sessions/session_20260921_225630_786148/runs/lab-a-faithful-photo: package_final batch 1/1

sessions/session_20260921_225630_786148/runs/lab-a-faithful-photo/README.md

@@ -0,0 +1,39 @@
+# lab-a-faithful-photo
+
+RT faithful photometric fit from the recorded image-scan parent lab-a-faithful-tracking c0012 (not tracking BEST): photometric CMA (100 generations, 800 asks) then projected photometric Adam (500 traversals); BEST c0495, FINAL c0500.
+
+| Field | Value |
+|---|---|
+| Status | complete |
+| Identity | session_id `session_20260921_225630_786148`, window_id `sync0402-0893` |
+| Parent | `lab-a-faithful-tracking` adam/c0012 (recorded image scan (scan_selected)) |
+| Stages | cma, photometric_adam |
+| Budget (completed/configured) | cma:  (completed_generations 100, issued_asks 800, told_asks 800, physical_failures 0); photometric_adam: traversals 500/500, updates 245500/245500 |
+| Labels | BEST adam/c0495, FINAL adam/c0500 |
+| Code revision(s) | `e80a85d1526e6d497541be68b9c4f1e709ec9987`; dirty tree by stage: cma reported clean, photometric_adam not recorded |
+| Checkpoint rows | 4357 (`checkpoints.tsv`) |
+| Archived native records | 11,608 per-step history files in 219 tar archives (owner D25); `archives/members.json` lists each member's native path and sha256, and `checkpoints.tsv` still lists every checkpoint file |
+
+## Stages
+
+- **cma** (`native/cma/manifest.json`): "mean of all four views per transition, then mean over K; RP1 active Q5 objective"
+- **photometric_adam** (`native/adam/manifest.json`): {"objective_id": "real_rgbd_active_photometric_v1", "source": "U gs_train.py:128-188 + loss_utils.py (PhysTwin 81c718790a37e5e0102eb77af2c6edd34a9db25f)", "weights": {"lambda_dssim": 0.2, "lambda_seg": 1.0, "lambda_depth": 0.001}, "rgb_ssim": "fused_ssim (U gaussian_splatting/submodules/fused-ssim, padding same, train True)", "seg_ssim": "reference ssim (U loss_utils.ssim, 11x11 window sigma 1.5, 
+  - stiffness update: projected: finite raw log Y moved back onto the physical cap after every update (protocol.projected_log_y true)
+
+## Capabilities
+
+- **portable_use**: native model arrays retained; fresh use (canonical q0/v0, zero updates) from a clean local copy is implemented and validated by PR4 on representative checkpoints; Hub fetch pending; photometric rendering also needs the recorded initial appearance and binding listed in dependencies.json
+- **interrupted_run_recovery**: unsupported for this publication (owner D21): every photometric checkpoint and its continuation state (optimizer moments, cursor, q/v and appearance carry, CMA strategy and asks) is retained, and its resume inputs are published or referenced (D15-D20), but no photometric restore is implemented or claimed
+- **extend_completed_budget**: not supported: the native protocols refuse to extend a finished run's horizon
+- **full_reproduction**: not claimed (D3); dirty-state and environment limits are listed under code
+
+## Limitations
+
+- continuing this fit re-hashes author weights TAPNext++ tapnextpp_512 checkpoint (Google DeepMind TAPNet) (/mnt/data2/magna/belt_perception/results/phystwin_real_rgbd/session_20260921_225630_786148/rt_waft_tapnextpp_refit_01/checkpoints/tapnextpp_512.ckpt); they are not published here (dependencies.json third_party_weights names their source and sha256)
+- historical depth: camera 12540311 recorded stream 5429f2cd45c9 is the original content of sessions/session_20260921_225630_786148/videos/zed_12540311_depth_waft_stereo_synlarge_dav2l5_zdepth.zdepth, replaced there by 80f9c31528de at DAIRLab/phystwin_dataset@c9fa16c0c8ac (original was the remote content at b61531e2f70d); a pin must name the original, not the current path
+- historical depth: camera 12933256 recorded stream 6ad35616256c is the original content of sessions/session_20260921_225630_786148/videos/zed_12933256_depth_waft_stereo_synlarge_dav2l5_zdepth.zdepth, replaced there by e6b07d4e756e at DAIRLab/phystwin_dataset@c9fa16c0c8ac (original was the remote content at b61531e2f70d); a pin must name the original, not the current path
+- historical depth: camera 17736741 recorded stream ba88326f4263 is the original content of sessions/session_20260921_225630_786148/videos/zed_17736741_depth_waft_stereo_synlarge_dav2l5_zdepth.zdepth, replaced there by a1d25bde7757 at DAIRLab/phystwin_dataset@6ce5a6472649 (original was the remote content at c8efd5c26071); a pin must name the original, not the current path
+- historical depth: camera 23007103 recorded stream ffb5bc058a27 is the original content of sessions/session_20260921_225630_786148/videos/zed_23007103_depth_waft_stereo_synlarge_dav2l5_zdepth.zdepth, replaced there by e3267dd44f22 at DAIRLab/phystwin_dataset@c9fa16c0c8ac (original was the remote content at b61531e2f70d); a pin must name the original, not the current path
+- photometric_adam: records name e80a85d1526e but none states whether the working tree was clean when this stage ran
+
+Native records under `native/` are authoritative; `run.json`, `checkpoints.tsv` and `dependencies.json` index them. License: see the repository `LICENSE` and card.

