docs(readme): cond-5 refined-extractor banner + Phase 3 staleness fixes

README.md

@@ -25,6 +25,10 @@ pipeline_tag: text-generation
 
 QLoRA adapters fine-tuned on multilingual code conditions for the **Language Decoded** project (part of [Cohere's Tiny Aya Expedition](https://aya.for.ai)).
 
+## ⚠️ Phase 3 eval numbers — read the experiments repo before citing
+
+Original Phase 3 `_summary_*.json` files on [`legesher/language-decoded-experiments`](https://huggingface.co/datasets/legesher/language-decoded-experiments) **under-report cond-5 SIB-200 accuracy by 20–35pp** because the strict inference-time extractor refused native-script answers. Cite the `_summary_reparsed_*.json` siblings (refined extractor) instead. **Five** Phase 3 SIB-200 conclusions also flip win→loss against baseline once the extractor is corrected (`cond-2-es-5k`, `cond-2-es-20k`, `cond-2-ur-20k`, `cond-2-zh-20k`, `cond-3-zh-5k`), and `cond-2-ur-5k`'s gain deflates 4.4×. See the [banner on the experiments repo](https://huggingface.co/datasets/legesher/language-decoded-experiments) (top of the README) for the full picture.
+
 ## Research Question
 
 > Does fine-tuning on non-English code improve multilingual reasoning — and is the benefit language-dependent or structure-dependent?
@@ -35,7 +39,7 @@ All adapters are trained on [CohereLabs/tiny-aya-base](https://huggingface.co/Co
 
 ## Model Structure
 
-This repo is the canonical hub for all Language Decoded LoRA adapters, organized by experimental condition:
+This repo is the canonical hub for the trained-from-scratch LoRA adapters, organized by experimental condition:
 
 | Subdirectory          | Condition   | Training Data                                         |
 | --------------------- | ----------- | ----------------------------------------------------- |
@@ -46,12 +50,15 @@ This repo is the canonical hub for all Language Decoded LoRA adapters, organized
 | `condition-2-ur-5k/`  | Condition 2 | Urdu keyword-swapped Python (Legesher-transpiled)     |
 | `condition-3-zh-5k/`  | Condition 3 | Transpiled + native Chinese code (blended)            |
 
+**Cond-5 (cross-lingual transfer)** is an evaluation pattern that re-uses condition-2 adapters with cross-language prompting — see [`phase3/conditions/condition-5-{zh,es,ur}-5k/`](https://huggingface.co/datasets/legesher/language-decoded-experiments/tree/main/phase3/conditions) on the experiments repo for the cross-lingual eval results.
+
 ### The Experimental Ladder
 
 - **Baseline --> 1**: Does code help at all?
 - **1 --> 2**: Does the language of keywords matter?
 - **2 --> 3**: Does diversity of native-language sources add value beyond keyword swap?
 - **3 --> 4**: Does code written in the cultural context of a language carry unique signal?
+- **--> 5**: Does shared script or language family create transfer effects when an adapter trained on one language is prompted in another?
 
 ## Usage
 
@@ -96,22 +103,25 @@ model = PeftModel.from_pretrained(base_model, "legesher/language-decoded-lora",
 
 ## Evaluation
 
-Models are evaluated on multilingual reasoning benchmarks with dual prompts (English + language-specific):
+Models are evaluated on multilingual reasoning benchmarks with dual prompts (English + language-specific). Phase 3 adds SIB-200 and Belebele to the Phase 2 benchmark set.
 
-| Benchmark | What it measures           | Examples per language |
-| --------- | -------------------------- | --------------------- |
-| MGSM      | Math reasoning             | 250 (full set)        |
-| X-CSQA    | Commonsense reasoning      | ~1,000 (full set)     |
-| XNLI      | Natural language inference | ~5,000 (full set)     |
+| Benchmark | What it measures           | Phase | Examples per language |
+| --------- | -------------------------- | ----- | --------------------- |
+| MGSM      | Math reasoning             | 2, 3  | 250                   |
+| X-CSQA    | Commonsense reasoning      | 2, 3  | ~1,000                |
+| XNLI      | Natural language inference | 2, 3  | ~5,000                |
+| SIB-200   | Topic classification       | 3     | ~204                  |
+| Belebele  | Reading comprehension      | 3     | ~900                  |
 
-_Results will be added as evaluation completes._
+Eval results live at [`legesher/language-decoded-experiments`](https://huggingface.co/datasets/legesher/language-decoded-experiments). **Cite `_summary_reparsed_*.json` files for Phase 3 numbers** — see the banner above.
 
 ## Limitations
 
 - **Single base model**: All adapters are trained on CohereLabs/tiny-aya-base (3.35B params). Results may not generalize to larger or architecturally different models.
 - **Limited training data**: Each condition uses a 5k-file subset for QLoRA fine-tuning, constrained by Kaggle T4 hardware limits.
-- **Evaluation scope**: Currently evaluated on 3 benchmarks (MGSM, X-CSQA, XNLI). Other reasoning tasks may show different patterns.
+- **Evaluation scope**: Currently evaluated on 5 benchmarks (MGSM, X-CSQA, XNLI, SIB-200, Belebele). Other reasoning tasks may show different patterns.
 - **Consumer hardware**: Training on Kaggle T4 (16GB) with 4-bit quantization introduces approximation that may affect adapter quality compared to full-precision training.
+- **Extractor coverage**: Phase 3 inference-time extractor under-counts native-script SIB-200 answers; refined post-hoc extractor recovers them. See the banner above and [`expedition-tiny-aya/analysis/phase-3/phase3-refined-evaluation.md`](https://github.com/legesher/research/blob/main/expedition-tiny-aya/analysis/phase-3/phase3-refined-evaluation.md) on the research repo.
 
 ## Related Resources