jlawcite 2.0.0__tar.gz

jlawcite-2.0.0/LICENSE

@@ -0,0 +1,201 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or Derivative
+          Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright 2026 The JLaw-CiteGraph authors
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

jlawcite-2.0.0/PKG-INFO

@@ -0,0 +1,207 @@
+Metadata-Version: 2.4
+Name: jlawcite
+Version: 2.0.0
+Summary: JLaw-CiteGraph: deterministic citation graph and embedding-free search for Japanese statutes (e-Gov 法令)
+Author: yabooung
+License: Apache-2.0
+Project-URL: Homepage, https://github.com/yabooung/jp-law-citation-graph
+Keywords: Japanese law,legal NLP,citation graph,e-Gov,statute,legal information retrieval
+Requires-Python: >=3.11
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: pydantic>=2.5
+Requires-Dist: tqdm>=4.66
+Provides-Extra: dev
+Requires-Dist: pytest>=8.0; extra == "dev"
+Provides-Extra: mcp
+Requires-Dist: mcp>=1.0.0; extra == "mcp"
+Dynamic: license-file
+
+# JLaw-CiteGraph 🇯🇵⚖️
+
+**English** · [日本語](https://github.com/yabooung/jp-law-citation-graph/blob/main/README.ja.md) · [한국어](https://github.com/yabooung/jp-law-citation-graph/blob/main/README.ko.md)
+
+![code: Apache-2.0](https://img.shields.io/badge/code-Apache--2.0-blue) ![data: CC BY 4.0](https://img.shields.io/badge/data-CC--BY--4.0-green) ![deterministic](https://img.shields.io/badge/pipeline-deterministic%20·%20no%20LLM-brightgreen) ![version](https://img.shields.io/badge/release-v2.0.0-informative)
+
+**An open, deterministic citation graph and search index for Japanese statutory law.**
+
+Every Japanese law in force is parsed from official [e-Gov](https://laws.e-gov.go.jp/) XML down
+to article (条), paragraph (項) and item (号), and citations in the text are resolved to the provision
+they point at: 92.9% of same-law and 82.2% of cross-law citations, with the unresolved ones listed.
+The result ships as data files, a single-file explorer, a `jlawcite` command-line tool
+that looks up and searches provisions without embeddings, and an MCP server for LLMs.
+
+[![JLaw-CiteGraph interactive explorer](https://raw.githubusercontent.com/yabooung/jp-law-citation-graph/main/assets/explorer-screenshot.png)](https://github.com/yabooung/jp-law-citation-graph/blob/main/explorer.html)
+
+<sub>[`explorer.html`](https://github.com/yabooung/jp-law-citation-graph/blob/main/explorer.html): pick a law and see what it cites (green) and what cites it (yellow).</sub>
+
+## At a glance (v2.0, e-Gov snapshot 2026-09-27)
+
+| | |
+|---|---|
+| **Laws** | 8,998, each at the version in force on 2026-09-29, plus **1,649 upcoming amendments** (施行日 + amending law) |
+| **Graph** | 1.89M nodes (条・項・号・附則・別表) · 1.42M citation edges · 67,666 delegation edges (政令で定める) · 37,377 別表/様式 references |
+| **Law → law network** | 70,577 distinct pairs · 453,390 distinct article-level links between laws |
+| **Citation resolution** | same-law 92.9% · cross-law 82.2% · relative refs (前条/同項/…) 92.2% |
+| **Precision** | ≈98% on hand-checked samples of the rules covering 86% of edges (preliminary, see below) |
+| **Search** | `jlawcite get 民法第七百九条` · BM25 search · on 1,170 real tax questions the citation graph lifts Recall@10 from 0.24 to 0.46 |
+| **Method** | 100% deterministic (rules + dictionaries + document context), no LLM, reproducible from the public e-Gov bulk download |
+
+## What's new in v2
+
+| | v1.0 (2026-06) | **v2.0 (2026-09)** |
+|---|---|---|
+| Unit | law → law (article strings) | article / paragraph / item nodes, incl. 附則 and attachments |
+| Edges | cross-law citations | + same-law citations, 前条/同項/前号, delegation, 別表 references |
+| Distinct article-level cross-law links | 173,844 | **453,390** |
+| Law → law pairs | 55,651 | **70,577** |
+| Versions | latest file per law | version in force on a date + upcoming amendments |
+| Search | – | `jlawcite` CLI (lookup, BM25, graph walk) + retrieval benchmark |
+| Precision | 0 errors / 400 (LLM-proposed labels) | per-rule samples with confidence intervals; 5 error classes found and fixed |
+
+v1 wrote one line per citation *mention*, so its 1.21M lines hold 173,844 distinct links; v2 counts
+each (source, target) link once. Full list in [CHANGELOG.md](https://github.com/yabooung/jp-law-citation-graph/blob/main/CHANGELOG.md).