sessions/session_20260921_225630_786148/runs/lab-a-faithful-photo/run.json

@@ -0,0 +1,622 @@
+{
+  "aliases": [
+    {
+      "bytes_identical": true,
+      "duplicate_of": "native/cma/generations/g073/a01/model/model.npz",
+      "path": "native/cma/winner/model/model.npz",
+      "relation": "byte copy of the committed ask (cma._stage_winner)",
+      "role": "CMA winner"
+    },
+    {
+      "bytes_identical": true,
+      "duplicate_of": "native/cma/generations/g073/a01/model/topology.npz",
+      "path": "native/cma/winner/model/topology.npz",
+      "relation": "byte copy of the committed ask (cma._stage_winner)",
+      "role": "CMA winner"
+    }
+  ],
+  "archived_native_records": {
+    "archives": 219,
+    "history_archives": 219,
+    "history_members": 11608,
+    "index": "archives/members.json",
+    "member_bytes": 56202643776,
+    "members": 11608,
+    "rule": "Owner decision D25 (2026-11-01): the Hub refuses repositories above 20,000 files, so this run's per-step history (CMA generations and candidates, Adam snapshots, continuation states, update rows and frozen scores; or Deform360 pass states, records and scores) is published inside these uncompressed tar archives, up to 256 MiB of members each. Member bytes are unchanged and checkpoints.tsv still lists every file with its sha256; extract each member to <run dir>/native/<member> to restore the native layout (scripts/phystwin_publish.py fetch extracts the members a checkpoint needs, and --all-checkpoints extracts all)."
+  },
+  "capabilities": {
+    "extend_completed_budget": "not supported: the native protocols refuse to extend a finished run's horizon",
+    "full_reproduction": "not claimed (D3); dirty-state and environment limits are listed under code",
+    "interrupted_run_recovery": "unsupported for this publication (owner D21): every photometric checkpoint and its continuation state (optimizer moments, cursor, q/v and appearance carry, CMA strategy and asks) is retained, and its resume inputs are published or referenced (D15-D20), but no photometric restore is implemented or claimed",
+    "portable_use": "native model arrays retained; fresh use (canonical q0/v0, zero updates) from a clean local copy is implemented and validated by PR4 on representative checkpoints; Hub fetch pending; photometric rendering also needs the recorded initial appearance and binding listed in dependencies.json"
+  },
+  "checkpoints": {
+    "counts": {
+      "adam_continuation": 2950,
+      "adam_traversal_snapshot": 501,
+      "adam_zero_update_check": 1,
+      "cma_candidate": 800,
+      "cma_generation_state": 100,
+      "cma_to_adam_handoff": 1,
+      "cma_winner": 1,
+      "model_initialization": 2,
+      "photometric_parent_p0": 1
+    },
+    "rows": 4357,
+    "table": "checkpoints.tsv"
+  },
+  "code": {
+    "belt_perception_commits": [
+      "e80a85d1526e6d497541be68b9c4f1e709ec9987"
+    ],
+    "dirty_reported": null,
+    "limitations": [
+      "photometric_adam: records name e80a85d1526e but none states whether the working tree was clean when this stage ran"
+    ],
+    "observations": [
+      {
+        "key": "code_revision",
+        "scope": "cma",
+        "source": "native/cma/manifest.json",
+        "value": {
+          "dirty": false,
+          "head": "e80a85d1526e6d497541be68b9c4f1e709ec9987"
+        }
+      },
+      {
+        "key": "revision",
+        "scope": "run",
+        "source": "native/campaign.json",
+        "value": "e80a85d1526e6d497541be68b9c4f1e709ec9987"
+      }
+    ],
+    "stages": {
+      "cma": {
+        "belt_perception_commits": [
+          "e80a85d1526e6d497541be68b9c4f1e709ec9987"
+        ],
+        "dirty_reported": false,
+        "sources": [
+          "native/cma/manifest.json:code_revision",
+          "native/campaign.json:revision"
+        ]
+      },
+      "photometric_adam": {
+        "belt_perception_commits": [
