Reliable Single-Pipeline Checkpoint
Existing A/B/C/D rank outputs are grid positions in the PhysX-Anything judge prompt, not verified method names. The current benchmark_light20 videos appear to be single-method renders judged with a grid-style schema.
Scale Error32.250lower is better
Affordance9.699proxy score
Material8.994proxy score
Description13.040proxy score
Grid-Position Results
Lower rank is better. These rows preserve judge output without treating grid labels as method names.
evaluation_kine_results
/data/250010098/PhysX-Anything/evaluation_kine_results
| Grid Label | n | Mean Geometry Rank | Mean Motion Rank | Geometry Rank-1 | Motion Rank-1 |
|---|---|---|---|---|---|
| A | 16 | 1.750 | 1.750 | 9 | 9 |
| B | 16 | 1.875 | 1.875 | 8 | 8 |
| C | 16 | 1.625 | 1.625 | 9 | 9 |
| D | 16 | 1.938 | 1.938 | 8 | 8 |
evaluation_kine_results_benchmark_light20
/data/250010098/PhysX-Anything/evaluation_kine_results_benchmark_light20
| Grid Label | n | Mean Geometry Rank | Mean Motion Rank | Geometry Rank-1 | Motion Rank-1 |
|---|---|---|---|---|---|
| A | 20 | 1.150 | 1.150 | 19 | 19 |
| B | 20 | 1.150 | 1.150 | 18 | 18 |
| C | 20 | 1.150 | 1.150 | 18 | 18 |
| D | 20 | 1.200 | 1.200 | 17 | 17 |
evaluation_kine_results_fixed
/data/250010098/PhysX-Anything/evaluation_kine_results_fixed
| Grid Label | n | Mean Geometry Rank | Mean Motion Rank | Geometry Rank-1 | Motion Rank-1 |
|---|---|---|---|---|---|
| A | 17 | 1.529 | 1.529 | 10 | 10 |
| B | 17 | 2 | 2 | 4 | 4 |
| C | 17 | 2.529 | 2.529 | 4 | 4 |
| D | 17 | 3 | 3 | 4 | 4 |
evaluation_kine_results_rerun
/data/250010098/PhysX-Anything/evaluation_kine_results_rerun
| Grid Label | n | Mean Geometry Rank | Mean Motion Rank | Geometry Rank-1 | Motion Rank-1 |
|---|---|---|---|---|---|
| A | 15 | 1.467 | 1.467 | 11 | 10 |
| B | 15 | 1.667 | 1.667 | 10 | 9 |
| C | 15 | 1.800 | 1.867 | 8 | 7 |
| D | 15 | 1.933 | 1.933 | 9 | 9 |
Evaluation Directory Inventory
| Status | Directory | JSON | Raw TXT | TXT | MP4 |
|---|---|---|---|---|---|
| rank_json_available | evaluation_kine_results | 17 | 0 | 0 | 0 |
| empty_or_not_completed | evaluation_kine_results_benchmark_completed123 | 0 | 0 | 0 | 0 |
| empty_or_not_completed | evaluation_kine_results_benchmark_full243 | 0 | 0 | 0 | 0 |
| rank_json_available | evaluation_kine_results_benchmark_light20 | 20 | 20 | 20 | 0 |
| empty_or_not_completed | evaluation_kine_results_benchmark_sharded | 0 | 0 | 0 | 0 |
| empty_or_not_completed | evaluation_kine_results_benchmark_sharded_diag | 0 | 0 | 0 | 0 |
| rank_json_available | evaluation_kine_results_fixed | 17 | 17 | 17 | 0 |
| rank_json_available | evaluation_kine_results_rerun | 17 | 0 | 0 | 0 |
| empty_or_not_completed | evaluation_phy_results_benchmark_completed123 | 0 | 0 | 0 | 0 |
| empty_or_not_completed | evaluation_phy_results_benchmark_full243 | 0 | 0 | 0 | 0 |
| text_only | evaluation_phy_results_benchmark_light20 | 0 | 0 | 1 | 0 |
| empty_or_not_completed | evaluation_phy_results_benchmark_sharded | 0 | 0 | 0 | 0 |
| empty_or_not_completed | evaluation_phy_results_benchmark_sharded_diag | 0 | 0 | 0 | 0 |
| video_only | evaluation_video | 0 | 0 | 0 | 1 |
| video_only | evaluation_video_physxanything | 0 | 0 | 0 | 17 |
| empty_or_not_completed | evaluation_video_physxanything_benchmark_completed123 | 0 | 0 | 0 | 0 |
| empty_or_not_completed | evaluation_video_physxanything_benchmark_full243 | 0 | 0 | 0 | 0 |
| video_only | evaluation_video_physxanything_benchmark_light20 | 0 | 0 | 0 | 20 |
| empty_or_not_completed | evaluation_video_physxanything_benchmark_sharded | 0 | 0 | 0 | 0 |
| empty_or_not_completed | evaluation_video_physxanything_benchmark_sharded_diag | 0 | 0 | 0 | 0 |
| video_only | evaluation_video_physxanything_rerun | 0 | 0 | 0 | 17 |
Uncertainty Notes
- Do not describe A/B/C/D as methods.
