amoe_loras/: every stack converted to safetensors (38 raw, bitwise-verified) + 36 function-first production artifacts carrying their own usage cards; catalog + SCHEMA. Closes the 15 missing companions (banks/monos/cond) the burndown claim overstated.

amoe_loras/README.md

@@ -0,0 +1,692 @@
+# AMoE-LoRA adapter catalog
+
+Every trained adapter from the r2 diffusion campaign, converted to safetensors, named for what it does, and documented with the number that was actually measured.
+
+Two views of the same tensors:
+
+| directory | naming | for |
+|---|---|---|
+| `raw/` | original experiment paths and filenames | reproducing the record |
+| `production/` | function-first names + a usage card in the file's own metadata | actually using them |
+
+The tensors are identical between the two; only names and metadata differ. Every file was reloaded and compared bitwise against its source after writing.
+
+- **Format + loader rules:** [SCHEMA.md](SCHEMA.md)
+- **Framework:** [amoe-lora](https://github.com/AbstractEyes/amoe-lora) (`pip install git+https://github.com/AbstractEyes/amoe-lora`)
+- **ComfyUI nodes:** [comfyui-geolip-amoe-lora](https://github.com/AbstractEyes/comfyui-geolip-amoe-lora)
+
+## Before you pick one
+
+**Match the trunk.** These are per-block adapters for a specific denoiser. An SD1.5-shaped stack will *geometrically* attach to any SD1.5-class UNet, but the measurements only hold on the trunk named in its card. Three trunks appear here:
+
+| trunk | objective | which adapters |
+|---|---|---|
+| `stable-diffusion-v1-5/stable-diffusion-v1-5` (stock) | epsilon | everything under `sd15/` |
+| `AbstractPhil/sd15-flow-lune-json-prompt` ckpt-2500 | rectified flow | `lune-json/` |
+| `AbstractPhil/sd15-flow-lune-flux` ckpt-18765 | rectified flow | `lune-flux/` |
+| `circlestone-labs/Anima` 2B DiT | flow | `anima/` — **non-commercial** |
+
+**Multiband stacks are step-gated.** Their three experts are combined by cosine crossfade windows on the normalized timestep, so they need a loader that sets band windows each sampling step. The ComfyUI nodes and `amoe.diffusion.StepGatedSampler` both do; a naive always-on load does not and will misbehave.
+
+**Site order is not execution order.** See [SCHEMA.md](SCHEMA.md) — the mid block is stored LAST. Loaders must map by site identity and verify the width signature.
+
+## Capability adapters
+
+Attachable, and they do something you can point at. Each row's *evidence* line is the measured result with its seed count — read it before you trust it.
+
+### `production/sd15/sd15-relay-grounding-v1-s0.safetensors`
+
+**SD1.5 Relay — Grounding v1 (seed 0)**  
+
+`relay` · 16 sites · 160 tensors · 12.9 MB · objective `eps` · seed 0 · trunk `stable-diffusion-v1-5/stable-diffusion-v1-5`
+
+*What it is.* An always-on 16-site relay for the stock SD1.5 epsilon trunk. Improves how closely a generation tracks its prompt without retraining the model. The default pick if you just want the adapter that works.
+
+*What was measured.* exp006, 2 seeds, matched controls: paired val eps-MSE 0.124788 (frozen) -> 0.121698 (s0) / 0.121709 (s1), -2.5%. A parameter-matched LoRA-r32 reached only 0.122674 AND traded away grounding (round-trip +0.1809 zero-shot -> +0.1596) where the relay gained it (+0.2172 / +0.2206). Toggle bit-exact post-train at both seeds. Gates GREW 0.0474 -> 0.0700 (the trunk opts in).
+
+*Caveats.*
+
+- Trained on the stock SD1.5 eps trunk at 512px; other trunks are untested.
+- Gauges are paired val-MSE and CLIP round-trip grounding, not aesthetics.
+
+*Raw twin.* `raw/exp006_sd15core_relay/relay_all16_s0.safetensors` · source `relay_all16_s0.pt` from the [exp006_sd15core_relay](https://huggingface.co/AbstractPhil/geolip-aleph-diffusion/tree/main/exp006_sd15core_relay) package
+
+### `production/sd15/sd15-relay-grounding-v1-s1.safetensors`
+
+**SD1.5 Relay — Grounding v1 (seed 1)**  
+
+`relay` · 16 sites · 160 tensors · 12.9 MB · objective `eps` · seed 1 · trunk `stable-diffusion-v1-5/stable-diffusion-v1-5`
+
+*What it is.* Second-seed twin of the grounding relay. Use it to check that an effect you see is the adapter and not a seed lottery.
+
+*What was measured.* exp006 s1: 0.121709 val (frozen 0.124788), grounding +0.2206. Replicates s0 to 5 decimal places — this pair is the campaign's cleanest replication.
+
+*Caveats.*
+
+- See the s0 card; identical recipe, different init seed.
+
+*Raw twin.* `raw/exp006_sd15core_relay/relay_all16_s1.safetensors` · source `relay_all16_s1.pt` from the [exp006_sd15core_relay](https://huggingface.co/AbstractPhil/geolip-aleph-diffusion/tree/main/exp006_sd15core_relay) package
+
+### `production/sd15/sd15-multiband-coarse2fine-v1-s0.safetensors`
+
+**SD1.5 Multiband — Coarse-to-Fine v1 (seed 0)**  
+
+`multiband3` · 16 sites · 160 tensors · 5.0 MB · objective `eps` · seed 0 · trunk `stable-diffusion-v1-5/stable-diffusion-v1-5`
+
+*What it is.* Three sigma-band experts per site, gated per sampling step: HIGH noise handles coarse structure, MID continuity, LOW fine detail. Lesion a band to see what it was carrying — this is the adapter to play with, not just run.
+
+*What was measured.* exp008, 2 seeds: band lesions are SURGICAL 3/3 — disabling a band damages its own noise range 50-200x more than any other (band0 own 0.005911 vs cross 0.000029). In image space (exp010) the step-gated controller lifted round-trip grounding to +0.2135 vs frozen +0.1247, and the HIGH-band lesion is 14x low-pass dominated — coarse-to-fine confirmed by lesion signature.
+
+*Bands.* 0: fidelity/detail (LOW noise) · 1: continuity/semantics (MID) · 2: diversity/structure (HIGH noise)
+
+*Caveats.*
+
+- On aggregate eps-MSE a matched rank-48 monolith still edges it (0.121736 vs 0.122004, both seeds). The value is the band structure, not the loss number — compare against sd15-monolith-r48-control.
+- Band edges (0.35/0.75) and crossfade (0.06) are fixed law constants, not tunables.
+
+*Raw twin.* `raw/exp008_multiband/mb3_s0.safetensors` · source `mb3_s0.pt` from the [exp008_multiband](https://huggingface.co/AbstractPhil/geolip-aleph-diffusion/tree/main/exp008_multiband) package
+
+### `production/sd15/sd15-multiband-coarse2fine-v1-s1.safetensors`
+
+**SD1.5 Multiband — Coarse-to-Fine v1 (seed 1)**  
+
+`multiband3` · 16 sites · 160 tensors · 5.0 MB · objective `eps` · seed 1 · trunk `stable-diffusion-v1-5/stable-diffusion-v1-5`
+
+*What it is.* Second-seed twin of the multiband stack.
+
+*What was measured.* exp008 s1: lesion asymmetries replicate near-exactly (band0 own 0.005958 vs cross 0.000029). s0's marginal own-band win did NOT replicate; the surgical structure did.
+
+*Bands.* 0: fidelity/detail (LOW noise) · 1: continuity/semantics (MID) · 2: diversity/structure (HIGH noise)
