Publish reviewed DVIDIA native robot simulation evidence and local tools

README.md

@@ -43,7 +43,7 @@ denominator and every attempt remain under `replay/receipt/`.
 
 ```sh
 python3 -m venv .venv
-.venv/bin/python -m pip install "dvidia-training[arm] @ git+https://github.com/Dvidia-Inference/dvidia-training.git@d5c1cc6adbf6566947aef6defb1bbc04207a96c4"
+.venv/bin/python -m pip install "dvidia-training[arm] @ git+https://github.com/Dvidia-Inference/dvidia-training.git@0545ac47aedcd7c197341986533aa3e74c263ac6"
 .venv/bin/dvidia-embodiment fetch-assets --output runs/reference-assets
 .venv/bin/dvidia-reference-task benchmark runs/reference-assets --output runs/grasp-development
 .venv/bin/dvidia-reference-task inspect runs/grasp-development
@@ -56,7 +56,7 @@ physics and learning are separate workloads; no minimum RAM or speed guarantee
 has been established for this task. WebGL2 is required only for the interactive
 browser viewer. Fetch dependencies and pinned assets once, then native simulation
 and exported replay work offline through a local HTTP server. The complete
-[local task guide](https://github.com/Dvidia-Inference/dvidia-training/blob/d5c1cc6adbf6566947aef6defb1bbc04207a96c4/docs/native-task-benchmark.md)
+[local task guide](https://github.com/Dvidia-Inference/dvidia-training/blob/0545ac47aedcd7c197341986533aa3e74c263ac6/docs/native-task-benchmark.md)
 describes controls, scoring and measured timing boundaries.
 
 ## Hardware profiles
@@ -80,7 +80,7 @@ Frozen confirmation cohort: 9 planned attempts across 3 synthetic scenes. Counts
 - low_friction / replay_open_jaw: 0/1 completed, 1 numerically valid
 - low_friction / hold: 0/1 completed, 1 numerically valid
 
-Authored controller, synthetic scenes and privileged native simulator state. Contact is uncalibrated; no learned skill or physical robot is qualified. This is separate from the unloaded PiPER mechanics bundle; no PiPER 3D viewer is included. Every attempted episode, including failed and invalid attempts, remains under `tasks/piper/attempts/`. Inspect [the complete task report](tasks/piper/report.html), [frozen protocol](tasks/piper/protocol.json), [file hashes](tasks/piper/integrity.json), and [original MIT model license](tasks/piper/licenses/agilex_piper/LICENSE). [Local PiPER contact guide](https://github.com/Dvidia-Inference/dvidia-training/blob/d5c1cc6adbf6566947aef6defb1bbc04207a96c4/docs/piper-contact-pilot.md).
+Authored controller, synthetic scenes and privileged native simulator state. Contact is uncalibrated; no learned skill or physical robot is qualified. This is separate from the unloaded PiPER mechanics bundle; no PiPER 3D viewer is included. Every attempted episode, including failed and invalid attempts, remains under `tasks/piper/attempts/`. Inspect [the complete task report](tasks/piper/report.html), [frozen protocol](tasks/piper/protocol.json), [file hashes](tasks/piper/integrity.json), and [original MIT model license](tasks/piper/licenses/agilex_piper/LICENSE). [Local PiPER contact guide](https://github.com/Dvidia-Inference/dvidia-training/blob/0545ac47aedcd7c197341986533aa3e74c263ac6/docs/piper-contact-pilot.md).
 
 
 ## PiPER guarded grip comparison
@@ -111,7 +111,7 @@ Frozen confirmation cohort: 30 planned attempts across six synthetic scenes. Two
 
 Baseline and guarded authored controllers use privileged native state and their own matched open-jaw replays plus a common hold control. Full qualification decisions, unresolved outcomes, absent opportunities, alarms, retries and aborts remain in the source evidence. These synthetic trials are not detector accuracy, learned competence or physical qualification.
 
-Every full attempt is stored as canonical deterministic gzip JSON under `tasks/piper-grip/attempts/`; the original seal records both compressed and decoded bytes and SHA-256. Download all files in `tasks/piper-grip/` together and run the pinned `dvidia-piper-grip inspect` command from [the local guide](https://github.com/Dvidia-Inference/dvidia-training/blob/d5c1cc6adbf6566947aef6defb1bbc04207a96c4/docs/piper-grip-recovery.md). No archive extraction is needed. [Full comparison](tasks/piper-grip/report.html) · [Original protocol](tasks/piper-grip/protocol.json) · [Stored and decoded hashes](tasks/piper-grip/integrity.json).
+Every full attempt is stored as canonical deterministic gzip JSON under `tasks/piper-grip/attempts/`; the original seal records both compressed and decoded bytes and SHA-256. Download all files in `tasks/piper-grip/` together and run the pinned `dvidia-piper-grip inspect` command from [the local guide](https://github.com/Dvidia-Inference/dvidia-training/blob/0545ac47aedcd7c197341986533aa3e74c263ac6/docs/piper-grip-recovery.md). No archive extraction is needed. [Full comparison](tasks/piper-grip/report.html) · [Original protocol](tasks/piper-grip/protocol.json) · [Stored and decoded hashes](tasks/piper-grip/integrity.json).
 
 
 ## PiPER grip recovery v0.4
@@ -167,7 +167,7 @@ Frozen confirmation cohort: 84 planned attempts across twelve synthetic scenes.
 
 Frozen v0.3, v0.4 carry-only and v0.4 full are authored controllers with privileged native state, each with its own matched open-jaw replay and a common hold control. Full diagnostics, contact-memory decisions, refusals, retries, resumes and aborts are retained. These synthetic trials establish no learned competence, physical reliability or detector accuracy.
 
-Every attempt is canonical deterministic gzip JSON under `tasks/piper-recovery-v04/attempts/`; the original seal records both stored and decoded bytes and SHA-256. Download all files in `tasks/piper-recovery-v04/` together for the pinned offline inspection workflow in [the v0.4 guide](https://github.com/Dvidia-Inference/dvidia-training/blob/d5c1cc6adbf6566947aef6defb1bbc04207a96c4/docs/piper-contact-recovery-v04.md). [Full comparison](tasks/piper-recovery-v04/report.html) · [Every outcome](tasks/piper-recovery-v04/report.json) · [Original protocol](tasks/piper-recovery-v04/protocol.json) · [Stored and decoded hashes](tasks/piper-recovery-v04/integrity.json).
+Every attempt is canonical deterministic gzip JSON under `tasks/piper-recovery-v04/attempts/`; the original seal records both stored and decoded bytes and SHA-256. Download all files in `tasks/piper-recovery-v04/` together for the pinned offline inspection workflow in [the v0.4 guide](https://github.com/Dvidia-Inference/dvidia-training/blob/0545ac47aedcd7c197341986533aa3e74c263ac6/docs/piper-contact-recovery-v04.md). [Full comparison](tasks/piper-recovery-v04/report.html) · [Every outcome](tasks/piper-recovery-v04/report.json) · [Original protocol](tasks/piper-recovery-v04/protocol.json) · [Stored and decoded hashes](tasks/piper-recovery-v04/integrity.json).
 
 
 ## PiPER contact memory v0.3
@@ -223,10 +223,196 @@ Frozen confirmation cohort: 84 planned attempts across twelve synthetic scenes.
 
 Baseline, probe-only and history are authored controllers with privileged native state, each with its own matched open-jaw replay and a common hold control. Full diagnostics, contact-memory decisions, refusals, retries, resumes and aborts are retained. These synthetic trials establish no learned competence, physical reliability or detector accuracy.
 
-Every attempt is canonical deterministic gzip JSON under `tasks/piper-contact-v03/attempts/`; the original seal records both stored and decoded bytes and SHA-256. Download all files in `tasks/piper-contact-v03/` together for the pinned offline inspection workflow in [the v0.3 guide](https://github.com/Dvidia-Inference/dvidia-training/blob/d5c1cc6adbf6566947aef6defb1bbc04207a96c4/docs/piper-contact-memory-v03.md). [Full comparison](tasks/piper-contact-v03/report.html) · [Every outcome](tasks/piper-contact-v03/report.json) · [Original protocol](tasks/piper-contact-v03/protocol.json) · [Stored and decoded hashes](tasks/piper-contact-v03/integrity.json).
+Every attempt is canonical deterministic gzip JSON under `tasks/piper-contact-v03/attempts/`; the original seal records both stored and decoded bytes and SHA-256. Download all files in `tasks/piper-contact-v03/` together for the pinned offline inspection workflow in [the v0.3 guide](https://github.com/Dvidia-Inference/dvidia-training/blob/0545ac47aedcd7c197341986533aa3e74c263ac6/docs/piper-contact-memory-v03.md). [Full comparison](tasks/piper-contact-v03/report.html) · [Every outcome](tasks/piper-contact-v03/report.json) · [Original protocol](tasks/piper-contact-v03/protocol.json) · [Stored and decoded hashes](tasks/piper-contact-v03/integrity.json).
 
 
-The reviewed publication now permits at most **256 MiB of stored files**, to retain prior
+## PiPER reliability v0.5 — confirmation-832847
+
+Placement completion: v0.4 4/12, v0.5 second lift 6/12, v0.5 full 7/12.
+
+v0.5 second lift versus v0.4: 2 gained, 0 lost, 4 shared successful scenes, 6 neither completed. Mean completion-time change on shared successes: +0.000 simulated seconds (candidate minus reference).
+
+v0.5 full versus v0.4: 3 gained, 0 lost, 4 shared successful scenes, 5 neither completed. Mean completion-time change on shared successes: +0.847 simulated seconds (candidate minus reference).
+
+v0.5 full versus v0.5 second lift: 1 gained, 0 lost, 6 shared successful scenes, 5 neither completed. Mean completion-time change on shared successes: +0.434 simulated seconds (candidate minus reference).
+
+Protocol cohort: confirmation; seed 832847. 84 planned attempts across twelve synthetic scenes. Matched open-jaw and hold controls: 0/48 completed. Every failed or invalid attempt remains in the denominator. Cohorts are reported separately; a cohort label alone does not establish independence. Counts are descriptive synthetic evidence, not physical reliability, detector accuracy, learned competence or real-time sensor performance.
+
+- Pilot gate complete planned denominator: passed
+- Pilot gate all native attempts valid: passed
+- Pilot gate all controls fail: passed
+- Pilot gate native integrity clean: passed
+- Pilot gate gained without lost completions: passed
+- μ=0.80, mass=0.04 kg / recovery_placement: 2/2 completed, 2 numerically valid
+- μ=0.80, mass=0.04 kg / recovery_open_jaw: 0/2 completed, 2 numerically valid
+- μ=0.80, mass=0.04 kg / reacquire_placement: 2/2 completed, 2 numerically valid
+- μ=0.80, mass=0.04 kg / reacquire_open_jaw: 0/2 completed, 2 numerically valid
+- μ=0.80, mass=0.04 kg / reacquire_grasp_placement: 2/2 completed, 2 numerically valid
+- μ=0.80, mass=0.04 kg / reacquire_grasp_open_jaw: 0/2 completed, 2 numerically valid
+- μ=0.80, mass=0.04 kg / hold: 0/2 completed, 2 numerically valid
+- μ=0.80, mass=0.06 kg / recovery_placement: 0/2 completed, 2 numerically valid
+- μ=0.80, mass=0.06 kg / recovery_open_jaw: 0/2 completed, 2 numerically valid
+- μ=0.80, mass=0.06 kg / reacquire_placement: 2/2 completed, 2 numerically valid
+- μ=0.80, mass=0.06 kg / reacquire_open_jaw: 0/2 completed, 2 numerically valid
+- μ=0.80, mass=0.06 kg / reacquire_grasp_placement: 2/2 completed, 2 numerically valid
+- μ=0.80, mass=0.06 kg / reacquire_grasp_open_jaw: 0/2 completed, 2 numerically valid
+- μ=0.80, mass=0.06 kg / hold: 0/2 completed, 2 numerically valid
+- μ=0.55, mass=0.04 kg / recovery_placement: 2/2 completed, 2 numerically valid
+- μ=0.55, mass=0.04 kg / recovery_open_jaw: 0/2 completed, 2 numerically valid
+- μ=0.55, mass=0.04 kg / reacquire_placement: 2/2 completed, 2 numerically valid
+- μ=0.55, mass=0.04 kg / reacquire_open_jaw: 0/2 completed, 2 numerically valid
+- μ=0.55, mass=0.04 kg / reacquire_grasp_placement: 2/2 completed, 2 numerically valid
+- μ=0.55, mass=0.04 kg / reacquire_grasp_open_jaw: 0/2 completed, 2 numerically valid
+- μ=0.55, mass=0.04 kg / hold: 0/2 completed, 2 numerically valid
+- μ=0.55, mass=0.06 kg / recovery_placement: 0/2 completed, 2 numerically valid
+- μ=0.55, mass=0.06 kg / recovery_open_jaw: 0/2 completed, 2 numerically valid
+- μ=0.55, mass=0.06 kg / reacquire_placement: 0/2 completed, 2 numerically valid
+- μ=0.55, mass=0.06 kg / reacquire_open_jaw: 0/2 completed, 2 numerically valid
+- μ=0.55, mass=0.06 kg / reacquire_grasp_placement: 1/2 completed, 2 numerically valid
+- μ=0.55, mass=0.06 kg / reacquire_grasp_open_jaw: 0/2 completed, 2 numerically valid
+- μ=0.55, mass=0.06 kg / hold: 0/2 completed, 2 numerically valid
+- μ=0.15, mass=0.04 kg / recovery_placement: 0/2 completed, 2 numerically valid
+- μ=0.15, mass=0.04 kg / recovery_open_jaw: 0/2 completed, 2 numerically valid
+- μ=0.15, mass=0.04 kg / reacquire_placement: 0/2 completed, 2 numerically valid
+- μ=0.15, mass=0.04 kg / reacquire_open_jaw: 0/2 completed, 2 numerically valid
+- μ=0.15, mass=0.04 kg / reacquire_grasp_placement: 0/2 completed, 2 numerically valid
+- μ=0.15, mass=0.04 kg / reacquire_grasp_open_jaw: 0/2 completed, 2 numerically valid
+- μ=0.15, mass=0.04 kg / hold: 0/2 completed, 2 numerically valid
+- μ=0.15, mass=0.06 kg / recovery_placement: 0/2 completed, 2 numerically valid
+- μ=0.15, mass=0.06 kg / recovery_open_jaw: 0/2 completed, 2 numerically valid
+- μ=0.15, mass=0.06 kg / reacquire_placement: 0/2 completed, 2 numerically valid
+- μ=0.15, mass=0.06 kg / reacquire_open_jaw: 0/2 completed, 2 numerically valid
+- μ=0.15, mass=0.06 kg / reacquire_grasp_placement: 0/2 completed, 2 numerically valid
+- μ=0.15, mass=0.06 kg / reacquire_grasp_open_jaw: 0/2 completed, 2 numerically valid
+- μ=0.15, mass=0.06 kg / hold: 0/2 completed, 2 numerically valid
+
+[Complete comparison](tasks/piper-reliability-v05/confirmation-832847/report.html) · [Original seal](tasks/piper-reliability-v05/confirmation-832847/integrity.json). Download this entire cohort directory to retain all attempts and original notices.
