Simplify public release surfaces around the technical note

README.md

@@ -26,12 +26,11 @@ tags:
 *The standalone model release from Evidence-Faithful Reasoning, built on the
 Qwen 3.5 Opus Distilled 27B base.*
 
-Quotebound 27B is the public release name for the standalone model
-previously referred to internally as `pilot 3`. I built it as the
-downloadable model release for Evidence-Faithful Reasoning: a LoRA adapter
-that turns its reasoning-distilled 27B base model into an evidence-first
-reader for closed packets of source text. Every answer has to land on the
-right evidence units, quote them verbatim, and stop with
+Quotebound 27B is the downloadable model release for
+Evidence-Faithful Reasoning: a LoRA adapter that turns its
+reasoning-distilled 27B base model into an evidence-first reader for
+closed packets of source text. Every answer has to land on the right
+evidence units, quote them verbatim, and stop with
 `Insufficient evidence.` when the packet does not justify a claim.
 
 ![Fresh public holdout: Quotebound 27B versus the prior bridge model](./standalone_holdout_comparison.svg)
@@ -59,10 +58,8 @@ quote normalizer carries the full stack to `0.9093` quote F1.*
 
 ## Read next
 
-- [Technical brief (PDF)](./evidence_faithful_reasoning_release_brief.pdf) — short, citation-friendly summary.
 - [Technical note](./technical_note_evidence_faithful_reasoning.md) — full method, results, and discussion.
 - [Frozen benchmark progression chart](./benchmark_progression.svg)
-- [Release architecture chart](./project_release_arc.svg)
 
 ## Quick start
 
@@ -225,8 +222,6 @@ Use this release for work that has to stay inside a fixed body of text:
 - Datasets:
   [fever/fever](https://huggingface.co/datasets/fever/fever),
   [hotpotqa/hotpot_qa](https://huggingface.co/datasets/hotpotqa/hotpot_qa)
-- Technical brief (PDF):
-  [evidence_faithful_reasoning_release_brief.pdf](./evidence_faithful_reasoning_release_brief.pdf)
 - Technical note:
   [technical_note_evidence_faithful_reasoning.md](./technical_note_evidence_faithful_reasoning.md)
 

evidence_faithful_reasoning_release_brief.md

@@ -13,7 +13,6 @@ Companion files:
 - [`technical_note_evidence_faithful_reasoning.md`](./technical_note_evidence_faithful_reasoning.md)
 - [`standalone_holdout_comparison.svg`](./standalone_holdout_comparison.svg)
 - [`benchmark_progression.svg`](./benchmark_progression.svg)
-- [`project_release_arc.svg`](./project_release_arc.svg)
 
 ## Executive summary
 
@@ -43,11 +42,10 @@ behavior at the model level.
 
 ## Quotebound 27B
 
-Quotebound 27B is the public release name for the standalone model
-previously referred to internally as `pilot 3`. It is the strongest
-standalone model the project produced and the artifact most readers will
-load first. It is the first standalone checkpoint in the project to hold
-up across multiple evaluation surfaces beyond the held-out probe.
+Quotebound 27B is the strongest standalone model the project produced and
+the artifact most readers will load first. It is the first standalone
+checkpoint in the project to hold up across multiple evaluation surfaces
+beyond the held-out probe.
 
 Fresh 36-task mixed public holdout:
 
@@ -80,19 +78,17 @@ remaining quote-faithful gap without leaving the closed-packet boundary.
 | Contrastive consistency | **1.0000** |
 | Invalid / missing rate | **0.0000** |
 
-## Project arc and stopping point
+## Release boundary
 
 The release has two public faces: Quotebound 27B, the standalone model that
 loads directly from Hugging Face, and a benchmark-facing hybrid stack that
 closes the last quote-faithfulness gap on the frozen held-out probe. The
 split is part of the project story, not hidden behind the fine print.
 
-A narrow follow-up — internally `pilot 4` — fixed one specific FEVER
-month/date temporal-insufficiency case but weakened broader behavior on
-larger evaluation surfaces. The project read that outcome as a stop signal
-rather than running additional local fixes, and froze at the point where
-Quotebound 27B was strongest and the benchmark-facing system was already
-complete.
+The public release stops at the point where the strongest benchmark-facing
+system and the strongest standalone model were both clearly in hand. That
+keeps the package centered on finished artifacts rather than on local
+variant history.
 
 ## Intended use and boundaries
 
@@ -121,5 +117,3 @@ Important boundaries:
   [`standalone_holdout_comparison.svg`](./standalone_holdout_comparison.svg)
 - Frozen benchmark progression chart:
   [`benchmark_progression.svg`](./benchmark_progression.svg)
-- Release architecture chart:
-  [`project_release_arc.svg`](./project_release_arc.svg)

evidence_faithful_reasoning_release_brief.pdf

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:4016a00664573e528b22b0d93a4b0d5ebe740c0c6f4a4e9fd6f6874a02c55d25
-size 243746

technical_note_evidence_faithful_reasoning.md

@@ -13,14 +13,11 @@ packet units as evidence, quote those units verbatim, and abstain with
 project ends in two finished results from the same frame. The first is a
 hybrid system — a trained bridge checkpoint plus a packet-local quote
 normalizer — that clears every gate of the contract on the frozen
-held-out probe (`probe_v0`). The second is Quotebound 27B, the public
-release name for the standalone model previously referred to internally as
-`pilot 3`, released as a LoRA adapter on Hugging Face
+held-out probe (`probe_v0`). The second is Quotebound 27B, released as a
+LoRA adapter on Hugging Face
 ([`darcar0/quotebound-27b`](https://huggingface.co/darcar0/quotebound-27b)).
-A narrow follow-up — internally `pilot 4` — was rejected as a stop signal
-after it traded one local fix for broader regressions. The hybrid system
-is the benchmark-facing release; Quotebound 27B is the downloadable model
-release.
+The hybrid system is the benchmark-facing release; Quotebound 27B is the
+downloadable model release.
 
