_left": 1.0797978639602661,
      "option2_audio_waveform_cosine": 0.8280527800122176,
      "option2_audio_log_spectrum_cosine": 0.9178043334104539,
      "gain_psnr_db_mean": 15.448783874511719,
      "gain_ssim_mean": 0.4732191264629364,
      "gain_motion_delta_cosine": 0.8320547406709057,
      "gain_motion_energy_ratio_right_over_left": 0.19380754232406616,
      "gain_audio_waveform_cosine": 0.18273677204376737,
      "gain_audio_log_spectrum_cosine": -0.006155801770215241
    },
    {
      "scene": "car_drift",
      "variant": "alibaba_pdd_8nfe",
      "label": "Alibaba PDD 8",
      "nfe": 8,
      "option1_psnr_db_mean": 11.911153793334961,
      "option1_ssim_mean": 0.3805326223373413,
      "option1_motion_delta_cosine": 0.17248190252643622,
      "option1_motion_energy_ratio_right_over_left": 1.0064672231674194,
      "option1_audio_waveform_cosine": 0.8219916804235595,
      "option1_audio_log_spectrum_cosine": 0.9326200804084621,
      "option2_psnr_db_mean": 27.392824172973633,
      "option2_ssim_mean": 0.8157745599746704,
      "option2_motion_delta_cosine": 0.9777372357368557,
      "option2_motion_energy_ratio_right_over_left": 1.1061314344406128,
      "option2_audio_waveform_cosine": 0.8173883730444477,
      "option2_audio_log_spectrum_cosine": 0.9221568279094919,
      "gain_psnr_db_mean": 15.481670379638672,
      "gain_ssim_mean": 0.4352419376373291,
      "gain_motion_delta_cosine": 0.8052553332104194,
      "gain_motion_energy_ratio_right_over_left": 0.09966421127319336,
      "gain_audio_waveform_cosine": -0.004603307379111854,
      "gain_audio_log_spectrum_cosine": -0.010463252498970177
    },
    {
      "scene": "car_drift",
      "variant": "lightx_turbo_4nfe",
      "label": "LightX2V Turbo 4",
      "nfe": 4,
      "option1_psnr_db_mean": 9.963949203491211,
      "option1_ssim_mean": 0.2976685166358948,
      "option1_motion_delta_cosine": -0.005563072779646719,
      "option1_motion_energy_ratio_right_over_left": 1.0449739694595337,
      "option1_audio_waveform_cosine": 0.43145609556488423,
      "option1_audio_log_spectrum_cosine": 0.8725122229455431,
      "option2_psnr_db_mean": 17.205333709716797,
      "option2_ssim_mean": 0.5568569898605347,
      "option2_motion_delta_cosine": 0.529365240805502,
      "option2_motion_energy_ratio_right_over_left": 1.034543514251709,
      "option2_audio_waveform_cosine": 0.7923379055478821,
      "option2_audio_log_spectrum_cosine": 0.9196274409793617,
      "gain_psnr_db_mean": 7.241384506225586,
      "gain_ssim_mean": 0.2591884732246399,
      "gain_motion_delta_cosine": 0.5349283135851487,
      "gain_motion_energy_ratio_right_over_left": -0.010430455207824707,
      "gain_audio_waveform_cosine": 0.36088180998299785,
      "gain_audio_log_spectrum_cosine": 0.04711521803381857
    },
    {
      "scene": "desert_observatory",
      "variant": "base_25nfe",
      "label": "Base 25",
      "nfe": 25,
      "option1_psnr_db_mean": 26.606433868408203,
      "option1_ssim_mean": 0.8262913227081299,
      "option1_motion_delta_cosine": 0.7195377965148275,
      "option1_motion_energy_ratio_right_over_left": 1.0016645193099976,
      "option1_audio_waveform_cosine": 0.8957697019168636,
      "option1_audio_log_spectrum_cosine": 0.9567942989456991,
      "option2_psnr_db_mean": 33.348777770996094,
      "option2_ssim_mean": 0.9241713285446167,
      "option2_motion_delta_cosine": 0.9637887185547814,
      "option2_motion_energy_ratio_right_over_left": 1.0850186347961426,
      "option2_audio_waveform_cosine": 0.7393157933234848,
      "option2_audio_log_spectrum_cosine": 0.8982141246068063,
      "gain_psnr_db_mean": 6.742343902587891,
      "gain_ssim_mean": 0.09788000583648682,
      "gain_motion_delta_cosine": 0.2442509220399539,
      "gain_motion_energy_ratio_right_over_left": 0.08335411548614502,
      "gain_audio_waveform_cosine": -0.1564539085933787,
      "gain_audio_log_spectrum_cosine": -0.05858017433889284
    },
    {
      "scene": "desert_observatory",
      "variant": "base_20nfe",
      "label": "Base 20",
      "nfe": 20,
      "option1_psnr_db_mean": 25.63969612121582,
      "option1_ssim_mean": 0.8015527129173279,
      "option1_motion_delta_cosine": 0.6695841781751989,
      "option1_motion_energy_ratio_right_over_left": 0.9995855093002319,
      "option1_audio_waveform_cosine": 0.8134245865201948,
      "option1_audio_log_spectrum_cosine": 0.943559175713588,
      "option2_psnr_db_mean": 33.36248016357422,
      "option2_ssim_mean": 0.9234410524368286,
      "option2_motion_delta_cosine": 0.9631428151146145,
      "option2_motion_energy_ratio_right_over_left": 1.0835517644882202,
      "option2_audio_waveform_cosine": 0.7436985168602224,
      "option2_audio_log_spectrum_cosine": 0.9021690136995468,
      "gain_psnr_db_mean": 7.722784042358398,
      "gain_ssim_mean": 0.12188833951950073,