+          "e80a85d1526e6d497541be68b9c4f1e709ec9987"
+        ],
+        "dirty_reported": null,
+        "sources": [
+          "native/campaign.json:revision"
+        ]
+      }
+    }
+  },
+  "description": "RT faithful photometric fit from the recorded image-scan parent lab-a-faithful-tracking c0012 (not tracking BEST): photometric CMA (100 generations, 800 asks) then projected photometric Adam (500 traversals); BEST c0495, FINAL c0500.",
+  "environment": {
+    "native/adam/manifest.json:identity.execution": {
+      "belt_perception_source": {
+        "files": 873,
+        "sha256": "d578ede701a56b360ebe39b72317188059d4b7b97a849a718ebda436b073b766"
+      },
+      "device_name": "NVIDIA GeForce RTX 4090",
+      "python": "3.11.14",
+      "torch_cuda": "12.8",
+      "versions": {
+        "cma": "4.4.4",
+        "numpy": "2.4.4",
+        "open3d": "0.19.0",
+        "torch": "2.11.0+cu128",
+        "warp-lang": "1.16.0"
+      }
+    },
+    "native/campaign.json:device_identities": {
+      "cuda:0": {
+        "name": "NVIDIA GeForce RTX 4090",
+        "total_memory": 25215303680,
+        "uuid": "30be4c6b-0cc3-a19f-14c8-b53e90ace6dc"
+      }
+    },
+    "native/campaign.json:lock_sha256": "673786110b5b79a5a6ecc5e6bf35d11413a342229be69cd028e7ce8bf1841a02",
+    "native/cma/manifest.json:execution_identity": {
+      "belt_perception_source": {
+        "files": 873,
+        "sha256": "d578ede701a56b360ebe39b72317188059d4b7b97a849a718ebda436b073b766"
+      },
+      "device_name": "NVIDIA GeForce RTX 4090",
+      "python": "3.11.14",
+      "torch_cuda": "12.8",
+      "versions": {
+        "cma": "4.4.4",
+        "numpy": "2.4.4",
+        "open3d": "0.19.0",
+        "torch": "2.11.0+cu128",
+        "warp-lang": "1.16.0"
+      }
+    }
+  },
+  "evidence_files": [
+    "evidence/rt_faithful_photo_20261011/dispatch.json",
+    "evidence/rt_faithful_photo_20261011/execute_task.py",
+    "evidence/rt_faithful_photo_20261011/focused_tests.log",
+    "evidence/rt_faithful_photo_20261011/prelaunch_final_check.log",
+    "evidence/rt_faithful_photo_20261011/prepare_full.py",
+    "evidence/rt_faithful_photo_20261011/qualification.log",
+    "evidence/rt_faithful_photo_20261011/qualification/driver_summary.json",
+    "evidence/rt_faithful_photo_20261011/readiness.json",
+    "evidence/rt_faithful_photo_20261011/run_config.json",
+    "evidence/rt_faithful_track_20261010/delivery/scan/canonical_binding.npz",
+    "evidence/rt_faithful_track_20261010/delivery/scan/contract.json",
+    "evidence/rt_faithful_track_20261010/delivery/scan/selection.json"
+  ],
+  "family": "real_rgbd_npz",
+  "gaps": [],
+  "identity": {
+    "session_id": "session_20260921_225630_786148",
+    "window_id": "sync0402-0893"
+  },
+  "inputs": [
+    {
+      "preprocessing": "photometric observation cache v1_0058966e635f5429 and appearance rp3 (see dependencies.json)",
+      "role": "photometric window",
+      "session_id": "session_20260921_225630_786148",
+      "window_id": "sync0402-0893"
+    }
+  ],
+  "labels": {
+    "BEST": {
+      "key": "best_candidate",
+      "metric": "RT photometric active full-window mean",
+      "score": 0.003553924426822046,
+      "source": "native/adam/best.json",
+      "status": "final",
+      "value": "adam/c0495"
+    },
+    "FINAL": {
+      "key": "final_candidate",
+      "note": "final traversal snapshot at the planned horizon (no FINAL export written)",
+      "source": "native/adam/training_complete.json",
+      "value": "adam/c0500"
+    }
+  },
+  "license": {
+    "attribution": null,
+    "id": "mit",
+    "scope": "MIT (owner decision D9) applies to the project-produced fit packages in this repository: native checkpoints, run records and the generated metadata. It does not relicense the linked DAIRLab/phystwin_dataset recordings, which declare no license, or any third-party code or data."
