references+attribution section, inline citations

TECHNICAL.md

@@ -1,13 +1,13 @@
 # Adopt-0 — Technical Companion
 
-**Repository:** `AbstractPhil/alephlm-adopt-0` · **Author:** AbstractPhil
+**Repository:** [`AbstractPhil/alephlm-adopt-0`](https://huggingface.co/AbstractPhil/alephlm-adopt-0) · **Author:** AbstractPhil
 **Companion to the week-in-review article. Runs dated August 4–5, 2026.**
 
 ---
 
 ## 1. Overview
 
-Adopt-0 is the first attachment of the aleph mechanism to a real pretrained LLM. Rather than training an aleph-routed trunk from scratch, the mechanism is *adopted onto* a completely frozen Qwen2.5-0.5B-Instruct as a set of small relay adapters, and asked to earn its place through distillation from the model's 3x-larger sibling, Qwen2.5-1.5B-Instruct.
+Adopt-0 is the first attachment of the aleph mechanism to a real pretrained LLM. Rather than training an aleph-routed trunk from scratch, the mechanism is *adopted onto* a completely frozen [Qwen2.5-0.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-0.5B-Instruct) as a set of small relay adapters, and asked to earn its place through [distillation](https://arxiv.org/abs/1503.02531) from the model's 3x-larger sibling, [Qwen2.5-1.5B-Instruct](https://huggingface.co/Qwen).
 
 The trainable budget is 2.87M parameters against a frozen half-billion-parameter trunk. Three arms ran to verdict — 20k steps and ~31M tokens each, ~2.5 GPU-hours per arm — and every artifact (all checkpoints, training logs, and evaluation results) ships publicly in this repository.
 
@@ -27,10 +27,10 @@ A companion instrument from the same working period, the cross-tokenizer alignme
 ### 2.1 Relay adapters
 
 - **Student:** Qwen2.5-0.5B-Instruct, completely frozen. No base weight is ever updated.
-- **Adapters:** one sigma-gated residual relay per transformer block, plus one separately-gated relay on the pre-head stream — the stream that feeds the token head directly. That last seat exists because of the program's placement law (Campaign Law 2, §6): the address mechanism is predicted to pay only where it parameterizes the output distribution, so the bed deliberately gives it a position there.
+- **Adapters:** one sigma-gated residual relay per [transformer](https://arxiv.org/abs/1706.03762) block, plus one separately-gated relay on the pre-head stream — the stream that feeds the token head directly. That last seat exists because of the program's placement law (Campaign Law 2, §6): the address mechanism is predicted to pay only where it parameterizes the output distribution, so the bed deliberately gives it a position there.
 - **Aleph arm:** relays route through the aleph's signed codebook read, K=64 per relay.
 - **Control arm:** plain-MLP relays at **matched placement and matched capacity** — the capacity control. Any difference between arms is mechanism, not parameter count.
-- **Teacher:** Qwen2.5-1.5B-Instruct. **Objective:** per-token KL divergence to the teacher at temperature 2, plus a 0.1-weighted cross-entropy term; pure Adam; streaming wikitext corpus.
+- **Teacher:** Qwen2.5-1.5B-Instruct. **Objective:** per-token KL divergence to the teacher at temperature 2, plus a 0.1-weighted cross-entropy term; pure Adam; streaming [wikitext](https://arxiv.org/abs/1609.07843) corpus.
 
 ### 2.2 Silent at initialization
 
@@ -52,7 +52,7 @@ The first smoke attempt froze the training host: an fp32 student with an uncappe
 | + aleph relays | 15.449 | 1.448 |
 | + mlp relays | 15.394 | 1.432 |
 
-Both adapter mechanisms cut KL to the teacher by ~25%, within ~1% relative of each other. This tie class has a prior sighting in the program: the **L-AR8 co-training bed (vision dial)**, and before that the seed-0 E1 trunk campaign's three-way tie, where learned, frozen-random, and dense arms scored .6031 / .6033 / .6026 — a spread of .0007. The consistent reading across all three sightings: **on the raw loss gauge alone, mechanism does not separate from capacity.** The verdict lives one level deeper, in how each mechanism spent its budget.
+Both adapter mechanisms cut KL to the teacher by ~25%, within ~1% relative of each other. This tie class has a prior sighting in the program: the **L-AR8 co-training bed (vision dial)**, and before that the [seed-0 E1 trunk campaign](https://huggingface.co/AbstractPhil/alephlm-0)'s three-way tie, where learned, frozen-random, and dense arms scored .6031 / .6033 / .6026 — a spread of .0007. The consistent reading across all three sightings: **on the raw loss gauge alone, mechanism does not separate from capacity.** The verdict lives one level deeper, in how each mechanism spent its budget.
 
 ### 3.2 The placement election
 
@@ -73,7 +73,7 @@ Both trained arms toggle off to recover the stock model to **4 decimal places**
 
 ### 3.4 Secondary instrument reads
 
-- **Positional integrity:** a wide-spectrum positional probe (15 depths to 8,000 tokens) placed the adopt-0 hybrid among ten models; integrity holds ~.98, essentially flat to depth 8,000 — the RoPE inheritance, recorded as the evidence for making RoPE the default in the next trunk generation.
+- **Positional integrity:** a wide-spectrum positional probe (15 depths to 8,000 tokens) placed the adopt-0 hybrid among ten models; integrity holds ~.98, essentially flat to depth 8,000 — the [RoPE](https://arxiv.org/abs/2104.09864) inheritance, recorded as the evidence for making RoPE the default in the next trunk generation.
 - **A measured cost:** the token-grid directional rank of the decoder sits 10–20x below the program's encoders, and KL distillation on the frozen trunk *narrowed* it further (.026 to .015) — distribution-matching compresses directional diversity. Logged as a caution for any plan that would use an adopted decoder as a conditioning encoder.
 - **Signed structure:** the program's first signed instruments read the adopt-0 relays as a **balanced bipolar code** — negative-weight fraction ~.50, magnitudes ~1/64, dense across the K=64 codebook, with zero net bias. This is the canonical reconstructive sign-code regime the aleph's reconstruction lineage predicts, and it was invisible to every prior density-based gauge (§6).
 
