Add benchmark wireframes and extended evaluation flow

docs/wireframes/pages/benchmark-annotation.md

@@ -0,0 +1,71 @@
+# Benchmark · Annotation
+Inspect evaluation answers and mark evidence quality.
+
+::: card {#tabs}
+[Upload & map] [Evaluation] [Results] [Annotation]*
+:::
+
+::: card {#evaluation}
+### Evaluation
+[Microsoft retrieval · v2____________v]
+
+ClimRetrieve v1 · Ranking
+
+Question [TCFD-01________________v]
+- TCFD-01
+- TCFD-02
+- TCFD-03
+
+12 / 16 evaluated · 3 annotations saved
+:::
+
+::: card {#question}
+### Question
+**How does the board oversee climate-related risks?**
+
+Reference type: Governance · Expected chunks: 3
+
+
+::: callout {for:evaluation side:left}
+choose a saved run
+:::
+
+::: callout {for:question side:right}
+review one question
+:::
+
+::: card {#evidence}
+### Retrieved evidence
+
+| Rank | Relevance | Source passage | Mark |
+|---:|---|---|---|
+| 1 | [Relevant v] | “The Sustainability Committee meets quarterly to review climate risk…” · p.14 | [x] |
+| 2 | [Partly relevant v] | “The CRO reports climate metrics to the audit committee…” · p.18 | [x] |
+| 3 | [Not relevant v] | “Scenario analysis is presented annually to the full board…” · p.22 | [ ] |
+
+**Relevance scale:** 0 Not relevant · 1 Partly relevant · 2 Relevant
+
+### Annotation note
+[The first passage directly answers the governance question.______________________________]
+
+[Save annotation]*  [Previous question]  [Next question →]
+:::
+
+::: callout {for:evidence side:left}
+mark the chunks
+:::
+
+::: card {#answer}
+### Evaluation details
+
+Model answer: The board’s Sustainability Committee reviews climate risks quarterly, with reporting from the CRO.
+
+Matched benchmark chunks: 2 / 3 · Evidence coverage: 67%
+
+Annotation history: **3 saved** · Last edited by you just now
+:::
+
+::: callout {for:answer side:right}
+revisit saved
+annotations
+:::

docs/wireframes/pages/benchmark-evaluation.md

@@ -0,0 +1,88 @@
+# Benchmark · Evaluation
+Run a ranking evaluation against a shared benchmark.
+
+::: card {#tabs}
+[Upload & map] [Evaluation]* [Results] [Annotation]
+:::
+
+::: card {#mode}
+### Evaluation mode
+
+- (x) Ranking
+- ( ) Classification
+
+Ranking compares the order of retrieved chunks. Classification compares one predicted label per question.
+:::
+
+::: callout {for:mode side:left}
+choose a track
+:::
+
+::: {#benchmark}
+### Benchmark set
+[ClimRetrieve v1________________v]
+- ClimRetrieve v1
+- ClimRetrieve report-level
+- ClimateFinanceBench
+
+16 questions · 4 question types · shared reference set
+:::
+
+::: {#dataset}
+### Your dataset
+[Microsoft retrieval · v2____________v]
+- Microsoft retrieval · v2
+- chunks_data.csv
+- Northwind retrieval · v1
+
+Saved from Upload & map · ranking format validated
+:::
+
+::: callout {for:benchmark side:left}
+same questions
+for every run
+:::
+
+::: callout {for:dataset side:right}
+your configured
+dataset
+:::
+
+::: card {#coverage}
+### Question matching
+
+**12 / 16 questions will be evaluated**
+
+███████████████░░░ 75%
+
+12 questions have matching IDs and compatible question types. 4 questions are not present in your dataset and will be excluded.
+
+| Match status | Questions | Action |
+|---|---:|---|
+| Ready to evaluate | 12 | Included |
+| Missing from dataset | 3 | Excluded |
+| Type mismatch | 1 | Excluded |
+
+Higher question coverage generally gives a more reliable and accurate benchmark result.
+:::
+
+::: callout {for:coverage side:left}
+coverage affects
+confidence
+:::
+
+::: card {#ranking}
+### Ranking configuration
+
+Ranking output: (x) Ordered chunks per question  ( ) Relevance scores only
+
+K values: [1, 3, 5, 10________________v]
+
+Evaluation name: [Microsoft v2 · ClimRetrieve v1________________]
+
+[Review matched questions]  [Start evaluation]*
+
+
+::: callout {for:ranking side:right}
+MAP · MRR · Precision@K · Recall@K
+:::