+  },
+  "limitations": [
+    "continuing this fit re-hashes author weights TAPNext++ tapnextpp_512 checkpoint (Google DeepMind TAPNet) (/mnt/data2/magna/belt_perception/results/phystwin_real_rgbd/session_20260921_225630_786148/rt_waft_tapnextpp_refit_01/checkpoints/tapnextpp_512.ckpt); they are not published here (dependencies.json third_party_weights names their source and sha256)",
+    "historical depth: camera 12540311 recorded stream 5429f2cd45c9 is the original content of sessions/session_20260921_225630_786148/videos/zed_12540311_depth_waft_stereo_synlarge_dav2l5_zdepth.zdepth, replaced there by 80f9c31528de at DAIRLab/phystwin_dataset@c9fa16c0c8ac (original was the remote content at b61531e2f70d); a pin must name the original, not the current path",
+    "historical depth: camera 12933256 recorded stream 6ad35616256c is the original content of sessions/session_20260921_225630_786148/videos/zed_12933256_depth_waft_stereo_synlarge_dav2l5_zdepth.zdepth, replaced there by e6b07d4e756e at DAIRLab/phystwin_dataset@c9fa16c0c8ac (original was the remote content at b61531e2f70d); a pin must name the original, not the current path",
+    "historical depth: camera 17736741 recorded stream ba88326f4263 is the original content of sessions/session_20260921_225630_786148/videos/zed_17736741_depth_waft_stereo_synlarge_dav2l5_zdepth.zdepth, replaced there by a1d25bde7757 at DAIRLab/phystwin_dataset@6ce5a6472649 (original was the remote content at c8efd5c26071); a pin must name the original, not the current path",
+    "historical depth: camera 23007103 recorded stream ffb5bc058a27 is the original content of sessions/session_20260921_225630_786148/videos/zed_23007103_depth_waft_stereo_synlarge_dav2l5_zdepth.zdepth, replaced there by e3267dd44f22 at DAIRLab/phystwin_dataset@c9fa16c0c8ac (original was the remote content at b61531e2f70d); a pin must name the original, not the current path",
+    "photometric_adam: records name e80a85d1526e but none states whether the working tree was clean when this stage ran"
+  ],
+  "native_files": {
+    "bytes": 56267700579,
+    "files": 11636
+  },
+  "native_reconciliation": {
+    "included_by_category": {
+      "adam_continuation": {
+        "bytes": 51166619284,
+        "files": 2950
+      },
+      "adam_snapshot": {
+        "bytes": 243791504,
+        "files": 1506
+      },
+      "adam_update_rows": {
+        "bytes": 1105516863,
+        "files": 2950
+      },
+      "cma_candidate": {
+        "bytes": 738487854,
+        "files": 3200
+      },
+      "cma_center_winner": {
+        "bytes": 8788338,
+        "files": 4
+      },
+      "cma_generation_state": {
+        "bytes": 5699626,
+        "files": 500
+      },
+      "frozen_score": {
+        "bytes": 2942528645,
+        "files": 502
+      },
+      "handoff": {
+        "bytes": 15998764,
+        "files": 3
+      },
+      "log": {
+        "bytes": 11457987,
+        "files": 7
+      },
+      "run_record": {
+        "bytes": 16954146,
+        "files": 4
+      },
+      "stage_record": {
+        "bytes": 11857568,
+        "files": 10
+      }
+    },
+    "included_files": 11636,
+    "not_selected": {
+      "post-hoc frozen-score evaluation trajectory; its scores remain in evaluations/*/result.json and best.json": {
+        "bytes": 4716687789,
+        "examples": [
+          "adam/evaluations/c0000/rollout.npz",
+          "adam/evaluations/c0001/rollout.npz",
+          "adam/evaluations/c0002/rollout.npz"
+        ],
+        "files": 502
+      },
+      "runtime process or lock marker": {
+        "bytes": 0,
+        "examples": [
+          "supervisor.lock"
+        ],
+        "files": 1
+      },
+      "telemetry journal for W&B delivery; no telemetry process owns scientific state": {
+        "bytes": 1406585177,
+        "examples": [
+          "telemetry-collector/real_collector.lock",
+          "telemetry-collector/real_collector_cursor.json",
+          "telemetry-collector/real_source_identity.json"
+        ],
+        "files": 8
+      }
+    },
+    "source_files": 12147,