+
+*Caveats.*
+
+- See the s0 card.
+
+*Raw twin.* `raw/exp008_multiband/mb3_s1.safetensors` · source `mb3_s1.pt` from the [exp008_multiband](https://huggingface.co/AbstractPhil/geolip-aleph-diffusion/tree/main/exp008_multiband) package
+
+### `production/sd15/sd15-multiband-realdata-v1-s0.safetensors`
+
+**SD1.5 Multiband — Real-Data v1 (seed 0)**  
+
+`multiband3` · 16 sites · 160 tensors · 5.0 MB · objective `eps` · seed 0 · trunk `stable-diffusion-v1-5/stable-diffusion-v1-5`
+
+*What it is.* The same three-band mechanism trained on real photographs with multiple entities (qwen-deepfashion-fused) rather than synthetic scenes. Prefer this one for photographic subjects.
+
+*What was measured.* exp011, 2 seeds: frozen 0.142435 -> 0.135215 (s0) / 0.135245 (s1). Adapters pay 2-3x more on real data than on synthetic rows, and the surgical lesion structure replicates 3/3 at both seeds.
+
+*Bands.* 0: fidelity/detail (LOW noise) · 1: continuity/semantics (MID) · 2: diversity/structure (HIGH noise)
+
+*Caveats.*
+
+- The matched monolith again edges the aggregate (0.134184 vs 0.135215).
+- Trained at 512px on fashion/person-centric imagery — that is where it was measured.
+
+*Raw twin.* `raw/exp011_fused_multiband/multiband3_s0.safetensors` · source `multiband3_s0.pt` from the [exp011_fused_multiband](https://huggingface.co/AbstractPhil/geolip-aleph-diffusion/tree/main/exp011_fused_multiband) package
+
+### `production/sd15/sd15-multiband-realdata-v1-s1.safetensors`
+
+**SD1.5 Multiband — Real-Data v1 (seed 1)**  
+
+`multiband3` · 16 sites · 160 tensors · 5.0 MB · objective `eps` · seed 1 · trunk `stable-diffusion-v1-5/stable-diffusion-v1-5`
+
+*What it is.* Second-seed twin of the real-data multiband stack.
+
+*What was measured.* exp011 s1: 0.135245 val, lesions surgical 3/3 — seed-robust.
+
+*Bands.* 0: fidelity/detail (LOW noise) · 1: continuity/semantics (MID) · 2: diversity/structure (HIGH noise)
+
+*Caveats.*
+
+- See the s0 card.
+
+*Raw twin.* `raw/exp011_fused_multiband/multiband3_s1.safetensors` · source `multiband3_s1.pt` from the [exp011_fused_multiband](https://huggingface.co/AbstractPhil/geolip-aleph-diffusion/tree/main/exp011_fused_multiband) package
+
+### `production/lune-json/lunejson-relay-fidelity-v1-s0.safetensors`
+
+**Lune-JSON Relay — Fidelity v1 (seed 0)**  
+
+`relay` · 16 sites · 160 tensors · 12.9 MB · objective `flow` · seed 0 · trunk `AbstractPhil/sd15-flow-lune-json-prompt@checkpoint-00002500`
+
+*What it is.* The first certified diffusion relay, on the SD15-Lune rectified-flow finetune. Belongs on that trunk with flow sampling, not on stock SD1.5.
+
+*What was measured.* exp001: paired val flow-MSE 0.522410 (frozen) -> 0.517960, -0.85%. The parameter-matched LoRA-r32 landed BELOW frozen (0.525033) and degraded round-trip grounding to +0.1694. Toggle bit-exact post-train.
+
+*Caveats.*
+
+- s0 round-trip grounding is +0.2052, which is BELOW the +0.2099 zero-shot wall for this trunk — it does not 'preserve' the wall as first reported; only s1 (+0.2158) clears it. The relay-beats-LoRA ordering is unaffected.
+- The LoRA control arm was run at s0 only, so 'relay >= matched LoRA' is 1-seed here (it is 2-seed on exp006).
+- Gates SHRANK on this trunk (0.0474 -> 0.0432) where they grew on the stock core — gate dynamics are substrate-dependent.
+
+*Raw twin.* `raw/exp001_sd15_relay/relay_all16_s0.safetensors` · source `relay_all16_s0.pt` from the [exp001_sd15_relay](https://huggingface.co/AbstractPhil/geolip-aleph-diffusion/tree/main/exp001_sd15_relay) package
+
+### `production/lune-json/lunejson-relay-fidelity-v1-s1.safetensors`
+
+**Lune-JSON Relay — Fidelity v1 (seed 1)**  
+
+`relay` · 16 sites · 160 tensors · 12.9 MB · objective `flow` · seed 1 · trunk `AbstractPhil/sd15-flow-lune-json-prompt@checkpoint-00002500`
+
+*What it is.* Second-seed twin of the Lune-JSON relay; the better-grounded of the pair.
+
+*What was measured.* exp001 s1: val 0.517623 vs frozen 0.522410; round-trip +0.2158, which does clear the +0.2099 wall.
+
+*Caveats.*
+
+- No LoRA control was run at this seed.
+
+*Raw twin.* `raw/exp001_sd15_relay/relay_all16_s1.safetensors` · source `relay_all16_s1.pt` from the [exp001_sd15_relay](https://huggingface.co/AbstractPhil/geolip-aleph-diffusion/tree/main/exp001_sd15_relay) package
+
+### `production/lune-flux/luneflux-blob-structure-lambda1-s0.safetensors`
+
+**Lune-Flux Blob-Structure — lambda 1.0 (seed 0)**  
+
+`multiband3` · 16 sites · 160 tensors · 5.0 MB · objective `flow` · seed 0 · trunk `AbstractPhil/sd15-flow-lune-flux@checkpoint-00018765`
+
+*What it is.* Multiband stack whose HIGH-noise band was additionally supervised on foreground structure (segmentation blobs). The demonstration artifact of the conditioning law: structural supervision pays on a flow trunk.
+
+*What was measured.* exp013 dose curve at lambda=1.0: the HIGH-band foreground gauge moves -8.3% relative to the uniform control, with the common gauge +0.4% (inside the 0.5% tolerance). lambda~1 is the declared operating point. The same coupling on an eps trunk moved +0.03%/-1.0% (exp012, 2 seeds) — a ~125-200x effect ratio, because flow recovers x0 = x_t - sigma*v exactly at every noise level while eps divides by a vanishing sqrt(alpha_bar) in exactly the supervised band.
+
+*Bands.* 0: fidelity/detail (LOW noise) · 1: continuity/semantics (MID) · 2: diversity/structure (HIGH noise)
+
+*Caveats.*
+
+- THIS FILE IS THE lambda=1.0 DOSE POINT, not the lambda=0.5 candidate its experiment README describes. The bed saved to a lambda-less filename and each dose run overwrote the previous; the lambda=0.5 s0 weights no longer exist anywhere. The s1 file IS lambda=0.5. Do not compare s0 against s1 as a seed pair.
+- Belongs on the base-Lune flux trunk with flow sampling.
+
+*Raw twin.* `raw/exp013_blob_flow/blob_mb3_s0.safetensors` · source `blob_mb3_s0.pt` from the [exp013_blob_flow](https://huggingface.co/AbstractPhil/geolip-aleph-diffusion/tree/main/exp013_blob_flow) package
+
+### `production/lune-flux/luneflux-blob-structure-lambda05-s1.safetensors`
+
+**Lune-Flux Blob-Structure — lambda 0.5 (seed 1)**  
+
+`multiband3` · 16 sites · 160 tensors · 5.0 MB · objective `flow` · seed 1 · trunk `AbstractPhil/sd15-flow-lune-flux@checkpoint-00018765`
+
+*What it is.* The lambda=0.5 arm of the same conditioning-law demonstration — a lighter structural coupling.
+
+*What was measured.* exp013 s1 at lambda=0.5: blob gauge 0.124435 vs uniform control 0.129276, -3.7% relative (s0 at the same lambda was -5.9%); both cleared the preregistered 5x bar over the eps reference.
+
+*Bands.* 0: fidelity/detail (LOW noise) · 1: continuity/semantics (MID) · 2: diversity/structure (HIGH noise)