+
+## Who is this for?
+| You are… | You use it to… |
+|---|---|
+| a **legal-NLP researcher** | add citation neighbours to statute retrieval / RAG (the benchmark below shows the gain), or reuse the deterministic resolver on your own corpus |
+| a **legal-tech developer** | answer "what cites X?" (amending 個人情報保護法 touches **111** laws) and "what changes when?" (`pending_versions.csv`) |
+| a **network / comparative-law researcher** | study hubs (地方自治法 is cited by 1,250 laws), delegation chains and dependency clusters |
+| building an **LLM legal assistant** | ground citations deterministically via the MCP server: `会社法第737条` → the exact article text |
+
+## Quick start
+```bash
+git clone https://github.com/yabooung/jp-law-citation-graph && cd jp-law-citation-graph
+pip install -e .                                     # Python 3.11+
+
+jlawcite fetch                                       # e-Gov bulk XML (~320 MB) → data/raw/law_xml
+jlawcite build --input data/raw/law_xml \
+    --csv data/raw/law_xml/all_law_list.csv --output data/parsed      # ~5 min, deterministic
+jlawcite validate --data data/parsed                 # 11 integrity checks
+jlawcite index                                       # search index (~1.5 min, 2.6 GB)
+
+jlawcite get 民法第七百九条                           # also: 労働基準法20条1項, 激甚法第三条, node ids
+jlawcite search 解雇 予告                             # BM25; --nl for a question sentence
+jlawcite refs 労働基準法第二十条                       # what it cites / what cites it
+jlawcite pending --until 20261231                    # amendments coming into force
+```
+
+```text
+$ jlawcite get 民法第七百九条
+民法  [129AC0000000089, act, 明治二十九年法律第八十九号]  現行 2026-06-24 施行中, 次回改正 2027-06-23
+[129AC0000000089_a709] Article
+
+第七百九条
+故意又は過失によって他人の権利又は法律上保護される利益を侵害した者は、これによって生じた損害を賠償する責任を負う。
+
+改正予定:
+  2027-06-23  民法 ← 民法等の一部を改正する法律 令和八年法律第四十五号 (公布の日から起算して一年を超えない範囲内において政令で定める日)
+  …
+```
+
+Every command takes `--json`. The same functions are available in Python (`jlawcite.search.SearchDB`).
+
+## What's inside (`/data`)
+| File | Content |
+|---|---|
+| `laws.csv` | `law_id, name, type, url` (v1) + `enforcement_date, next_enforcement_date, pending_versions` |
+| `cites_law_to_law.csv` | aggregated `src_law → tgt_law` counts (v1 columns) |
+| `cites_edges.jsonl.gz` | every resolved citation of a named law: v1 fields (`src_article`, `tgt_article`, `via`, `confidence`) + `src_node`, `tgt_node`, `fallback_level` |
+| `cites_all_edges.jsonl.gz` | **every** edge of the graph: CITES (incl. same-law and 前条/同項), DELEGATES_TO, REFERS_TO_ATTACHMENT, AMENDS, each with `extracted_from` |
+| `pending_versions.csv` | upcoming amendments: 施行日, 施行日備考, amending law, e-Gov URL |
+| `release_stats.json` | the counts quoted here |
+
+The full node file (1.89M nodes, article and paragraph text included) is attached to the GitHub
+release, or you can rebuild it with the Quick start commands.
+
+```python
+import pandas as pd
+edges = pd.read_csv("data/cites_law_to_law.csv")
+hubs = edges.groupby("tgt_law")["src_law_id"].nunique().sort_values(ascending=False).head(10)
+```
+
+## Use it from an LLM: MCP server (`mcp/`)
+`resolve_citation`, `what_cites`, `what_law_cites`, `citation_path`, `get_law`, and in v2
+`get_provision` (citation → text), `search_statutes` and `pending_amendments`.
+See [`mcp/README.md`](https://github.com/yabooung/jp-law-citation-graph/blob/main/mcp/README.md).