+
+## PiPER reliability v0.5 — confirmation-227037
+
+Placement completion: v0.4 6/12, v0.5 second lift 6/12, v0.5 full 8/12.
+
+v0.5 second lift versus v0.4: 0 gained, 0 lost, 6 shared successful scenes, 6 neither completed. Mean completion-time change on shared successes: +0.000 simulated seconds (candidate minus reference).
+
+v0.5 full versus v0.4: 2 gained, 0 lost, 6 shared successful scenes, 4 neither completed. Mean completion-time change on shared successes: +0.698 simulated seconds (candidate minus reference).
+
+v0.5 full versus v0.5 second lift: 2 gained, 0 lost, 6 shared successful scenes, 4 neither completed. Mean completion-time change on shared successes: +0.698 simulated seconds (candidate minus reference).
+
+Protocol cohort: confirmation; seed 227037. 84 planned attempts across twelve synthetic scenes. Matched open-jaw and hold controls: 0/48 completed. Every failed or invalid attempt remains in the denominator. Cohorts are reported separately; a cohort label alone does not establish independence. Counts are descriptive synthetic evidence, not physical reliability, detector accuracy, learned competence or real-time sensor performance.
+
+- Pilot gate complete planned denominator: passed
+- Pilot gate all native attempts valid: passed
+- Pilot gate all controls fail: passed
+- Pilot gate native integrity clean: passed
+- Pilot gate gained without lost completions: passed
+- μ=0.80, mass=0.04 kg / recovery_placement: 2/2 completed, 2 numerically valid
+- μ=0.80, mass=0.04 kg / recovery_open_jaw: 0/2 completed, 2 numerically valid
+- μ=0.80, mass=0.04 kg / reacquire_placement: 2/2 completed, 2 numerically valid
+- μ=0.80, mass=0.04 kg / reacquire_open_jaw: 0/2 completed, 2 numerically valid
+- μ=0.80, mass=0.04 kg / reacquire_grasp_placement: 2/2 completed, 2 numerically valid
+- μ=0.80, mass=0.04 kg / reacquire_grasp_open_jaw: 0/2 completed, 2 numerically valid
+- μ=0.80, mass=0.04 kg / hold: 0/2 completed, 2 numerically valid
+- μ=0.80, mass=0.06 kg / recovery_placement: 2/2 completed, 2 numerically valid
+- μ=0.80, mass=0.06 kg / recovery_open_jaw: 0/2 completed, 2 numerically valid
+- μ=0.80, mass=0.06 kg / reacquire_placement: 2/2 completed, 2 numerically valid
+- μ=0.80, mass=0.06 kg / reacquire_open_jaw: 0/2 completed, 2 numerically valid
+- μ=0.80, mass=0.06 kg / reacquire_grasp_placement: 2/2 completed, 2 numerically valid
+- μ=0.80, mass=0.06 kg / reacquire_grasp_open_jaw: 0/2 completed, 2 numerically valid
+- μ=0.80, mass=0.06 kg / hold: 0/2 completed, 2 numerically valid
+- μ=0.55, mass=0.04 kg / recovery_placement: 2/2 completed, 2 numerically valid
+- μ=0.55, mass=0.04 kg / recovery_open_jaw: 0/2 completed, 2 numerically valid
+- μ=0.55, mass=0.04 kg / reacquire_placement: 2/2 completed, 2 numerically valid
+- μ=0.55, mass=0.04 kg / reacquire_open_jaw: 0/2 completed, 2 numerically valid
+- μ=0.55, mass=0.04 kg / reacquire_grasp_placement: 2/2 completed, 2 numerically valid
+- μ=0.55, mass=0.04 kg / reacquire_grasp_open_jaw: 0/2 completed, 2 numerically valid
+- μ=0.55, mass=0.04 kg / hold: 0/2 completed, 2 numerically valid
+- μ=0.55, mass=0.06 kg / recovery_placement: 0/2 completed, 2 numerically valid
+- μ=0.55, mass=0.06 kg / recovery_open_jaw: 0/2 completed, 2 numerically valid
+- μ=0.55, mass=0.06 kg / reacquire_placement: 0/2 completed, 2 numerically valid
+- μ=0.55, mass=0.06 kg / reacquire_open_jaw: 0/2 completed, 2 numerically valid
+- μ=0.55, mass=0.06 kg / reacquire_grasp_placement: 2/2 completed, 2 numerically valid
+- μ=0.55, mass=0.06 kg / reacquire_grasp_open_jaw: 0/2 completed, 2 numerically valid
+- μ=0.55, mass=0.06 kg / hold: 0/2 completed, 2 numerically valid
+- μ=0.15, mass=0.04 kg / recovery_placement: 0/2 completed, 2 numerically valid
+- μ=0.15, mass=0.04 kg / recovery_open_jaw: 0/2 completed, 2 numerically valid
+- μ=0.15, mass=0.04 kg / reacquire_placement: 0/2 completed, 2 numerically valid
+- μ=0.15, mass=0.04 kg / reacquire_open_jaw: 0/2 completed, 2 numerically valid
+- μ=0.15, mass=0.04 kg / reacquire_grasp_placement: 0/2 completed, 2 numerically valid
+- μ=0.15, mass=0.04 kg / reacquire_grasp_open_jaw: 0/2 completed, 2 numerically valid
+- μ=0.15, mass=0.04 kg / hold: 0/2 completed, 2 numerically valid
+- μ=0.15, mass=0.06 kg / recovery_placement: 0/2 completed, 2 numerically valid
+- μ=0.15, mass=0.06 kg / recovery_open_jaw: 0/2 completed, 2 numerically valid
+- μ=0.15, mass=0.06 kg / reacquire_placement: 0/2 completed, 2 numerically valid
+- μ=0.15, mass=0.06 kg / reacquire_open_jaw: 0/2 completed, 2 numerically valid
+- μ=0.15, mass=0.06 kg / reacquire_grasp_placement: 0/2 completed, 2 numerically valid
+- μ=0.15, mass=0.06 kg / reacquire_grasp_open_jaw: 0/2 completed, 2 numerically valid
+- μ=0.15, mass=0.06 kg / hold: 0/2 completed, 2 numerically valid
+
+[Complete comparison](tasks/piper-reliability-v05/confirmation-227037/report.html) · [Original seal](tasks/piper-reliability-v05/confirmation-227037/integrity.json). Download this entire cohort directory to retain all attempts and original notices.
+
+## PiPER reliability v0.5 — confirmation-862186
+
+Placement completion: v0.4 5/12, v0.5 second lift 6/12, v0.5 full 8/12.
+
+v0.5 second lift versus v0.4: 1 gained, 0 lost, 5 shared successful scenes, 6 neither completed. Mean completion-time change on shared successes: +0.000 simulated seconds (candidate minus reference).
+
+v0.5 full versus v0.4: 3 gained, 0 lost, 5 shared successful scenes, 4 neither completed. Mean completion-time change on shared successes: +0.800 simulated seconds (candidate minus reference).
+
+v0.5 full versus v0.5 second lift: 2 gained, 0 lost, 6 shared successful scenes, 4 neither completed. Mean completion-time change on shared successes: +0.602 simulated seconds (candidate minus reference).
+
+Protocol cohort: confirmation; seed 862186. 84 planned attempts across twelve synthetic scenes. Matched open-jaw and hold controls: 0/48 completed. Every failed or invalid attempt remains in the denominator. Cohorts are reported separately; a cohort label alone does not establish independence. Counts are descriptive synthetic evidence, not physical reliability, detector accuracy, learned competence or real-time sensor performance.
+
+- Pilot gate complete planned denominator: passed
+- Pilot gate all native attempts valid: passed
+- Pilot gate all controls fail: passed
+- Pilot gate native integrity clean: passed
+- Pilot gate gained without lost completions: passed
+- μ=0.80, mass=0.04 kg / recovery_placement: 2/2 completed, 2 numerically valid
+- μ=0.80, mass=0.04 kg / recovery_open_jaw: 0/2 completed, 2 numerically valid
+- μ=0.80, mass=0.04 kg / reacquire_placement: 2/2 completed, 2 numerically valid
+- μ=0.80, mass=0.04 kg / reacquire_open_jaw: 0/2 completed, 2 numerically valid
+- μ=0.80, mass=0.04 kg / reacquire_grasp_placement: 2/2 completed, 2 numerically valid
+- μ=0.80, mass=0.04 kg / reacquire_grasp_open_jaw: 0/2 completed, 2 numerically valid
+- μ=0.80, mass=0.04 kg / hold: 0/2 completed, 2 numerically valid
+- μ=0.80, mass=0.06 kg / recovery_placement: 1/2 completed, 2 numerically valid
+- μ=0.80, mass=0.06 kg / recovery_open_jaw: 0/2 completed, 2 numerically valid
+- μ=0.80, mass=0.06 kg / reacquire_placement: 2/2 completed, 2 numerically valid
+- μ=0.80, mass=0.06 kg / reacquire_open_jaw: 0/2 completed, 2 numerically valid
+- μ=0.80, mass=0.06 kg / reacquire_grasp_placement: 2/2 completed, 2 numerically valid
+- μ=0.80, mass=0.06 kg / reacquire_grasp_open_jaw: 0/2 completed, 2 numerically valid
+- μ=0.80, mass=0.06 kg / hold: 0/2 completed, 2 numerically valid
+- μ=0.55, mass=0.04 kg / recovery_placement: 2/2 completed, 2 numerically valid
+- μ=0.55, mass=0.04 kg / recovery_open_jaw: 0/2 completed, 2 numerically valid
+- μ=0.55, mass=0.04 kg / reacquire_placement: 2/2 completed, 2 numerically valid
+- μ=0.55, mass=0.04 kg / reacquire_open_jaw: 0/2 completed, 2 numerically valid
+- μ=0.55, mass=0.04 kg / reacquire_grasp_placement: 2/2 completed, 2 numerically valid
+- μ=0.55, mass=0.04 kg / reacquire_grasp_open_jaw: 0/2 completed, 2 numerically valid
+- μ=0.55, mass=0.04 kg / hold: 0/2 completed, 2 numerically valid
+- μ=0.55, mass=0.06 kg / recovery_placement: 0/2 completed, 2 numerically valid
+- μ=0.55, mass=0.06 kg / recovery_open_jaw: 0/2 completed, 2 numerically valid
+- μ=0.55, mass=0.06 kg / reacquire_placement: 0/2 completed, 2 numerically valid
+- μ=0.55, mass=0.06 kg / reacquire_open_jaw: 0/2 completed, 2 numerically valid
+- μ=0.55, mass=0.06 kg / reacquire_grasp_placement: 2/2 completed, 2 numerically valid
+- μ=0.55, mass=0.06 kg / reacquire_grasp_open_jaw: 0/2 completed, 2 numerically valid
+- μ=0.55, mass=0.06 kg / hold: 0/2 completed, 2 numerically valid
+- μ=0.15, mass=0.04 kg / recovery_placement: 0/2 completed, 2 numerically valid
+- μ=0.15, mass=0.04 kg / recovery_open_jaw: 0/2 completed, 2 numerically valid
+- μ=0.15, mass=0.04 kg / reacquire_placement: 0/2 completed, 2 numerically valid
+- μ=0.15, mass=0.04 kg / reacquire_open_jaw: 0/2 completed, 2 numerically valid
+- μ=0.15, mass=0.04 kg / reacquire_grasp_placement: 0/2 completed, 2 numerically valid
+- μ=0.15, mass=0.04 kg / reacquire_grasp_open_jaw: 0/2 completed, 2 numerically valid
+- μ=0.15, mass=0.04 kg / hold: 0/2 completed, 2 numerically valid
+- μ=0.15, mass=0.06 kg / recovery_placement: 0/2 completed, 2 numerically valid
+- μ=0.15, mass=0.06 kg / recovery_open_jaw: 0/2 completed, 2 numerically valid
+- μ=0.15, mass=0.06 kg / reacquire_placement: 0/2 completed, 2 numerically valid
+- μ=0.15, mass=0.06 kg / reacquire_open_jaw: 0/2 completed, 2 numerically valid
+- μ=0.15, mass=0.06 kg / reacquire_grasp_placement: 0/2 completed, 2 numerically valid
+- μ=0.15, mass=0.06 kg / reacquire_grasp_open_jaw: 0/2 completed, 2 numerically valid
+- μ=0.15, mass=0.06 kg / hold: 0/2 completed, 2 numerically valid
+
+[Complete comparison](tasks/piper-reliability-v05/confirmation-862186/report.html) · [Original seal](tasks/piper-reliability-v05/confirmation-862186/integrity.json). Download this entire cohort directory to retain all attempts and original notices.