+
+*Caveats.*
+
+- lambda differs from the s0 file in this family (1.0 vs 0.5) — they are dose points, not a seed pair.
+- Belongs on the base-Lune flux trunk with flow sampling.
+
+*Raw twin.* `raw/exp013_blob_flow/blob_mb3_s1.safetensors` · source `blob_mb3_s1.pt` from the [exp013_blob_flow](https://huggingface.co/AbstractPhil/geolip-aleph-diffusion/tree/main/exp013_blob_flow) package
+
+### `production/anima/anima-dit-relay-v1-epoch4.safetensors`
+
+**Anima 2B DiT Relay v1 (epoch 4) — NON-COMMERCIAL**  
+
+`relay` · 28 sites · 280 tensors · 28.6 MB · objective `flow` · seed 0 · trunk `circlestone-labs/Anima@anima-base-v1.0` · **NC (CircleStone NC + NVIDIA Open Model License)**
+
+*What it is.* A 28-site bf16 relay for the Anima 2B DiT, trained end-to-end through the diffusion-pipe fork. Proof the machinery crosses architectures.
+
+*What was measured.* exp004, single seed: training loss 0.1229 -> 0.1154 (improving) while a native LoRA-r16 control on the identical run went 0.1375 -> 0.1424 (degrading) at 2.6x the parameters.
+
+*Caveats.*
+
+- DERIVED FROM NON-COMMERCIAL WEIGHTS — non-commercial use only.
+- This is the weakest-evidenced deliverable in the campaign: exp004 produced no results.json, so the comparison rests on training-loss endpoints rather than a paired held-out validation.
+- All 28 gate scalars still read exactly -3.0. bf16 resolution there is 0.0078, so any gate movement is bounded below that — the 'trunk opts in' gate reading from the SD1.5 experiments has no counterpart here.
+- Not loadable by the SD1.5/SDXL ComfyUI nodes — different architecture (28 sites, width 2048).
+
+*Raw twin.* `raw/exp004_anima_relay/aleph_relay.safetensors` · source `aleph_relay.pt` from the [exp004_anima_relay](https://huggingface.co/AbstractPhil/geolip-aleph-diffusion/tree/main/exp004_anima_relay) package
+
+## Matched controls
+
+The falsifiers and reference arms. Published so you can A/B the claims yourself rather than take them on faith. Several of these BEAT their treatment arm on the aggregate metric — that is stated, not buried.
+
+### `production/controls/sd15-monolith-r48-control-s0.safetensors`
+
+**SD1.5 Monolith r48 — matched control (seed 0)**  
+
+`mono` · 16 sites · 64 tensors · 4.8 MB · objective `eps` · seed 0 · trunk `stable-diffusion-v1-5/stable-diffusion-v1-5`
+
+*What it is.* The parameter-matched single-expert falsifier for the multiband stack. Attach it to A/B whether banding buys anything on YOUR gauge.
+
+*What was measured.* exp008: 0.121736 (s0) / 0.121745 (s1) vs multiband 0.122004 / 0.121970 — the monolith WINS on aggregate eps-MSE at both seeds. Architecture alone does not pay; differentiated pressure has to.
+
+*Caveats.*
+
+- A control, published as evidence. It has no band structure to lesion and no coarse-to-fine behaviour.
+
+*Raw twin.* `raw/exp008_multiband/mono48_s0.safetensors` · source `mono48_s0.pt` from the [exp008_multiband](https://huggingface.co/AbstractPhil/geolip-aleph-diffusion/tree/main/exp008_multiband) package
+
+### `production/controls/sd15-monolith-r48-control-s1.safetensors`
+
+**SD1.5 Monolith r48 — matched control (seed 1)**  
+
+`mono` · 16 sites · 64 tensors · 4.8 MB · objective `eps` · seed 1 · trunk `stable-diffusion-v1-5/stable-diffusion-v1-5`
+
+*What it is.* Second-seed twin of the monolith control.
+
+*What was measured.* exp008 s1: 0.121745 vs multiband 0.121970.
+
+*Caveats.*
+
+- See the s0 card.
+
+*Raw twin.* `raw/exp008_multiband/mono48_s1.safetensors` · source `mono48_s1.pt` from the [exp008_multiband](https://huggingface.co/AbstractPhil/geolip-aleph-diffusion/tree/main/exp008_multiband) package
+
+### `production/controls/sd15-monolith-r48-realdata-control-s0.safetensors`
+
+**SD1.5 Monolith r48 Real-Data — matched control (seed 0)**  
+
+`mono` · 16 sites · 64 tensors · 4.8 MB · objective `eps` · seed 0 · trunk `stable-diffusion-v1-5/stable-diffusion-v1-5`
+
+*What it is.* Monolith control for the real-data multiband stack.
+
+*What was measured.* exp011: 0.134184 (s0) / 0.134221 (s1) vs multiband 0.135215 / 0.135245 — monolith wins the aggregate on real data too.
+
+*Caveats.*
+
+- A control, published as evidence.
+
+*Raw twin.* `raw/exp011_fused_multiband/monolith_s0.safetensors` · source `monolith_s0.pt` from the [exp011_fused_multiband](https://huggingface.co/AbstractPhil/geolip-aleph-diffusion/tree/main/exp011_fused_multiband) package
+
+### `production/controls/sd15-monolith-r48-realdata-control-s1.safetensors`
+
+**SD1.5 Monolith r48 Real-Data — matched control (seed 1)**  
+
+`mono` · 16 sites · 64 tensors · 4.8 MB · objective `eps` · seed 1 · trunk `stable-diffusion-v1-5/stable-diffusion-v1-5`
+
+*What it is.* Second-seed twin.
+
+*What was measured.* exp011 s1: 0.134221.
+
+*Caveats.*
+
+- A control, published as evidence.
+
+*Raw twin.* `raw/exp011_fused_multiband/monolith_s1.safetensors` · source `monolith_s1.pt` from the [exp011_fused_multiband](https://huggingface.co/AbstractPhil/geolip-aleph-diffusion/tree/main/exp011_fused_multiband) package
+
+### `production/controls/sd15-monolith-r32-control-s0.safetensors`
+
+**SD1.5 Monolith r32 — dispatch falsifier (seed 0)**  
+
+`mono` · 16 sites · 64 tensors · 3.3 MB · objective `eps` · seed 0 · trunk `stable-diffusion-v1-5/stable-diffusion-v1-5`
+
+*What it is.* The matched monolith that falsified the 4-expert dispatch bank.
+
+*What was measured.* exp007: monolith 0.121777 (s0) / 0.121799 (s1) BEAT the 4-expert dispatch bank 0.122015 / 0.122011 while using 11% FEWER parameters.
+
+*Caveats.*
+
+- A control, published as evidence.
+
+*Raw twin.* `raw/exp007_amoe_lora/mono_core_s0.safetensors` · source `mono_core_s0.pt` from the [exp007_amoe_lora](https://huggingface.co/AbstractPhil/geolip-aleph-diffusion/tree/main/exp007_amoe_lora) package
+
+### `production/controls/sd15-monolith-r32-control-s1.safetensors`
+
+**SD1.5 Monolith r32 — dispatch falsifier (seed 1)**  
+
+`mono` · 16 sites · 64 tensors · 3.3 MB · objective `eps` · seed 1 · trunk `stable-diffusion-v1-5/stable-diffusion-v1-5`
+
+*What it is.* Second-seed twin.
+
+*What was measured.* exp007 s1: 0.121799.
+
+*Caveats.*
+
+- A control, published as evidence.
+
+*Raw twin.* `raw/exp007_amoe_lora/mono_core_s1.safetensors` · source `mono_core_s1.pt` from the [exp007_amoe_lora](https://huggingface.co/AbstractPhil/geolip-aleph-diffusion/tree/main/exp007_amoe_lora) package
+
+### `production/controls/sd15-blob-on-eps-control-s0.safetensors`
+
+**SD1.5 Blob-on-eps — conditioning-law control (seed 0)**  
+
+`multiband3` · 16 sites · 160 tensors · 5.0 MB · objective `eps` · seed 0 · trunk `stable-diffusion-v1-5/stable-diffusion-v1-5`
+