+
+## Retrieval benchmark
+Each of 1,170 National Tax Agency Q&A cases (質疑応答事例) is a real tax question whose answer cites
+specific articles. The question is the query, and hits are counted at the article level
+(`jlawcite eval`).
+
+| method | R@1 | R@5 | R@10 | R@20 | R@50 | MRR@50 | s/query |
+|---|---:|---:|---:|---:|---:|---:|---:|
+| BM25 (character-trigram OR) | 0.086 | 0.192 | 0.244 | 0.326 | 0.437 | 0.140 | 0.11 |
+| BM25 + 1-hop citation graph | **0.256** | **0.403** | **0.459** | **0.500** | **0.550** | **0.325** | 0.11 |
+
+<sub>1,170 queries · e-Gov snapshot 2026-09-27 · `eval/v2/nta_retrieval_results.json`</sub>
+
+The one-hop expansion adds the articles that the top hits cite. A retrieved 施行令 paragraph pulls
+up the parent-act article it implements. Both rows use no embeddings; they are a baseline for dense
+or hybrid retrievers.
+
+## Quality, honestly
+- **Coverage.** No law is left without body text, the 11 integrity checks pass (no dangling edges),
+  and the same input produces the same output.
+- **Resolution rates** leave out citations whose target is not in a current-law corpus: pre-amendment
+  text (旧法), amending acts (改正法), and citations inside amending-law 附則 blocks. These are counted
+  separately in `jp_cites_stats.json`.
+- **Precision is preliminary.** 180 random edges (10–20 per resolution rule) were checked by hand
+  against their source text during development. Five error classes turned up and were fixed. The rules covering 86% of edges now
+  measure ≈98%. Samples are small (10/10 still has a 72% lower bound) and were not blind, so treat it
+  as indicative. Citations inside amending-law 附則 are about 40% right and are flagged with
+  confidence 0.4. Citations of pre-amendment text (「旧○○法第N条」) point at the current version and
+  carry `version: "pre_amendment"`. Details: [docs/METHODOLOGY.md](https://github.com/yabooung/jp-law-citation-graph/blob/main/docs/METHODOLOGY.md).
+- **Scope.** National statutes in force only: no case law, 通達, local ordinances, or text of repealed
+  and amending acts. イ/ロ/ハ subitems are folded into their item.
+
+## Reproduce
+```bash
+jlawcite fetch --zip all_xml.zip       # re-extract an archived snapshot for an exact rebuild
+jlawcite build … --as-of 20260929      # same snapshot + same as-of date → same graph
+jlawcite export --out data             # regenerate the files in /data
+python tools/build_explorer.py         # regenerate explorer.html
+python -m pytest                       # 177 tests
+```
+
+## Related work
+- **弁護士ドットコム (DDS 2026)** built a citation graph over e-Gov statutes (条・項・号) together with
+  books, guidelines and court decisions. It reports P 98.8 / R 92.1 for law-to-law citations; same-law
+  references are outside its evaluation, and the graph is not public.
+  [paper](https://dbsj.org/wp-content/uploads/2025/11/dds-vol4-no3.pdf)
+- **[DaisukeHori/japan-law](https://github.com/DaisukeHori/japan-law)** publishes about 112k article-level
+  cross-references for about 8,000 laws (CC0), without an accuracy evaluation.
+- Reference resolution in Japanese statutes goes back to Tran, Nguyen & Shimazu (ICAIL 2013). Using
+  citation structure for statute retrieval has been shown on the Japanese Civil Code (Mizuno & Kano,
+  COLIEE 2025; Vuong et al., *Applied Intelligence* 2025) and on Belgian law (Louis et al., EACL 2023).
+
+JLaw-CiteGraph adds same-law and relative references (前条・同条・同項・前号・同法), version selection with
+upcoming amendments, per-rule precision, and a retrieval evaluation over the whole corpus, all as open data.