+
+The reviewed publication now permits at most **512 MiB of stored files**, to retain prior
 evidence alongside complete new comparisons and their failed attempts.
 The **32 MiB per-file limit** and bounded single-member gzip decoding remain in place.
 This is a packaging limit, not a hardware or training memory requirement.

index.html

@@ -5,6 +5,6 @@
 <h1>See the motion. Inspect the evidence.</h1><p>A native six-joint arm, an articulated gripper and a free rigid object. Recorded task attempts make the simulator's behavior visible, and the complete receipts make its limits checkable.</p><p class="scope">This is recorded simulation from an authored controller with privileged simulator state. The browser does not run physics or connect to hardware. Learned skills, shoe manipulation and physical transfer remain future stages.</p>
 <div class="summary"><strong>Frozen confirmation cohort: 18 planned attempts across 6 synthetic scenes. Counts are descriptive, with no population or physical reliability claim.</strong><br>nominal / placement: 4/4 completed, 4 numerically valid<br>nominal / replay_open_jaw: 0/4 completed, 4 numerically valid<br>nominal / hold: 0/4 completed, 4 numerically valid<br>low_friction / placement: 2/2 completed, 2 numerically valid<br>low_friction / replay_open_jaw: 0/2 completed, 2 numerically valid<br>low_friction / hold: 0/2 completed, 2 numerically valid</div>
 <section aria-labelledby="replay-title"><h2 id="replay-title">Native grasp, carry and release.</h2><div class="links"><a href="replay/index.html">Open the full 3D replay ↗</a><a href="replay/receipt/report.html">Every attempted task ↗</a><a href="README.md">Install and reproduce ↗</a></div><div class="replay"><iframe src="replay/index.html" title="DVIDIA recorded native robot task replay" allow="fullscreen"></iframe></div><p class="tiny">Use orbit, zoom, recorded motion selection and the timeline inside the viewer. Replay is an excerpt; the full benchmark includes every matched control and invalid attempt. The native meshes, binary poses, complete receipts and license notices are served locally by this Space.</p></section>
-<section aria-labelledby="profiles-title"><h2 id="profiles-title">Hardware profiles and the next experiments.</h2><div class="gallery"><article class="profile"><span class="status">Recorded native contact task</span><h2>UR5e + Robotiq 2F-85</h2><p>Six arm joints, eight articulated gripper coordinates and a free rigid block. Full source outcomes and matched controls are available.</p><a href="replay/index.html">Inspect the task replay ↗</a></article><article class="profile"><span class="status">PiPER grip recovery v0.4 · synthetic</span><h2>Measure recovery and grip refusal.</h2><div class="summary"><p><strong>Placement completion: v0.3 4/12, v0.4 carry-only 4/12, v0.4 full 4/12.</strong></p><p>Retries, resumes and grip refusals do not imply successful placement or recovery. Shared successful scenes: 4; gained placements: 0; lost placements: 0. Mean completion-time change on shared successes: -1.270 simulated seconds (v0.4 minus v0.3). Hold-duration and post-resume motion remain separate in the report.</p><p>Frozen confirmation cohort: 84 planned attempts across twelve synthetic scenes. Three frictions, two masses and two shared layouts; seven variants per scene. Every failed or invalid attempt remains in the denominator. Counts are descriptive, not physical reliability or detector accuracy.</p><details><summary>Inspect all friction, mass and control counts</summary>μ=0.80, mass=0.04 kg / history_placement: 2/2 completed, 2 numerically valid<br>μ=0.80, mass=0.04 kg / history_open_jaw: 0/2 completed, 2 numerically valid<br>μ=0.80, mass=0.04 kg / recovery_carry_placement: 2/2 completed, 2 numerically valid<br>μ=0.80, mass=0.04 kg / recovery_carry_open_jaw: 0/2 completed, 2 numerically valid<br>μ=0.80, mass=0.04 kg / recovery_placement: 2/2 completed, 2 numerically valid<br>μ=0.80, mass=0.04 kg / recovery_open_jaw: 0/2 completed, 2 numerically valid<br>μ=0.80, mass=0.04 kg / hold: 0/2 completed, 2 numerically valid<br>μ=0.80, mass=0.06 kg / history_placement: 0/2 completed, 2 numerically valid<br>μ=0.80, mass=0.06 kg / history_open_jaw: 0/2 completed, 2 numerically valid<br>μ=0.80, mass=0.06 kg / recovery_carry_placement: 0/2 completed, 2 numerically valid<br>μ=0.80, mass=0.06 kg / recovery_carry_open_jaw: 0/2 completed, 2 numerically valid<br>μ=0.80, mass=0.06 kg / recovery_placement: 0/2 completed, 2 numerically valid<br>μ=0.80, mass=0.06 kg / recovery_open_jaw: 0/2 completed, 2 numerically valid<br>μ=0.80, mass=0.06 kg / hold: 0/2 completed, 2 numerically valid<br>μ=0.55, mass=0.04 kg / history_placement: 2/2 completed, 2 numerically valid<br>μ=0.55, mass=0.04 kg / history_open_jaw: 0/2 completed, 2 numerically valid<br>μ=0.55, mass=0.04 kg / recovery_carry_placement: 2/2 completed, 2 numerically valid<br>μ=0.55, mass=0.04 kg / recovery_carry_open_jaw: 0/2 completed, 2 numerically valid<br>μ=0.55, mass=0.04 kg / recovery_placement: 2/2 completed, 2 numerically valid<br>μ=0.55, mass=0.04 kg / recovery_open_jaw: 0/2 completed, 2 numerically valid<br>μ=0.55, mass=0.04 kg / hold: 0/2 completed, 2 numerically valid<br>μ=0.55, mass=0.06 kg / history_placement: 0/2 completed, 2 numerically valid<br>μ=0.55, mass=0.06 kg / history_open_jaw: 0/2 completed, 2 numerically valid<br>μ=0.55, mass=0.06 kg / recovery_carry_placement: 0/2 completed, 2 numerically valid<br>μ=0.55, mass=0.06 kg / recovery_carry_open_jaw: 0/2 completed, 2 numerically valid<br>μ=0.55, mass=0.06 kg / recovery_placement: 0/2 completed, 2 numerically valid<br>μ=0.55, mass=0.06 kg / recovery_open_jaw: 0/2 completed, 2 numerically valid<br>μ=0.55, mass=0.06 kg / hold: 0/2 completed, 2 numerically valid<br>μ=0.15, mass=0.04 kg / history_placement: 0/2 completed, 2 numerically valid<br>μ=0.15, mass=0.04 kg / history_open_jaw: 0/2 completed, 2 numerically valid<br>μ=0.15, mass=0.04 kg / recovery_carry_placement: 0/2 completed, 2 numerically valid<br>μ=0.15, mass=0.04 kg / recovery_carry_open_jaw: 0/2 completed, 2 numerically valid<br>μ=0.15, mass=0.04 kg / recovery_placement: 0/2 completed, 2 numerically valid<br>μ=0.15, mass=0.04 kg / recovery_open_jaw: 0/2 completed, 2 numerically valid<br>μ=0.15, mass=0.04 kg / hold: 0/2 completed, 2 numerically valid<br>μ=0.15, mass=0.06 kg / history_placement: 0/2 completed, 2 numerically valid<br>μ=0.15, mass=0.06 kg / history_open_jaw: 0/2 completed, 2 numerically valid<br>μ=0.15, mass=0.06 kg / recovery_carry_placement: 0/2 completed, 2 numerically valid<br>μ=0.15, mass=0.06 kg / recovery_carry_open_jaw: 0/2 completed, 2 numerically valid<br>μ=0.15, mass=0.06 kg / recovery_placement: 0/2 completed, 2 numerically valid<br>μ=0.15, mass=0.06 kg / recovery_open_jaw: 0/2 completed, 2 numerically valid<br>μ=0.15, mass=0.06 kg / hold: 0/2 completed, 2 numerically valid</details></div><p>Frozen v0.3, v0.4 carry-only and v0.4 full use privileged native simulator state. Each placement policy has its own matched open-jaw replay; a shared hold control remains. Failed grip tests, native motion, decisions, refusals, retries, resumes, aborts and invalid outcomes are retained. Uncalibrated contact proxies do not qualify a learned skill, physical detector or robot.</p><div class="links"><a href="tasks/piper-recovery-v04/report.html">Full three-policy comparison ↗</a><a href="tasks/piper-recovery-v04/report.json">Every outcome and diagnostic ↗</a><a href="tasks/piper-recovery-v04/protocol.json">Frozen recovery protocol ↗</a><a href="tasks/piper-recovery-v04/integrity.json">Stored and decoded attempt hashes ↗</a><a href="https://github.com/Dvidia-Inference/dvidia-training/blob/d5c1cc6adbf6566947aef6defb1bbc04207a96c4/docs/piper-contact-recovery-v04.md">Pinned offline inspection guide ↗</a></div><p class="tiny">All eighty-four full attempts are retained as deterministic gzip JSON with original stored and decoded hashes. Previous task and numerical evidence remains separate and unchanged. This adds no PiPER 3D viewer or physical qualification.</p></article><article class="profile"><span class="status">PiPER contact memory v0.3 · synthetic</span><h2>Compare probe and contact history.</h2><div class="summary"><p><strong>Placement completion: baseline 4/12, probe-only 4/12, history 6/12.</strong></p><p>Retries, resumes and release refusals do not imply successful placement or recovery.</p><p>Frozen confirmation cohort: 84 planned attempts across twelve synthetic scenes. Three frictions, two masses and two shared layouts; seven variants per scene. Every failed or invalid attempt remains in the denominator. Counts are descriptive, not physical reliability or detector accuracy.</p><details><summary>Inspect all friction, mass and control counts</summary>μ=0.80, mass=0.04 kg / baseline_placement: 2/2 completed, 2 numerically valid<br>μ=0.80, mass=0.04 kg / baseline_open_jaw: 0/2 completed, 2 numerically valid<br>μ=0.80, mass=0.04 kg / probe_only_placement: 2/2 completed, 2 numerically valid<br>μ=0.80, mass=0.04 kg / probe_only_open_jaw: 0/2 completed, 2 numerically valid<br>μ=0.80, mass=0.04 kg / history_placement: 2/2 completed, 2 numerically valid<br>μ=0.80, mass=0.04 kg / history_open_jaw: 0/2 completed, 2 numerically valid<br>μ=0.80, mass=0.04 kg / hold: 0/2 completed, 2 numerically valid<br>μ=0.80, mass=0.06 kg / baseline_placement: 0/2 completed, 2 numerically valid<br>μ=0.80, mass=0.06 kg / baseline_open_jaw: 0/2 completed, 2 numerically valid<br>μ=0.80, mass=0.06 kg / probe_only_placement: 0/2 completed, 2 numerically valid<br>μ=0.80, mass=0.06 kg / probe_only_open_jaw: 0/2 completed, 2 numerically valid<br>μ=0.80, mass=0.06 kg / history_placement: 2/2 completed, 2 numerically valid<br>μ=0.80, mass=0.06 kg / history_open_jaw: 0/2 completed, 2 numerically valid<br>μ=0.80, mass=0.06 kg / hold: 0/2 completed, 2 numerically valid<br>μ=0.55, mass=0.04 kg / baseline_placement: 2/2 completed, 2 numerically valid<br>μ=0.55, mass=0.04 kg / baseline_open_jaw: 0/2 completed, 2 numerically valid<br>μ=0.55, mass=0.04 kg / probe_only_placement: 2/2 completed, 2 numerically valid<br>μ=0.55, mass=0.04 kg / probe_only_open_jaw: 0/2 completed, 2 numerically valid<br>μ=0.55, mass=0.04 kg / history_placement: 2/2 completed, 2 numerically valid<br>μ=0.55, mass=0.04 kg / history_open_jaw: 0/2 completed, 2 numerically valid<br>μ=0.55, mass=0.04 kg / hold: 0/2 completed, 2 numerically valid<br>μ=0.55, mass=0.06 kg / baseline_placement: 0/2 completed, 2 numerically valid<br>μ=0.55, mass=0.06 kg / baseline_open_jaw: 0/2 completed, 2 numerically valid<br>μ=0.55, mass=0.06 kg / probe_only_placement: 0/2 completed, 2 numerically valid<br>μ=0.55, mass=0.06 kg / probe_only_open_jaw: 0/2 completed, 2 numerically valid<br>μ=0.55, mass=0.06 kg / history_placement: 0/2 completed, 2 numerically valid<br>μ=0.55, mass=0.06 kg / history_open_jaw: 0/2 completed, 2 numerically valid<br>μ=0.55, mass=0.06 kg / hold: 0/2 completed, 2 numerically valid<br>μ=0.15, mass=0.04 kg / baseline_placement: 0/2 completed, 2 numerically valid<br>μ=0.15, mass=0.04 kg / baseline_open_jaw: 0/2 completed, 2 numerically valid<br>μ=0.15, mass=0.04 kg / probe_only_placement: 0/2 completed, 2 numerically valid<br>μ=0.15, mass=0.04 kg / probe_only_open_jaw: 0/2 completed, 2 numerically valid<br>μ=0.15, mass=0.04 kg / history_placement: 0/2 completed, 2 numerically valid<br>μ=0.15, mass=0.04 kg / history_open_jaw: 0/2 completed, 2 numerically valid<br>μ=0.15, mass=0.04 kg / hold: 0/2 completed, 2 numerically valid<br>μ=0.15, mass=0.06 kg / baseline_placement: 0/2 completed, 2 numerically valid<br>μ=0.15, mass=0.06 kg / baseline_open_jaw: 0/2 completed, 2 numerically valid<br>μ=0.15, mass=0.06 kg / probe_only_placement: 0/2 completed, 2 numerically valid<br>μ=0.15, mass=0.06 kg / probe_only_open_jaw: 0/2 completed, 2 numerically valid<br>μ=0.15, mass=0.06 kg / history_placement: 0/2 completed, 2 numerically valid<br>μ=0.15, mass=0.06 kg / history_open_jaw: 0/2 completed, 2 numerically valid<br>μ=0.15, mass=0.06 kg / hold: 0/2 completed, 2 numerically valid</details></div><p>Three authored controllers use privileged native simulator state. Each placement policy has its own matched open-jaw replay; a shared hold control remains. Full contact history, decisions, refusals, retries, resumes, aborts and invalid outcomes are retained. Uncalibrated contact proxies do not qualify a learned skill, physical detector or robot.