      "gain_motion_delta_cosine": 0.29355863693941564,
      "gain_motion_energy_ratio_right_over_left": 0.08396625518798828,
      "gain_audio_waveform_cosine": -0.06972606965997241,
      "gain_audio_log_spectrum_cosine": -0.04139016201404122
    },
    {
      "scene": "desert_observatory",
      "variant": "base_15nfe",
      "label": "Base 15",
      "nfe": 15,
      "option1_psnr_db_mean": 25.567264556884766,
      "option1_ssim_mean": 0.8057519197463989,
      "option1_motion_delta_cosine": 0.6220148725642158,
      "option1_motion_energy_ratio_right_over_left": 0.9412403702735901,
      "option1_audio_waveform_cosine": 0.8533099635146477,
      "option1_audio_log_spectrum_cosine": 0.9561662519891593,
      "option2_psnr_db_mean": 33.36954879760742,
      "option2_ssim_mean": 0.9230095148086548,
      "option2_motion_delta_cosine": 0.9628628282401892,
      "option2_motion_energy_ratio_right_over_left": 1.078690528869629,
      "option2_audio_waveform_cosine": 0.7369217402304636,
      "option2_audio_log_spectrum_cosine": 0.9050169501281284,
      "gain_psnr_db_mean": 7.802284240722656,
      "gain_ssim_mean": 0.11725759506225586,
      "gain_motion_delta_cosine": 0.34084795567597337,
      "gain_motion_energy_ratio_right_over_left": 0.13745015859603882,
      "gain_audio_waveform_cosine": -0.11638822328418408,
      "gain_audio_log_spectrum_cosine": -0.05114930186103084
    },
    {
      "scene": "desert_observatory",
      "variant": "base_10nfe",
      "label": "Base 10",
      "nfe": 10,
      "option1_psnr_db_mean": 24.79360580444336,
      "option1_ssim_mean": 0.7818913459777832,
      "option1_motion_delta_cosine": 0.5418805703456274,
      "option1_motion_energy_ratio_right_over_left": 0.9123114943504333,
      "option1_audio_waveform_cosine": 0.5733368818346539,
      "option1_audio_log_spectrum_cosine": 0.8966554522912287,
      "option2_psnr_db_mean": 33.30785369873047,
      "option2_ssim_mean": 0.9220978617668152,
      "option2_motion_delta_cosine": 0.9604529537358298,
      "option2_motion_energy_ratio_right_over_left": 1.0647106170654297,
      "option2_audio_waveform_cosine": 0.7012193092915889,
      "option2_audio_log_spectrum_cosine": 0.9025573721676666,
      "gain_psnr_db_mean": 8.51424789428711,
      "gain_ssim_mean": 0.14020651578903198,
      "gain_motion_delta_cosine": 0.4185723833902024,
      "gain_motion_energy_ratio_right_over_left": 0.15239912271499634,
      "gain_audio_waveform_cosine": 0.127882427456935,
      "gain_audio_log_spectrum_cosine": 0.0059019198764379555
    },
    {
      "scene": "desert_observatory",
      "variant": "alibaba_pdd_8nfe",
      "label": "Alibaba PDD 8",
      "nfe": 8,
      "option1_psnr_db_mean": 23.734195709228516,
      "option1_ssim_mean": 0.7553485035896301,
      "option1_motion_delta_cosine": 0.4781023762085052,
      "option1_motion_energy_ratio_right_over_left": 0.9298186302185059,
      "option1_audio_waveform_cosine": 0.793359173554984,
      "option1_audio_log_spectrum_cosine": 0.9186183045504354,
      "option2_psnr_db_mean": 33.29010009765625,
      "option2_ssim_mean": 0.9227285385131836,
      "option2_motion_delta_cosine": 0.9625017676741647,
      "option2_motion_energy_ratio_right_over_left": 1.0738049745559692,
      "option2_audio_waveform_cosine": 0.6911181622111507,
      "option2_audio_log_spectrum_cosine": 0.9087592076109895,
      "gain_psnr_db_mean": 9.555904388427734,
      "gain_ssim_mean": 0.16738003492355347,
      "gain_motion_delta_cosine": 0.4843993914656595,
      "gain_motion_energy_ratio_right_over_left": 0.14398634433746338,
      "gain_audio_waveform_cosine": -0.10224101134383323,
      "gain_audio_log_spectrum_cosine": -0.009859096939445866
    },
    {
      "scene": "desert_observatory",
      "variant": "lightx_turbo_4nfe",
      "label": "LightX2V Turbo 4",
      "nfe": 4,
      "option1_psnr_db_mean": 16.10015106201172,
      "option1_ssim_mean": 0.5152208805084229,
      "option1_motion_delta_cosine": 0.00819057950891805,
      "option1_motion_energy_ratio_right_over_left": 2.091298818588257,
      "option1_audio_waveform_cosine": 0.13763523847236667,
      "option1_audio_log_spectrum_cosine": 0.6530958409092313,
      "option2_psnr_db_mean": 16.245616912841797,
      "option2_ssim_mean": 0.5032937526702881,
      "option2_motion_delta_cosine": 0.004348951691830817,
      "option2_motion_energy_ratio_right_over_left": 1.715761423110962,
      "option2_audio_waveform_cosine": 0.6817673738662553,
      "option2_audio_log_spectrum_cosine": 0.9217231908580823,
      "gain_psnr_db_mean": 0.14546585083007812,
      "gain_ssim_mean": -0.011927127838134766,
      "gain_motion_delta_cosine": -0.003841627817087233,
      "gain_motion_energy_ratio_right_over_left": -0.3755373954772949,
      "gain_audio_waveform_cosine": 0.5441321353938886,
      "gain_audio_log_spectrum_cosine": 0.26862734994885096
    }
  ]
}
