sieve-scope 1.3.0__tar.gz

sieve_scope-1.3.0/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2026 Kai IWASAKI
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

sieve_scope-1.3.0/PKG-INFO

@@ -0,0 +1,168 @@
+Metadata-Version: 2.4
+Name: sieve-scope
+Version: 1.3.0
+Summary: Deterministic and Explainable Code Plagiarism Detection Engine with 7-bit Observation Space
+Author: Kai IWASAKI
+License: MIT
+Project-URL: Homepage, https://github.com/neguseatama/sieve-scope
+Project-URL: Repository, https://github.com/neguseatama/sieve-scope.git
+Project-URL: Bug Tracker, https://github.com/neguseatama/sieve-scope/issues
+Classifier: Development Status :: 5 - Production/Stable
+Classifier: Intended Audience :: Developers
+Classifier: Intended Audience :: Education
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Topic :: Software Development :: Libraries :: Python Modules
+Classifier: Topic :: Text Processing :: Linguistic
+Requires-Python: >=3.9
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Dynamic: license-file
+
+# Sieve Scope v1.3
+
+**English** | [日本語](README.ja.md)
+
+> **"See through the formatting, and look into the pure logic of the algorithm."**
+> A fully local, zero-dependency, deterministic (100% reproducible) code plagiarism and structural similarity detection engine.
+> Extends [Sieve-Core](https://github.com/neguseatama/sieve-core)'s deterministic similarity engine and [Sieve-Referee](https://github.com/neguseatama/sieve-referee)'s multi-hypothesis LUT judgment philosophy to the **source code domain**.
+
+[![CI](https://github.com/neguseatama/sieve-scope/actions/workflows/test.yml/badge.svg)](https://github.com/neguseatama/sieve-scope/actions/workflows/test.yml)
+[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
+[![Python Version](https://img.shields.io/badge/python-3.9%20%7C%203.10%20%7C%203.11%20%7C%203.12-blue)](https://www.python.org/)
+
+---
+
+## 💡 Concept & Philosophy
+
+The starting point of this project is **Sieve-Core**, a core engine that applies the "sieve of set theory" design philosophy of **Sieve-AI**—inspired by the Sieve of Eratosthenes—to the more general domain of text and data processing.
+
+Next, **Sieve Referee**, which adds a "sieve of combinatorics" to Sieve-Core, is a zero-dependency Python library that extracts reliable information from noise based on corroboration from multiple independent sources.
+
+Then, **Sieve Scope** further adds a two-axis evaluation and redesigns the approach, making it an explainable code plagiarism detection engine that observes the **surface format** (variable names, comments, whitespace) and the **essential logic** (algorithm structure) separately.
+
+Traditional string comparison and simple similarity measures struggle to distinguish between:
+- Plagiarism by merely renaming variables (**variable laundering**)
+- Coincidental matches due to shared templates (**boilerplate**)
+
+`Sieve Scope` observes two axes independently:
+- **AST (Abstract Syntax Tree)** — extracting the "logic skeleton" with identifiers removed
+- **tokenize** — extracting "identifier vocabulary and order"
+
+By inheriting the hypothesis mask (H1–H7) and LUT from Sieve-Referee, it fully explains why a judgment was made.
+
+> The name "Sieve Scope" comes from the design philosophy of seeing through the surface of code (format) and comparing only the pure logic, like a microscope.
+
+---
+
+## 🔥 Key Features
+
+- **7-bit Observation Space (H1–H7)**  
+  Independently evaluates AST skeleton, identifier vocabulary, positional/order (g_POS), constants (g_CONST), and vocabulary context (g_FREQ).
+- **v0_mask compatibility**  
+  The legacy 4-bit v0_mask is preserved and regression-tested.
+- **Strict Cluster Safety Invariant**  
+  H4 is promoted to 1 only when the cluster size is at least 3 **and** there is direct similarity evidence (H2∨H3). Indirect "telephone game" chains are never mixed into direct judgments.
+- **Short-Circuit Optimization**  
+  Pairs with no structural or vocabulary similarity (H2=0 ∧ H3=0) are immediately returned as `1000-000`, skipping expensive hash computations.
+- **Zero Dependencies & Deterministic**  
