Add v0.9.4 update section: six differentiation bets

README sync for the v0.9.4 release (https://github.com/joemunene-by/GhostLM/releases/tag/v0.9.4). Adds the six-bets table near the top with three measured results (bet 3 settled at +4%, bet 5 MoE smoke PASS, bet 6 baseline 0/8 with eval harness). Updates citation note to v0.9.4. Refreshes roadmap to describe how the bets compose on top of ghost-base when GPU lands. v0.9 chat checkpoint itself is unchanged; bench numbers are intact.

README.md

@@ -76,6 +76,29 @@ parameters the model has the *register* of cybersec writing but not the
 This repo holds the slim inference checkpoint
 (`best_model.pt`, 324 MB, model + config only, optimizer state stripped).
 
+## v0.9.4 update (2026-05-08): six differentiation bets
+
+The v0.9.4 release adds six concrete bets to make GhostLM not-another-
+point-on-the-small-cybersec-LM-plot. Each has a runnable scaffold in
+the GitHub repo. Three are already measured. Strategic frame:
+[`docs/differentiation.md`](https://github.com/joemunene-by/GhostLM/blob/main/docs/differentiation.md).
+
+| Bet | Status | Result |
+|---|---|---|
+| 1. Tool-grounded SFT | scaffolded | scripts/distill_tool_use.py, ~$200 budget |
+| 2. Daily LoRA over fresh threat-intel | scaffolded | scripts/daily_finetune.py, ~1-2 GPU hr/day |
+| 3. Custom 32K BPE | **measured + settled** | +4.0% on cyber, -2.5% on general vs GPT-2 BPE; +25-35% projection falsified, see [bpe_corpus_ablation.md](https://github.com/joemunene-by/GhostLM/blob/main/docs/bpe_corpus_ablation.md) |
+| 4. Long context via RoPE NTK | scaffolded | scripts/extend_context_ntk.py, ~3-5 GPU hr |
+| 5. MoE for ghost-1B+ | **smoke validated** | 100-step training PASS, see [moe_training_smoke.md](https://github.com/joemunene-by/GhostLM/blob/main/docs/moe_training_smoke.md); presets `ghost-1b` (2.1B/1.2B-active) and `ghost-3b` (6.0B/3.3B-active) |
+| 6. Format-aware pretrain (STIX/YARA/Sigma/MISP) | **end-to-end measurable** | v0.9 baseline locked at 0/8 = 0%, see [format_baseline_v09.md](https://github.com/joemunene-by/GhostLM/blob/main/docs/format_baseline_v09.md); 560 templated training records ready, see [format_synth.md](https://github.com/joemunene-by/GhostLM/blob/main/docs/format_synth.md) |
+
+The strategic claim isn't that any one bet definitely works; it's
+that the **combination** of six reasonable bets gives GhostLM a
+defensible identity that parameter-scale-only roadmaps don't.
+
+The v0.9 chat checkpoint in this repo is unchanged; it's the
+baseline against which the bet measurements are made.
+
 ## Bench numbers
 
 All benches run with debiased multi-permutation text-scoring on
@@ -224,7 +247,7 @@ output rather than reliable answers.
   author        = {Munene, Joe},
   year          = {2026},
   howpublished  = {\url{https://github.com/joemunene-by/GhostLM}},
-  note          = {v0.9.2 release; 81M-parameter chat checkpoint}
+  note          = {v0.9.4 release; 81M-parameter chat checkpoint plus six differentiation bets}
 }
 ```
 
@@ -242,6 +265,14 @@ The fact-recall bar is the truth metric. Spec at
 multi-year pathway through ghost-7B in
 [`docs/hardware_pathway.md`](https://github.com/joemunene-by/GhostLM/blob/main/docs/hardware_pathway.md).
 
+After ghost-base lands, the v0.9.4 differentiation bets compose on
+top of it: tool-use SFT (bet 1) on the fresh ghost-base, format-aware
+pretrain mix (bet 6) using the 560 templated records plus
+LLM-distilled traces, RoPE NTK context extension to 16K (bet 4), and
+eventually ghost-1B with native MoE from step 0 (bet 5). Sequencing
+detail in
+[`docs/differentiation.md`](https://github.com/joemunene-by/GhostLM/blob/main/docs/differentiation.md).
+
 ## License
 
 Apache 2.0. Same license as the GhostLM source code.