receiptscc 1.0.0 → 1.0.1

package/README.md

@@ -11,7 +11,7 @@
 </p>
 
 <p align="center">
-<img src="assets/terminal.png" alt="receipts" width="550">
+<img src="https://raw.githubusercontent.com/JamesWeatherhead/reciepts/main/assets/terminal.png" alt="receipts" width="550">
 </p>
 
 <p align="center">
@@ -90,7 +90,7 @@ npm install -g @anthropic-ai/claude-code
 ```
 
 <p align="center">
-<img src="assets/screenshots/step0.png" alt="Install Claude Code" width="550">
+<img src="https://raw.githubusercontent.com/JamesWeatherhead/reciepts/main/assets/screenshots/step0.png" alt="Install Claude Code" width="550">
 </p>
 
 Wait for it to finish.
@@ -106,7 +106,7 @@ npx receiptscc
 ```
 
 <p align="center">
-<img src="assets/screenshots/step1.png" alt="Install receiptscc" width="420">
+<img src="https://raw.githubusercontent.com/JamesWeatherhead/reciepts/main/assets/screenshots/step1.png" alt="Install receiptscc" width="420">
 </p>
 
 You will see a receipt banner. That means it worked. You only do this once.
@@ -118,7 +118,7 @@ You will see a receipt banner. That means it worked. You only do this once.
 Create a folder with your paper and sources:
 
 <p align="center">
-<img src="assets/screenshots/step2.png" alt="Folder structure" width="380">
+<img src="https://raw.githubusercontent.com/JamesWeatherhead/reciepts/main/assets/screenshots/step2.png" alt="Folder structure" width="380">
 </p>
 
 ```
@@ -144,7 +144,7 @@ claude
 ```
 
 <p align="center">
-<img src="assets/screenshots/step3a.png" alt="Start Claude Code" width="460">
+<img src="https://raw.githubusercontent.com/JamesWeatherhead/reciepts/main/assets/screenshots/step3a.png" alt="Start Claude Code" width="460">
 </p>
 
 **Windows users:** Replace `~/Desktop/thesis` with your actual path, like `C:\Users\YourName\Desktop\thesis`
@@ -162,7 +162,7 @@ Now you are inside Claude Code. Type this command:
 ```
 
 <p align="center">
-<img src="assets/screenshots/step3.png" alt="Run /receipts" width="500">
+<img src="https://raw.githubusercontent.com/JamesWeatherhead/reciepts/main/assets/screenshots/step3.png" alt="Run /receipts" width="500">
 </p>
 
 **Important:** The `/receipts` command only works inside Claude Code. If you type it in your regular terminal, it will not work.
@@ -173,31 +173,56 @@ receipts will read your paper, read your sources, and check every citation. When
 
 ## What You Get
 
-A report showing which citations check out and which don't:
-
-```
-# Citation Verification Report
-
-| Status  | Count |
-|---------|-------|
-| VALID   | 47    |
-| ADJUST  | 2     |
-| INVALID | 1     |
-
-## Issues Found
-
-### [23] Smith et al. (2020)
-
-**Your claim:** "achieved 99% accuracy on all benchmarks"
-**Source says:** "achieves 73% accuracy on the standard benchmark"
-**Fix:** Change "99%" to "73%", remove "all benchmarks"
-```
-
-| Status | What it means |
-|--------|---------------|
-| **VALID** | Your citation is accurate |
-| **ADJUST** | Small fix needed (wrong number, slightly off wording) |
-| **INVALID** | Source does not support your claim |
+A detailed verdict for each citation showing exactly what's wrong and how to fix it. [See example verdicts →](https://github.com/JamesWeatherhead/receipts/tree/main/demo/verdicts)
+
+> ### Verdict: Reference 1 — ADJUST
+>
+> **Citation:** Srivastava et al. (2014). *Dropout: A Simple Way to Prevent Neural Networks from Overfitting.* JMLR.
+>
+> **Summary:** Reference 1 is cited four times in the manuscript. Two citations are accurate: the general description of dropout and the direct quote about co-adaptations. However, two citations contain errors that require correction.
+>
+> ---
+>
+> #### Instance 2 — Section "Dropout Regularization", paragraph 2
+>
+> **Manuscript claims:**
+> > *"According to Srivastava et al., the optimal dropout probability is **p=0.5 for all layers**, which they found to work well across a wide range of networks and tasks."*
+>
+> **Source states:**
+> > *"In the simplest case, each unit is retained with a fixed probability p independent of other units, where p can be chosen using a validation set or can simply be set at 0.5, which seems to be close to optimal for a wide range of networks and tasks."*
+>
+> **Source also states:**
+> > ***"All dropout nets use p=0.5 for hidden units and p=0.8 for input units."***
+>
+> **Assessment:** NOT SUPPORTED
+>
+> **Discrepancy:** The manuscript claims "p=0.5 for all layers" but the source explicitly states p=0.5 for HIDDEN units and p=0.8 for INPUT units.
+>
+> ---
+>
+> #### Instance 3 — Section "Dropout Regularization", paragraph 2
+>
+> **Manuscript claims:**
+> > *"Using this approach, they achieved an error rate of **0.89% on MNIST**, demonstrating state-of-the-art performance at the time."*
+>
+> **Source states:**
+> > *"Error rates can be further improved to **0.94%** by replacing ReLU units with maxout units."*
+>
+> **Assessment:** NOT SUPPORTED
+>
+> **Discrepancy:** The manuscript claims 0.89% error rate, but the source states 0.94%. The figure 0.89% does not appear in the source.
+>
+> ---
+>
+> #### Required Corrections
+> 1. Change `p=0.5 for all layers` → `p=0.5 for hidden units and p=0.8 for input units`
+> 2. Change `0.89%` → `0.94%`
+
+| Status | Meaning |
+|--------|---------|
+| **VALID** | Citation is accurate |
+| **ADJUST** | Small fix needed |
+| **INVALID** | Source doesn't support claim |
 
 ---
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "receiptscc",
-  "version": "1.0.0",
+  "version": "1.0.1",
   "description": "Verify your citations say what you claim. One command.",
   "keywords": [
     "citations",