+  Implemented using only the Python standard library. No external packages, no API costs, no probabilistic elements.
+
+---
+
+## 📐 7-bit Observation Space
+
+The evaluation function `f_v1.3(C1, C2)` projects a code pair into seven boolean hypotheses `(H1, H2, H3, H4, H5, H6, H7)`.
+
+| Hypothesis | Name | What it measures | Criterion / Threshold |
+| :--- | :--- | :--- | :--- |
+| **H1** | Parseability | Can both be parsed as Python syntax? | Success/failure of AST construction |
+| **H2** | AST Skeleton | Do the AST node type sequences match exactly? | Exact match of skeleton strings |
+| **H3** | Identifier Similarity | Jaccard + sequence similarity of identifiers | Score `> 0.50` |
+| **H4** | Cluster Safety | Direct similarity + membership in a valid cluster (size ≥3) | Invariant condition satisfied |
+| **H5** | g_POS | SHA-256 hash of recursive AST field representation | Exact hash match |
+| **H6** | g_CONST | Constants / literals set match | Sorted constant list exact match |
+| **H7** | g_FREQ | Weighted identifier bi-gram Dice coefficient | Score `>= 0.60` |
+
+Mask notation is `v0_mask (4-bit) - extension (3-bit)`.
+Example: `1100-011` → H1=1, H2=1, H3=0, H4=0 / H5=0, H6=1, H7=1
+
+---
+
+## 📊 Representative LUT Patterns
+
+| v0_mask | Extended Example | Judgment Label | Description |
+|:---:|:---:|:---|:---|
+| `1110` | `1110-111` | `EXACT_CLONE` | Observation-space exact match |
+| `1100` | `1100-110` | `VARIABLE_LAUNDERING` | Logic matches but surface differs |
+| `1010` | `1010-011` | `COINCIDENTAL_FRAMEWORK_MATCH` | Logic differs but surface matches |
+| `1000` | `1000-000` | `INDEPENDENT_LOGIC` | No direct similarity (short-circuit) |
+| `1110` | `1110-101` | `CONSTANT_MODIFIED_CLONE` | Only constants differ |
+| `1110` | `1110-011` | `PERMUTATED_CLONE` | Non-commutative order reversed |
+
+---
+
+## 💻 Quick Start
+
+```python
+from sieve_scope import SieveScopeEngineV1_3, SieveClusterAnalyzerV1_3
+
+engine = SieveScopeEngineV1_3(jaccard_threshold=0.50, freq_dice_threshold=0.60)
+
+code_a = "def calc_sum(a, b):\n    return a + b"
+code_b = "def calc_sum(x, y):\n    return x + y"
+
+result = engine.evaluate_pair(code_a, code_b)
+
+print(result["v0_mask"])   # e.g., 1100
+print(result["mask"])      # e.g., 1100-110
+
+---
+
+### Configuration / Thresholds
+
+- `jaccard_threshold` (default: `0.50`): Threshold for H3 Multiset Jaccard + sequence similarity.
+- `freq_dice_threshold` (default: `0.60`): Threshold for H7 Weighted identifier bi-gram Dice coefficient.
+
+> **Note on Calibration & Defaults (v1.3)**:
+> Exhaustive grid search experiments on synthetic benchmark datasets demonstrate optimal class separation ($F1 = 1.0000$) across a wide threshold range of `0.35` to `0.75`. However, the default threshold parameters are strictly maintained at **`0.50` / `0.60`** in order to preserve backwards compatibility with v0, maintain regression test stability, and prevent potential false positives caused by shared domain vocabulary in production codebases.
+
+---
+
+## 🔬 Testing & Verification
+Cross-Python Validation Summary
+24 regression cases (test_v1_3_full_suite.py): PASSED
+
+5 compatibility tests (test_v1_3_regression.py): PASSED
+
+6 edge-case & parallel determinism tests (test_v1_3_edge_cases.py): PASSED
+
+81 synthetic threshold configurations (threshold_tuning.py): PASSED
+
+All test suites and synthetic experiments passed completely without errors across Python 3.9, 3.10, 3.11, and 3.12.
+
+Threshold Calibration & Synthetic Validation
+The threshold parameters (H3 Multiset Jaccard: 0.50, H7 Weighted Bi-gram Dice: 0.60) were designed and calibrated using a synthetic validation pair set (Positive 6 pairs / Negative 3 pairs).
+The engine's 1110-111 indicates an exact match in the current 7-dimensional observation space (Observation Clones), and does not guarantee complete semantic equivalence (Semantic Clones).
+
+---
+
+## 📚 Documentation
+
+- 🏛️ Architecture Specification
+
+- 🔌 API & Integration Guide
+
+- 🚀 Deployment Guide
+
+- 🔐 CI/CD & Security Guide
+
+## 📄 License
+MIT License. See LICENSE for details.
+
+## 👤 Author
+Kai IWASAKI