 **Keywords:** evidence-faithful reasoning, grounded QA, claim
 verification, closed-packet reasoning, abstention, attribution.
@@ -77,8 +74,8 @@ normalizer was layered on as a finishing repair, and held-out evaluation
 was rerun on the protected split. Once the hybrid stack solved the
 held-out probe, a teacher–student distillation cycle pushed the winning
 behavior back into the model itself, evaluated entirely off the held-out
-probe. The cycle was stopped when the strongest standalone release
-artifact emerged and a focused follow-up showed clear regressions.
+probe. The public release stops at the strongest standalone artifact that
+preserved the broader gains reported below.
 
 Train and dev surfaces are derived from public FEVER-style
 verify-claim data, public HotpotQA-style grounded-QA data, and
@@ -126,14 +123,10 @@ question inside the same frame: how much of that winning behavior can be
 moved into the model itself, evaluated on surfaces outside the held-out
 probe?
 
-That question produced Quotebound 27B — the public release name for the
-standalone model previously referred to internally as `pilot 3` — a
-teacher-student distillation checkpoint published as a LoRA adapter on top
-of
+That question produced Quotebound 27B, a teacher-student distillation
+checkpoint published as a LoRA adapter on top of
 [`Jackrong/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-v2`](https://huggingface.co/Jackrong/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-v2).
 
-- **Internal checkpoint:**
-  `outputs/sft_v1_v2_teacher_distill_pilot_v3_partialdev/checkpoint-16`
 - **Public release identity:**
   [`darcar0/quotebound-27b`](https://huggingface.co/darcar0/quotebound-27b)
 
@@ -182,18 +175,13 @@ at the system level on this slice. The standalone freeze memo
 outcome; per-metric numbers were not recorded for this surface, so it stands
 as a narrative parity result rather than a table cell.
 
-## 8. Stop-signal follow-up
-
-A narrow follow-up — internally `pilot 4` — was built to fix one specific
-FEVER month/date temporal-insufficiency error. It fixed that single row but
-weakened broader behavior on the larger evaluation surfaces. The project read
-that outcome as a stop signal: further local-fix iteration was trading visible
-gains for wider regressions, so Quotebound 27B froze at the prior
-checkpoint. Canonical memo:
-`reports/sft_v1_v2_teacher_distill_pilot_v4_partialdev_status.md`.
+## 8. Release boundary
 
-See [Figure 3: project release arc](./project_release_arc.svg) for the full
-arc from baseline through stop signal.
+The public release centers on the two strongest finished artifacts from the
+project: the benchmark-winning hybrid stack on frozen `probe_v0`, and
+Quotebound 27B as the strongest standalone model. That boundary keeps the
+package focused on the results that held up across the evaluation surfaces
+reported here.
 
 ## 9. Discussion
 
@@ -216,11 +204,10 @@ model in the project to hold up across multiple evaluation surfaces beyond
 the held-out probe; calling it the standalone release artifact is faithful
 to that evidence.
 
-**Why the stop signal matters.** The follow-up was a deliberate narrow
-refinement. It worked on the one row it targeted and regressed broader
-behavior. Reading that result as a stop signal — rather than running
-additional local fixes — is the discipline the project decided to keep
-visible in the release trail.
+**Why the release stops here.** The package is intentionally centered on
+the strongest benchmark-facing system and the strongest standalone model.
+That keeps the public release focused on finished results rather than on
+intermediate local variations.
 
 **Distinction held throughout.** Perfect frozen `probe_v0` belongs to the
 hybrid stack, not to the standalone adapter alone. The release ships both
@@ -241,8 +228,9 @@ results without collapsing them into one claim.
    the project to hold up across multiple evaluation surfaces beyond
    `probe_v0`, and that roughly doubles raw quote-faithful behavior over
    the earlier bridge.
-5. A documented stop signal that marks the point at which further local-fix
-   iteration began trading visible gains for wider regressions.
+5. A public artifact set centered on the benchmark-winning hybrid system,
+   Quotebound 27B, and the technical note that explains how the two fit
+   together.
 
 ## 11. Intended use and limitations
 
@@ -274,7 +262,6 @@ Canonical project surfaces:
 - final artifact memo: `reports/sft_v1_final_artifact_status.md`
 - standalone freeze memo: `reports/standalone_model_v2_freeze_memo.md`
 - fresh holdout comparison: `reports/standalone_model_v2_holdout_v1_bridge_vs_pilot3_status.md`
-- stop-signal memo: `reports/sft_v1_v2_teacher_distill_pilot_v4_partialdev_status.md`
-- release brief: `evidence_faithful_reasoning_release_brief.pdf`
 - model card: `README.md`
+- technical note: `technical_note_evidence_faithful_reasoning.md`
 - Hugging Face release: [`darcar0/quotebound-27b`](https://huggingface.co/darcar0/quotebound-27b)