</p><div class="links"><a href="tasks/piper-contact-v03/report.html">Full three-policy comparison ↗</a><a href="tasks/piper-contact-v03/report.json">Every outcome and diagnostic ↗</a><a href="tasks/piper-contact-v03/protocol.json">Frozen contact-memory protocol ↗</a><a href="tasks/piper-contact-v03/integrity.json">Stored and decoded attempt hashes ↗</a><a href="https://github.com/Dvidia-Inference/dvidia-training/blob/d5c1cc6adbf6566947aef6defb1bbc04207a96c4/docs/piper-contact-memory-v03.md">Pinned offline inspection guide ↗</a></div><p class="tiny">All eighty-four full attempts are retained as deterministic gzip JSON with original stored and decoded hashes. Previous task and numerical evidence remains separate and unchanged. This adds no PiPER 3D viewer or physical qualification.</p></article><article class="profile"><span class="status">Recorded PiPER contact pilot · synthetic</span><h2>PiPER: authored grasp, carry and release</h2><p>Six arm commands in radians and one jaw command in metres. This pilot uses an authored controller and privileged native simulator state. Contact is uncalibrated; no learned skill, shoe competence or physical robot is qualified. No PiPER 3D viewer is included.</p><div class="summary"><strong>Frozen confirmation cohort: 9 planned attempts across 3 synthetic scenes. Counts are descriptive, with no population or physical reliability claim.</strong><br>nominal / placement: 2/2 completed, 2 numerically valid<br>nominal / replay_open_jaw: 0/2 completed, 2 numerically valid<br>nominal / hold: 0/2 completed, 2 numerically valid<br>low_friction / placement: 0/1 completed, 1 numerically valid<br>low_friction / replay_open_jaw: 0/1 completed, 1 numerically valid<br>low_friction / hold: 0/1 completed, 1 numerically valid</div><div class="links"><a href="tasks/piper/report.html">Every contact attempt ↗</a><a href="tasks/piper/report.json">Complete task report ↗</a><a href="tasks/piper/protocol.json">Frozen protocol ↗</a><a href="tasks/piper/integrity.json">All task file hashes ↗</a><a href="tasks/piper/licenses/agilex_piper/LICENSE">Original MIT model license ↗</a><a href="https://github.com/Dvidia-Inference/dvidia-training/blob/d5c1cc6adbf6566947aef6defb1bbc04207a96c4/docs/piper-contact-pilot.md">Pinned PiPER contact guide ↗</a></div></article><article class="profile"><span class="status">PiPER guarded grip comparison · synthetic</span><h2>Test the grip. Inspect recovery.</h2><div class="summary"><p><strong>Placement completion: baseline 4/6 versus guarded 2/6.</strong> This cohort does not show improved placement success.</p><p>Retries and qualification decisions do not imply successful recovery.</p><p>Frozen confirmation cohort: 30 planned attempts across six synthetic scenes. Two shared layouts at each friction; five variants per scene. Counts are descriptive, not physical reliability or detector accuracy.</p>μ=0.80 / baseline_placement: 2/2 completed, 2 numerically valid<br>μ=0.80 / baseline_open_jaw: 0/2 completed, 2 numerically valid<br>μ=0.80 / guarded_placement: 2/2 completed, 2 numerically valid<br>μ=0.80 / guarded_open_jaw: 0/2 completed, 2 numerically valid<br>μ=0.80 / hold: 0/2 completed, 2 numerically valid<br>μ=0.55 / baseline_placement: 2/2 completed, 2 numerically valid<br>μ=0.55 / baseline_open_jaw: 0/2 completed, 2 numerically valid<br>μ=0.55 / guarded_placement: 0/2 completed, 2 numerically valid<br>μ=0.55 / guarded_open_jaw: 0/2 completed, 2 numerically valid<br>μ=0.55 / hold: 0/2 completed, 2 numerically valid<br>μ=0.15 / baseline_placement: 0/2 completed, 2 numerically valid<br>μ=0.15 / baseline_open_jaw: 0/2 completed, 2 numerically valid<br>μ=0.15 / guarded_placement: 0/2 completed, 2 numerically valid<br>μ=0.15 / guarded_open_jaw: 0/2 completed, 2 numerically valid<br>μ=0.15 / hold: 0/2 completed, 2 numerically valid</div><p>Baseline and guarded controllers use privileged native state. Each has its own matched open-jaw replay; a shared hold control remains. Qualification decisions, retries, alarms, unresolved opportunities and aborts are retained. These are authored policies with uncalibrated contact, not learned skills or a physically qualified detector.</p><div class="links"><a href="tasks/piper-grip/report.html">Full paired comparison ↗</a><a href="tasks/piper-grip/report.json">All outcomes and diagnostics ↗</a><a href="tasks/piper-grip/protocol.json">Frozen guard and evaluation contract ↗</a><a href="tasks/piper-grip/integrity.json">Stored and decoded attempt hashes ↗</a><a href="https://github.com/Dvidia-Inference/dvidia-training/blob/d5c1cc6adbf6566947aef6defb1bbc04207a96c4/docs/piper-grip-recovery.md">Pinned offline inspection guide ↗</a></div><p class="tiny">Every full attempt is retained as deterministic gzip JSON. The CLI checks compressed and decoded hashes with bounded decompression; no archive extraction is needed. This comparison adds numerical evidence to the existing contact pilot; it adds no PiPER 3D viewer.</p></article><article class="profile"><span class="status">Recorded native mechanics · unloaded</span><h2>AgileX PiPER</h2><p>6 arm axes + 1 gripper axis. This separate bundle measures native model structure and authored unloaded motion. Its numerical receipts do not qualify a contact task, learned policy or physical robot. Simulation asset license: MIT.</p><div class="links"><a href="profiles/piper/report.html">Numerical report ↗</a><a href="profiles/piper/report.json">Complete recorded states ↗</a><a href="profiles/piper/integrity.json">File hashes ↗</a><a href="profiles/piper/licenses/piper/LICENSE">Model license ↗</a></div><a href="https://github.com/Dvidia-Inference/dvidia-training/blob/d5c1cc6adbf6566947aef6defb1bbc04207a96c4/docs/robot-simulation-library.md">Pinned local simulator guide ↗</a></article><article class="profile"><span class="status">Recorded native mechanics · unloaded</span><h2>The Robot Studio SO101</h2><p>5 arm axes + 1 gripper axis. This separate bundle measures native model structure and authored unloaded motion. Its numerical receipts do not qualify a contact task, learned policy or physical robot. Simulation asset license: Apache-2.0.</p><div class="links"><a href="profiles/so101/report.html">Numerical report ↗</a><a href="profiles/so101/report.json">Complete recorded states ↗</a><a href="profiles/so101/integrity.json">File hashes ↗</a><a href="profiles/so101/licenses/so101/LICENSE">Model license ↗</a></div><a href="https://github.com/Dvidia-Inference/dvidia-training/blob/d5c1cc6adbf6566947aef6defb1bbc04207a96c4/docs/robot-simulation-library.md">Pinned local simulator guide ↗</a></article><article class="profile"><span class="status">Upcoming · no task evidence</span><h2>Two arms and dexterous hands</h2><p>The roadmap extends to bilateral manipulation and five-finger hands. Contact tasks, sensing adapters and physical qualification remain to be built.</p><a href="https://research.dvidia.org/">Follow the research ↗</a></article></div><p class="tiny">A native mechanics benchmark establishes model structure and recorded motion. A native task benchmark adds measured contact outcomes. Neither establishes hardware reliability or a learned motor policy. Upcoming profiles have no verified implementation claim.</p></section>
-<section><h2>Run it on your own machine.</h2><p>The native task is a local CPU workload. Fetch the pinned dependencies and assets once, then simulate offline. WebGL2 supports viewing; no hosted inference or paid GPU server is requested by this static Space. Minimum RAM and arbitrary-dataset speed guarantees remain unmeasured.</p><div class="links"><a href="https://github.com/Dvidia-Inference/dvidia-training/blob/d5c1cc6adbf6566947aef6defb1bbc04207a96c4/docs/native-task-benchmark.md">Local installation and benchmark guide ↗</a><a href="provenance.json">Artifact provenance ↗</a><a href="replay/replay-integrity.json">Replay file hashes ↗</a><a href="replay/licenses/universal_robots_ur5e/LICENSE">UR5e model license ↗</a><a href="replay/licenses/robotiq_2f85/LICENSE">Gripper model license ↗</a></div></section>
+<section aria-labelledby="profiles-title"><h2 id="profiles-title">Hardware profiles and the next experiments.</h2><div class="gallery"><article class="profile"><span class="status">Recorded native contact task</span><h2>UR5e + Robotiq 2F-85</h2><p>Six arm joints, eight articulated gripper coordinates and a free rigid block. Full source outcomes and matched controls are available.</p><a href="replay/index.html">Inspect the task replay ↗</a></article><article class="profile"><span class="status">PiPER reliability v0.5 · synthetic</span><h2>Measure placement reliability.</h2><div class="summary"><p><strong>Placement completion: v0.4 4/12, v0.5 second lift 6/12, v0.5 full 7/12.</strong></p><p>v0.5 second lift versus v0.4: 2 gained, 0 lost, 4 shared successful scenes, 6 neither completed. Mean completion-time change on shared successes: +0.000 simulated seconds (candidate minus reference).</p><p>v0.5 full versus v0.4: 3 gained, 0 lost, 4 shared successful scenes, 5 neither completed. Mean completion-time change on shared successes: +0.847 simulated seconds (candidate minus reference).</p><p>v0.5 full versus v0.5 second lift: 1 gained, 0 lost, 6 shared successful scenes, 5 neither completed. Mean completion-time change on shared successes: +0.434 simulated seconds (candidate minus reference).</p><p>Protocol cohort: confirmation; seed 832847. 84 planned attempts across twelve synthetic scenes. Matched open-jaw and hold controls: 0/48 completed. Every failed or invalid attempt remains in the denominator. Cohorts are reported separately; a cohort label alone does not establish independence. Counts are descriptive synthetic evidence, not physical reliability, detector accuracy, learned competence or real-time sensor performance.