docs/wireframes/pages/benchmark-results-compare.md

@@ -0,0 +1,52 @@
+# Benchmark · Results
+Review metrics and compare saved evaluations.
+
+::: card {#tabs}
+[Upload & map] [Evaluation] [Results]* [Annotation]
+:::
+
+::: card {#summary}
+### Microsoft retrieval · v2
+ClimRetrieve v1 · Ranking · Completed 02 Sep 2026, 14:32
+
+**12 / 16 questions evaluated** · 75% coverage · 4 excluded
+
+Higher values indicate that relevant chunks were ranked earlier and the result is more accurate against the reference set.
+:::
+
+### Result
+| MAP | MRR | Precision@5 | Recall@10 |
+|---|---|---|---|
+| 0.742 | 0.833 | 0.780 | 0.910 |
+
+
+
+::: callout {for:map side:left}
+primary ranking score
+:::
+
+::: card {#compare}
+### Compare evaluations
+
+Select saved runs to compare side by side.
+
+| Evaluation | Dataset | Questions | MAP | MRR | Precision@5 |
+|---|---|---:|---:|---:|---:|
+| [x] Microsoft v2 | Microsoft retrieval · v2 | 12/16 | **0.742** | **0.833** | **0.780** |
+| [x] Northwind v1 | Northwind retrieval · v1 | 16/16 | 0.681 | 0.750 | 0.702 |
+| [ ] Chunks baseline | chunks_data.csv | 10/16 | 0.554 | 0.600 | 0.571 |
+
+### Metric comparison
+
+| Metric | Microsoft v2 | Northwind v1 | Difference |
+|---|---:|---:|---:|
+| MAP | 0.742 | 0.681 | +0.061 |
+| MRR | 0.833 | 0.750 | +0.083 |
+| Precision@5 | 0.780 | 0.702 | +0.078 |
+
+[Open question-level comparison]  [Save comparison]  [Export CSV]
+
+::: callout {for:compare side:right}
+spot meaningful
+differences
+:::

docs/wireframes/pages/benchmark-upload-align-mapping.md

@@ -0,0 +1,84 @@
+# Benchmark · Upload and map
+Prepare a dataset for evaluation.
+
+::: card {#tabs}
+[Upload & map]* [Evaluation] [Results] [Annotation]
+:::
+
+::: card {#steps}
+### 1. Upload · 2. Align · 3. Review mapping
+
+Upload your system output, align it with the benchmark format, then confirm the detected fields before evaluation.
+:::
+
+::: card {#upload}
+### Upload dataset
+
+[Drop CSV, Excel, YAML or JSON here____________________] [Browse files]
+
+Selected file: **chunks_Microsoft_2024.csv**  ·  1,240 rows  ·  Uploaded just now
+
+Supported ranking fields: query/item ID, report ID, chunk ID, position/rank, optional score.
+:::
+
+::: card {#benchmark}
+### Benchmark format
+
+Reference set: [ClimRetrieve v1________________v]
+
+- 16 benchmark questions
+- 4 expected question types
+- Ground-truth labels managed by the benchmark owner
+
+[Download sample format]
+:::
+
+::: callout {for:upload side:left}
+your dataset
+:::
+
+::: callout {for:benchmark side:right}
+reference structure
+:::
+
+::: card {#align}
+### Align columns
+
+| Your column | Benchmark field | Status |
+|---|---|---|
+| [query_id________v] | Query / question ID | ✓ matched |
+| [report_id_______v] | Report ID | ✓ matched |
+| [chunk_id________v] | Retrieved chunk ID | ✓ matched |
+| [position________v] | Rank / position | ✓ matched |
+| [score___________v] | Relevance score | Optional |
+
+[Auto-detect fields]  [Validate alignment]*
+:::
+
+::: callout {for:align side:left}
+map once,
+reuse later
+:::
+
+::: card {#mapping}
+### Mapping preview
+
+16 / 16 benchmark questions found · 1,240 / 1,240 rows valid · 0 errors
+
+| Question ID | Report | Top retrieved chunks | Question type |
+|---|---|---|---|
+| TCFD-01 | Microsoft 2024 | chunk_014, chunk_088, chunk_102 | Governance |
+| TCFD-02 | Microsoft 2024 | chunk_031, chunk_044, chunk_090 | Strategy |
+| TCFD-03 | Microsoft 2024 | chunk_052, chunk_067, chunk_071 | Risk |
+
+### Dataset name
+[Microsoft retrieval · v2________________________]
+
+[Save dataset]*  [Continue to evaluation]*
+:::
+
+::: callout {for:mapping side:right}
+the user sees
+the mapped result
+:::
+