+
+## Documentation
+[CHANGELOG](https://github.com/yabooung/jp-law-citation-graph/blob/main/CHANGELOG.md) · [DATA_CARD](https://github.com/yabooung/jp-law-citation-graph/blob/main/DATA_CARD.md) · [METHODOLOGY](https://github.com/yabooung/jp-law-citation-graph/blob/main/docs/METHODOLOGY.md) ·
+[eval protocol](https://github.com/yabooung/jp-law-citation-graph/blob/main/eval/EVAL_PROTOCOL.md) · detailed Korean docs: [dataset](https://github.com/yabooung/jp-law-citation-graph/blob/main/docs/ko/DATASET.md),
+[schema & resolution rules](https://github.com/yabooung/jp-law-citation-graph/blob/main/docs/ko/GRAPH_SCHEMA.md), [search](https://github.com/yabooung/jp-law-citation-graph/blob/main/docs/ko/SEARCH.md),
+[improvement handbook](https://github.com/yabooung/jp-law-citation-graph/blob/main/docs/ko/IMPROVING_THE_GRAPH.md)
+
+## Contributing
+Issues and PRs are welcome: [CONTRIBUTING.md](https://github.com/yabooung/jp-law-citation-graph/blob/main/CONTRIBUTING.md). A blind annotation round
+(`eval/`) would turn the preliminary precision into a validated number, and it is the most useful
+single contribution.
+
+## License
+Code: Apache-2.0. Data: CC BY 4.0 (source: e-Gov 法令データ; NTA 質疑応答事例 for `eval/v2/nta_gold.jsonl`).
+See [DATA_LICENSE.md](https://github.com/yabooung/jp-law-citation-graph/blob/main/DATA_LICENSE.md). This is not legal advice; check e-Gov / 官報 for legal decisions.
+
+## Citation
+```bibtex
+@misc{jlaw_citegraph_2026,
+  title   = {JLaw-CiteGraph: An open citation graph of Japanese statutory law},
+  version = {2.0.0},
+  year    = {2026},
+  note    = {e-Gov 2026-09-27 snapshot},
+  url     = {https://github.com/yabooung/jp-law-citation-graph}
+}
+```

jlawcite-2.0.0/README.md

@@ -0,0 +1,188 @@
+# JLaw-CiteGraph 🇯🇵⚖️
+
+**English** · [日本語](https://github.com/yabooung/jp-law-citation-graph/blob/main/README.ja.md) · [한국어](https://github.com/yabooung/jp-law-citation-graph/blob/main/README.ko.md)
+
+![code: Apache-2.0](https://img.shields.io/badge/code-Apache--2.0-blue) ![data: CC BY 4.0](https://img.shields.io/badge/data-CC--BY--4.0-green) ![deterministic](https://img.shields.io/badge/pipeline-deterministic%20·%20no%20LLM-brightgreen) ![version](https://img.shields.io/badge/release-v2.0.0-informative)
+
+**An open, deterministic citation graph and search index for Japanese statutory law.**
+
+Every Japanese law in force is parsed from official [e-Gov](https://laws.e-gov.go.jp/) XML down
+to article (条), paragraph (項) and item (号), and citations in the text are resolved to the provision
+they point at: 92.9% of same-law and 82.2% of cross-law citations, with the unresolved ones listed.
+The result ships as data files, a single-file explorer, a `jlawcite` command-line tool
+that looks up and searches provisions without embeddings, and an MCP server for LLMs.
+
+[![JLaw-CiteGraph interactive explorer](https://raw.githubusercontent.com/yabooung/jp-law-citation-graph/main/assets/explorer-screenshot.png)](https://github.com/yabooung/jp-law-citation-graph/blob/main/explorer.html)
+
+<sub>[`explorer.html`](https://github.com/yabooung/jp-law-citation-graph/blob/main/explorer.html): pick a law and see what it cites (green) and what cites it (yellow).</sub>
+
+## At a glance (v2.0, e-Gov snapshot 2026-09-27)
+
+| | |
+|---|---|
+| **Laws** | 8,998, each at the version in force on 2026-09-29, plus **1,649 upcoming amendments** (施行日 + amending law) |
+| **Graph** | 1.89M nodes (条・項・号・附則・別表) · 1.42M citation edges · 67,666 delegation edges (政令で定める) · 37,377 別表/様式 references |
+| **Law → law network** | 70,577 distinct pairs · 453,390 distinct article-level links between laws |
+| **Citation resolution** | same-law 92.9% · cross-law 82.2% · relative refs (前条/同項/…) 92.2% |
+| **Precision** | ≈98% on hand-checked samples of the rules covering 86% of edges (preliminary, see below) |
+| **Search** | `jlawcite get 民法第七百九条` · BM25 search · on 1,170 real tax questions the citation graph lifts Recall@10 from 0.24 to 0.46 |
+| **Method** | 100% deterministic (rules + dictionaries + document context), no LLM, reproducible from the public e-Gov bulk download |
+
+## What's new in v2
+
+| | v1.0 (2026-06) | **v2.0 (2026-09)** |
+|---|---|---|
+| Unit | law → law (article strings) | article / paragraph / item nodes, incl. 附則 and attachments |
+| Edges | cross-law citations | + same-law citations, 前条/同項/前号, delegation, 別表 references |
+| Distinct article-level cross-law links | 173,844 | **453,390** |
+| Law → law pairs | 55,651 | **70,577** |
+| Versions | latest file per law | version in force on a date + upcoming amendments |
+| Search | – | `jlawcite` CLI (lookup, BM25, graph walk) + retrieval benchmark |
+| Precision | 0 errors / 400 (LLM-proposed labels) | per-rule samples with confidence intervals; 5 error classes found and fixed |
+
+v1 wrote one line per citation *mention*, so its 1.21M lines hold 173,844 distinct links; v2 counts
+each (source, target) link once. Full list in [CHANGELOG.md](https://github.com/yabooung/jp-law-citation-graph/blob/main/CHANGELOG.md).