</p><details><summary>Inspect every stratum, control and pilot gate</summary>Pilot gate complete planned denominator: passed<br>Pilot gate all native attempts valid: passed<br>Pilot gate all controls fail: passed<br>Pilot gate native integrity clean: passed<br>Pilot gate gained without lost completions: passed<br>μ=0.80, mass=0.04 kg / recovery_placement: 2/2 completed, 2 numerically valid<br>μ=0.80, mass=0.04 kg / recovery_open_jaw: 0/2 completed, 2 numerically valid<br>μ=0.80, mass=0.04 kg / reacquire_placement: 2/2 completed, 2 numerically valid<br>μ=0.80, mass=0.04 kg / reacquire_open_jaw: 0/2 completed, 2 numerically valid<br>μ=0.80, mass=0.04 kg / reacquire_grasp_placement: 2/2 completed, 2 numerically valid<br>μ=0.80, mass=0.04 kg / reacquire_grasp_open_jaw: 0/2 completed, 2 numerically valid<br>μ=0.80, mass=0.04 kg / hold: 0/2 completed, 2 numerically valid<br>μ=0.80, mass=0.06 kg / recovery_placement: 0/2 completed, 2 numerically valid<br>μ=0.80, mass=0.06 kg / recovery_open_jaw: 0/2 completed, 2 numerically valid<br>μ=0.80, mass=0.06 kg / reacquire_placement: 2/2 completed, 2 numerically valid<br>μ=0.80, mass=0.06 kg / reacquire_open_jaw: 0/2 completed, 2 numerically valid<br>μ=0.80, mass=0.06 kg / reacquire_grasp_placement: 2/2 completed, 2 numerically valid<br>μ=0.80, mass=0.06 kg / reacquire_grasp_open_jaw: 0/2 completed, 2 numerically valid<br>μ=0.80, mass=0.06 kg / hold: 0/2 completed, 2 numerically valid<br>μ=0.55, mass=0.04 kg / recovery_placement: 2/2 completed, 2 numerically valid<br>μ=0.55, mass=0.04 kg / recovery_open_jaw: 0/2 completed, 2 numerically valid<br>μ=0.55, mass=0.04 kg / reacquire_placement: 2/2 completed, 2 numerically valid<br>μ=0.55, mass=0.04 kg / reacquire_open_jaw: 0/2 completed, 2 numerically valid<br>μ=0.55, mass=0.04 kg / reacquire_grasp_placement: 2/2 completed, 2 numerically valid<br>μ=0.55, mass=0.04 kg / reacquire_grasp_open_jaw: 0/2 completed, 2 numerically valid<br>μ=0.55, mass=0.04 kg / hold: 0/2 completed, 2 numerically valid<br>μ=0.55, mass=0.06 kg / recovery_placement: 0/2 completed, 2 numerically valid<br>μ=0.55, mass=0.06 kg / recovery_open_jaw: 0/2 completed, 2 numerically valid<br>μ=0.55, mass=0.06 kg / reacquire_placement: 0/2 completed, 2 numerically valid<br>μ=0.55, mass=0.06 kg / reacquire_open_jaw: 0/2 completed, 2 numerically valid<br>μ=0.55, mass=0.06 kg / reacquire_grasp_placement: 1/2 completed, 2 numerically valid<br>μ=0.55, mass=0.06 kg / reacquire_grasp_open_jaw: 0/2 completed, 2 numerically valid<br>μ=0.55, mass=0.06 kg / hold: 0/2 completed, 2 numerically valid<br>μ=0.15, mass=0.04 kg / recovery_placement: 0/2 completed, 2 numerically valid<br>μ=0.15, mass=0.04 kg / recovery_open_jaw: 0/2 completed, 2 numerically valid<br>μ=0.15, mass=0.04 kg / reacquire_placement: 0/2 completed, 2 numerically valid<br>μ=0.15, mass=0.04 kg / reacquire_open_jaw: 0/2 completed, 2 numerically valid<br>μ=0.15, mass=0.04 kg / reacquire_grasp_placement: 0/2 completed, 2 numerically valid<br>μ=0.15, mass=0.04 kg / reacquire_grasp_open_jaw: 0/2 completed, 2 numerically valid<br>μ=0.15, mass=0.04 kg / hold: 0/2 completed, 2 numerically valid<br>μ=0.15, mass=0.06 kg / recovery_placement: 0/2 completed, 2 numerically valid<br>μ=0.15, mass=0.06 kg / recovery_open_jaw: 0/2 completed, 2 numerically valid<br>μ=0.15, mass=0.06 kg / reacquire_placement: 0/2 completed, 2 numerically valid<br>μ=0.15, mass=0.06 kg / reacquire_open_jaw: 0/2 completed, 2 numerically valid<br>μ=0.15, mass=0.06 kg / reacquire_grasp_placement: 0/2 completed, 2 numerically valid<br>μ=0.15, mass=0.06 kg / reacquire_grasp_open_jaw: 0/2 completed, 2 numerically valid<br>μ=0.15, mass=0.06 kg / hold: 0/2 completed, 2 numerically valid</details></div><p>The original height, retention and placement gates remain. Second-lift and alternate-grasp controllers use privileged simulator observations; a recovered grip is not automatically a completed placement. These are recorded receipts, with no PiPER 3D viewer or live browser physics.</p><div class="links"><a href="tasks/piper-reliability-v05/confirmation-832847/report.html">Complete paired comparison ↗</a><a href="tasks/piper-reliability-v05/confirmation-832847/report.json">Every outcome and diagnostic ↗</a><a href="tasks/piper-reliability-v05/confirmation-832847/protocol.json">Frozen protocol ↗</a><a href="tasks/piper-reliability-v05/confirmation-832847/integrity.json">Stored and decoded hashes ↗</a><a href="tasks/piper-reliability-v05/confirmation-832847/licenses/agilex_piper/LICENSE">Original MIT model license ↗</a><a href="https://github.com/Dvidia-Inference/dvidia-training/blob/0545ac47aedcd7c197341986533aa3e74c263ac6/docs/piper-reliability-v05-plan.md">Pinned experiment plan ↗</a></div></article><article class="profile"><span class="status">PiPER reliability v0.5 · synthetic</span><h2>Measure placement reliability.</h2><div class="summary"><p><strong>Placement completion: v0.4 6/12, v0.5 second lift 6/12, v0.5 full 8/12.</strong></p><p>v0.5 second lift versus v0.4: 0 gained, 0 lost, 6 shared successful scenes, 6 neither completed. Mean completion-time change on shared successes: +0.000 simulated seconds (candidate minus reference).</p><p>v0.5 full versus v0.4: 2 gained, 0 lost, 6 shared successful scenes, 4 neither completed. Mean completion-time change on shared successes: +0.698 simulated seconds (candidate minus reference).</p><p>v0.5 full versus v0.5 second lift: 2 gained, 0 lost, 6 shared successful scenes, 4 neither completed. Mean completion-time change on shared successes: +0.698 simulated seconds (candidate minus reference).</p><p>Protocol cohort: confirmation; seed 227037. 84 planned attempts across twelve synthetic scenes. Matched open-jaw and hold controls: 0/48 completed. Every failed or invalid attempt remains in the denominator. Cohorts are reported separately; a cohort label alone does not establish independence. Counts are descriptive synthetic evidence, not physical reliability, detector accuracy, learned competence or real-time sensor performance.</p><details><summary>Inspect every stratum, control and pilot gate</summary>Pilot gate complete planned denominator: passed<br>Pilot gate all native attempts valid: passed<br>Pilot gate all controls fail: passed<br>Pilot gate native integrity clean: passed<br>Pilot gate gained without lost completions: passed<br>μ=0.80, mass=0.04 kg / recovery_placement: 2/2 completed, 2 numerically valid<br>μ=0.80, mass=0.04 kg / recovery_open_jaw: 0/2 completed, 2 numerically valid<br>μ=0.80, mass=0.04 kg / reacquire_placement: 2/2 completed, 2 numerically valid<br>μ=0.80, mass=0.04 kg / reacquire_open_jaw: 0/2 completed, 2 numerically valid<br>μ=0.80, mass=0.04 kg / reacquire_grasp_placement: 2/2 completed, 2 numerically valid<br>μ=0.80, mass=0.04 kg / reacquire_grasp_open_jaw: 0/2 completed, 2 numerically valid<br>μ=0.80, mass=0.04 kg / hold: 0/2 completed, 2 numerically valid<br>μ=0.80, mass=0.06 kg / recovery_placement: 2/2 completed, 2 numerically valid<br>μ=0.80, mass=0.06 kg / recovery_open_jaw: 0/2 completed, 2 numerically valid<br>μ=0.80, mass=0.06 kg / reacquire_placement: 2/2 completed, 2 numerically valid<br>μ=0.80, mass=0.06 kg / reacquire_open_jaw: 0/2 completed, 2 numerically valid<br>μ=0.80, mass=0.06 kg / reacquire_grasp_placement: 2/2 completed, 2 numerically valid<br>μ=0.80, mass=0.06 kg / reacquire_grasp_open_jaw: 0/2 completed, 2 numerically valid<br>μ=0.80, mass=0.06 kg / hold: 0/2 completed, 2 numerically valid<br>μ=0.55, mass=0.04 kg / recovery_placement: 2/2 completed, 2 numerically valid<br>μ=0.55, mass=0.04 kg / recovery_open_jaw: 0/2 completed, 2 numerically valid<br>μ=0.55, mass=0.04 kg / reacquire_placement: 2/2 completed, 2 numerically valid<br>μ=0.55, mass=0.04 kg / reacquire_open_jaw: 0/2 completed, 2 numerically valid<br>μ=0.55, mass=0.04 kg / reacquire_grasp_placement: 2/2 completed, 2 numerically valid<br>μ=0.55, mass=0.04 kg / reacquire_grasp_open_jaw: 0/2 completed, 2 numerically valid<br>μ=0.55, mass=0.04 kg / hold: 0/2 completed, 2 numerically valid<br>μ=0.55, mass=0.06 kg / recovery_placement: 0/2 completed, 2 numerically valid<br>μ=0.55, mass=0.06 kg / recovery_open_jaw: 0/2 completed, 2 numerically valid<br>μ=0.55, mass=0.06 kg / reacquire_placement: 0/2 completed, 2 numerically valid<br>μ=0.55, mass=0.06 kg / reacquire_open_jaw: 0/2 completed, 2 numerically valid<br>μ=0.55, mass=0.06 kg / reacquire_grasp_placement: 2/2 completed, 2 numerically valid<br>μ=0.55, mass=0.06 kg / reacquire_grasp_open_jaw: 0/2 completed, 2 numerically valid<br>μ=0.55, mass=0.06 kg / hold: 0/2 completed, 2 numerically valid<br>μ=0.15, mass=0.04 kg / recovery_placement: 0/2 completed, 2 numerically valid<br>μ=0.15, mass=0.04 kg / recovery_open_jaw: 0/2 completed, 2 numerically valid<br>μ=0.15, mass=0.04 kg / reacquire_placement: 0/2 completed, 2 numerically valid<br>μ=0.15, mass=0.04 kg / reacquire_open_jaw: 0/2 completed, 2 numerically valid<br>μ=0.15, mass=0.04 kg / reacquire_grasp_placement: 0/2 completed, 2 numerically valid<br>μ=0.15, mass=0.04 kg / reacquire_grasp_open_jaw: 0/2 completed, 2 numerically valid<br>μ=0.15, mass=0.04 kg / hold: 0/2 completed, 2 numerically valid<br>μ=0.15, mass=0.06 kg / recovery_placement: 0/2 completed, 2 numerically valid<br>μ=0.15, mass=0.06 kg / recovery_open_jaw: 0/2 completed, 2 numerically valid<br>μ=0.15, mass=0.06 kg / reacquire_placement: 0/2 completed, 2 numerically valid<br>μ=0.15, mass=0.06 kg / reacquire_open_jaw: 0/2 completed, 2 numerically valid<br>μ=0.15, mass=0.06 kg / reacquire_grasp_placement: 0/2 completed, 2 numerically valid<br>μ=0.15, mass=0.06 kg / reacquire_grasp_open_jaw: 0/2 completed, 2 numerically valid<br>μ=0.15, mass=0.06 kg / hold: 0/2 completed, 2 numerically valid</details></div><p>The original height, retention and placement gates remain. Second-lift and alternate-grasp controllers use privileged simulator observations; a recovered grip is not automatically a completed placement. These are recorded receipts, with no PiPER 3D viewer or live browser physics.</p><div class="links"><a href="tasks/piper-reliability-v05/confirmation-227037/report.html">Complete paired comparison ↗</a><a href="tasks/piper-reliability-v05/confirmation-227037/report.json">Every outcome and diagnostic ↗</a><a href="tasks/piper-reliability-v05/confirmation-227037/protocol.json">Frozen protocol ↗</a><a href="tasks/piper-reliability-v05/confirmation-227037/integrity.json">Stored and decoded hashes ↗</a><a href="tasks/piper-reliability-v05/confirmation-227037/licenses/agilex_piper/LICENSE">Original MIT model license ↗</a><a href="https://github.com/Dvidia-Inference/dvidia-training/blob/0545ac47aedcd7c197341986533aa3e74c263ac6/docs/piper-reliability-v05-plan.md">Pinned experiment plan ↗</a></div></article><article class="profile"><span class="status">PiPER reliability v0.5 · synthetic</span><h2>Measure placement reliability.</h2><div class="summary"><p><strong>Placement completion: v0.4 5/12, v0.5 second lift 6/12, v0.5 full 8/12.</strong></p><p>v0.5 second lift versus v0.4: 1 gained, 0 lost, 5 shared successful scenes, 6 neither completed. Mean completion-time change on shared successes: +0.000 simulated seconds (candidate minus reference).</p><p>v0.5 full versus v0.4: 3 gained, 0 lost, 5 shared successful scenes, 4 neither completed. Mean completion-time change on shared successes: +0.800 simulated seconds (candidate minus reference).</p><p>v0.5 full versus v0.5 second lift: 2 gained, 0 lost, 6 shared successful scenes, 4 neither completed. Mean completion-time change on shared successes: +0.602 simulated seconds (candidate minus reference).</p><p>Protocol cohort: confirmation; seed 862186. 84 planned attempts across twelve synthetic scenes. Matched open-jaw and hold controls: 0/48 completed. Every failed or invalid attempt remains in the denominator. Cohorts are reported separately; a cohort label alone does not establish independence. Counts are descriptive synthetic evidence, not physical reliability, detector accuracy, learned competence or real-time sensor performance.