references+attribution section, inline citations

deep-arm/TECHNICAL.md

@@ -1,7 +1,7 @@
 # Deep Arm — Depth Extension for captionbert-8192-v2-B
 
 **A technical companion to the week-in-review article. Ships as `deep-arm/TECHNICAL.md` inside the
-`AbstractPhil/captionbert-8192-v2-B` repository.**
+[`AbstractPhil/captionbert-8192-v2-B`](https://huggingface.co/AbstractPhil/captionbert-8192-v2-B) repository.**
 
 This document describes **deep-1**: a ~5M-parameter depth-extension module ("deep arm") that
 extends the encoder's usable conditioning depth from 256 tokens to 2048+ while leaving the base
@@ -26,7 +26,8 @@ The deep arm is a **switchable long-prompt mode** layered over that frozen base:
 
 The arm adds ~5M trainable parameters (~4.06M re-initialized deep position rows + ~0.92M gated
 relay adapters) against a frozen trunk, trained in 8k steps overnight on a single consumer GPU by
-distilling token-state behavior from Longformer-base-4096 across a learned cross-dimensional
+[distilling](https://arxiv.org/abs/1503.02531) token-state behavior from
+[Longformer-base-4096](https://arxiv.org/abs/2004.05150) across a learned cross-dimensional
 bridge. Its preregistered depth gate passed, and a labeled harder secondary passed as well.
 
 ---
@@ -44,8 +45,8 @@ models), the encoder's state-similarity curve looks healthy at depth: a degraded
 plateau around **.77** with no cliff. Token recoverability also holds up, at **.61–.66 through
 depth 1024** — the strongest of the models tested. But the semantic gauge tells a different
 story: **attribute binding collapses to roughly chance (~1.0) near token depth 480 and never
-returns.** For reference on the same instrument, t5-base holds binding 1.9–3.0 through 2048
-(relative position encodings are the real long-context contribution there), and bert-base reads
+returns.** For reference on the same instrument, [t5-base](https://arxiv.org/abs/1910.10683) holds binding 1.9–3.0 through 2048
+(relative position encodings are the real long-context contribution there), and [bert-base](https://arxiv.org/abs/1810.04805) reads
 3.6 within its native 512.
 
 *The binding gauge, briefly:* a contrast score read from the token states at the two noun
@@ -93,7 +94,7 @@ Seven load-bearing elements:
    around each frozen block, sigma-gated.
 4. **Longformer targets.** Teacher token states from Longformer-base-4096 on long documents,
    span-resampled onto the encoder's token grid, then mapped 768→512.
-5. **Cross-dimensional Procrustes bridge.** A whitened-Procrustes map into the encoder's real
+5. **Cross-dimensional [Procrustes](https://doi.org/10.1007/BF02291478) bridge.** A whitened-Procrustes map into the encoder's real
    512-d token frame, fit at **cos .5013 / retrieval R@1 .849**, with a paired shuffled-null
    control at floor. This exceeds the earlier 768-d proxy-frame fit (.35). Stage 0 aborts by
    construction if the fit lands below cos .20.
@@ -176,7 +177,8 @@ a single scoreboard number would erase the mechanism:
   its way from .72 → 3.80; depth 2288 crosses 1.5 only in the final 500 of 8k steps.
 - **Relay adapters (~0.92M params):** retroactive-binding amplification wherever gradient
   reached — bind1 moved first at every depth. The adapter gates finished **.35 → .51, opening
-  monotonically with depth** — the third independent architecture in this research line to show
+  monotonically with depth** — the third independent architecture in
+  [this research line](https://huggingface.co/blog/AbstractPhil/geometric-memory-ft4) to show
   the depth-gradient regularity (its third substrate).
 - **Longformer supervision through the .5013-cos bridge:** shallow behavior **improved** under
   it — depth-10 binding 1.59/2.01 → 2.69/2.27. Depth was bought without taxing the trained
@@ -210,8 +212,8 @@ it off for short ones. The capability trade is a mode switch, not a regression.
 | V2 | Joint-objective revision | Named, unbuilt | Distillation plus a shallow-capability anchor, to close the .5655 engaged-mode gap; the refinement path recorded on the model card |
 | V3 | Token-fidelity masked-span arm | Named, unbuilt | A span-reconstruction objective on the existing trunks — the targeted fix for the encoder's binding gap and the conditioning line's shelf upgrade |
 | V4 | Interpolation-init deep rows | Named, unbuilt | Interpolation initialization as an ablation against tiling (which is free and strong) |
-| V5 | Anchored-trunk deep arm | Named, unbuilt — queue head | The V1 recipe applied to the AlephLM-0 anchored trunks — the variant that extends that family's inference depth. Two free reads: whether signed dispatch shapes depth repair differently than a dense trunk, and whether the a3 trunk's early-grid diversity advantage survives depth extension. Requires normalized-gauge grid reads and context layer-norm in any consumer |
-| V6 | RoPE-native next trunk | Design-level | A related hybrid with a RoPE trunk measures ~.98 positional integrity, flat to depth 8000 — evidence that rotary positions remove the position-row problem at the root for the *next* pretrain, rather than retrofitting this one |
+| V5 | Anchored-trunk deep arm | Named, unbuilt — queue head | The V1 recipe applied to the [AlephLM-0](https://huggingface.co/AbstractPhil/alephlm-0) anchored trunks — the variant that extends that family's inference depth. Two free reads: whether signed dispatch shapes depth repair differently than a dense trunk, and whether the a3 trunk's early-grid diversity advantage survives depth extension. Requires normalized-gauge grid reads and context layer-norm in any consumer |
+| V6 | [RoPE](https://arxiv.org/abs/2104.09864)-native next trunk | Design-level | A related hybrid with a RoPE trunk measures ~.98 positional integrity, flat to depth 8000 — evidence that rotary positions remove the position-row problem at the root for the *next* pretrain, rather than retrofitting this one |
 