+
+## Who is this for?
+| You are… | You use it to… |
+|---|---|
+| a **legal-NLP researcher** | add citation neighbours to statute retrieval / RAG (the benchmark below shows the gain), or reuse the deterministic resolver on your own corpus |
+| a **legal-tech developer** | answer "what cites X?" (amending 個人情報保護法 touches **111** laws) and "what changes when?" (`pending_versions.csv`) |
+| a **network / comparative-law researcher** | study hubs (地方自治法 is cited by 1,250 laws), delegation chains and dependency clusters |
+| building an **LLM legal assistant** | ground citations deterministically via the MCP server: `会社法第737条` → the exact article text |
+
+## Quick start
+```bash
+git clone https://github.com/yabooung/jp-law-citation-graph && cd jp-law-citation-graph
+pip install -e .                                     # Python 3.11+
+
+jlawcite fetch                                       # e-Gov bulk XML (~320 MB) → data/raw/law_xml
+jlawcite build --input data/raw/law_xml \
+    --csv data/raw/law_xml/all_law_list.csv --output data/parsed      # ~5 min, deterministic
+jlawcite validate --data data/parsed                 # 11 integrity checks
+jlawcite index                                       # search index (~1.5 min, 2.6 GB)
+
+jlawcite get 民法第七百九条                           # also: 労働基準法20条1項, 激甚法第三条, node ids
+jlawcite search 解雇 予告                             # BM25; --nl for a question sentence
+jlawcite refs 労働基準法第二十条                       # what it cites / what cites it
+jlawcite pending --until 20261231                    # amendments coming into force
+```
+
+```text
+$ jlawcite get 民法第七百九条
+民法  [129AC0000000089, act, 明治二十九年法律第八十九号]  現行 2026-06-24 施行中, 次回改正 2027-06-23
+[129AC0000000089_a709] Article
+
+第七百九条
+故意又は過失によって他人の権利又は法律上保護される利益を侵害した者は、これによって生じた損害を賠償する責任を負う。
+
+改正予定:
+  2027-06-23  民法 ← 民法等の一部を改正する法律 令和八年法律第四十五号 (公布の日から起算して一年を超えない範囲内において政令で定める日)
+  …
+```
+
+Every command takes `--json`. The same functions are available in Python (`jlawcite.search.SearchDB`).
+
+## What's inside (`/data`)
+| File | Content |
+|---|---|
+| `laws.csv` | `law_id, name, type, url` (v1) + `enforcement_date, next_enforcement_date, pending_versions` |
+| `cites_law_to_law.csv` | aggregated `src_law → tgt_law` counts (v1 columns) |
+| `cites_edges.jsonl.gz` | every resolved citation of a named law: v1 fields (`src_article`, `tgt_article`, `via`, `confidence`) + `src_node`, `tgt_node`, `fallback_level` |
+| `cites_all_edges.jsonl.gz` | **every** edge of the graph: CITES (incl. same-law and 前条/同項), DELEGATES_TO, REFERS_TO_ATTACHMENT, AMENDS, each with `extracted_from` |
+| `pending_versions.csv` | upcoming amendments: 施行日, 施行日備考, amending law, e-Gov URL |
+| `release_stats.json` | the counts quoted here |
+
+The full node file (1.89M nodes, article and paragraph text included) is attached to the GitHub
+release, or you can rebuild it with the Quick start commands.