+    "unclassified": [],
+    "unclassified_files": 0
+  },
+  "notes": [],
+  "parent": {
+    "declared": {
+      "checkpoint": "adam/c0012",
+      "relation": "recorded image scan (scan_selected)",
+      "run_id": "lab-a-faithful-tracking"
+    },
+    "native": {
+      "checkpoint": "adam/c0012",
+      "expected_sha256": {
+        "adam/model_init.npz": "52afd51ea6e81b548921caac77c6ae5d05a0498f86429fc656b4c5f31a483549",
+        "adam/snapshots/c0012/model/model.npz": "7df2b760b6946a2007c8e9774731cbaa79aead70ccf13f162cfd63dad5e2fbba",
+        "adam/snapshots/c0012/model/topology.npz": "bb4dd13bdfaa127174fc8c34d3eb55ef9fd10427a4eac694ca579cba4239efa6"
+      },
+      "fit_run": "/mnt/data0/magna/belt_perception_runs/rt_faithful_track_20261010/full_fit_cma250_projadam_01",
+      "key": "identity.inputs.parent",
+      "kind": "parent_traversal_snapshot",
+      "selection_role": "scan_selected",
+      "source": "native/adam/manifest.json"
+    },
+    "native_run_id": "lab-a-faithful-tracking",
+    "verified": true,
+    "verified_files": [
+      "adam/model_init.npz",
+      "adam/snapshots/c0012/model/model.npz",
+      "adam/snapshots/c0012/model/topology.npz"
+    ]
+  },
+  "relocation": {
+    "path_in_repo": "sessions/session_20260921_225630_786148/runs/lab-a-faithful-photo/native",
+    "recorded_aliases": [
+      "/vast/projects/posa/contact-rich-robot/data/belt_perception_runs/rt_faithful_photo_20261011/full_fit_01"
+    ],
+    "recorded_root": "/mnt/data0/magna/belt_perception_runs/rt_faithful_photo_20261011/full_fit_01",
+    "resolved_root": "/mnt/data0/magna/belt_perception_runs/rt_faithful_photo_20261011/full_fit_01",
+    "rule": "native/<path relative to the recorded root>; native records keep recorded paths"
+  },
+  "repo_id": "DAIRLab/phystwin_models",
+  "run_id": "lab-a-faithful-photo",
+  "schema": "phystwin_model_run_v1",
+  "stages": [
+    {
+      "active_coordinates": {
+        "key": "protocol.map.coordinates (each maps to a leaf or setting)",
+        "source": "native/cma/manifest.json",
+        "value": [
+          "ground_restitution",
+          "ground_friction",
+          "drag_damping",
+          "dashpot_damping"
+        ]
+      },
+      "budget": {
+        "completed": {
+          "center_evaluations": {
+            "key": "center_evaluations",
+            "source": "native/cma/result.json",
+            "value": null
+          },
+          "completed_generations": {
+            "key": "completed_generations",
+            "source": "native/cma/result.json",
+            "value": 100
+          },
+          "issued_asks": {
+            "key": "issued_asks",
+            "source": "native/cma/result.json",
+            "value": 800
+          },
+          "physical_failures": {
+            "key": "physical_failures",
+            "source": "native/cma/result.json",
+            "value": 0
+          },
+          "status": {
+            "key": "status",
+            "source": "native/cma/result.json",
+            "value": "winner"
+          },
+          "stop_reason": {
+            "key": "stop_reason",
+            "source": "native/cma/result.json",
+            "value": "max_generations"
+          },
+          "told_asks": {
+            "key": "told_asks",
+            "source": "native/cma/result.json",
+            "value": 800
+          }
+        },
+        "configured": {
+          "generations": {
+            "key": "protocol.max_generations",
+            "source": "native/cma/manifest.json",
+            "value": 100
+          }
+        }
+      },
+      "carried_fixed": {
+        "key": "protocol.map.carried_inactive",
+        "source": "native/cma/manifest.json",
+        "value": [
+          "object_restitution",
+          "object_friction",
+          "collision_distance_m"
+        ]
+      },
+      "inactive_coordinates": {
+        "key": "protocol.map.coordinates",
+        "source": "native/cma/manifest.json",
+        "value": []
+      },
+      "kind": "photometric_cma",
+      "manifest": "native/cma/manifest.json",