- Rank JSON directories are useful for auditing judge behavior, but are not method leaderboard entries.
- Full243/sharded benchmark directories contain no completed rank JSON in this workspace snapshot.
Required Before Method Ranking
- Recover or create a montage manifest mapping grid positions to real method names.
- Separate native/generated/manually cleaned assets according to the v0.1 metric rules.
- Keep failed samples in reports with failure cause and repair status.
Embedded Source JSON
{
"leaderboard_id": "articulated_generation_leaderboard_v0.1",
"benchmark_id": "articulated_generation_v0.1",
"generated_at_utc": "2026-05-09T03:21:13+00:00",
"sources": {
"metrics_spec": "/data/250010098/Unified_dataset/articulated_generation_benchmark/metrics/articulated_generation_metrics_v0.1.json",
"reproduced_summary_json": "/data/250010098/Unified_dataset/articulated_generation_benchmark/experiments/reproduced_method_eval_summary.json",
"reproduced_summary_md": "/data/250010098/Unified_dataset/articulated_generation_benchmark/experiments/reproduced_method_eval_summary.md",
"physx_evaluation_root": "/data/250010098/PhysX-Anything"
},
"decision": {
"method_leaderboard_status": "not_yet_reliable",
"reason": "Existing A/B/C/D rank outputs are grid positions in the PhysX-Anything judge prompt, not verified method names. The current benchmark_light20 videos appear to be single-method renders judged with a grid-style schema.",
"required_before_method_ranking": [
"Recover or create a montage manifest mapping grid positions to real method names.",
"Separate native/generated/manually cleaned assets according to the v0.1 metric rules.",
"Keep failed samples in reports with failure cause and repair status."
]
},
"reliable_results": [
{
"entry_id": "physxanything_pipeline_benchmark_light20_physics_proxy",
"display_name": "PhysX-Anything pipeline, benchmark_light20 physics proxy",
"split": "benchmark_light20",
"sample_count_inferred_from_video_dir": 20,
"metric_source": "/data/250010098/PhysX-Anything/evaluation_phy_results_benchmark_light20/phy_stdout.txt",
"metrics": {
"scale": 32.25,
"affordance": 9.698711012010476,
"material": 8.993700337231624,
"description": 13.040154636356394
},
"confidence": "limited",
"limitations": [
"The stdout contains aggregate scalar proxy metrics, not per-sample JSON.",
"Lower scale error is better; affordance/material/description are PSNR-like scores where higher is better.",
"This is a single-pipeline result and is not a method-vs-method leaderboard."