+*What it is.* Blob supervision applied to an EPSILON trunk — the control that shows the conditioning law from its negative side. Compare against the flow-trunk lune-flux blob stacks.
+
+*What was measured.* exp012, 2 seeds: INERT. s0 moved the HIGH-band gauge 0.111495 vs the uniform 0.111528 (+0.03%, a 3.3e-05 margin) and s1 INVERTED to 0.112651. The keeper from this experiment is a different measurement: on the role-aligned foreground gauge multiband 0.111528 beats the matched monolith 0.123388 (frozen 0.155490) by ~10% at both seeds.
+
+*Bands.* 0: fidelity/detail (LOW noise) · 1: continuity/semantics (MID) · 2: diversity/structure (HIGH noise)
+
+*Caveats.*
+
+- The shipped results.json reads "hit": true for the s0 blob gauge. That is a 3.3e-05 margin that inverts at s1 — the honest verdict is INERT. Do not read the raw flag as a pass.
+- A control, published as evidence.
+
+*Raw twin.* `raw/exp012_blob_supervised/blob_mb3_s0.safetensors` · source `blob_mb3_s0.pt` from the [exp012_blob_supervised](https://huggingface.co/AbstractPhil/geolip-aleph-diffusion/tree/main/exp012_blob_supervised) package
+
+### `production/controls/sd15-blob-on-eps-control-s1.safetensors`
+
+**SD1.5 Blob-on-eps — conditioning-law control (seed 1)**  
+
+`multiband3` · 16 sites · 160 tensors · 5.0 MB · objective `eps` · seed 1 · trunk `stable-diffusion-v1-5/stable-diffusion-v1-5`
+
+*What it is.* Second-seed twin of the eps blob control.
+
+*What was measured.* exp012 s1: 0.112651 vs uniform 0.111528 — the s0 'hit' inverts here.
+
+*Bands.* 0: fidelity/detail (LOW noise) · 1: continuity/semantics (MID) · 2: diversity/structure (HIGH noise)
+
+*Caveats.*
+
+- A control, published as evidence.
+
+*Raw twin.* `raw/exp012_blob_supervised/blob_mb3_s1.safetensors` · source `blob_mb3_s1.pt` from the [exp012_blob_supervised](https://huggingface.co/AbstractPhil/geolip-aleph-diffusion/tree/main/exp012_blob_supervised) package
+
+### `production/controls/luneflux-uniform-mb3-control-s0.safetensors`
+
+**Lune-Flux Uniform Multiband — control (seed 0)**  
+
+`multiband3` · 16 sites · 160 tensors · 5.0 MB · objective `flow` · seed 0 · trunk `AbstractPhil/sd15-flow-lune-flux@checkpoint-00018765`
+
+*What it is.* The un-blob-supervised multiband stack on the same flow trunk: the reference arm the blob stacks are measured against.
+
+*What was measured.* exp013: the uniform reference against which blob supervision moved -5.9% (lambda 0.5) and -8.3% (lambda 1.0) on the HIGH-band foreground gauge.
+
+*Bands.* 0: fidelity/detail (LOW noise) · 1: continuity/semantics (MID) · 2: diversity/structure (HIGH noise)
+
+*Caveats.*
+
+- Saved by the same lambda-less filename scheme as its treatment arm; this s0 file is from the lambda=1.0 run.
+- A control, published as evidence.
+
+*Raw twin.* `raw/exp013_blob_flow/uniform_mb3_s0.safetensors` · source `uniform_mb3_s0.pt` from the [exp013_blob_flow](https://huggingface.co/AbstractPhil/geolip-aleph-diffusion/tree/main/exp013_blob_flow) package
+
+### `production/controls/luneflux-uniform-mb3-control-s1.safetensors`
+
+**Lune-Flux Uniform Multiband — control (seed 1)**  
+
+`multiband3` · 16 sites · 160 tensors · 5.0 MB · objective `flow` · seed 1 · trunk `AbstractPhil/sd15-flow-lune-flux@checkpoint-00018765`
+
+*What it is.* Second-seed twin of the flow uniform control.
+
+*What was measured.* exp013 s1: uniform 0.129276 vs blob 0.124435.
+
+*Bands.* 0: fidelity/detail (LOW noise) · 1: continuity/semantics (MID) · 2: diversity/structure (HIGH noise)
+
+*Caveats.*
+
+- A control, published as evidence.
+
+*Raw twin.* `raw/exp013_blob_flow/uniform_mb3_s1.safetensors` · source `uniform_mb3_s1.pt` from the [exp013_blob_flow](https://huggingface.co/AbstractPhil/geolip-aleph-diffusion/tree/main/exp013_blob_flow) package
+
+## Negatives and falsified artifacts
+
+Evidence, explicitly not capability. Dispatch banks and the cond adapter are **load-only** — `amoe.attach` refuses them by design and tells you why. They are here because a falsification with weights attached is worth more than one without.
+
+### `production/negatives/sd15-multiband-freqroles-inert-s0.safetensors`
+
+**SD1.5 Multiband Frequency-Roles — measured inert (seed 0)**  
+
+`multiband3` · 16 sites · 160 tensors · 5.0 MB · objective `eps` · seed 0 · trunk `stable-diffusion-v1-5/stable-diffusion-v1-5`
+
+*What it is.* Multiband trained with frequency-reweighted role pressure (LOW gets high-pass loss, HIGH gets low-pass). Kept as evidence that this particular pressure is not the one that pays.
+
+*What was measured.* exp009, 2 seeds + rejudge: role gauges improved over uniform multiband in both gauges at both seeds (4/4 directional) but by 0.05-0.2% — nearly collinear with the base objective. In image space (exp010) its lesion signature is IDENTICAL to uniform's (band2 LP 0.0724 vs 0.0727) and it slightly cost grounding (+0.1996 vs +0.2135).
+
+*Bands.* 0: fidelity/detail (LOW noise) · 1: continuity/semantics (MID) · 2: diversity/structure (HIGH noise)
+
+*Caveats.*
+
+- Published as a negative. Band roles need qualitatively different supervision, not frequency reweighting.
+- The as-run reference arms lacked role gauges; that instrument gap was confessed and rejudged.
+
+*Raw twin.* `raw/exp009_bandroles/roles_s0.safetensors` · source `roles_s0.pt` from the [exp009_bandroles](https://huggingface.co/AbstractPhil/geolip-aleph-diffusion/tree/main/exp009_bandroles) package
+
+### `production/negatives/sd15-multiband-freqroles-inert-s1.safetensors`
+
+**SD1.5 Multiband Frequency-Roles — measured inert (seed 1)**  
+
+`multiband3` · 16 sites · 160 tensors · 5.0 MB · objective `eps` · seed 1 · trunk `stable-diffusion-v1-5/stable-diffusion-v1-5`
+
+*What it is.* Second-seed twin.
+
+*What was measured.* exp009 s1: 0.121971 vs uniform 0.122004.
+
+*Bands.* 0: fidelity/detail (LOW noise) · 1: continuity/semantics (MID) · 2: diversity/structure (HIGH noise)
+
+*Caveats.*
+
+- Published as a negative.
+
+*Raw twin.* `raw/exp009_bandroles/roles_s1.safetensors` · source `roles_s1.pt` from the [exp009_bandroles](https://huggingface.co/AbstractPhil/geolip-aleph-diffusion/tree/main/exp009_bandroles) package
+
+### `production/negatives/sd15-dispatch-bank-a4-falsified-s0.safetensors`
+
+**SD1.5 Dispatch Bank A=4 — falsified (seed 0)**  
+
+`bank` · 16 sites · 256 tensors · 3.6 MB · objective `eps` · seed 0 · trunk `stable-diffusion-v1-5/stable-diffusion-v1-5`
+
+*What it is.* Four rank-8 experts with a dense signed aleph dispatch keyed on hidden state + sigma. The first MoE-structure test on diffusion. NOT attachable — kept as evidence.
+