sieve_scope-1.3.0/README.md

@@ -0,0 +1,143 @@
+# Sieve Scope v1.3
+
+**English** | [日本語](README.ja.md)
+
+> **"See through the formatting, and look into the pure logic of the algorithm."**
+> A fully local, zero-dependency, deterministic (100% reproducible) code plagiarism and structural similarity detection engine.
+> Extends [Sieve-Core](https://github.com/neguseatama/sieve-core)'s deterministic similarity engine and [Sieve-Referee](https://github.com/neguseatama/sieve-referee)'s multi-hypothesis LUT judgment philosophy to the **source code domain**.
+
+[![CI](https://github.com/neguseatama/sieve-scope/actions/workflows/test.yml/badge.svg)](https://github.com/neguseatama/sieve-scope/actions/workflows/test.yml)
+[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
+[![Python Version](https://img.shields.io/badge/python-3.9%20%7C%203.10%20%7C%203.11%20%7C%203.12-blue)](https://www.python.org/)
+
+---
+
+## 💡 Concept & Philosophy
+
+The starting point of this project is **Sieve-Core**, a core engine that applies the "sieve of set theory" design philosophy of **Sieve-AI**—inspired by the Sieve of Eratosthenes—to the more general domain of text and data processing.
+
+Next, **Sieve Referee**, which adds a "sieve of combinatorics" to Sieve-Core, is a zero-dependency Python library that extracts reliable information from noise based on corroboration from multiple independent sources.
+
+Then, **Sieve Scope** further adds a two-axis evaluation and redesigns the approach, making it an explainable code plagiarism detection engine that observes the **surface format** (variable names, comments, whitespace) and the **essential logic** (algorithm structure) separately.
+
+Traditional string comparison and simple similarity measures struggle to distinguish between:
+- Plagiarism by merely renaming variables (**variable laundering**)
+- Coincidental matches due to shared templates (**boilerplate**)
+
+`Sieve Scope` observes two axes independently:
+- **AST (Abstract Syntax Tree)** — extracting the "logic skeleton" with identifiers removed
+- **tokenize** — extracting "identifier vocabulary and order"
+
+By inheriting the hypothesis mask (H1–H7) and LUT from Sieve-Referee, it fully explains why a judgment was made.
+
+> The name "Sieve Scope" comes from the design philosophy of seeing through the surface of code (format) and comparing only the pure logic, like a microscope.
+
+---
+
+## 🔥 Key Features
+
+- **7-bit Observation Space (H1–H7)**  
+  Independently evaluates AST skeleton, identifier vocabulary, positional/order (g_POS), constants (g_CONST), and vocabulary context (g_FREQ).
+- **v0_mask compatibility**  
+  The legacy 4-bit v0_mask is preserved and regression-tested.
+- **Strict Cluster Safety Invariant**  
+  H4 is promoted to 1 only when the cluster size is at least 3 **and** there is direct similarity evidence (H2∨H3). Indirect "telephone game" chains are never mixed into direct judgments.
+- **Short-Circuit Optimization**  
+  Pairs with no structural or vocabulary similarity (H2=0 ∧ H3=0) are immediately returned as `1000-000`, skipping expensive hash computations.
+- **Zero Dependencies & Deterministic**  
+  Implemented using only the Python standard library. No external packages, no API costs, no probabilistic elements.
+
+---
+
+## 📐 7-bit Observation Space
+
+The evaluation function `f_v1.3(C1, C2)` projects a code pair into seven boolean hypotheses `(H1, H2, H3, H4, H5, H6, H7)`.
+
+| Hypothesis | Name | What it measures | Criterion / Threshold |
+| :--- | :--- | :--- | :--- |
+| **H1** | Parseability | Can both be parsed as Python syntax? | Success/failure of AST construction |