]
}
],
"grid_position_unknown_results": [
{
"path": "/data/250010098/PhysX-Anything/evaluation_kine_results",
"sample_count": 16,
"json_file_count": 17,
"invalid_or_unparseable_files": [
"3.json"
],
"label_status": "grid-position/unknown",
"methods": {
"A": {
"n": 16,
"mean_geometry_rank": 1.75,
"mean_motion_rank": 1.75,
"geometry_rank1_count": 9,
"motion_rank1_count": 9
},
"B": {
"n": 16,
"mean_geometry_rank": 1.875,
"mean_motion_rank": 1.875,
"geometry_rank1_count": 8,
"motion_rank1_count": 8
},
"C": {
"n": 16,
"mean_geometry_rank": 1.625,
"mean_motion_rank": 1.625,
"geometry_rank1_count": 9,
"motion_rank1_count": 9
},
"D": {
"n": 16,
"mean_geometry_rank": 1.9375,
"mean_motion_rank": 1.9375,
"geometry_rank1_count": 8,
"motion_rank1_count": 8
}
}
},
{
"path": "/data/250010098/PhysX-Anything/evaluation_kine_results_benchmark_light20",
"sample_count": 20,
"json_file_count": 20,
"invalid_or_unparseable_files": [],
"label_status": "grid-position/unknown",
"methods": {
"A": {
"n": 20,
"mean_geometry_rank": 1.15,
"mean_motion_rank": 1.15,
"geometry_rank1_count": 19,
"motion_rank1_count": 19
},
"B": {
"n": 20,
"mean_geometry_rank": 1.15,
"mean_motion_rank": 1.15,
"geometry_rank1_count": 18,
"motion_rank1_count": 18
},
"C": {
"n": 20,
"mean_geometry_rank": 1.15,
"mean_motion_rank": 1.15,
"geometry_rank1_count": 18,
"motion_rank1_count": 18
},
"D": {
"n": 20,
"mean_geometry_rank": 1.2,
"mean_motion_rank": 1.2,
"geometry_rank1_count": 17,
"motion_rank1_count": 17
}
}
},
{
"path": "/data/250010098/PhysX-Anything/evaluation_kine_results_fixed",
"sample_count": 17,
"json_file_count": 17,
"invalid_or_unparseable_files": [],
"label_status": "grid-position/unknown",
"methods": {
"A": {
"n": 17,
"mean_geometry_rank": 1.5294117647058822,
"mean_motion_rank": 1.5294117647058822,
"geometry_rank1_count": 10,
"motion_rank1_count": 10
},
"B": {
"n": 17,
"mean_geometry_rank": 2,
"mean_motion_rank": 2,
"geometry_rank1_count": 4,
"motion_rank1_count": 4
},
"C": {
"n": 17,
"mean_geometry_rank": 2.5294117647058822,
"mean_motion_rank": 2.5294117647058822,
"geometry_rank1_count": 4,
"motion_rank1_count": 4
},
"D": {
"n": 17,
"mean_geometry_rank": 3,
"mean_motion_rank": 3,
"geometry_rank1_count": 4,
"motion_rank1_count": 4
}
}
},
{
"path": "/data/250010098/PhysX-Anything/evaluation_kine_results_rerun",
"sample_count": 15,
"json_file_count": 17,
"invalid_or_unparseable_files": [
"5.json",
"7.json"
],
"label_status": "grid-position/unknown",
"methods": {
"A": {
"n": 15,
"mean_geometry_rank": 1.4666666666666666,
"mean_motion_rank": 1.4666666666666666,
"geometry_rank1_count": 11,
"motion_rank1_count": 10
},
"B": {
"n": 15,
"mean_geometry_rank": 1.6666666666666667,
"mean_motion_rank": 1.6666666666666667,
"geometry_rank1_count": 10,
"motion_rank1_count": 9
},
"C": {
"n": 15,
"mean_geometry_rank": 1.8,
"mean_motion_rank": 1.8666666666666667,
"geometry_rank1_count": 8,
"motion_rank1_count": 7
},
"D": {
"n": 15,
"mean_geometry_rank": 1.9333333333333333,
"mean_motion_rank": 1.9333333333333333,
"geometry_rank1_count": 9,
"motion_rank1_count": 9
}
}
}
],
"existing_summary_snapshot": {
"metric_source": "existing VLM/manual rank JSON files; lower rank is better",
"method_label_warning": "A/B/C/D are grid-position labels in PhysX-Anything evaluation prompts, not verified method names. Current benchmark_light20 videos appear to be single-method renders passed through a grid-style judge, so these ranks must not be interpreted as method comparisons until a montage manifest or method-position mapping is recovered.",
"evaluations": [
{
"path": "/data/250010098/PhysX-Anything/evaluation_kine_results_benchmark_light20",
"sample_count": 20,
"methods": {
"A": {