+
+```python
+import pandas as pd
+edges = pd.read_csv("data/cites_law_to_law.csv")
+hubs = edges.groupby("tgt_law")["src_law_id"].nunique().sort_values(ascending=False).head(10)
+```
+
+## Use it from an LLM: MCP server (`mcp/`)
+`resolve_citation`, `what_cites`, `what_law_cites`, `citation_path`, `get_law`, and in v2
+`get_provision` (citation → text), `search_statutes` and `pending_amendments`.
+See [`mcp/README.md`](https://github.com/yabooung/jp-law-citation-graph/blob/main/mcp/README.md).
+
+## Retrieval benchmark
+Each of 1,170 National Tax Agency Q&A cases (質疑応答事例) is a real tax question whose answer cites
+specific articles. The question is the query, and hits are counted at the article level
+(`jlawcite eval`).
+
+| method | R@1 | R@5 | R@10 | R@20 | R@50 | MRR@50 | s/query |
+|---|---:|---:|---:|---:|---:|---:|---:|
+| BM25 (character-trigram OR) | 0.086 | 0.192 | 0.244 | 0.326 | 0.437 | 0.140 | 0.11 |
+| BM25 + 1-hop citation graph | **0.256** | **0.403** | **0.459** | **0.500** | **0.550** | **0.325** | 0.11 |
+
+<sub>1,170 queries · e-Gov snapshot 2026-09-27 · `eval/v2/nta_retrieval_results.json`</sub>
+
+The one-hop expansion adds the articles that the top hits cite. A retrieved 施行令 paragraph pulls
+up the parent-act article it implements. Both rows use no embeddings; they are a baseline for dense
+or hybrid retrievers.
+
+## Quality, honestly
+- **Coverage.** No law is left without body text, the 11 integrity checks pass (no dangling edges),
+  and the same input produces the same output.
+- **Resolution rates** leave out citations whose target is not in a current-law corpus: pre-amendment
+  text (旧法), amending acts (改正法), and citations inside amending-law 附則 blocks. These are counted
+  separately in `jp_cites_stats.json`.
+- **Precision is preliminary.** 180 random edges (10–20 per resolution rule) were checked by hand
+  against their source text during development. Five error classes turned up and were fixed. The rules covering 86% of edges now
+  measure ≈98%. Samples are small (10/10 still has a 72% lower bound) and were not blind, so treat it
+  as indicative. Citations inside amending-law 附則 are about 40% right and are flagged with
+  confidence 0.4. Citations of pre-amendment text (「旧○○法第N条」) point at the current version and
+  carry `version: "pre_amendment"`. Details: [docs/METHODOLOGY.md](https://github.com/yabooung/jp-law-citation-graph/blob/main/docs/METHODOLOGY.md).
+- **Scope.** National statutes in force only: no case law, 通達, local ordinances, or text of repealed
+  and amending acts. イ/ロ/ハ subitems are folded into their item.
+
+## Reproduce
+```bash
+jlawcite fetch --zip all_xml.zip       # re-extract an archived snapshot for an exact rebuild
+jlawcite build … --as-of 20260929      # same snapshot + same as-of date → same graph
+jlawcite export --out data             # regenerate the files in /data
+python tools/build_explorer.py         # regenerate explorer.html
+python -m pytest                       # 177 tests
+```
+
+## Related work
+- **弁護士ドットコム (DDS 2026)** built a citation graph over e-Gov statutes (条・項・号) together with
+  books, guidelines and court decisions. It reports P 98.8 / R 92.1 for law-to-law citations; same-law
+  references are outside its evaluation, and the graph is not public.
+  [paper](https://dbsj.org/wp-content/uploads/2025/11/dds-vol4-no3.pdf)
+- **[DaisukeHori/japan-law](https://github.com/DaisukeHori/japan-law)** publishes about 112k article-level
+  cross-references for about 8,000 laws (CC0), without an accuracy evaluation.
+- Reference resolution in Japanese statutes goes back to Tran, Nguyen & Shimazu (ICAIL 2013). Using
+  citation structure for statute retrieval has been shown on the Japanese Civil Code (Mizuno & Kano,
+  COLIEE 2025; Vuong et al., *Applied Intelligence* 2025) and on Belgian law (Louis et al., EACL 2023).
+
+JLaw-CiteGraph adds same-law and relative references (前条・同条・同項・前号・同法), version selection with
+upcoming amendments, per-rule precision, and a retrieval evaluation over the whole corpus, all as open data.
