Colorizer round6: GPU backward and initial full checkpoints verified

experiments/round6-20260928/SHA256SUMS.json

@@ -1,6 +1,13 @@
 {
   "PROTOCOL.md": "9b8094cf5cc2c785409b4a9850da742e5fab193e7ab96bc4a5fbd524f4327aa8",
+  "dense/initial/README.md": "67b6b8e7697e8a64f150dc87760d54081af5b0f20d826b6d685c8fc9c7a121ef",
+  "dense/initial/config.json": "b45b92885f4715a02034212261db30ba48d6ed39af57c3a1d08a3b5e464f1fdc",
+  "dense/initial/model.safetensors": "e20e980bca6280c109b451ef5a0725e8b6f82d07dd07fbf88f6d5b8e8b29c09e",
+  "palette/initial/README.md": "2508e51f14898f651c49adb184d1570b8adad3702313dee9bdac6fa0390d2bec",
+  "palette/initial/config.json": "eaeb49b39f9116bfed0d954e81852dc93476298752787dba88a63c0eec97ccec",
+  "palette/initial/model.safetensors": "fb06a0f076357d849196b6a99a5ff66e1cccf04c53f000dd079df4081620f828",
   "previous_manifest.json": "24bc081bf48f1109d9dfa217ae0d8593c0c06af6785a5cbfc5dc5d9e25461f5c",
+  "provenance.json": "8ef963ac4db5aef9ed2ad89e745f8479e46afd8e4b776fd2488533dee9a772df",
   "source/data.py": "eb43b886fe45435841439c36646985f914386a48faa712fb6806accac2ad48e0",
   "source/legacy_eval.py": "dd7e8bd5f961dfb6f1c2ce98fac41824c5009188e306000b195e922e4ed03e58",
   "source/metrics.py": "af0ac996f6be0a351a55e372fab637a0d06740afe4a744cb80d0eae56ec97f66",

experiments/round6-20260928/dense/initial/README.md

@@ -0,0 +1,5 @@
+# Experimental semantic colorizer
+
+Head: dense. Parameters: 3708978.
+
+Not approved for production. Requires semantic_model.py; incompatible with the old U-Net loader. Input is Lab lightness normalized to [-1,1]; output is Lab ab. See the run protocol, provenance, selection and visual comparisons. Predictions are plausible colors, not recovered historical truth.

experiments/round6-20260928/dense/initial/config.json

@@ -0,0 +1,7 @@
+{
+  "architecture": "SemanticColorizer",
+  "head": "dense",
+  "width": 128,
+  "queries": 16,
+  "format_version": 1
+}

experiments/round6-20260928/dense/initial/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e20e980bca6280c109b451ef5a0725e8b6f82d07dd07fbf88f6d5b8e8b29c09e
+size 14965384

experiments/round6-20260928/palette/initial/README.md

@@ -0,0 +1,5 @@
+# Experimental semantic colorizer
+
+Head: palette. Parameters: 3994676.
+
+Not approved for production. Requires semantic_model.py; incompatible with the old U-Net loader. Input is Lab lightness normalized to [-1,1]; output is Lab ab. See the run protocol, provenance, selection and visual comparisons. Predictions are plausible colors, not recovered historical truth.

experiments/round6-20260928/palette/initial/config.json

@@ -0,0 +1,7 @@
+{
+  "architecture": "SemanticColorizer",
+  "head": "palette",
+  "width": 128,
+  "queries": 16,
+  "format_version": 1
+}

experiments/round6-20260928/palette/initial/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb06a0f076357d849196b6a99a5ff66e1cccf04c53f000dd079df4081620f828
+size 16112432

experiments/round6-20260928/provenance.json

@@ -0,0 +1,15 @@
+{
+  "parameters": {
+    "dense": 3708978,
+    "palette": 3994676
+  },
+  "encoder_weights": "torchvision MobileNet_V3_Large_Weights.IMAGENET1K_V2",
+  "torchvision": "0.21.0",
+  "teacher_id": "piddnad/ddcolor_artistic",
+  "teacher_revision": "aa10f72fffc89a6658e37b48556050b4d9a26f63",
+  "base_revision": "704fa80d792c3d759db91daa00b2dcfe6f0f6412",
+  "steps_per_head": 10000,
+  "seed": 609,
+  "target": "single DDColor output per image, no averaging with ground-truth colors",
+  "caveat": "Development holdouts previously used; pretrained encoder and teacher have possible upstream overlap. No claim of production readiness."
+}