"n": 20,
"mean_geometry_rank": 1.15,
"mean_motion_rank": 1.15,
"geometry_rank1_count": 19,
"motion_rank1_count": 19
},
"B": {
"n": 20,
"mean_geometry_rank": 1.15,
"mean_motion_rank": 1.15,
"geometry_rank1_count": 18,
"motion_rank1_count": 18
},
"C": {
"n": 20,
"mean_geometry_rank": 1.15,
"mean_motion_rank": 1.15,
"geometry_rank1_count": 18,
"motion_rank1_count": 18
},
"D": {
"n": 20,
"mean_geometry_rank": 1.2,
"mean_motion_rank": 1.2,
"geometry_rank1_count": 17,
"motion_rank1_count": 17
}
}
},
{
"path": "/data/250010098/PhysX-Anything/evaluation_kine_results_fixed",
"sample_count": 17,
"methods": {
"A": {
"n": 17,
"mean_geometry_rank": 1.5294117647058822,
"mean_motion_rank": 1.5294117647058822,
"geometry_rank1_count": 10,
"motion_rank1_count": 10
},
"B": {
"n": 17,
"mean_geometry_rank": 2.0,
"mean_motion_rank": 2.0,
"geometry_rank1_count": 4,
"motion_rank1_count": 4
},
"C": {
"n": 17,
"mean_geometry_rank": 2.5294117647058822,
"mean_motion_rank": 2.5294117647058822,
"geometry_rank1_count": 4,
"motion_rank1_count": 4
},
"D": {
"n": 17,
"mean_geometry_rank": 3.0,
"mean_motion_rank": 3.0,
"geometry_rank1_count": 4,
"motion_rank1_count": 4
}
}
},
{
"path": "/data/250010098/PhysX-Anything/evaluation_kine_results",
"sample_count": 15,
"methods": {
"A": {
"n": 15,
"mean_geometry_rank": 1.6,
"mean_motion_rank": 1.6,
"geometry_rank1_count": 8,
"motion_rank1_count": 8
},
"B": {
"n": 15,
"mean_geometry_rank": 1.7333333333333334,
"mean_motion_rank": 1.7333333333333334,
"geometry_rank1_count": 7,
"motion_rank1_count": 7
},
"C": {
"n": 15,
"mean_geometry_rank": 1.5333333333333334,
"mean_motion_rank": 1.5333333333333334,
"geometry_rank1_count": 8,
"motion_rank1_count": 8
},
"D": {
"n": 15,
"mean_geometry_rank": 1.9333333333333333,
"mean_motion_rank": 1.9333333333333333,
"geometry_rank1_count": 6,
"motion_rank1_count": 6
}
}
}
]
},
"evaluation_dir_inventory": [
{
"path": "/data/250010098/PhysX-Anything/evaluation_kine_results",
"name": "evaluation_kine_results",
"json_count": 17,
"raw_txt_count": 0,
"txt_count": 0,
"mp4_count": 0
},
{
"path": "/data/250010098/PhysX-Anything/evaluation_kine_results_benchmark_completed123",
"name": "evaluation_kine_results_benchmark_completed123",
"json_count": 0,
"raw_txt_count": 0,
"txt_count": 0,
"mp4_count": 0
},
{
"path": "/data/250010098/PhysX-Anything/evaluation_kine_results_benchmark_full243",
"name": "evaluation_kine_results_benchmark_full243",
"json_count": 0,
"raw_txt_count": 0,
"txt_count": 0,
"mp4_count": 0
},
{
"path": "/data/250010098/PhysX-Anything/evaluation_kine_results_benchmark_light20",
"name": "evaluation_kine_results_benchmark_light20",
"json_count": 20,
"raw_txt_count": 20,
"txt_count": 20,
"mp4_count": 0
},
{
"path": "/data/250010098/PhysX-Anything/evaluation_kine_results_benchmark_sharded",
"name": "evaluation_kine_results_benchmark_sharded",
"json_count": 0,
"raw_txt_count": 0,
"txt_count": 0,
"mp4_count": 0
},
{
"path": "/data/250010098/PhysX-Anything/evaluation_kine_results_benchmark_sharded_diag",
"name": "evaluation_kine_results_benchmark_sharded_diag",
"json_count": 0,
"raw_txt_count": 0,
"txt_count": 0,
"mp4_count": 0
},
{
"path": "/data/250010098/PhysX-Anything/evaluation_kine_results_fixed",
"name": "evaluation_kine_results_fixed",
"json_count": 17,
"raw_txt_count": 17,
"txt_count": 17,
"mp4_count": 0
},
{
"path": "/data/250010098/PhysX-Anything/evaluation_kine_results_rerun",
"name": "evaluation_kine_results_rerun",
"json_count": 17,
"raw_txt_count": 0,
"txt_count": 0,
"mp4_count": 0
},
{
"path": "/data/250010098/PhysX-Anything/evaluation_phy_results_benchmark_completed123",
"name": "evaluation_phy_results_benchmark_completed123",
"json_count": 0,