+| **H2** | AST Skeleton | Do the AST node type sequences match exactly? | Exact match of skeleton strings |
+| **H3** | Identifier Similarity | Jaccard + sequence similarity of identifiers | Score `> 0.50` |
+| **H4** | Cluster Safety | Direct similarity + membership in a valid cluster (size ≥3) | Invariant condition satisfied |
+| **H5** | g_POS | SHA-256 hash of recursive AST field representation | Exact hash match |
+| **H6** | g_CONST | Constants / literals set match | Sorted constant list exact match |
+| **H7** | g_FREQ | Weighted identifier bi-gram Dice coefficient | Score `>= 0.60` |
+
+Mask notation is `v0_mask (4-bit) - extension (3-bit)`.
+Example: `1100-011` → H1=1, H2=1, H3=0, H4=0 / H5=0, H6=1, H7=1
+
+---
+
+## 📊 Representative LUT Patterns
+
+| v0_mask | Extended Example | Judgment Label | Description |
+|:---:|:---:|:---|:---|
+| `1110` | `1110-111` | `EXACT_CLONE` | Observation-space exact match |
+| `1100` | `1100-110` | `VARIABLE_LAUNDERING` | Logic matches but surface differs |
+| `1010` | `1010-011` | `COINCIDENTAL_FRAMEWORK_MATCH` | Logic differs but surface matches |
+| `1000` | `1000-000` | `INDEPENDENT_LOGIC` | No direct similarity (short-circuit) |
+| `1110` | `1110-101` | `CONSTANT_MODIFIED_CLONE` | Only constants differ |
+| `1110` | `1110-011` | `PERMUTATED_CLONE` | Non-commutative order reversed |
+
+---
+
+## 💻 Quick Start
+
+```python
+from sieve_scope import SieveScopeEngineV1_3, SieveClusterAnalyzerV1_3
+
+engine = SieveScopeEngineV1_3(jaccard_threshold=0.50, freq_dice_threshold=0.60)
+
+code_a = "def calc_sum(a, b):\n    return a + b"
+code_b = "def calc_sum(x, y):\n    return x + y"
+
+result = engine.evaluate_pair(code_a, code_b)
+
+print(result["v0_mask"])   # e.g., 1100
+print(result["mask"])      # e.g., 1100-110
+
+---
+
+### Configuration / Thresholds
+
+- `jaccard_threshold` (default: `0.50`): Threshold for H3 Multiset Jaccard + sequence similarity.
+- `freq_dice_threshold` (default: `0.60`): Threshold for H7 Weighted identifier bi-gram Dice coefficient.
+
+> **Note on Calibration & Defaults (v1.3)**:
+> Exhaustive grid search experiments on synthetic benchmark datasets demonstrate optimal class separation ($F1 = 1.0000$) across a wide threshold range of `0.35` to `0.75`. However, the default threshold parameters are strictly maintained at **`0.50` / `0.60`** in order to preserve backwards compatibility with v0, maintain regression test stability, and prevent potential false positives caused by shared domain vocabulary in production codebases.
+
+---
+
+## 🔬 Testing & Verification
+Cross-Python Validation Summary
+24 regression cases (test_v1_3_full_suite.py): PASSED
+
+5 compatibility tests (test_v1_3_regression.py): PASSED
+
+6 edge-case & parallel determinism tests (test_v1_3_edge_cases.py): PASSED
+
+81 synthetic threshold configurations (threshold_tuning.py): PASSED
+
+All test suites and synthetic experiments passed completely without errors across Python 3.9, 3.10, 3.11, and 3.12.
+
+Threshold Calibration & Synthetic Validation
+The threshold parameters (H3 Multiset Jaccard: 0.50, H7 Weighted Bi-gram Dice: 0.60) were designed and calibrated using a synthetic validation pair set (Positive 6 pairs / Negative 3 pairs).
+The engine's 1110-111 indicates an exact match in the current 7-dimensional observation space (Observation Clones), and does not guarantee complete semantic equivalence (Semantic Clones).
+
+---
+
+## 📚 Documentation
+
+- 🏛️ Architecture Specification
+
+- 🔌 API & Integration Guide
+
+- 🚀 Deployment Guide
+
+- 🔐 CI/CD & Security Guide
+
+## 📄 License
+MIT License. See LICENSE for details.
+
+## 👤 Author
+Kai IWASAKI