+*What was measured.* exp007, 2 seeds: the bank ties/loses to a rank-32 monolith (0.122015 vs 0.121777) with 11% MORE parameters, and sigma-band usage is FLAT (spread 0.0009) with all four experts alive. Aggregation alone creates no specialization.
+
+*Caveats.*
+
+- Load-only: amoe.attach refuses dispatch banks by design.
+
+*Raw twin.* `raw/exp007_amoe_lora/amoe_core_s0.safetensors` · source `amoe_core_s0.pt` from the [exp007_amoe_lora](https://huggingface.co/AbstractPhil/geolip-aleph-diffusion/tree/main/exp007_amoe_lora) package
+
+### `production/negatives/sd15-dispatch-bank-a4-falsified-s1.safetensors`
+
+**SD1.5 Dispatch Bank A=4 — falsified (seed 1)**  
+
+`bank` · 16 sites · 256 tensors · 3.6 MB · objective `eps` · seed 1 · trunk `stable-diffusion-v1-5/stable-diffusion-v1-5`
+
+*What it is.* Second-seed twin.
+
+*What was measured.* exp007 s1: 0.122011, usage spread 0.00385.
+
+*Caveats.*
+
+- Load-only.
+
+*Raw twin.* `raw/exp007_amoe_lora/amoe_core_s1.safetensors` · source `amoe_core_s1.pt` from the [exp007_amoe_lora](https://huggingface.co/AbstractPhil/geolip-aleph-diffusion/tree/main/exp007_amoe_lora) package
+
+### `production/negatives/luneflux-router-sigmakey-control-s0.safetensors`
+
+**Lune-Flux Router — state+sigma key control (seed 0)**  
+
+`bank` · 16 sites · 256 tensors · 3.6 MB · objective `flow` · seed 0 · trunk `AbstractPhil/sd15-flow-lune-flux@checkpoint-00018765`
+
+*What it is.* The control arm of the router experiment: dispatch keyed on hidden state and sigma alone, no text. It won.
+
+*What was measured.* exp014, 2 seeds: 0.573713 (s0) / 0.572191 (s1) — the BEST of the three router arms. Its usage variance by prompt is 2.36e-02 with zero text input, meaning the hidden-state key already routes by prompt on its own.
+
+*Caveats.*
+
+- Load-only: dispatch banks are not attachable.
+
+*Raw twin.* `raw/exp014_te_dispatch/sigma_key_s0.safetensors` · source `sigma_key_s0.pt` from the [exp014_te_dispatch](https://huggingface.co/AbstractPhil/geolip-aleph-diffusion/tree/main/exp014_te_dispatch) package
+
+### `production/negatives/luneflux-router-sigmakey-control-s1.safetensors`
+
+**Lune-Flux Router — state+sigma key control (seed 1)**  
+
+`bank` · 16 sites · 256 tensors · 3.6 MB · objective `flow` · seed 1 · trunk `AbstractPhil/sd15-flow-lune-flux@checkpoint-00018765`
+
+*What it is.* Second-seed twin.
+
+*What was measured.* exp014 s1: 0.572191, the best arm again.
+
+*Caveats.*
+
+- Load-only.
+
+*Raw twin.* `raw/exp014_te_dispatch/sigma_key_s1.safetensors` · source `sigma_key_s1.pt` from the [exp014_te_dispatch](https://huggingface.co/AbstractPhil/geolip-aleph-diffusion/tree/main/exp014_te_dispatch) package
+
+### `production/negatives/luneflux-router-addrkey-falsified-s0.safetensors`
+
+**Lune-Flux Router — flat address key, falsified (seed 0)**  
+
+`bank` · 16 sites · 272 tensors · 4.7 MB · objective `flow` · seed 0 · trunk `AbstractPhil/sd15-flow-lune-flux@checkpoint-00018765`
+
+*What it is.* Dispatch keyed on the raw flattened [32,128] aleph address.
+
+*What was measured.* exp014, 2 seeds: WORST arm (0.577551 / 0.577694) and it KILLS routing — usage variance collapses to 1.40e-05 against the control's 2.36e-02. The high-dimensional disease geometry of the language line, reproduced on a dispatch key.
+
+*Caveats.*
+
+- Load-only.
+
+*Raw twin.* `raw/exp014_te_dispatch/addr_key_s0.safetensors` · source `addr_key_s0.pt` from the [exp014_te_dispatch](https://huggingface.co/AbstractPhil/geolip-aleph-diffusion/tree/main/exp014_te_dispatch) package
+
+### `production/negatives/luneflux-router-addrkey-falsified-s1.safetensors`
+
+**Lune-Flux Router — flat address key, falsified (seed 1)**  
+
+`bank` · 16 sites · 272 tensors · 4.7 MB · objective `flow` · seed 1 · trunk `AbstractPhil/sd15-flow-lune-flux@checkpoint-00018765`
+
+*What it is.* Second-seed twin.
+
+*What was measured.* exp014 s1: 0.577694, routing dead at both seeds.
+
+*Caveats.*
+
+- Load-only.
+
+*Raw twin.* `raw/exp014_te_dispatch/addr_key_s1.safetensors` · source `addr_key_s1.pt` from the [exp014_te_dispatch](https://huggingface.co/AbstractPhil/geolip-aleph-diffusion/tree/main/exp014_te_dispatch) package
+
+### `production/negatives/luneflux-router-tekey-falsified-s0.safetensors`
+
+**Lune-Flux Router — trained text-encoder key, falsified (seed 0)**  
+
+`bank` · 16 sites · 272 tensors · 3.8 MB · objective `flow` · seed 0 · trunk `AbstractPhil/sd15-flow-lune-flux@checkpoint-00018765`
+
+*What it is.* The 'router solidifier': a trained CLIP-pooler adapter feeding the dispatch key.
+
+*What was measured.* exp014, 2 seeds: 0.574217 / 0.574678 — does not beat the state+sigma control (0.573713 / 0.572191). At s0 its by-prompt usage variance (2.598e-02) is actually BELOW its own shuffled null (2.707e-02).
+
+*Caveats.*
+
+- Load-only.
+- The bed confessed its own null was wrong (a shuffled-key null measures diversity, not correctness); exp015 rebuilt it as a repeated-key null.
+
+*Raw twin.* `raw/exp014_te_dispatch/te_key_s0.safetensors` · source `te_key_s0.pt` from the [exp014_te_dispatch](https://huggingface.co/AbstractPhil/geolip-aleph-diffusion/tree/main/exp014_te_dispatch) package
+
+### `production/negatives/luneflux-router-tekey-falsified-s1.safetensors`
+
+**Lune-Flux Router — trained text-encoder key, falsified (seed 1)**  
+
+`bank` · 16 sites · 272 tensors · 3.8 MB · objective `flow` · seed 1 · trunk `AbstractPhil/sd15-flow-lune-flux@checkpoint-00018765`
+
+*What it is.* Second-seed twin.
+
+*What was measured.* exp014 s1: 0.574678.
+
+*Caveats.*
+
+- Load-only.
+
+*Raw twin.* `raw/exp014_te_dispatch/te_key_s1.safetensors` · source `te_key_s1.pt` from the [exp014_te_dispatch](https://huggingface.co/AbstractPhil/geolip-aleph-diffusion/tree/main/exp014_te_dispatch) package
+
+### `production/negatives/luneflux-routerv2-statesigma-control-s0.safetensors`
+
+**Lune-Flux Router v2 — state+sigma control (seed 0)**  
+
+`bank` · 16 sites · 256 tensors · 3.6 MB · objective `flow` · seed 0 · trunk `AbstractPhil/sd15-flow-lune-flux@checkpoint-00018765`
+
+*What it is.* Control arm of the corrected router test.
+
+*What was measured.* exp015, 2 seeds: 0.573098 / 0.571703 — again the better arm.
+
+*Caveats.*
+
+- Load-only.
+
+*Raw twin.* `raw/exp015_router_v2/state_sigma_s0.safetensors` · source `state_sigma_s0.pt` from the [exp015_router_v2](https://huggingface.co/AbstractPhil/geolip-aleph-diffusion/tree/main/exp015_router_v2) package
+
+### `production/negatives/luneflux-routerv2-statesigma-control-s1.safetensors`
+
+**Lune-Flux Router v2 — state+sigma control (seed 1)**  
+
+`bank` · 16 sites · 256 tensors · 3.6 MB · objective `flow` · seed 1 · trunk `AbstractPhil/sd15-flow-lune-flux@checkpoint-00018765`
+
+*What it is.* Second-seed twin.
+
+*What was measured.* exp015 s1: 0.571703.
+
+*Caveats.*
+