"raw_txt_count": 0,
"txt_count": 0,
"mp4_count": 0
},
{
"path": "/data/250010098/PhysX-Anything/evaluation_phy_results_benchmark_full243",
"name": "evaluation_phy_results_benchmark_full243",
"json_count": 0,
"raw_txt_count": 0,
"txt_count": 0,
"mp4_count": 0
},
{
"path": "/data/250010098/PhysX-Anything/evaluation_phy_results_benchmark_light20",
"name": "evaluation_phy_results_benchmark_light20",
"json_count": 0,
"raw_txt_count": 0,
"txt_count": 1,
"mp4_count": 0
},
{
"path": "/data/250010098/PhysX-Anything/evaluation_phy_results_benchmark_sharded",
"name": "evaluation_phy_results_benchmark_sharded",
"json_count": 0,
"raw_txt_count": 0,
"txt_count": 0,
"mp4_count": 0
},
{
"path": "/data/250010098/PhysX-Anything/evaluation_phy_results_benchmark_sharded_diag",
"name": "evaluation_phy_results_benchmark_sharded_diag",
"json_count": 0,
"raw_txt_count": 0,
"txt_count": 0,
"mp4_count": 0
},
{
"path": "/data/250010098/PhysX-Anything/evaluation_video",
"name": "evaluation_video",
"json_count": 0,
"raw_txt_count": 0,
"txt_count": 0,
"mp4_count": 1
},
{
"path": "/data/250010098/PhysX-Anything/evaluation_video_physxanything",
"name": "evaluation_video_physxanything",
"json_count": 0,
"raw_txt_count": 0,
"txt_count": 0,
"mp4_count": 17
},
{
"path": "/data/250010098/PhysX-Anything/evaluation_video_physxanything_benchmark_completed123",
"name": "evaluation_video_physxanything_benchmark_completed123",
"json_count": 0,
"raw_txt_count": 0,
"txt_count": 0,
"mp4_count": 0
},
{
"path": "/data/250010098/PhysX-Anything/evaluation_video_physxanything_benchmark_full243",
"name": "evaluation_video_physxanything_benchmark_full243",
"json_count": 0,
"raw_txt_count": 0,
"txt_count": 0,
"mp4_count": 0
},
{
"path": "/data/250010098/PhysX-Anything/evaluation_video_physxanything_benchmark_light20",
"name": "evaluation_video_physxanything_benchmark_light20",
"json_count": 0,
"raw_txt_count": 0,
"txt_count": 0,
"mp4_count": 20
},
{
"path": "/data/250010098/PhysX-Anything/evaluation_video_physxanything_benchmark_sharded",
"name": "evaluation_video_physxanything_benchmark_sharded",
"json_count": 0,
"raw_txt_count": 0,
"txt_count": 0,
"mp4_count": 0
},
{
"path": "/data/250010098/PhysX-Anything/evaluation_video_physxanything_benchmark_sharded_diag",
"name": "evaluation_video_physxanything_benchmark_sharded_diag",
"json_count": 0,
"raw_txt_count": 0,
"txt_count": 0,
"mp4_count": 0
},
{
"path": "/data/250010098/PhysX-Anything/evaluation_video_physxanything_rerun",
"name": "evaluation_video_physxanything_rerun",
"json_count": 0,
"raw_txt_count": 0,
"txt_count": 0,
"mp4_count": 17
}
],
"evaluation_dir_status": {
"empty_or_not_completed": [
{
"path": "/data/250010098/PhysX-Anything/evaluation_kine_results_benchmark_completed123",
"name": "evaluation_kine_results_benchmark_completed123",
"json_count": 0,
"raw_txt_count": 0,
"txt_count": 0,
"mp4_count": 0
},
{
"path": "/data/250010098/PhysX-Anything/evaluation_kine_results_benchmark_full243",
"name": "evaluation_kine_results_benchmark_full243",
"json_count": 0,
"raw_txt_count": 0,
"txt_count": 0,
"mp4_count": 0
},
{
"path": "/data/250010098/PhysX-Anything/evaluation_kine_results_benchmark_sharded",
"name": "evaluation_kine_results_benchmark_sharded",
"json_count": 0,
"raw_txt_count": 0,
"txt_count": 0,
"mp4_count": 0
},
{
"path": "/data/250010098/PhysX-Anything/evaluation_kine_results_benchmark_sharded_diag",
"name": "evaluation_kine_results_benchmark_sharded_diag",
"json_count": 0,
"raw_txt_count": 0,
"txt_count": 0,
"mp4_count": 0
},
{
"path": "/data/250010098/PhysX-Anything/evaluation_phy_results_benchmark_completed123",
"name": "evaluation_phy_results_benchmark_completed123",
"json_count": 0,
"raw_txt_count": 0,