sieve_scope-1.3.0/pyproject.toml

@@ -0,0 +1,36 @@
+[build-system]
+requires = ["setuptools>=61.0"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "sieve-scope"
+version = "1.3.0"
+description = "Deterministic and Explainable Code Plagiarism Detection Engine with 7-bit Observation Space"
+readme = "README.md"
+authors = [
+    { name = "Kai IWASAKI" }
+]
+license = { text = "MIT" }
+classifiers = [
+    "Development Status :: 5 - Production/Stable",
+    "Intended Audience :: Developers",
+    "Intended Audience :: Education",
+    "License :: OSI Approved :: MIT License",
+    "Programming Language :: Python :: 3",
+    "Programming Language :: Python :: 3.9",
+    "Programming Language :: Python :: 3.10",
+    "Programming Language :: Python :: 3.11",
+    "Programming Language :: Python :: 3.12",
+    "Topic :: Software Development :: Libraries :: Python Modules",
+    "Topic :: Text Processing :: Linguistic"
+]
+requires-python = ">=3.9"
+dependencies = []
+
+[project.urls]
+Homepage = "https://github.com/neguseatama/sieve-scope"
+Repository = "https://github.com/neguseatama/sieve-scope.git"
+"Bug Tracker" = "https://github.com/neguseatama/sieve-scope/issues"
+
+[tool.setuptools]
+py-modules = ["sieve_scope"]