+- Load-only.
+
+*Raw twin.* `raw/exp015_router_v2/state_sigma_s1.safetensors` · source `state_sigma_s1.pt` from the [exp015_router_v2](https://huggingface.co/AbstractPhil/geolip-aleph-diffusion/tree/main/exp015_router_v2) package
+
+### `production/negatives/luneflux-routerv2-mhataddr-falsified-s0.safetensors`
+
+**Lune-Flux Router v2 — M-hat address key, FALSIFIED (seed 0)**  
+
+`bank` · 16 sites · 288 tensors · 3.7 MB · objective `flow` · seed 0 · trunk `AbstractPhil/sd15-flow-lune-flux@checkpoint-00018765`
+
+*What it is.* The address read through 32 slots and projected 128->4 before routing — the form the disease-geometry lesson demanded. This is where address-as-key closed.
+
+*What was measured.* exp015, 2 seeds with corrected instruments: routing excess over a REPEATED-key null is +2.53e-06 at s0 and -4.25e-06 at s1; match advantage ~0. Val 0.574912 vs the control's 0.573098. Address-as-key in its frozen form is FALSIFIED.
+
+*Caveats.*
+
+- Load-only.
+- The open form is TE+AMoE joint training, which this does not test.
+
+*Raw twin.* `raw/exp015_router_v2/mhat_addr_s0.safetensors` · source `mhat_addr_s0.pt` from the [exp015_router_v2](https://huggingface.co/AbstractPhil/geolip-aleph-diffusion/tree/main/exp015_router_v2) package
+
+### `production/negatives/luneflux-routerv2-mhataddr-falsified-s1.safetensors`
+
+**Lune-Flux Router v2 — M-hat address key, FALSIFIED (seed 1)**  
+
+`bank` · 16 sites · 288 tensors · 3.7 MB · objective `flow` · seed 1 · trunk `AbstractPhil/sd15-flow-lune-flux@checkpoint-00018765`
+
+*What it is.* Second-seed twin.
+
+*What was measured.* exp015 s1: 0.573888; routing excess -4.25e-06 (negative).
+
+*Caveats.*
+
+- Load-only.
+
+*Raw twin.* `raw/exp015_router_v2/mhat_addr_s1.safetensors` · source `mhat_addr_s1.pt` from the [exp015_router_v2](https://huggingface.co/AbstractPhil/geolip-aleph-diffusion/tree/main/exp015_router_v2) package
+
+### `production/negatives/lunejson-addrcond-guidepost-negative-s0.safetensors`
+
+**Lune-JSON Address-Conditioning — guidepost negative (seed 0)**  
+
+`cond` · 1 sites · 4 tensors · 0.5 MB · objective `flow` · seed 0 · trunk `AbstractPhil/sd15-flow-lune-json-prompt@checkpoint-00002500`
+
+*What it is.* Injects the frozen byte-trigram aleph address as 32 extra conditioning positions. A conditioning-stream adapter, not a block adapter.
+
+*What was measured.* exp002: appended beside FULL text conditioning it is marginally inert — real vs deranged -0.0009, real vs no-append -0.0068. But the address ALONE (text zeroed) steers: +0.0287 after 2k steps, and the trunk grew its gate 0.047 -> 0.0597 to read it. Redundant-in-context, not dead.
+
+*Caveats.*
+
+- Load-only: a cond-stream adapter, not attachable by the block-adapter verbs.
+- The redesign target is complementarity — inject where text is not.
+
+*Raw twin.* `raw/exp002_sd15_addrcond/addrcond_s0.safetensors` · source `addrcond_s0.pt` from the [exp002_sd15_addrcond](https://huggingface.co/AbstractPhil/geolip-aleph-diffusion/tree/main/exp002_sd15_addrcond) package
+
+## Companion pairs
+
+Which adapter to compare against which, when you want to see the claim rather than read it:
+
+| treatment | companion | the question it answers |
+|---|---|---|
+| `sd15/sd15-relay-grounding-v1-s0` | `controls/…` — see the LoRA note below | does the aleph relay beat a parameter-matched LoRA? (yes, at both seeds) |
+| `sd15/sd15-multiband-coarse2fine-v1-s0` | `controls/sd15-monolith-r48-control-s0` | does splitting into sigma bands buy anything over one bigger expert? (not on aggregate loss — but the bands are surgically separable) |
+| `sd15/sd15-multiband-realdata-v1-s0` | `controls/sd15-monolith-r48-realdata-control-s0` | same question on real photographs (same answer, larger effects) |
+| `lune-flux/luneflux-blob-structure-lambda1-s0` | `controls/luneflux-uniform-mb3-control-s0` | does structural supervision pay on a flow trunk? (yes, -8.3% on the foreground gauge) |
+| `controls/sd15-blob-on-eps-control-s0` | `lune-flux/luneflux-blob-structure-lambda05-s1` | the conditioning law from both sides: inert on eps, paying on flow |
+| `negatives/sd15-dispatch-bank-a4-falsified-s0` | `controls/sd15-monolith-r32-control-s0` | does a 4-expert dispatch beat one monolith? (no — it loses with 11% more parameters) |
+| `negatives/luneflux-routerv2-mhataddr-falsified-s0` | `negatives/luneflux-routerv2-statesigma-control-s0` | can the aleph address route the dispatch? (no — 2.5e-06 over a repeated-key null) |
+| `negatives/sd15-multiband-freqroles-inert-s0` | `sd15/sd15-multiband-coarse2fine-v1-s0` | does frequency-reweighted role pressure specialize the bands? (directionally, negligibly) |
+
+**LoRA controls.** The matched LoRA arms (exp001 s0, exp006 s0+s1, and the Anima LoRA-r16) are PEFT-format adapters, not amoe anchors, so they are not renamed here — they stay in their experiment packages under `lora_r32_s*/` and `lora_ctrl/`. Note that `exp006_sd15core_relay/lora_r32_s{0,1}/` and `exp004_anima_relay/lora_ctrl/*/` are missing their `adapter_config.json` on the hub, so PEFT cannot load them directly from there; exp001's does have one.
+
+## Known record corrections
+
+Found while building this catalog, kept here rather than quietly fixed:
+
+1. **exp013 s0 lambda mismatch.** The bed saved to a lambda-less filename and each dose run overwrote the last, so the shipped s0 weights are the **lambda=1.0** dose point while the package's `results.json` describes lambda=0.5. The lambda=0.5 s0 weights no longer exist. s1 is lambda=0.5. The production names encode lambda; s0 and s1 in that family are **dose points, not a seed pair**.
+
+2. **exp012's `"hit": true`.** A 3.3e-05 margin that inverts at s1. The honest verdict is *inert*, which is what the timeline says; any tool reading the raw JSON flag will print the wrong thing.
+
+3. **exp001 'preserves the wall'.** s0's round-trip grounding is +0.2052 against a +0.2099 zero-shot wall — below it. Only s1 (+0.2158) clears it. The relay-vs-LoRA ordering is unaffected.
+
+4. **exp001's LoRA arm is single-seed**, so 'relay ≥ matched LoRA' is 2-seed on exp006 and 1-seed on exp001.
+
+5. **exp004 has no `results.json`.** Its verdict rests on training-loss endpoints and tfevents, not a paired held-out validation — the weakest-evidenced deliverable in the campaign. Its 28 gates also never moved off −3.0 (bf16 resolution there is 0.0078).
+
+6. **The burndown claimed safetensors companions 'for every adapter stack'.** It covered 21 of them; the dispatch banks, monoliths and the cond adapter were missing. That is closed here — all 38 stacks are converted, and the classifier bug that would have mislabeled banks as multiband stacks is fixed in amoe 0.2.1.