"txt_count": 0,
"mp4_count": 0
},
{
"path": "/data/250010098/PhysX-Anything/evaluation_phy_results_benchmark_full243",
"name": "evaluation_phy_results_benchmark_full243",
"json_count": 0,
"raw_txt_count": 0,
"txt_count": 0,
"mp4_count": 0
},
{
"path": "/data/250010098/PhysX-Anything/evaluation_phy_results_benchmark_sharded",
"name": "evaluation_phy_results_benchmark_sharded",
"json_count": 0,
"raw_txt_count": 0,
"txt_count": 0,
"mp4_count": 0
},
{
"path": "/data/250010098/PhysX-Anything/evaluation_phy_results_benchmark_sharded_diag",
"name": "evaluation_phy_results_benchmark_sharded_diag",
"json_count": 0,
"raw_txt_count": 0,
"txt_count": 0,
"mp4_count": 0
},
{
"path": "/data/250010098/PhysX-Anything/evaluation_video_physxanything_benchmark_completed123",
"name": "evaluation_video_physxanything_benchmark_completed123",
"json_count": 0,
"raw_txt_count": 0,
"txt_count": 0,
"mp4_count": 0
},
{
"path": "/data/250010098/PhysX-Anything/evaluation_video_physxanything_benchmark_full243",
"name": "evaluation_video_physxanything_benchmark_full243",
"json_count": 0,
"raw_txt_count": 0,
"txt_count": 0,
"mp4_count": 0
},
{
"path": "/data/250010098/PhysX-Anything/evaluation_video_physxanything_benchmark_sharded",
"name": "evaluation_video_physxanything_benchmark_sharded",
"json_count": 0,
"raw_txt_count": 0,
"txt_count": 0,
"mp4_count": 0
},
{
"path": "/data/250010098/PhysX-Anything/evaluation_video_physxanything_benchmark_sharded_diag",
"name": "evaluation_video_physxanything_benchmark_sharded_diag",
"json_count": 0,
"raw_txt_count": 0,
"txt_count": 0,
"mp4_count": 0
}
],
"rank_json_available": [
{
"path": "/data/250010098/PhysX-Anything/evaluation_kine_results",
"name": "evaluation_kine_results",
"json_count": 17,
"raw_txt_count": 0,
"txt_count": 0,
"mp4_count": 0
},
{
"path": "/data/250010098/PhysX-Anything/evaluation_kine_results_benchmark_light20",
"name": "evaluation_kine_results_benchmark_light20",
"json_count": 20,
"raw_txt_count": 20,
"txt_count": 20,
"mp4_count": 0
},
{
"path": "/data/250010098/PhysX-Anything/evaluation_kine_results_fixed",
"name": "evaluation_kine_results_fixed",
"json_count": 17,
"raw_txt_count": 17,
"txt_count": 17,
"mp4_count": 0
},
{
"path": "/data/250010098/PhysX-Anything/evaluation_kine_results_rerun",
"name": "evaluation_kine_results_rerun",
"json_count": 17,
"raw_txt_count": 0,
"txt_count": 0,
"mp4_count": 0
}
],
"text_only": [
{
"path": "/data/250010098/PhysX-Anything/evaluation_phy_results_benchmark_light20",
"name": "evaluation_phy_results_benchmark_light20",
"json_count": 0,
"raw_txt_count": 0,
"txt_count": 1,
"mp4_count": 0
}
],
"video_only": [
{
"path": "/data/250010098/PhysX-Anything/evaluation_video",
"name": "evaluation_video",
"json_count": 0,
"raw_txt_count": 0,
"txt_count": 0,
"mp4_count": 1
},
{
"path": "/data/250010098/PhysX-Anything/evaluation_video_physxanything",
"name": "evaluation_video_physxanything",
"json_count": 0,
"raw_txt_count": 0,
"txt_count": 0,
"mp4_count": 17
},
{
"path": "/data/250010098/PhysX-Anything/evaluation_video_physxanything_benchmark_light20",
"name": "evaluation_video_physxanything_benchmark_light20",
"json_count": 0,
"raw_txt_count": 0,
"txt_count": 0,
"mp4_count": 20
},
{
"path": "/data/250010098/PhysX-Anything/evaluation_video_physxanything_rerun",
"name": "evaluation_video_physxanything_rerun",
"json_count": 0,
"raw_txt_count": 0,
"txt_count": 0,
"mp4_count": 17
}
]
},
"uncertainty_notes": [
"Do not describe A/B/C/D as methods.",
"Rank JSON directories are useful for auditing judge behavior, but are not method leaderboard entries.",
"Full243/sharded benchmark directories contain no completed rank JSON in this workspace snapshot."
]
}