+      "objective": {
+        "key": "protocol.score",
+        "source": "native/cma/manifest.json",
+        "value": "mean of all four views per transition, then mean over K; RP1 active Q5 objective"
+      },
+      "schema": "real_rgbd_photometric_cma_v1",
+      "searched_coordinates": {
+        "key": "protocol.map.coordinates",
+        "source": "native/cma/manifest.json",
+        "value": [
+          "ground_restitution",
+          "ground_friction",
+          "drag_damping",
+          "dashpot_damping"
+        ]
+      },
+      "settings": {
+        "backend": {
+          "key": "strategy.backend_id",
+          "source": "native/cma/manifest.json",
+          "value": "pycma_4_4_4_serial_ask_tell_v1"
+        },
+        "dimension": {
+          "key": "strategy.dimension",
+          "source": "native/cma/manifest.json",
+          "value": 4
+        },
+        "initial_sigma": {
+          "key": "strategy.initial_sigma",
+          "source": "native/cma/manifest.json",
+          "value": 0.16666666666666666
+        },
+        "population_size": {
+          "key": "strategy.population_size",
+          "source": "native/cma/manifest.json",
+          "value": 8
+        },
+        "seed": {
+          "key": "strategy.seed",
+          "source": "native/cma/manifest.json",
+          "value": 42
+        },
+        "stopping": {
+          "key": "protocol.stopping",
+          "source": "native/cma/manifest.json",
+          "value": "native es.stop() at loop head after first generation; else generation cap"
+        }
+      },
+      "stage": "cma",
+      "supervision": {
+        "key": "supervision",
+        "source": "native/cma/manifest.json",
+        "value": null
+      }
+    },
+    {
+      "best_metric": {
+        "key": "protocol.best_metric",
+        "source": "native/adam/manifest.json",
+        "value": "RT photometric active full-window mean"
+      },
+      "budget": {
+        "completed": {
+          "traversals": {
+            "key": "complete_traversals",
+            "source": "native/adam/training_complete.json",
+            "value": 500
+          },
+          "updates": {
+            "key": "total_updates",
+            "source": "native/adam/training_complete.json",
+            "value": 245500
+          }
+        },
+        "configured": {
+          "traversals": {
+            "key": "protocol.complete_traversals",
+            "source": "native/adam/manifest.json",
+            "value": 500
+          },
+          "updates": {
+            "key": "protocol.complete_traversals * protocol.updates_per_traversal",
+            "source": "native/adam/manifest.json",
+            "value": 245500
+          },
+          "updates_per_traversal": {
+            "key": "protocol.updates_per_traversal",
+            "source": "native/adam/manifest.json",
+            "value": 491
+          }
+        }
+      },
+      "manifest": "native/adam/manifest.json",
+      "objective": {
+        "key": "identity.inputs.objective",
+        "source": "native/adam/manifest.json",
+        "value": {
+          "depth_rule": "q5_valid_indicator_numerator",
+          "depth_target": "stored uint16 / 1000.0 (float64), masked by 1[O > 0.5]",
+          "fused_ssim_binary_sha256": "5450554b6f6e961faa8f719f34f624309100fa60cdfb90b90700c46f629184c4",
+          "fused_ssim_module": "/mnt/data0/magna/belt_perception_wt_rt_faithful_track_20261010/.venv/lib/python3.11/site-packages/fused_ssim/__init__.py",
+          "fused_ssim_wrapper_sha256": "c4a9caf98599b378050d1aa258a0b5d8b5817635bc5aefa29ab6893f442490bf",
+          "masking": "rendered x (1 - H); observed RGB x O; observed depth x 1[O > 0.5]",
+          "means": "full image, all channels",
+          "objective_id": "real_rgbd_active_photometric_v1",
+          "rgb_ssim": "fused_ssim (U gaussian_splatting/submodules/fused-ssim, padding same, train True)",
+          "seg_ssim": "reference ssim (U loss_utils.ssim, 11x11 window sigma 1.5, zero padding)",
+          "source": "U gs_train.py:128-188 + loss_utils.py (PhysTwin 81c718790a37e5e0102eb77af2c6edd34a9db25f)",