@@ -81,7 +81,7 @@ Both trained arms toggle off to recover the stock model to **4 decimal places**
 
 ## 4. The honest task-transfer null
 
-The shipped models were benchmarked on lm-eval, 0-shot (arc_easy, hellaswag, piqa, winogrande):
+The shipped models were benchmarked on [lm-eval](https://github.com/EleutherAI/lm-evaluation-harness), 0-shot (arc_easy, hellaswag, piqa, winogrande):
 
 | model | 4-task mean |
 |---|---|
@@ -106,9 +106,9 @@ The next distillation plans want multiple teachers — which raises a gating que
 
 | pair | held-out token cosine | token R@1 |
 |---|---|---|
-| distilbert → bert (same tokenizer — the ceiling) | .648 | .966 |
-| t5 → bert (SentencePiece → WordPiece) | .333 | **.840** |
-| clip → bert (BPE, causal, 77-token cap) | .183 | .445 |
+| [distilbert](https://arxiv.org/abs/1910.01108) → [bert](https://arxiv.org/abs/1810.04805) (same tokenizer — the ceiling) | .648 | .966 |
+| [t5](https://arxiv.org/abs/1910.10683) → bert ([SentencePiece](https://arxiv.org/abs/1808.06226) → [WordPiece](https://arxiv.org/abs/1810.04805)) | .333 | **.840** |
+| [clip](https://arxiv.org/abs/2103.00020) → bert (BPE, causal, 77-token cap) | .183 | .445 |
 | shuffled-correspondence nulls | — | ~.0005 (dead) |
 
 The headline is the t5 row: across a fully different tokenization scheme, the correct token is retrieved first-try 84% of the time from a ~15,000-token gallery where chance is ~.0005. **Roughly half the alignment strength survives the vocabulary mismatch — a tax, never a wall.** The room between .840 and the .966 same-tokenizer ceiling is the price of the bridge; the room between .840 and .0005 is why the bridge is worth building. A three-member span-aligned token consensus built on these maps retains 93% of the reference member's effective rank (72.7 of 77.9), with bert/t5 cross-teacher agreement ~.76.
@@ -131,3 +131,35 @@ The headline is the t5 row: across a fully different tokenization scheme, the co
 ## 7. Provenance
 
 All numbers in this document are verified against the research record. Three arms (frozen / aleph / mlp) ran to verdict at 20k steps and ~31M tokens each on a streaming wikitext corpus, August 4–5, 2026; all weights, training logs, and evaluation outputs for every arm ship in this repository (`AbstractPhil/alephlm-adopt-0`). The tokenizer-alignment instrument (§5) was run in the same working period under the program's certified out-of-sample protocol. Author: AbstractPhil.
+
+---
+
+## References and attribution
+
+**Models**
+
+- Qwen2.5-0.5B-Instruct (the frozen student trunk) and Qwen2.5-1.5B-Instruct (the distillation teacher) — the [Qwen team](https://huggingface.co/Qwen) — [Qwen2.5-0.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-0.5B-Instruct)
+- BERT (Devlin et al.) — reference member and WordPiece side of the tokenizer-alignment instrument — https://arxiv.org/abs/1810.04805
+- DistilBERT (Sanh et al.) — the same-tokenizer ceiling pair — https://arxiv.org/abs/1910.01108
+- T5 (Raffel et al.) — the cross-tokenizer pair — https://arxiv.org/abs/1910.10683
+- CLIP (Radford et al.) — the causal, 77-token-capped pair — https://arxiv.org/abs/2103.00020
+
+**Data**
+
+- WikiText-2 (Merity et al.) — the streaming distillation corpus, ~31M tokens per arm — https://arxiv.org/abs/1609.07843
+
+**Methods**
+
+- Knowledge distillation (Hinton et al.) — the per-token KL-to-teacher objective at temperature 2 — https://arxiv.org/abs/1503.02531
+- Attention / the transformer (Vaswani et al.) — the trunk architecture the relays attach to — https://arxiv.org/abs/1706.03762
+- LoRA (Hu et al.) — lineage of the zero-init, detachable adapter convention — https://arxiv.org/abs/2106.09685
+- Mixture-of-experts routing (Shazeer et al.) — lineage and contrast class of the gated relay design — https://arxiv.org/abs/1701.06538
+- Rotary position embeddings (Su et al.) — the positional scheme whose depth integrity §3.4 measures — https://arxiv.org/abs/2104.09864
+- SentencePiece (Kudo & Richardson) — T5's tokenizer in the alignment instrument — https://arxiv.org/abs/1808.06226
+
+**Infrastructure**
+
+- lm-evaluation-harness (EleutherAI) — the 0-shot benchmark verdict (arc_easy, hellaswag, piqa, winogrande) — https://github.com/EleutherAI/lm-evaluation-harness
+- PyTorch — every trainer and instrument in the bed — https://pytorch.org
+
+**Related artifacts:** [alephlm-adopt-0](https://huggingface.co/AbstractPhil/alephlm-adopt-0) (this release) · [alephlm-0](https://huggingface.co/AbstractPhil/alephlm-0) (the E1 trunk campaign whose three-way tie §3.1 references) · prior installment: [Geometric Memory FT4](https://huggingface.co/blog/AbstractPhil/geometric-memory-ft4)