Lean v0 card + simple headline figure

README.md

@@ -20,61 +20,33 @@ tags:
 
 # ZeroProof Intent Model 0 (v0)
 
-A QLoRA adapter over `gemma-3-1b` that reads a payment or ecommerce conversation and returns one structured intent object. It is the model side of ZeroProof's behavioral attestation stack: it decides what the user actually intended so a downstream layer can verify an agent's action against it. This is v0, our first release, evaluated against the frozen base on a de-duplicated, per-intent balanced held-out set.
+A QLoRA adapter over `gemma-3-1b` that reads a payment or ecommerce conversation and returns one structured intent object. It is the model side of ZeroProof's behavioral attestation stack: it decides what the user intended so a downstream layer can verify an agent's action against it. Small on purpose, so it can run on every transaction. This is v0, our first release.
 
 ![evaluation](eval_report.png)
 
-## Model description
+## What it does
 
-- Base: `gemma-3-1b` (frozen, pinned snapshot)
-- Method: QLoRA supervised fine tuning, rank-16 adapter, response-only supervision, 2 epochs
-- Task: route a conversation to one of 7 intents (`spend`, `send`, `exchange`, `recur`, `bill`, `reverse`, `none`) and extract the fields for that intent
-- Language: English
+In: a short conversation. Out: one intent object, the intent plus the fields that matter for it. It routes to one of 7 intents: `spend`, `send`, `exchange`, `recur`, `bill`, `reverse`, `none`. `none` is first class. In an attestation setting a false positive is a false attestation, so getting the no-action boundary right matters most.
 
-Ground truth is taken from the user turns only. `none` is first class: in an attestation setting a false positive is a false attestation, so the model is trained and measured on getting the no-action boundary right.
+## Results
 
-## Model sources
+Scored against the frozen base on 4,000 held-out conversations, greedy decoding, both models in one engine. Core-type is reported macro (equal weight per intent).
 
-- Org: [zero-proof-ai](https://huggingface.co/zero-proof-ai) · Collection: ZeroProof Intent Models
-- Website: [zeroproofai.com](https://www.zeroproofai.com/)
-- Paper: in progress
-
-## Versions
-
-| Version | Base | Status | Notes |
-|---|---|---|---|
-| **v0 (this)** | gemma-3-1b | released | first controlled base-vs-SFT result |
-| v1 | TBD | planned | balanced trap-laden eval, frontier and peer comparison, long-context |
-
-## Performance
-
-Base and the adapter are scored in one engine on the identical 4,000 held-out conversations, greedy decoding. Only the adapter differs. Core-type is reported macro (equal weight per intent) because the eval is 57% `none`; the micro number is shown for completeness only.
-
-| Metric | Base gemma-3-1b | **Model 0** |
+| Metric | Base gemma-3-1b | Model 0 |
 |---|---|---|
-| Valid structured output | 87.5 | **99.8** |
-| Intent detected (act vs none) | 35.0 | **81.9** |
-| **Core-type routing, macro** | 14.4 | **70.0** |
-| Core-type routing, micro | 7.6 | 79.8 |
-| Detail extraction | 19.7 | **61.3** |
-
-Per-intent core-type accuracy (n = held-out count):
+| Valid output | 87.5 | 99.8 |
+| Intent detected | 35.0 | 81.9 |
+| Core-type (macro) | 14.4 | 70.0 |
 
-| | none | reverse | send | exchange | bill | spend | recur |
-|---|---|---|---|---|---|---|---|
-| n | 2286 | 300 | 300 | 214 | 300 | 300 | 300 |
-| base | 0 | 0 | 10 | 0 | 6 | 84 | 0 |
-| **Model 0** | **90** | **74** | **72** | **68** | **65** | 63 | **59** |
+The base defaults to a single class. Model 0 routes across all seven.
 
-The base does not fail at random. It collapses to a single class, predicting `spend` on 80.7% of all inputs regardless of the true intent, so its only strong column is `spend`. The adapter trades that false strength for real coverage of all seven intents. Columns for a peer 1B (Llama) and a frontier parent are the v1 comparison, run on this same eval.
+## Method
 
-## Training
+QLoRA SFT on a frozen, pinned `gemma-3-1b`, rank-16 adapter, 2 epochs, trained on Modal. Trained on ZeroProof's own conversation dataset: 6,000 train / 4,000 eval, balanced across the action intents, with near-duplicates removed so eval gains are not memorized.
 
-QLoRA SFT on Modal, effective batch 16, 2 epochs, learning rate 2e-4, response-only masking on the frozen base. Trained on ZeroProof's own conversation dataset: 6,000 train / 4,000 eval, human-realistic conversations across a wide range of people and situations, with near-duplicates removed so eval gains are not memorized.
+## Status
 
-## Intended use and limitations
-
-Intended for intent detection inside the ZeroProof attestation pipeline. v0, single base family, English. Weakest intents are `recur` (59) and `spend` (63), the status-vs-action and purchase-vs-defer boundaries, which the next data cycle targets. The confidence field is not yet calibrated; treat it as a rough signal. No frontier or peer comparison is claimed in v0.
+v0, first release, English. Next: a broader, harder eval, comparisons against peer 1B and frontier models, and more intents and domains.
 
 ## Citation
 
@@ -86,3 +58,5 @@ Intended for intent detection inside the ZeroProof attestation pipeline. v0, sin
   howpublished = {\url{https://huggingface.co/zero-proof-ai/intent-model-0}}
 }
 ```
+
+Built by [ZeroProof](https://www.zeroproofai.com/) · [zero-proof-ai](https://huggingface.co/zero-proof-ai)