amoe_loras/SCHEMA.md

@@ -0,0 +1,143 @@
+# `amoe.diffusion.anchor` — the adapter file format
+
+One file = one adapter stack for one trunk. The file carries its own
+documentation: a loader can tell you what the adapter is, what it was
+trained on, what it measurably does, how strongly to run it, and what it
+does *not* do — without any external database.
+
+Two containers, same logical content:
+
+| container | when | notes |
+|---|---|---|
+| `.safetensors` | **preferred**, and what ComfyUI loads | meta rides in the safetensors metadata block (str→str) |
+| `.pt` | the campaign's original saves | meta rides as a plain dict under `"meta"` |
+
+## Tensor layout
+
+Flat, one namespace, site index first:
+
+```
+blocks.{site_index}.{param_path}        # in the safetensors key space
+{site_index}.{param_path}               # in memory / in the .pt payload
+```
+
+`site_index` is `0..n_sites-1` in **training enumeration order**.
+
+> ### The ordering law (read this before writing a loader)
+>
+> Site order is diffusers `named_modules()` order, which registers
+> `down_blocks` → `up_blocks` → `mid_block`. **The mid block is LAST**, not
+> in the middle. For SD1.5 the width signature is
+>
+> ```
+> [320,320,640,640,1280,1280, 1280,1280,1280, 640,640,640, 320,320,320, 1280]
+> ```
+>
+> A denoiser's *execution* order is different (`input → middle → output`,
+> giving `…1280,1280,1280,1280…` with mid at index 6). Zipping the two
+> positionally misplaces 7 of 16 sites **and still runs**, producing quietly
+> wrong images. Map by site identity, then verify the width signature —
+> the two orders differ at indices 9 and 15, so the signature catches it.
+> `DiffusionAnchorCheckpoint.widths` reads the signature off the tensors.
+
+## Metadata
+
+### Required (provenance — every file has these)
+
+| field | type | meaning |
+|---|---|---|
+| `format` | str | `"amoe.diffusion.anchor"` |
+| `version` | int/str | `1` |
+| `adapter.kind` | str | `relay` · `multiband3` · `mono` · `bank` · `cond` |
+| `substrate.family` | str | `sd15_unet` · `sdxl_unet` · `cosmos_dit` |
+| `substrate.n_sites` | int | must equal the enumerated site count at attach |
+
+Only `relay` and `multiband3` are **attachable**. `mono` and `bank` are
+matched controls and falsified-routing evidence; `cond` is the Law-2
+negative. Loaders may read them; `attach()` refuses them by design and
+says why.
+
+### Optional (provenance, written when known)
+
+`adapter.*` spec (`n_slots`/`K`/`tau`/`hidden` for relay, `rank` for
+multiband3) · `substrate.base_model_id` · `substrate.site_names` ·
+`substrate.widths` · `objective.kind` (`eps`|`flow`|`v`) ·
+`objective.shift` · `blob.lambda` · `dtype` · `seed` · `recipe.*` ·
+`created` · `content_hash_v2` · `imported_from` · `home_reconstructed`
+
+### Optional (the usage card — schema v1.1)
+
+What a UI renders. All optional, so raw campaign stacks stay valid.
+
+| field | type | meaning |
+|---|---|---|
+| `display_name` | str | human name, e.g. `"SD1.5 Relay — Grounding v1 (seed 0)"` |
+| `usage` | str | what it does and when to reach for it |
+| `evidence` | str | the measured verdict **with numbers and seed status** |
+| `recommended_strength` | float | sane default for a strength slider |
+| `band_roles` | list[str] | multiband only: role per band, LOW→HIGH |
+| `caveats` | list[str] | what it costs, where it fails, what is unverified |
+| `license` | str | SPDX-ish string |
+| `nc` | bool | `true` = non-commercial (derived from NC weights) |
+
+`DiffusionAnchorCheckpoint.card()` returns exactly this block with safe
+defaults filled in.
+
+### Honesty rule for `evidence`
+
+`evidence` states what was measured, at how many seeds, against what
+control — never a marketing claim. If a result is single-seed, it says so.
+If a matched control beat it on the aggregate metric, that goes in
+`evidence` or `caveats`, not omitted. Controls and falsified artifacts
+carry `evidence` describing what they *refuted*; that is their value.
+
+## Worked example
+
+```json
+{
+  "format": "amoe.diffusion.anchor",
+  "version": 1,
+  "display_name": "SD1.5 Multiband — Coarse-to-Fine v1 (seed 0)",
+  "adapter": {"kind": "multiband3", "rank": 16},
+  "substrate": {"family": "sd15_unet", "n_sites": 16,
+                "base_model_id": "stable-diffusion-v1-5/stable-diffusion-v1-5"},
+  "objective": {"kind": "eps"},
+  "band_roles": ["fidelity/detail (LOW noise)",
+                 "continuity/semantics (MID)",
+                 "diversity/structure (HIGH noise)"],
+  "usage": "Three sigma-band experts gated per sampling step. Lesion a band to see what it carries.",
+  "evidence": "exp008, 2 seeds: band lesions surgical 3/3 — own-band damage 50-200x cross-band. A matched rank-48 monolith still edges it on aggregate eps-MSE under uniform pressure.",
+  "recommended_strength": 1.0,
+  "caveats": ["Trained on the stock SD1.5 eps trunk; other trunks are untested.",
+              "The aggregate win belongs to the monolith control — the value here is the band structure, not the loss number."],
+  "license": "MIT", "nc": false,
+  "dtype": "float32", "seed": 0
+}
+```
+
+## Band gating (multiband3 only)
+
+Band windows are cosine crossfades on `s01`, the **normalized discrete
+timestep**:
+
+```
+s01 = t / 1000            # eps trunks — t from the model's own sampling
+s01 = sigma               # flow trunks — the SHIFT-warped sigma
+edges = (0.35, 0.75)      # LAW constants, not tunables
+xfade = 0.06
+```
+
+> `s01` is **not** a noise-level proxy. On the real SD1.5 schedule,
+> `1 - alphas_cumprod[t]` puts 316 of 1000 timesteps in a different band
+> than the one the expert was trained on. In ComfyUI, get it from
+> `model_sampling.timestep(sigma) / 1000`.
+
+## Loader checklist
+
+1. Read meta; reject if `format` is absent or unknown.
+2. Enumerate the host's sites; sort into **training order**.
+3. Assert `n_sites` matches, then assert the width signature matches
+   `checkpoint.widths` — refuse loudly on mismatch.
+4. Cast adapters to the trunk's declared dtype (the dtype law).
+5. `kind` in `{relay, multiband3}` to attach; otherwise explain and stop.
+6. Render `card()` so the user sees provenance, evidence, and caveats.

amoe_loras/production/anima/anima-dit-relay-v1-epoch4.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69d37a2c1f68d8dd817f45e6aff6205c35dafe0be14816618ece967dc5d0ee54
+size 28607464

amoe_loras/production/controls/luneflux-uniform-mb3-control-s0.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e547c9b38fb4488240526bec16c8d81b0dc0656aebbb68dbd652f9af610d134d
+size 4957616

amoe_loras/production/controls/luneflux-uniform-mb3-control-s1.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fbe0cf09ff4b3edf871efbfc41099e71c34b5f7bbc10e5d9b96e7cc6ef0b4906
+size 4957336

amoe_loras/production/controls/sd15-blob-on-eps-control-s0.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1bcaf6c33fcdff8eaf053caf53013942a46681937ba31637e5af281336de9fd
+size 4957976

amoe_loras/production/controls/sd15-blob-on-eps-control-s1.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10e278300b1b2ff1e69761fa71e813a5617031575a1dc85fb02e9361d48b6d10
+size 4957392

amoe_loras/production/controls/sd15-monolith-r32-control-s0.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b57b35e2e4adb4d621d3b4993de98119c9afbcdeddda4d504fb6f17b01b3f41
+size 3251304

amoe_loras/production/controls/sd15-monolith-r32-control-s1.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a106b56166d66480ac3e5acd9211d92ce21cdbf3b66747c33688934ff8c4d10d
+size 3251144

amoe_loras/production/controls/sd15-monolith-r48-control-s0.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ecf7d52814d54c963cc51014a9e9ba6d8315ee1bae8e5265d1e5477e13d1740c
+size 4848952