+
+## Documentation
+[CHANGELOG](https://github.com/yabooung/jp-law-citation-graph/blob/main/CHANGELOG.md) · [DATA_CARD](https://github.com/yabooung/jp-law-citation-graph/blob/main/DATA_CARD.md) · [METHODOLOGY](https://github.com/yabooung/jp-law-citation-graph/blob/main/docs/METHODOLOGY.md) ·
+[eval protocol](https://github.com/yabooung/jp-law-citation-graph/blob/main/eval/EVAL_PROTOCOL.md) · detailed Korean docs: [dataset](https://github.com/yabooung/jp-law-citation-graph/blob/main/docs/ko/DATASET.md),
+[schema & resolution rules](https://github.com/yabooung/jp-law-citation-graph/blob/main/docs/ko/GRAPH_SCHEMA.md), [search](https://github.com/yabooung/jp-law-citation-graph/blob/main/docs/ko/SEARCH.md),
+[improvement handbook](https://github.com/yabooung/jp-law-citation-graph/blob/main/docs/ko/IMPROVING_THE_GRAPH.md)
+
+## Contributing
+Issues and PRs are welcome: [CONTRIBUTING.md](https://github.com/yabooung/jp-law-citation-graph/blob/main/CONTRIBUTING.md). A blind annotation round
+(`eval/`) would turn the preliminary precision into a validated number, and it is the most useful
+single contribution.
+
+## License
+Code: Apache-2.0. Data: CC BY 4.0 (source: e-Gov 法令データ; NTA 質疑応答事例 for `eval/v2/nta_gold.jsonl`).
+See [DATA_LICENSE.md](https://github.com/yabooung/jp-law-citation-graph/blob/main/DATA_LICENSE.md). This is not legal advice; check e-Gov / 官報 for legal decisions.
+
+## Citation
+```bibtex
+@misc{jlaw_citegraph_2026,
+  title   = {JLaw-CiteGraph: An open citation graph of Japanese statutory law},
+  version = {2.0.0},
+  year    = {2026},
+  note    = {e-Gov 2026-09-27 snapshot},
+  url     = {https://github.com/yabooung/jp-law-citation-graph}
+}
+```

jlawcite-2.0.0/pyproject.toml

@@ -0,0 +1,39 @@
+[project]
+name = "jlawcite"
+version = "2.0.0"
+description = "JLaw-CiteGraph: deterministic citation graph and embedding-free search for Japanese statutes (e-Gov 法令)"
+readme = "README.md"
+requires-python = ">=3.11"
+license = {text = "Apache-2.0"}
+authors = [{name = "yabooung"}]
+keywords = ["Japanese law", "legal NLP", "citation graph", "e-Gov", "statute", "legal information retrieval"]
+dependencies = [
+    "pydantic>=2.5",
+    "tqdm>=4.66",
+]
+
+[project.optional-dependencies]
+dev = ["pytest>=8.0"]
+mcp = ["mcp>=1.0.0"]
+
+[project.urls]
+Homepage = "https://github.com/yabooung/jp-law-citation-graph"
+
+[project.scripts]
+jlawcite = "jlawcite.cli:main"
+
+[build-system]
+requires = ["setuptools>=61.0"]
+build-backend = "setuptools.build_meta"
+
+[tool.setuptools]
+package-dir = {"" = "src"}
+
+[tool.setuptools.packages.find]
+where = ["src"]
+
+[tool.setuptools.package-data]
+jlawcite = ["*.json"]
+
+[tool.pytest.ini_options]
+testpaths = ["tests"]

jlawcite-2.0.0/setup.cfg

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

jlawcite-2.0.0/src/jlawcite/__init__.py

@@ -0,0 +1,13 @@
+"""jlawcite — deterministic Japanese statutory citation graph and search.
+
+Modules (v1 names kept):
+    parser      e-Gov 法令 XML → Law / Article / Paragraph / Item / Attachment records
+    citation    rule-based citation extraction (external / internal / referential / …)
+    resolver    LawNameIndex (promulgation / canonical / 旧法令名 / alias / defined
+                abbreviations) and referential resolution (前条・同項・前号 …)
+    search      SQLite FTS5 search index and SearchDB API
+    pipeline    fetch → build → validate → export / index / eval  (CLI: `jlawcite`)
+"""
+from __future__ import annotations
+
+__version__ = "2.0.0"