sieve_scope-1.3.0/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+

sieve_scope-1.3.0/sieve_scope.egg-info/PKG-INFO

@@ -0,0 +1,168 @@
+Metadata-Version: 2.4
+Name: sieve-scope
+Version: 1.3.0
+Summary: Deterministic and Explainable Code Plagiarism Detection Engine with 7-bit Observation Space
+Author: Kai IWASAKI
+License: MIT
+Project-URL: Homepage, https://github.com/neguseatama/sieve-scope
+Project-URL: Repository, https://github.com/neguseatama/sieve-scope.git
+Project-URL: Bug Tracker, https://github.com/neguseatama/sieve-scope/issues
+Classifier: Development Status :: 5 - Production/Stable
+Classifier: Intended Audience :: Developers
+Classifier: Intended Audience :: Education
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Topic :: Software Development :: Libraries :: Python Modules
+Classifier: Topic :: Text Processing :: Linguistic
+Requires-Python: >=3.9
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Dynamic: license-file
+
+# Sieve Scope v1.3
+
+**English** | [日本語](README.ja.md)
+
+> **"See through the formatting, and look into the pure logic of the algorithm."**
+> A fully local, zero-dependency, deterministic (100% reproducible) code plagiarism and structural similarity detection engine.
+> Extends [Sieve-Core](https://github.com/neguseatama/sieve-core)'s deterministic similarity engine and [Sieve-Referee](https://github.com/neguseatama/sieve-referee)'s multi-hypothesis LUT judgment philosophy to the **source code domain**.
+
+[![CI](https://github.com/neguseatama/sieve-scope/actions/workflows/test.yml/badge.svg)](https://github.com/neguseatama/sieve-scope/actions/workflows/test.yml)
+[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
+[![Python Version](https://img.shields.io/badge/python-3.9%20%7C%203.10%20%7C%203.11%20%7C%203.12-blue)](https://www.python.org/)
+
+---
+
+## 💡 Concept & Philosophy
+
+The starting point of this project is **Sieve-Core**, a core engine that applies the "sieve of set theory" design philosophy of **Sieve-AI**—inspired by the Sieve of Eratosthenes—to the more general domain of text and data processing.
+
+Next, **Sieve Referee**, which adds a "sieve of combinatorics" to Sieve-Core, is a zero-dependency Python library that extracts reliable information from noise based on corroboration from multiple independent sources.
+
+Then, **Sieve Scope** further adds a two-axis evaluation and redesigns the approach, making it an explainable code plagiarism detection engine that observes the **surface format** (variable names, comments, whitespace) and the **essential logic** (algorithm structure) separately.
+
+Traditional string comparison and simple similarity measures struggle to distinguish between:
+- Plagiarism by merely renaming variables (**variable laundering**)
+- Coincidental matches due to shared templates (**boilerplate**)
+
+`Sieve Scope` observes two axes independently:
+- **AST (Abstract Syntax Tree)** — extracting the "logic skeleton" with identifiers removed
+- **tokenize** — extracting "identifier vocabulary and order"
+
+By inheriting the hypothesis mask (H1–H7) and LUT from Sieve-Referee, it fully explains why a judgment was made.
+
+> The name "Sieve Scope" comes from the design philosophy of seeing through the surface of code (format) and comparing only the pure logic, like a microscope.
+
+---
+
+## 🔥 Key Features
+
+- **7-bit Observation Space (H1–H7)**  
+  Independently evaluates AST skeleton, identifier vocabulary, positional/order (g_POS), constants (g_CONST), and vocabulary context (g_FREQ).
+- **v0_mask compatibility**  
+  The legacy 4-bit v0_mask is preserved and regression-tested.
+- **Strict Cluster Safety Invariant**  
+  H4 is promoted to 1 only when the cluster size is at least 3 **and** there is direct similarity evidence (H2∨H3). Indirect "telephone game" chains are never mixed into direct judgments.
+- **Short-Circuit Optimization**  
+  Pairs with no structural or vocabulary similarity (H2=0 ∧ H3=0) are immediately returned as `1000-000`, skipping expensive hash computations.
+- **Zero Dependencies & Deterministic**  
+  Implemented using only the Python standard library. No external packages, no API costs, no probabilistic elements.
+
+---
+
+## 📐 7-bit Observation Space
+
+The evaluation function `f_v1.3(C1, C2)` projects a code pair into seven boolean hypotheses `(H1, H2, H3, H4, H5, H6, H7)`.