</p><details><summary>Inspect every stratum, control and pilot gate</summary>Pilot gate complete planned denominator: passed<br>Pilot gate all native attempts valid: passed<br>Pilot gate all controls fail: passed<br>Pilot gate native integrity clean: passed<br>Pilot gate gained without lost completions: passed<br>μ=0.80, mass=0.04 kg / recovery_placement: 2/2 completed, 2 numerically valid<br>μ=0.80, mass=0.04 kg / recovery_open_jaw: 0/2 completed, 2 numerically valid<br>μ=0.80, mass=0.04 kg / reacquire_placement: 2/2 completed, 2 numerically valid<br>μ=0.80, mass=0.04 kg / reacquire_open_jaw: 0/2 completed, 2 numerically valid<br>μ=0.80, mass=0.04 kg / reacquire_grasp_placement: 2/2 completed, 2 numerically valid<br>μ=0.80, mass=0.04 kg / reacquire_grasp_open_jaw: 0/2 completed, 2 numerically valid<br>μ=0.80, mass=0.04 kg / hold: 0/2 completed, 2 numerically valid<br>μ=0.80, mass=0.06 kg / recovery_placement: 1/2 completed, 2 numerically valid<br>μ=0.80, mass=0.06 kg / recovery_open_jaw: 0/2 completed, 2 numerically valid<br>μ=0.80, mass=0.06 kg / reacquire_placement: 2/2 completed, 2 numerically valid<br>μ=0.80, mass=0.06 kg / reacquire_open_jaw: 0/2 completed, 2 numerically valid<br>μ=0.80, mass=0.06 kg / reacquire_grasp_placement: 2/2 completed, 2 numerically valid<br>μ=0.80, mass=0.06 kg / reacquire_grasp_open_jaw: 0/2 completed, 2 numerically valid<br>μ=0.80, mass=0.06 kg / hold: 0/2 completed, 2 numerically valid<br>μ=0.55, mass=0.04 kg / recovery_placement: 2/2 completed, 2 numerically valid<br>μ=0.55, mass=0.04 kg / recovery_open_jaw: 0/2 completed, 2 numerically valid<br>μ=0.55, mass=0.04 kg / reacquire_placement: 2/2 completed, 2 numerically valid<br>μ=0.55, mass=0.04 kg / reacquire_open_jaw: 0/2 completed, 2 numerically valid<br>μ=0.55, mass=0.04 kg / reacquire_grasp_placement: 2/2 completed, 2 numerically valid<br>μ=0.55, mass=0.04 kg / reacquire_grasp_open_jaw: 0/2 completed, 2 numerically valid<br>μ=0.55, mass=0.04 kg / hold: 0/2 completed, 2 numerically valid<br>μ=0.55, mass=0.06 kg / recovery_placement: 0/2 completed, 2 numerically valid<br>μ=0.55, mass=0.06 kg / recovery_open_jaw: 0/2 completed, 2 numerically valid<br>μ=0.55, mass=0.06 kg / reacquire_placement: 0/2 completed, 2 numerically valid<br>μ=0.55, mass=0.06 kg / reacquire_open_jaw: 0/2 completed, 2 numerically valid<br>μ=0.55, mass=0.06 kg / reacquire_grasp_placement: 2/2 completed, 2 numerically valid<br>μ=0.55, mass=0.06 kg / reacquire_grasp_open_jaw: 0/2 completed, 2 numerically valid<br>μ=0.55, mass=0.06 kg / hold: 0/2 completed, 2 numerically valid<br>μ=0.15, mass=0.04 kg / recovery_placement: 0/2 completed, 2 numerically valid<br>μ=0.15, mass=0.04 kg / recovery_open_jaw: 0/2 completed, 2 numerically valid<br>μ=0.15, mass=0.04 kg / reacquire_placement: 0/2 completed, 2 numerically valid<br>μ=0.15, mass=0.04 kg / reacquire_open_jaw: 0/2 completed, 2 numerically valid<br>μ=0.15, mass=0.04 kg / reacquire_grasp_placement: 0/2 completed, 2 numerically valid<br>μ=0.15, mass=0.04 kg / reacquire_grasp_open_jaw: 0/2 completed, 2 numerically valid<br>μ=0.15, mass=0.04 kg / hold: 0/2 completed, 2 numerically valid<br>μ=0.15, mass=0.06 kg / recovery_placement: 0/2 completed, 2 numerically valid<br>μ=0.15, mass=0.06 kg / recovery_open_jaw: 0/2 completed, 2 numerically valid<br>μ=0.15, mass=0.06 kg / reacquire_placement: 0/2 completed, 2 numerically valid<br>μ=0.15, mass=0.06 kg / reacquire_open_jaw: 0/2 completed, 2 numerically valid<br>μ=0.15, mass=0.06 kg / reacquire_grasp_placement: 0/2 completed, 2 numerically valid<br>μ=0.15, mass=0.06 kg / reacquire_grasp_open_jaw: 0/2 completed, 2 numerically valid<br>μ=0.15, mass=0.06 kg / hold: 0/2 completed, 2 numerically valid</details></div><p>The original height, retention and placement gates remain. Second-lift and alternate-grasp controllers use privileged simulator observations; a recovered grip is not automatically a completed placement. These are recorded receipts, with no PiPER 3D viewer or live browser physics.</p><div class="links"><a href="tasks/piper-reliability-v05/confirmation-862186/report.html">Complete paired comparison ↗</a><a href="tasks/piper-reliability-v05/confirmation-862186/report.json">Every outcome and diagnostic ↗</a><a href="tasks/piper-reliability-v05/confirmation-862186/protocol.json">Frozen protocol ↗</a><a href="tasks/piper-reliability-v05/confirmation-862186/integrity.json">Stored and decoded hashes ↗</a><a href="tasks/piper-reliability-v05/confirmation-862186/licenses/agilex_piper/LICENSE">Original MIT model license ↗</a><a href="https://github.com/Dvidia-Inference/dvidia-training/blob/0545ac47aedcd7c197341986533aa3e74c263ac6/docs/piper-reliability-v05-plan.md">Pinned experiment plan ↗</a></div></article><article class="profile"><span class="status">PiPER grip recovery v0.4 · synthetic</span><h2>Measure recovery and grip refusal.</h2><div class="summary"><p><strong>Placement completion: v0.3 4/12, v0.4 carry-only 4/12, v0.4 full 4/12.</strong></p><p>Retries, resumes and grip refusals do not imply successful placement or recovery. Shared successful scenes: 4; gained placements: 0; lost placements: 0. Mean completion-time change on shared successes: -1.270 simulated seconds (v0.4 minus v0.3). Hold-duration and post-resume motion remain separate in the report.</p><p>Frozen confirmation cohort: 84 planned attempts across twelve synthetic scenes. Three frictions, two masses and two shared layouts; seven variants per scene. Every failed or invalid attempt remains in the denominator. Counts are descriptive, not physical reliability or detector accuracy.</p><details><summary>Inspect all friction, mass and control counts</summary>μ=0.80, mass=0.04 kg / history_placement: 2/2 completed, 2 numerically valid<br>μ=0.80, mass=0.04 kg / history_open_jaw: 0/2 completed, 2 numerically valid<br>μ=0.80, mass=0.04 kg / recovery_carry_placement: 2/2 completed, 2 numerically valid<br>μ=0.80, mass=0.04 kg / recovery_carry_open_jaw: 0/2 completed, 2 numerically valid<br>μ=0.80, mass=0.04 kg / recovery_placement: 2/2 completed, 2 numerically valid<br>μ=0.80, mass=0.04 kg / recovery_open_jaw: 0/2 completed, 2 numerically valid<br>μ=0.80, mass=0.04 kg / hold: 0/2 completed, 2 numerically valid<br>μ=0.80, mass=0.06 kg / history_placement: 0/2 completed, 2 numerically valid<br>μ=0.80, mass=0.06 kg / history_open_jaw: 0/2 completed, 2 numerically valid<br>μ=0.80, mass=0.06 kg / recovery_carry_placement: 0/2 completed, 2 numerically valid<br>μ=0.80, mass=0.06 kg / recovery_carry_open_jaw: 0/2 completed, 2 numerically valid<br>μ=0.80, mass=0.06 kg / recovery_placement: 0/2 completed, 2 numerically valid<br>μ=0.80, mass=0.06 kg / recovery_open_jaw: 0/2 completed, 2 numerically valid<br>μ=0.80, mass=0.06 kg / hold: 0/2 completed, 2 numerically valid<br>μ=0.55, mass=0.04 kg / history_placement: 2/2 completed, 2 numerically valid<br>μ=0.55, mass=0.04 kg / history_open_jaw: 0/2 completed, 2 numerically valid<br>μ=0.55, mass=0.04 kg / recovery_carry_placement: 2/2 completed, 2 numerically valid<br>μ=0.55, mass=0.04 kg / recovery_carry_open_jaw: 0/2 completed, 2 numerically valid<br>μ=0.55, mass=0.04 kg / recovery_placement: 2/2 completed, 2 numerically valid<br>μ=0.55, mass=0.04 kg / recovery_open_jaw: 0/2 completed, 2 numerically valid<br>μ=0.55, mass=0.04 kg / hold: 0/2 completed, 2 numerically valid<br>μ=0.55, mass=0.06 kg / history_placement: 0/2 completed, 2 numerically valid<br>μ=0.55, mass=0.06 kg / history_open_jaw: 0/2 completed, 2 numerically valid<br>μ=0.55, mass=0.06 kg / recovery_carry_placement: 0/2 completed, 2 numerically valid<br>μ=0.55, mass=0.06 kg / recovery_carry_open_jaw: 0/2 completed, 2 numerically valid<br>μ=0.55, mass=0.06 kg / recovery_placement: 0/2 completed, 2 numerically valid<br>μ=0.55, mass=0.06 kg / recovery_open_jaw: 0/2 completed, 2 numerically valid<br>μ=0.55, mass=0.06 kg / hold: 0/2 completed, 2 numerically valid<br>μ=0.15, mass=0.04 kg / history_placement: 0/2 completed, 2 numerically valid<br>μ=0.15, mass=0.04 kg / history_open_jaw: 0/2 completed, 2 numerically valid<br>μ=0.15, mass=0.04 kg / recovery_carry_placement: 0/2 completed, 2 numerically valid<br>μ=0.15, mass=0.04 kg / recovery_carry_open_jaw: 0/2 completed, 2 numerically valid<br>μ=0.15, mass=0.04 kg / recovery_placement: 0/2 completed, 2 numerically valid<br>μ=0.15, mass=0.04 kg / recovery_open_jaw: 0/2 completed, 2 numerically valid<br>μ=0.15, mass=0.04 kg / hold: 0/2 completed, 2 numerically valid<br>μ=0.15, mass=0.06 kg / history_placement: 0/2 completed, 2 numerically valid<br>μ=0.15, mass=0.06 kg / history_open_jaw: 0/2 completed, 2 numerically valid<br>μ=0.15, mass=0.06 kg / recovery_carry_placement: 0/2 completed, 2 numerically valid<br>μ=0.15, mass=0.06 kg / recovery_carry_open_jaw: 0/2 completed, 2 numerically valid<br>μ=0.15, mass=0.06 kg / recovery_placement: 0/2 completed, 2 numerically valid<br>μ=0.15, mass=0.06 kg / recovery_open_jaw: 0/2 completed, 2 numerically valid<br>μ=0.15, mass=0.06 kg / hold: 0/2 completed, 2 numerically valid</details></div><p>Frozen v0.3, v0.4 carry-only and v0.4 full use privileged native simulator state. Each placement policy has its own matched open-jaw replay; a shared hold control remains. Failed grip tests, native motion, decisions, refusals, retries, resumes, aborts and invalid outcomes are retained. Uncalibrated contact proxies do not qualify a learned skill, physical detector or robot.</p><div class="links"><a href="tasks/piper-recovery-v04/report.html">Full three-policy comparison ↗</a><a href="tasks/piper-recovery-v04/report.json">Every outcome and diagnostic ↗</a><a href="tasks/piper-recovery-v04/protocol.json">Frozen recovery protocol ↗</a><a href="tasks/piper-recovery-v04/integrity.json">Stored and decoded attempt hashes ↗</a><a href="https://github.com/Dvidia-Inference/dvidia-training/blob/0545ac47aedcd7c197341986533aa3e74c263ac6/docs/piper-contact-recovery-v04.md">Pinned offline inspection guide ↗</a></div><p class="tiny">All eighty-four full attempts are retained as deterministic gzip JSON with original stored and decoded hashes. Previous task and numerical evidence remains separate and unchanged. This adds no PiPER 3D viewer or physical qualification.</p></article><article class="profile"><span class="status">PiPER contact memory v0.3 · synthetic</span><h2>Compare probe and contact history.</h2><div class="summary"><p><strong>Placement completion: baseline 4/12, probe-only 4/12, history 6/12.</strong></p><p>Retries, resumes and release refusals do not imply successful placement or recovery.</p><p>Frozen confirmation cohort: 84 planned attempts across twelve synthetic scenes. Three frictions, two masses and two shared layouts; seven variants per scene. Every failed or invalid attempt remains in the denominator. Counts are descriptive, not physical reliability or detector accuracy.