amoe_loras/production/controls/sd15-monolith-r48-control-s1.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bdc8192311b61aae94138e9f7e25a54673dc9a1c2c8b801a9af1c34ddabbb432
+size 4848624

amoe_loras/production/controls/sd15-monolith-r48-realdata-control-s0.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de1e5cbe763eb288f740c6c92b94a46b04c06adf8fee3a1f9fccf571c5127d41
+size 4848752

amoe_loras/production/controls/sd15-monolith-r48-realdata-control-s1.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65296f67733da0d0cd22fbd4e4500838f2cfa7917ed57fff5d5293d215e79e0b
+size 4848616

amoe_loras/production/lune-flux/luneflux-blob-structure-lambda05-s1.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed7eb93dd01d76c05ca1e6abb02305d9fa5dfb588ef4a72dde8319e85392f650
+size 4957696

amoe_loras/production/lune-flux/luneflux-blob-structure-lambda1-s0.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ecac64a9c5d8b955437f441830b7bc7342b8176e74d5e41cf94e7dfb83171bc7
+size 4958280

amoe_loras/production/lune-json/lunejson-relay-fidelity-v1-s0.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff68504a51da685e7a845094a66172e28a8facc579f847da12e1478853192afc
+size 12942608

amoe_loras/production/lune-json/lunejson-relay-fidelity-v1-s1.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c65a4f8f3017eae430a7af1322812a15f3413248907433003ed40fa14a3b70b
+size 12942000

amoe_loras/production/negatives/luneflux-router-addrkey-falsified-s0.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1fb2d976ff9a0677a4a27dd976843f8daaa7eb143d77ff60c07354dc34de4d0f
+size 4671232

amoe_loras/production/negatives/luneflux-router-addrkey-falsified-s1.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40ab827cbb2710b72957bb604258a05c0322ec1a613228de127aba35122f383e
+size 4671008

amoe_loras/production/negatives/luneflux-router-sigmakey-control-s0.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3300d45d61fb1e202c65f2c38029722ee2c33f0d82b29ae5fce1bd47216b12a
+size 3621144

amoe_loras/production/negatives/luneflux-router-sigmakey-control-s1.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81129839acf2086078fbeeda5ce80497fa424ac9836345d220f4bef3eb824612
+size 3620848

amoe_loras/production/negatives/luneflux-router-tekey-falsified-s0.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e2be13cf8330018581ed6f6e9c176dbbb24f0e482f4b2ea8a3c8e73d9174849
+size 3819312

amoe_loras/production/negatives/luneflux-router-tekey-falsified-s1.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34f440a04597602a27535aae5feb083b1fdfbd0f4a04b64e7573ab5397cd1294
+size 3818912

amoe_loras/production/negatives/luneflux-routerv2-mhataddr-falsified-s0.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8df29f76de48dbc374a85052041d34b0ea69743af57effc97ea765b4e12f95a7
+size 3656832

amoe_loras/production/negatives/luneflux-routerv2-mhataddr-falsified-s1.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d930593343d13e322fa86d2ed5c0554adba70e8b262eff6697a5af05de9da39
+size 3656440

amoe_loras/production/negatives/luneflux-routerv2-statesigma-control-s0.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:263817ca0db056d777eed712dd703da762a4d3df16640282b0478c4a7966cd94
+size 3620896

amoe_loras/production/negatives/luneflux-routerv2-statesigma-control-s1.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e1679ea716aa7b77710f1f5ca14e8e4e8793da6e93b83f99afd0de7e9a9e654
+size 3620824

amoe_loras/production/negatives/lunejson-addrcond-guidepost-negative-s0.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2e8920bf5239df1d70a8acc91050a230137085be4af678149bc5abc8866275a
+size 496644

amoe_loras/production/negatives/sd15-dispatch-bank-a4-falsified-s0.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b6238f3cde72d6be08b36bd545c41925477da053a24f6582411619773647154
+size 3621208

amoe_loras/production/negatives/sd15-dispatch-bank-a4-falsified-s1.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c0faff4739053f0d286b8df13e6eb7f22d033b1b6506c543ed463990a87b0d8
+size 3620832

amoe_loras/production/negatives/sd15-multiband-freqroles-inert-s0.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f03e65868ae725605566c6f0ea72574e6ea215b3c3909c2f7bcc4163d8bbf063
+size 4957920

amoe_loras/production/negatives/sd15-multiband-freqroles-inert-s1.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e9f44a807a8fa930abcdf55184a88cae817bd59abd9f9df2a38039fc79cb2df
+size 4957288

amoe_loras/production/sd15/sd15-multiband-coarse2fine-v1-s0.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f684bab2679d541a8f3fd94aa3ab66cca5eb70d710e3967132ebc4e4ead720ef
+size 4958088

amoe_loras/production/sd15/sd15-multiband-coarse2fine-v1-s1.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6eae8777f5a8e37bec5bae597a575c98ff4fde477f97a6b33d4898d8b00b93b
+size 4957416

amoe_loras/production/sd15/sd15-multiband-realdata-v1-s0.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa6ae6e9959a1f926f70dd8545ef97841fe0e7ec4b9fe4871ebfe8786d519c5e
+size 4957736

amoe_loras/production/sd15/sd15-multiband-realdata-v1-s1.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06a3fc8a8eb281cbdd1a9651cb4239066eb5638a087f07c7c13458217320de66
+size 4957336

amoe_loras/production/sd15/sd15-relay-grounding-v1-s0.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c689768457e98fe123588a8801fc85d946221f27f9fb18b464c1c692876dd50
+size 12942496

amoe_loras/production/sd15/sd15-relay-grounding-v1-s1.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5bbdabf7a546603d17b7a4499fde363cfcbef8fda51bfc7cec24066e6e3cd845
+size 12942104

amoe_loras/raw/exp001_sd15_relay/relay_all16_s0.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fb402a9a0b303d83aa55b5d0089436454213668515b564eeff2cf89392a0d32
+size 12941560

amoe_loras/raw/exp001_sd15_relay/relay_all16_s1.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82d0b401afb991cb7711cd3e754f9c3681b9fe90f196cf4d53040ed580cb5c34
+size 12941560

amoe_loras/raw/exp002_sd15_addrcond/addrcond_s0.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88ea4fc086f0ea9f55231ff046d2be22185fdbb1681b40ab5a86e465501206f5
+size 495820

amoe_loras/raw/exp004_anima_relay/ckpt/epoch1/aleph_relay.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0dcc0858884f2fa9226438c427fe41ea2ac07a9855e0fd9a2af4d147aaa3c0d9
+size 28606296

amoe_loras/raw/exp004_anima_relay/ckpt/epoch4/aleph_relay.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ec722819cc7ee968e1bfe7789814571d8526546fa321a7a98d06bf4cc55daa4
+size 28606296

amoe_loras/raw/exp004_anima_relay/ckpt/step2500/aleph_relay.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26449135045fa0be1c50be925ec91f7613475335812e1d805a9dc4e9c46b67c9
+size 28606296

amoe_loras/raw/exp006_sd15core_relay/relay_all16_s0.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c777ee0760723f8778d8d87a61402fb510380b291b43c7673ede7b029191a08
+size 12941544

amoe_loras/raw/exp006_sd15core_relay/relay_all16_s1.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3eb4f96c454a7a1f135a46f95ab6053cf2f8fb3137230808821f648b5a90f03f
+size 12941544

amoe_loras/raw/exp007_amoe_lora/amoe_core_s0.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16380169a836d1e1353b145e693cc2a8eac6df3b857e7c1ef83db874863a99ae
+size 3620520

amoe_loras/raw/exp007_amoe_lora/amoe_core_s1.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4bc35609be9154e2e191d0a04b1385452a9c721a308a5da1eab612874a551b3e
+size 3620520

amoe_loras/raw/exp007_amoe_lora/mono_core_s0.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:074e8dfb5be7925173d1221910ad4c62c48d48d13b3709e73706a13b2d1e83b1
+size 3250832

amoe_loras/raw/exp007_amoe_lora/mono_core_s1.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d49bd952db1d7a9b8d8f6f87e86a021a8053f4d15d5a344ffe5ff320b555a177
+size 3250832