 **Queue by leverage:** V5 → V2 → V3 → V6. All of V2/V3/V5 are single-consumer-GPU overnight runs
 at the deep arm's ~5M-parameter scale.
@@ -259,3 +261,48 @@ engaged-mode benchmark (`deep_arm_bench.json`), alongside the model-card section
 construction, the before/after battery, the bridge fit, the honest cost, toggle semantics, and
 usage. Every number in this document is inherited from the registered measurement record for
 that window.
+
+---
+
+## References and attribution
+
+**Models**
+
+- Longformer — Beltagy et al., [arXiv:2004.05150](https://arxiv.org/abs/2004.05150). The
+  distillation teacher (longformer-base-4096), source of the deep token-state targets.
+- T5 — Raffel et al., [arXiv:1910.10683](https://arxiv.org/abs/1910.10683). Depth-battery
+  comparator (t5-base), whose relative position encodings hold binding through 2048.
+- BERT — Devlin et al., [arXiv:1810.04805](https://arxiv.org/abs/1810.04805). Depth-battery
+  comparator (bert-base), read within its native 512.
+- CLIP — Radford et al., [arXiv:2103.00020](https://arxiv.org/abs/2103.00020). Lineage of the
+  conditioning-consumer framing: downstream consumers read per-token encoder states through
+  cross-attention rather than a pooled vector.
+
+**Data**
+
+- MTEB — [arXiv:2210.07316](https://arxiv.org/abs/2210.07316). Source of the suites behind the
+  certified 8-task short-input benchmark used for the engaged-mode cost.
+
+**Methods**
+
+- Procrustes analysis — Schönemann (1966), [doi:10.1007/BF02291478](https://doi.org/10.1007/BF02291478).
+  The cross-dimensional bridge: a whitened-Procrustes map from the teacher's 768-d frame into the
+  encoder's 512-d token frame.
+- Knowledge distillation — Hinton et al., [arXiv:1503.02531](https://arxiv.org/abs/1503.02531).
+  The training scheme's lineage; here, per-token state distillation from the teacher across the
+  bridge.
+- LoRA — Hu et al., [arXiv:2106.09685](https://arxiv.org/abs/2106.09685). Lineage of the small
+  gated relay adapters trained over the frozen trunk.
+- RoPE — Su et al., [arXiv:2104.09864](https://arxiv.org/abs/2104.09864). Rotary position
+  embedding; the V6 design direction that removes the position-row problem at the root.
+
+**Infrastructure**
+
+- PyTorch — [pytorch.org](https://pytorch.org). Training and evaluation stack for the arm and
+  its batteries.
+
+**Related artifacts:** the trunk this arm extends,
+[AbstractPhil/captionbert-8192-v2-B](https://huggingface.co/AbstractPhil/captionbert-8192-v2-B)
+(this repository; the arm ships under `deep-arm/`) · the anchored trunks named as the V5 target,
+[AbstractPhil/alephlm-0](https://huggingface.co/AbstractPhil/alephlm-0) · the prior installment
+of this series, [geometric-memory-ft4](https://huggingface.co/blog/AbstractPhil/geometric-memory-ft4).