</p><details><summary>Inspect all friction, mass and control counts</summary>μ=0.80, mass=0.04 kg / baseline_placement: 2/2 completed, 2 numerically valid<br>μ=0.80, mass=0.04 kg / baseline_open_jaw: 0/2 completed, 2 numerically valid<br>μ=0.80, mass=0.04 kg / probe_only_placement: 2/2 completed, 2 numerically valid<br>μ=0.80, mass=0.04 kg / probe_only_open_jaw: 0/2 completed, 2 numerically valid<br>μ=0.80, mass=0.04 kg / history_placement: 2/2 completed, 2 numerically valid<br>μ=0.80, mass=0.04 kg / history_open_jaw: 0/2 completed, 2 numerically valid<br>μ=0.80, mass=0.04 kg / hold: 0/2 completed, 2 numerically valid<br>μ=0.80, mass=0.06 kg / baseline_placement: 0/2 completed, 2 numerically valid<br>μ=0.80, mass=0.06 kg / baseline_open_jaw: 0/2 completed, 2 numerically valid<br>μ=0.80, mass=0.06 kg / probe_only_placement: 0/2 completed, 2 numerically valid<br>μ=0.80, mass=0.06 kg / probe_only_open_jaw: 0/2 completed, 2 numerically valid<br>μ=0.80, mass=0.06 kg / history_placement: 2/2 completed, 2 numerically valid<br>μ=0.80, mass=0.06 kg / history_open_jaw: 0/2 completed, 2 numerically valid<br>μ=0.80, mass=0.06 kg / hold: 0/2 completed, 2 numerically valid<br>μ=0.55, mass=0.04 kg / baseline_placement: 2/2 completed, 2 numerically valid<br>μ=0.55, mass=0.04 kg / baseline_open_jaw: 0/2 completed, 2 numerically valid<br>μ=0.55, mass=0.04 kg / probe_only_placement: 2/2 completed, 2 numerically valid<br>μ=0.55, mass=0.04 kg / probe_only_open_jaw: 0/2 completed, 2 numerically valid<br>μ=0.55, mass=0.04 kg / history_placement: 2/2 completed, 2 numerically valid<br>μ=0.55, mass=0.04 kg / history_open_jaw: 0/2 completed, 2 numerically valid<br>μ=0.55, mass=0.04 kg / hold: 0/2 completed, 2 numerically valid<br>μ=0.55, mass=0.06 kg / baseline_placement: 0/2 completed, 2 numerically valid<br>μ=0.55, mass=0.06 kg / baseline_open_jaw: 0/2 completed, 2 numerically valid<br>μ=0.55, mass=0.06 kg / probe_only_placement: 0/2 completed, 2 numerically valid<br>μ=0.55, mass=0.06 kg / probe_only_open_jaw: 0/2 completed, 2 numerically valid<br>μ=0.55, mass=0.06 kg / history_placement: 0/2 completed, 2 numerically valid<br>μ=0.55, mass=0.06 kg / history_open_jaw: 0/2 completed, 2 numerically valid<br>μ=0.55, mass=0.06 kg / hold: 0/2 completed, 2 numerically valid<br>μ=0.15, mass=0.04 kg / baseline_placement: 0/2 completed, 2 numerically valid<br>μ=0.15, mass=0.04 kg / baseline_open_jaw: 0/2 completed, 2 numerically valid<br>μ=0.15, mass=0.04 kg / probe_only_placement: 0/2 completed, 2 numerically valid<br>μ=0.15, mass=0.04 kg / probe_only_open_jaw: 0/2 completed, 2 numerically valid<br>μ=0.15, mass=0.04 kg / history_placement: 0/2 completed, 2 numerically valid<br>μ=0.15, mass=0.04 kg / history_open_jaw: 0/2 completed, 2 numerically valid<br>μ=0.15, mass=0.04 kg / hold: 0/2 completed, 2 numerically valid<br>μ=0.15, mass=0.06 kg / baseline_placement: 0/2 completed, 2 numerically valid<br>μ=0.15, mass=0.06 kg / baseline_open_jaw: 0/2 completed, 2 numerically valid<br>μ=0.15, mass=0.06 kg / probe_only_placement: 0/2 completed, 2 numerically valid<br>μ=0.15, mass=0.06 kg / probe_only_open_jaw: 0/2 completed, 2 numerically valid<br>μ=0.15, mass=0.06 kg / history_placement: 0/2 completed, 2 numerically valid<br>μ=0.15, mass=0.06 kg / history_open_jaw: 0/2 completed, 2 numerically valid<br>μ=0.15, mass=0.06 kg / hold: 0/2 completed, 2 numerically valid</details></div><p>Three authored controllers use privileged native simulator state. Each placement policy has its own matched open-jaw replay; a shared hold control remains. Full contact history, decisions, refusals, retries, resumes, aborts and invalid outcomes are retained. Uncalibrated contact proxies do not qualify a learned skill, physical detector or robot.</p><div class="links"><a href="tasks/piper-contact-v03/report.html">Full three-policy comparison ↗</a><a href="tasks/piper-contact-v03/report.json">Every outcome and diagnostic ↗</a><a href="tasks/piper-contact-v03/protocol.json">Frozen contact-memory protocol ↗</a><a href="tasks/piper-contact-v03/integrity.json">Stored and decoded attempt hashes ↗</a><a href="https://github.com/Dvidia-Inference/dvidia-training/blob/0545ac47aedcd7c197341986533aa3e74c263ac6/docs/piper-contact-memory-v03.md">Pinned offline inspection guide ↗</a></div><p class="tiny">All eighty-four full attempts are retained as deterministic gzip JSON with original stored and decoded hashes. Previous task and numerical evidence remains separate and unchanged. This adds no PiPER 3D viewer or physical qualification.</p></article><article class="profile"><span class="status">Recorded PiPER contact pilot · synthetic</span><h2>PiPER: authored grasp, carry and release</h2><p>Six arm commands in radians and one jaw command in metres. This pilot uses an authored controller and privileged native simulator state. Contact is uncalibrated; no learned skill, shoe competence or physical robot is qualified. No PiPER 3D viewer is included.</p><div class="summary"><strong>Frozen confirmation cohort: 9 planned attempts across 3 synthetic scenes. Counts are descriptive, with no population or physical reliability claim.</strong><br>nominal / placement: 2/2 completed, 2 numerically valid<br>nominal / replay_open_jaw: 0/2 completed, 2 numerically valid<br>nominal / hold: 0/2 completed, 2 numerically valid<br>low_friction / placement: 0/1 completed, 1 numerically valid<br>low_friction / replay_open_jaw: 0/1 completed, 1 numerically valid<br>low_friction / hold: 0/1 completed, 1 numerically valid</div><div class="links"><a href="tasks/piper/report.html">Every contact attempt ↗</a><a href="tasks/piper/report.json">Complete task report ↗</a><a href="tasks/piper/protocol.json">Frozen protocol ↗</a><a href="tasks/piper/integrity.json">All task file hashes ↗</a><a href="tasks/piper/licenses/agilex_piper/LICENSE">Original MIT model license ↗</a><a href="https://github.com/Dvidia-Inference/dvidia-training/blob/0545ac47aedcd7c197341986533aa3e74c263ac6/docs/piper-contact-pilot.md">Pinned PiPER contact guide ↗</a></div></article><article class="profile"><span class="status">PiPER guarded grip comparison · synthetic</span><h2>Test the grip. Inspect recovery.</h2><div class="summary"><p><strong>Placement completion: baseline 4/6 versus guarded 2/6.</strong> This cohort does not show improved placement success.</p><p>Retries and qualification decisions do not imply successful recovery.</p><p>Frozen confirmation cohort: 30 planned attempts across six synthetic scenes. Two shared layouts at each friction; five variants per scene. Counts are descriptive, not physical reliability or detector accuracy.</p>μ=0.80 / baseline_placement: 2/2 completed, 2 numerically valid<br>μ=0.80 / baseline_open_jaw: 0/2 completed, 2 numerically valid<br>μ=0.80 / guarded_placement: 2/2 completed, 2 numerically valid<br>μ=0.80 / guarded_open_jaw: 0/2 completed, 2 numerically valid<br>μ=0.80 / hold: 0/2 completed, 2 numerically valid<br>μ=0.55 / baseline_placement: 2/2 completed, 2 numerically valid<br>μ=0.55 / baseline_open_jaw: 0/2 completed, 2 numerically valid<br>μ=0.55 / guarded_placement: 0/2 completed, 2 numerically valid<br>μ=0.55 / guarded_open_jaw: 0/2 completed, 2 numerically valid<br>μ=0.55 / hold: 0/2 completed, 2 numerically valid<br>μ=0.15 / baseline_placement: 0/2 completed, 2 numerically valid<br>μ=0.15 / baseline_open_jaw: 0/2 completed, 2 numerically valid<br>μ=0.15 / guarded_placement: 0/2 completed, 2 numerically valid<br>μ=0.15 / guarded_open_jaw: 0/2 completed, 2 numerically valid<br>μ=0.15 / hold: 0/2 completed, 2 numerically valid</div><p>Baseline and guarded controllers use privileged native state. Each has its own matched open-jaw replay; a shared hold control remains. Qualification decisions, retries, alarms, unresolved opportunities and aborts are retained. These are authored policies with uncalibrated contact, not learned skills or a physically qualified detector.</p><div class="links"><a href="tasks/piper-grip/report.html">Full paired comparison ↗</a><a href="tasks/piper-grip/report.json">All outcomes and diagnostics ↗</a><a href="tasks/piper-grip/protocol.json">Frozen guard and evaluation contract ↗</a><a href="tasks/piper-grip/integrity.json">Stored and decoded attempt hashes ↗</a><a href="https://github.com/Dvidia-Inference/dvidia-training/blob/0545ac47aedcd7c197341986533aa3e74c263ac6/docs/piper-grip-recovery.md">Pinned offline inspection guide ↗</a></div><p class="tiny">Every full attempt is retained as deterministic gzip JSON. The CLI checks compressed and decoded hashes with bounded decompression; no archive extraction is needed. This comparison adds numerical evidence to the existing contact pilot; it adds no PiPER 3D viewer.</p></article><article class="profile"><span class="status">Recorded native mechanics · unloaded</span><h2>AgileX PiPER</h2><p>6 arm axes + 1 gripper axis. This separate bundle measures native model structure and authored unloaded motion. Its numerical receipts do not qualify a contact task, learned policy or physical robot. Simulation asset license: MIT.</p><div class="links"><a href="profiles/piper/report.html">Numerical report ↗</a><a href="profiles/piper/report.json">Complete recorded states ↗</a><a href="profiles/piper/integrity.json">File hashes ↗</a><a href="profiles/piper/licenses/piper/LICENSE">Model license ↗</a></div><a href="https://github.com/Dvidia-Inference/dvidia-training/blob/0545ac47aedcd7c197341986533aa3e74c263ac6/docs/robot-simulation-library.md">Pinned local simulator guide ↗</a></article><article class="profile"><span class="status">Recorded native mechanics · unloaded</span><h2>The Robot Studio SO101</h2><p>5 arm axes + 1 gripper axis. This separate bundle measures native model structure and authored unloaded motion. Its numerical receipts do not qualify a contact task, learned policy or physical robot. Simulation asset license: Apache-2.0.</p><div class="links"><a href="profiles/so101/report.html">Numerical report ↗</a><a href="profiles/so101/report.json">Complete recorded states ↗</a><a href="profiles/so101/integrity.json">File hashes ↗</a><a href="profiles/so101/licenses/so101/LICENSE">Model license ↗</a></div><a href="https://github.com/Dvidia-Inference/dvidia-training/blob/0545ac47aedcd7c197341986533aa3e74c263ac6/docs/robot-simulation-library.md">Pinned local simulator guide ↗</a></article><article class="profile"><span class="status">Upcoming · no task evidence</span><h2>Two arms and dexterous hands</h2><p>The roadmap extends to bilateral manipulation and five-finger hands. Contact tasks, sensing adapters and physical qualification remain to be built.</p><a href="https://research.dvidia.org/">Follow the research ↗</a></article></div><p class="tiny">A native mechanics benchmark establishes model structure and recorded motion. A native task benchmark adds measured contact outcomes. Neither establishes hardware reliability or a learned motor policy. Upcoming profiles have no verified implementation claim.</p></section>
+<section><h2>Run it on your own machine.</h2><p>The native task is a local CPU workload. Fetch the pinned dependencies and assets once, then simulate offline. WebGL2 supports viewing; no hosted inference or paid GPU server is requested by this static Space. Minimum RAM and arbitrary-dataset speed guarantees remain unmeasured.</p><div class="links"><a href="https://github.com/Dvidia-Inference/dvidia-training/blob/0545ac47aedcd7c197341986533aa3e74c263ac6/docs/native-task-benchmark.md">Local installation and benchmark guide ↗</a><a href="provenance.json">Artifact provenance ↗</a><a href="replay/replay-integrity.json">Replay file hashes ↗</a><a href="replay/licenses/universal_robots_ur5e/LICENSE">UR5e model license ↗</a><a href="replay/licenses/robotiq_2f85/LICENSE">Gripper model license ↗</a></div></section>
 <footer><span>Open-source DVIDIA research</span><a href="https://x.com/iammrriver">@iammrriver ↗</a><a href="mailto:hello@dvidia.org">hello@dvidia.org</a><a href="https://huggingface.co/Dvidia">Hugging Face organization ↗</a></footer></main></body></html>