+
+| Hypothesis | Name | What it measures | Criterion / Threshold |
+| :--- | :--- | :--- | :--- |
+| **H1** | Parseability | Can both be parsed as Python syntax? | Success/failure of AST construction |
+| **H2** | AST Skeleton | Do the AST node type sequences match exactly? | Exact match of skeleton strings |
+| **H3** | Identifier Similarity | Jaccard + sequence similarity of identifiers | Score `> 0.50` |
+| **H4** | Cluster Safety | Direct similarity + membership in a valid cluster (size ≥3) | Invariant condition satisfied |
+| **H5** | g_POS | SHA-256 hash of recursive AST field representation | Exact hash match |
+| **H6** | g_CONST | Constants / literals set match | Sorted constant list exact match |
+| **H7** | g_FREQ | Weighted identifier bi-gram Dice coefficient | Score `>= 0.60` |
+
+Mask notation is `v0_mask (4-bit) - extension (3-bit)`.
+Example: `1100-011` → H1=1, H2=1, H3=0, H4=0 / H5=0, H6=1, H7=1
+
+---
+
+## 📊 Representative LUT Patterns
+
+| v0_mask | Extended Example | Judgment Label | Description |
+|:---:|:---:|:---|:---|
+| `1110` | `1110-111` | `EXACT_CLONE` | Observation-space exact match |
+| `1100` | `1100-110` | `VARIABLE_LAUNDERING` | Logic matches but surface differs |
+| `1010` | `1010-011` | `COINCIDENTAL_FRAMEWORK_MATCH` | Logic differs but surface matches |
+| `1000` | `1000-000` | `INDEPENDENT_LOGIC` | No direct similarity (short-circuit) |
+| `1110` | `1110-101` | `CONSTANT_MODIFIED_CLONE` | Only constants differ |
+| `1110` | `1110-011` | `PERMUTATED_CLONE` | Non-commutative order reversed |
+
+---
+
+## 💻 Quick Start
+
+```python
+from sieve_scope import SieveScopeEngineV1_3, SieveClusterAnalyzerV1_3
+
+engine = SieveScopeEngineV1_3(jaccard_threshold=0.50, freq_dice_threshold=0.60)
+
+code_a = "def calc_sum(a, b):\n    return a + b"
+code_b = "def calc_sum(x, y):\n    return x + y"
+
+result = engine.evaluate_pair(code_a, code_b)
+
+print(result["v0_mask"])   # e.g., 1100
+print(result["mask"])      # e.g., 1100-110
+
+---
+
+### Configuration / Thresholds
+
+- `jaccard_threshold` (default: `0.50`): Threshold for H3 Multiset Jaccard + sequence similarity.
+- `freq_dice_threshold` (default: `0.60`): Threshold for H7 Weighted identifier bi-gram Dice coefficient.
+
+> **Note on Calibration & Defaults (v1.3)**:
+> Exhaustive grid search experiments on synthetic benchmark datasets demonstrate optimal class separation ($F1 = 1.0000$) across a wide threshold range of `0.35` to `0.75`. However, the default threshold parameters are strictly maintained at **`0.50` / `0.60`** in order to preserve backwards compatibility with v0, maintain regression test stability, and prevent potential false positives caused by shared domain vocabulary in production codebases.
+
+---
+
+## 🔬 Testing & Verification
+Cross-Python Validation Summary
+24 regression cases (test_v1_3_full_suite.py): PASSED
+
+5 compatibility tests (test_v1_3_regression.py): PASSED
+
+6 edge-case & parallel determinism tests (test_v1_3_edge_cases.py): PASSED
+
+81 synthetic threshold configurations (threshold_tuning.py): PASSED
+
+All test suites and synthetic experiments passed completely without errors across Python 3.9, 3.10, 3.11, and 3.12.
+
+Threshold Calibration & Synthetic Validation
+The threshold parameters (H3 Multiset Jaccard: 0.50, H7 Weighted Bi-gram Dice: 0.60) were designed and calibrated using a synthetic validation pair set (Positive 6 pairs / Negative 3 pairs).
+The engine's 1110-111 indicates an exact match in the current 7-dimensional observation space (Observation Clones), and does not guarantee complete semantic equivalence (Semantic Clones).
+
+---
+
+## 📚 Documentation
+
+- 🏛️ Architecture Specification
+
+- 🔌 API & Integration Guide
+
+- 🚀 Deployment Guide
+
+- 🔐 CI/CD & Security Guide
+
+## 📄 License
+MIT License. See LICENSE for details.
+
+## 👤 Author
+Kai IWASAKI

sieve_scope-1.3.0/sieve_scope.egg-info/SOURCES.txt

@@ -0,0 +1,11 @@
+LICENSE
+README.md
+pyproject.toml
+sieve_scope.py
+sieve_scope.egg-info/PKG-INFO
+sieve_scope.egg-info/SOURCES.txt
+sieve_scope.egg-info/dependency_links.txt
+sieve_scope.egg-info/top_level.txt
+tests/test_v1_3_edge_cases.py
+tests/test_v1_3_full_suite.py
+tests/test_v1_3_regression.py

sieve_scope-1.3.0/sieve_scope.egg-info/dependency_links.txt

@@ -0,0 +1 @@
+

sieve_scope-1.3.0/sieve_scope.egg-info/top_level.txt

@@ -0,0 +1 @@
+sieve_scope