+          "view_aggregation": "arithmetic mean over all supervising views",
+          "weights": {
+            "lambda_depth": 0.001,
+            "lambda_dssim": 0.2,
+            "lambda_seg": 1.0
+          }
+        }
+      },
+      "optimizer": {
+        "betas": {
+          "key": "protocol.betas",
+          "source": "native/adam/manifest.json",
+          "value": [
+            0.9,
+            0.99
+          ]
+        },
+        "eps": {
+          "key": "protocol.eps",
+          "source": "native/adam/manifest.json",
+          "value": 1e-08
+        },
+        "lr": {
+          "key": "protocol.lr",
+          "source": "native/adam/manifest.json",
+          "value": 0.001
+        },
+        "optimizer": {
+          "key": "protocol.optimizer",
+          "source": "native/adam/manifest.json",
+          "value": null
+        },
+        "scheduler": {
+          "key": "protocol.scheduler",
+          "source": "native/adam/manifest.json",
+          "value": null
+        },
+        "weight_decay": {
+          "key": "protocol.weight_decay",
+          "source": "native/adam/manifest.json",
+          "value": null
+        }
+      },
+      "parameters": {
+        "leaf_decision": {
+          "key": "protocol.leaf_decision",
+          "source": "native/adam/manifest.json",
+          "value": "Q7 (A) 2026-09-25: the R7/source leaf set (every object and attachment log_spring_y, raw ground restitution and friction; inactive object-contact leaves carried with zero gradient asserted)"
+        },
+        "leaf_set_contract": {
+          "key": "contract.adam_leaf_set",
+          "source": "native/cma/manifest.json",
+          "value": {
+            "decision": "Q7 (A) 2026-09-25: the R7/source leaf set (every object and attachment log_spring_y, raw ground restitution and friction; inactive object-contact leaves carried with zero gradient asserted)",
+            "frozen": [
+              "drag_damping",
+              "dashpot_damping",
+              "collision_distance_m",
+              "topology",
+              "rests",
+              "masses",
+              "attachments",
+              "q0/v0",
+              "controls",
+              "clock"
+            ],
+            "initialization": "exact photometric CMA winner arrays after a passed zero-update handoff",
+            "logged_activity": [
+              "raw_ground_restitution",
+              "raw_ground_friction"
+            ],
+            "optimizer_leaves": [
+              "log_spring_y",
+              "raw_ground_restitution",
+              "raw_ground_friction",
+              "raw_object_restitution",
+              "raw_object_friction"
+            ],
+            "zero_gradient_asserted": [
+              "raw_object_restitution",
+              "raw_object_friction"
+            ]
+          }
+        },
+        "optimizer_leaves": {
+          "key": "protocol.leaves",
+          "source": "native/adam/manifest.json",
+          "value": [
+            "log_spring_y",
+            "raw_ground_restitution",
+            "raw_ground_friction",
+            "raw_object_restitution",
+            "raw_object_friction"
+          ]
+        }
+      },
+      "schema": "real_rgbd_photometric_adam_v1",
+      "seed": {
+        "reason": "the Adam stage records no random seed; its traversal order is chronological",
+        "searched": [
+          "native/adam/manifest.json"
+        ],
+        "value": null
+      },
+      "stage": "photometric_adam",
+      "stiffness_update": {
+        "key": "protocol.projected_log_y",
+        "source": "native/adam/manifest.json",
+        "value": "projected: finite raw log Y moved back onto the physical cap after every update (protocol.projected_log_y true)"
+      }
+    }
+  ],
+  "status": {
+    "completion_evidence": [
+      "native/adam/training_complete.json",
+      "native/adam/best.json",
+      "native/cma/result.json"
+    ],
+    "label": "complete",
+    "note": null
+  },
+  "unknowns": []
+}