tasks/piper-reliability-v05/confirmation-227037/attempts/friction015-mass040-layout00--hold.json.gz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7ea4fa51fac0fabbd332225eb6ac72ac94427d10d884876db923cfd20d613be
+size 348100

tasks/piper-reliability-v05/confirmation-227037/attempts/friction015-mass040-layout00--reacquire_grasp_open_jaw.json.gz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:880ba3b16f9e4cfc4a1e0bde8389c2309850122be682f9fee0dabaa82bdf16f5
+size 620434

tasks/piper-reliability-v05/confirmation-227037/attempts/friction015-mass040-layout00--reacquire_grasp_placement.json.gz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2939186ad9e667d526a9472fcca08a8ff4606580d55b38cbb3b242ade417fed
+size 719745

tasks/piper-reliability-v05/confirmation-227037/attempts/friction015-mass040-layout00--reacquire_open_jaw.json.gz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13025a164052d07b2dcb754c2da03cc1c0ebdf97e2e28b4de7efb6590fc5ee27
+size 631436

tasks/piper-reliability-v05/confirmation-227037/attempts/friction015-mass040-layout00--reacquire_placement.json.gz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9020eabe61a3fb9e64e312614cfd414e9d7fb5641f6cf3071396793598826f1
+size 755508

tasks/piper-reliability-v05/confirmation-227037/attempts/friction015-mass040-layout00--recovery_open_jaw.json.gz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5432d9f45a23ea0661e750858487d2fcadb4d562044c16eea4c00b312ef70d62
+size 630775

tasks/piper-reliability-v05/confirmation-227037/attempts/friction015-mass040-layout00--recovery_placement.json.gz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:caced57a65c3003e60ac180e8ec9876f31d3256984972caa0f966a5710a711cf
+size 749576

tasks/piper-reliability-v05/confirmation-227037/attempts/friction015-mass040-layout01--hold.json.gz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bbd68cb70e30c3348492e7e0a445b7a41832b7cfdc21c8581a0dc22553b0478c
+size 347703

tasks/piper-reliability-v05/confirmation-227037/attempts/friction015-mass040-layout01--reacquire_grasp_open_jaw.json.gz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c2ddd3939100f3d3175cf2132f3f06715e28eed6eebfdcb3ff53546c8bd46fb
+size 621204

tasks/piper-reliability-v05/confirmation-227037/attempts/friction015-mass040-layout01--reacquire_grasp_placement.json.gz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ada48c6ed1b8397e7b0a39db669774a6e69ca6f1726503b65b13c8d0ab52303
+size 718656

tasks/piper-reliability-v05/confirmation-227037/attempts/friction015-mass040-layout01--reacquire_open_jaw.json.gz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ae2ed074cd1a2ace5408609299d53005ad20332b2b8331d5e75f91f799a626c
+size 609684

tasks/piper-reliability-v05/confirmation-227037/attempts/friction015-mass040-layout01--reacquire_placement.json.gz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b10d188246d0794aa8ad47b3e9092bd3b99d3a0b88b32a34ad351798b1a31196
+size 738073

tasks/piper-reliability-v05/confirmation-227037/attempts/friction015-mass040-layout01--recovery_open_jaw.json.gz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a225f7a866c2fdca23d51c87db1ae8dd8337584ffa7d3b16db7da812e22c971a
+size 609370

tasks/piper-reliability-v05/confirmation-227037/attempts/friction015-mass040-layout01--recovery_placement.json.gz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe7f7418a89434c2e8d0dd09166927e0e4d572429faa1f9bd8e553185dff7c27
+size 732852

tasks/piper-reliability-v05/confirmation-227037/attempts/friction015-mass060-layout00--hold.json.gz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ad22e8bb689c7898082087b9408aba1aae90a6aa5df64759c1147b7a8b33d47
+size 347180

tasks/piper-reliability-v05/confirmation-227037/attempts/friction015-mass060-layout00--reacquire_grasp_open_jaw.json.gz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:111b0a8bfb27f456ca9ace911845d5aaf6b88372d9cf5084e96cd52066878aa2
+size 619027

tasks/piper-reliability-v05/confirmation-227037/attempts/friction015-mass060-layout00--reacquire_grasp_placement.json.gz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8b0f67e75b5ad2b8146c09f56bec6dd90f2250704192177471100d1e5574322
+size 714867

tasks/piper-reliability-v05/confirmation-227037/attempts/friction015-mass060-layout00--reacquire_open_jaw.json.gz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a943fcfa2dd8ea42ebfc2928ad2198a85d362d457332c80c708323152f39e7e
+size 630459

tasks/piper-reliability-v05/confirmation-227037/attempts/friction015-mass060-layout00--reacquire_placement.json.gz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f57dbb7e7a971aef13e72bbe3db8c9b83d0dba09ee72329cb184e3013160101
+size 753242

tasks/piper-reliability-v05/confirmation-227037/attempts/friction015-mass060-layout00--recovery_open_jaw.json.gz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6856229f611629a599729b04a05efcda572c647a51f1beb461e86758ae558cf
+size 629907

tasks/piper-reliability-v05/confirmation-227037/attempts/friction015-mass060-layout00--recovery_placement.json.gz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9923f28e3d9f8b8090df7a55a57f858e1de7953ec34ded32dd22779d213b95f
+size 747250

tasks/piper-reliability-v05/confirmation-227037/attempts/friction015-mass060-layout01--hold.json.gz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44449c8c8978fb37c1bb2e9a9c943a705b7c339917f1a49c25c1faf9efdda1f9
+size 347562

tasks/piper-reliability-v05/confirmation-227037/attempts/friction015-mass060-layout01--reacquire_grasp_open_jaw.json.gz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e6a19db0c66092347a6ebbd49d185695bce88b563debcb63d6edde443448061
+size 620742

tasks/piper-reliability-v05/confirmation-227037/attempts/friction015-mass060-layout01--reacquire_grasp_placement.json.gz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0fc39a99bda32f6f6d19c5b81623008a9c8e9fc801e08ceb316c6328513be91
+size 714791

tasks/piper-reliability-v05/confirmation-227037/attempts/friction015-mass060-layout01--reacquire_open_jaw.json.gz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27ef7811bfd1bda003b3691e69954ee6d4f38331d7d45f1ec03fef8cd8739d50
+size 609204

tasks/piper-reliability-v05/confirmation-227037/attempts/friction015-mass060-layout01--reacquire_placement.json.gz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b5e106979dd34f4a90aadaa21ca6d31232a172aa36df8f6cb0926ba8b3f6b35
+size 736758

tasks/piper-reliability-v05/confirmation-227037/attempts/friction015-mass060-layout01--recovery_open_jaw.json.gz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7a16a4e2b1221b4ad068d5b0b2d1842725498c5ee526b627e340f700bd97b40
+size 608863

tasks/piper-reliability-v05/confirmation-227037/attempts/friction015-mass060-layout01--recovery_placement.json.gz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c72d9dee6b3c35b624c5dd299922629ba45cd588fe13c23974e760c9ec6c9e7e
+size 731494

tasks/piper-reliability-v05/confirmation-227037/attempts/friction055-mass040-layout00--hold.json.gz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da54423624c601cfa68526016f9c0531b617e3acaaab0378257cf3ef9e55eaa5
+size 351769

tasks/piper-reliability-v05/confirmation-227037/attempts/friction055-mass040-layout00--reacquire_grasp_open_jaw.json.gz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7df03ce042542ed14ed24a2e06653f4c0e5958c36e0390e4c38940923faccab
+size 698866

tasks/piper-reliability-v05/confirmation-227037/attempts/friction055-mass040-layout00--reacquire_grasp_placement.json.gz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4dab9fa8fc1912e42b56f2f2a5239eefb277d09080f15fa1c37eea5ceb6941fe
+size 806354

tasks/piper-reliability-v05/confirmation-227037/attempts/friction055-mass040-layout00--reacquire_open_jaw.json.gz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be3a73e0b216e9e90fa0832230644b7923a36b9aeb458d2c186c3d09ba018786
+size 688615

tasks/piper-reliability-v05/confirmation-227037/attempts/friction055-mass040-layout00--reacquire_placement.json.gz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1a1324be3e91c9737b5b9f4da5bd1effd4dfcd31f44248ae4e34bd2207846b1
+size 824512

tasks/piper-reliability-v05/confirmation-227037/attempts/friction055-mass040-layout00--recovery_open_jaw.json.gz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f49cbfb09c5eeea12e7578b3b0135a76d6b8fbfcf95eab6e54d6de04fcccf16b
+size 688459

tasks/piper-reliability-v05/confirmation-227037/attempts/friction055-mass040-layout00--recovery_placement.json.gz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f01da380f632446e16fcc1453a1a32558cbef9da347a5b10006d4d2a1e6d97f9
+size 817070

tasks/piper-reliability-v05/confirmation-227037/attempts/friction055-mass040-layout01--hold.json.gz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5252d3563ac9f49b292ff3daf5d3a717eced65e0d9d2d3338ad672d37bad762
+size 351255

tasks/piper-reliability-v05/confirmation-227037/attempts/friction055-mass040-layout01--reacquire_grasp_open_jaw.json.gz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84c3edaba15c7a241394e21d15303c593e6d7dd1725ccb9c06e2059a660655c3
+size 689672

tasks/piper-reliability-v05/confirmation-227037/attempts/friction055-mass040-layout01--reacquire_grasp_placement.json.gz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1e9d1ccc07bb1580dd7d6956e0fe3521556e0016f4ed8441e97a4c71dab6eed
+size 803688

tasks/piper-reliability-v05/confirmation-227037/attempts/friction055-mass040-layout01--reacquire_open_jaw.json.gz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c90a0a6532e728565fe34996512258290e51279ba2be1dc16c886d8db7a8ce4f
+size 688325

tasks/piper-reliability-v05/confirmation-227037/attempts/friction055-mass040-layout01--reacquire_placement.json.gz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50abe72adf11bc531f38bb4ce078bbbf93d87d11bc36ee099369604371262fba
+size 824482

tasks/piper-reliability-v05/confirmation-227037/attempts/friction055-mass040-layout01--recovery_open_jaw.json.gz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af45afc2e6156ddd9c27ee79788aeeaad80d54eb3adb3ba2a8ca3e9df7a5cdcc
+size 687728

tasks/piper-reliability-v05/confirmation-227037/attempts/friction055-mass040-layout01--recovery_placement.json.gz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb826a207b3b782aac3154394ca8383b20a5294857936fc7c523ed5b75797085
+size 817225

tasks/piper-reliability-v05/confirmation-227037/attempts/friction055-mass060-layout00--hold.json.gz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39cb6a536a589ad6e128f1061204fe44bf9675c1e3e2441ff034dd7e53f8172a
+size 350845

tasks/piper-reliability-v05/confirmation-227037/attempts/friction055-mass060-layout00--reacquire_grasp_open_jaw.json.gz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4576bec40fdd2dcf7dc4cccf587751c81f16c2427e08ca0dc6fad0aee43d6a2d
+size 688994

tasks/piper-reliability-v05/confirmation-227037/attempts/friction055-mass060-layout00--reacquire_grasp_placement.json.gz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97ef1da1810d29bb7cac986a2540be1a70b07b856a635100889ff15a6abe4796
+size 810536

tasks/piper-reliability-v05/confirmation-227037/attempts/friction055-mass060-layout00--reacquire_open_jaw.json.gz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71db38f2fc1d3ec63efbe34ce712777975998a687f6f3997415b15f61194c1dd
+size 635929

tasks/piper-reliability-v05/confirmation-227037/attempts/friction055-mass060-layout00--reacquire_placement.json.gz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a61a75889c7c29a52d36b012ad7dd0ab4f3806fb53c092a2d11173e5f1db4851
+size 756469