{
  "method": "LIVE",
  "dataset": "RE10K",
  "official_repository": "https://github.com/Junchao-cs/LIVE",
  "official_commit": "5f0fe658330c64c585874acad3149aa15ba82d1b",
  "checkpoint_repository": "junchaoh-cs/LIVE-Re10K",
  "checkpoint_files": [
    "live-re10k.ckpt",
    "vae-kl16.ckpt"
  ],
  "checkpoint_global_step": 20500,
  "weight_source": "raw state_dict; verified no EMA keys",
  "vae_weight_consistency": "Every VAE inference tensor in final checkpoint equals the separate released VAE tensor exactly",
  "backbone_checkpoint_tensors": 174,
  "backbone_checkpoint_elements": 772346944,
  "backbone_parameters_verified": 772346944,
  "vae_checkpoint_tensors": 312,
  "vae_checkpoint_elements": 66456019,
  "vae_parameters_verified": 66456019,
  "optimizer_groups": [],
  "training_lr_stages": "not applicable: inference only",
  "evaluation_trainable_parameters": 0,
  "lora_or_adapters": false,
  "activation_checkpointing": false,
  "per_gpu_batch_size": 1,
  "global_parallelism": "independent per-scene workers, 8 GPUs per Berzelius node",
  "sampler": "official 18-step flow DPM, shift 3, one frame per step",
  "selector": "native contiguous latest 31 context frames + one generated frame",
  "context_noise": true,
  "kv_cache": false,
  "network_precision": "native fp16 autocast",
  "vae_precision": "fp32",
  "vae_scale": 0.2325,
  "vae_posterior": "native stochastic sample",
  "common_protocol": {
    "scene_scope": "final100 (monitor8 smoke subset)",
    "trajectory": "G0..G199,G199..G0",
    "source_stride": 1,
    "observed_frames": 100,
    "generated_frames": 300,
    "resolution": [
      256,
      256
    ],
    "camera_mapping": "DFoT normalized intrinsics plus raw world-to-camera extrinsics; native window-first normalization",
    "targets": "shared DFoT-prepared RGB decoded and preprocessed by shared/protocol.py",
    "model_inputs": "observed RGB only; future camera poses allowed, future RGB excluded",
    "output": "generated suffix only; shared saver and metric implementation"
  },
  "adaptations": [
    "Use exact shared scene manifest, RGB preprocessing and camera timeline",
    "Pass all 100 observed frames to native autoregressive sampler; preserve its 32-frame context limit",
    "Disable compilation for portable bounded smoke and evaluation",
    "Skip unused native metric models; scoring is external and common across methods",
    "Skip unused FlexAttention mask construction when official SDPA is selected",
    "Construct deterministic cycle masks on the existing buffer device; normal module device transfer moves them",
    "Normalize compiled checkpoint key prefixes and strictly load all inference tensors"
  ],
  "paper_protocol_difference": "Official paper evaluates skip 2 with one prompt frame and open rollout; common WorldMem evaluation uses skip 1, 100 observations and a closed revisit. Published scores cannot be directly compared.",
  "required_runtime": {
    "python": "3.10",
    "torch": "2.6.0+cu124",
    "lightning": "2.5.2",
    "torchmetrics": "1.7.4",
    "diffusers": "0.34.0",
    "attention": "torch SDPA efficient_attention (no xformers or FlashAttention dependency)"
  },
  "verification": {
    "official_clone": "passed",
    "both_weight_downloads": "passed",
    "checkpoint_weight_audit": "passed",
    "python_syntax": "passed",
    "setup_shell_syntax": "passed",
    "environment_install": "passed; exact released requirements plus pytorch-lightning 2.5.2 and setuptools 80.9.0",
    "production_model_preflight": "passed on CPU in dedicated env; strict load of all 486 inference tensors",
    "real_data_preflight": "passed; first monitor8 scene RGB400x3x256x256, cameras400x16, exact duplicated turnaround and closed endpoint",
    "native_sampler_boundary_check": "passed; actual 18-step sampler with a constant-flow probe preserves observed latents and matches five explicit sliding camera windows through reversal",
    "local_gpu_smoke": "root agent schedules after preflight"
  },
  "numerical_failure_policy": "Raise FloatingPointError on sampler/decoder NaN/Inf; never replace with zero frames",
  "evaluation_case_seed": "1_000_003 * metadata_index + 7 at protocol seed0; NumPy seeds modulo2**32"
}