attribution-suite 0.6.0__tar.gz

attribution_suite-0.6.0/.github/workflows/ci.yml

@@ -0,0 +1,23 @@
+name: CI
+on:
+  push: { branches: [main] }
+  pull_request: { branches: [main] }
+
+jobs:
+  test:
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        python-version: ["3.11", "3.12", "3.13"]
+    steps:
+      - uses: actions/checkout@v4
+      - uses: actions/setup-python@v5
+        with: { python-version: "${{ matrix.python-version }}" }
+      - run: pip install -e ".[dev]"
+      - run: ruff check .
+      - run: pytest -q
+      - name: Run examples
+        run: |
+          for f in examples/*.py; do
+            [ -f "$f" ] && python "$f" > /dev/null || true
+          done

attribution_suite-0.6.0/.github/workflows/release.yml

@@ -0,0 +1,58 @@
+name: Release
+
+on:
+  push:
+    tags: ["v*"]
+
+permissions:
+  contents: write
+  id-token: write        # OIDC token for keyless Sigstore signing
+
+jobs:
+  release:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+        with: { fetch-depth: 0 }
+
+      - uses: actions/setup-python@v5
+        with: { python-version: "3.12" }
+
+      - name: Build
+        run: |
+          pip install build
+          python -m build
+
+      # CycloneDX SBOM. For a security tool aimed at security teams, shipping
+      # without one is an easy thing to be criticised for.
+      - name: Generate SBOM
+        run: |
+          pip install cyclonedx-bom
+          cyclonedx-py environment -o sbom.cyclonedx.json --output-format json
+
+      # Keyless signing via OIDC: no long-lived key to leak or rotate. The
+      # signing identity is the GitHub workflow itself, recorded in the public
+      # Rekor transparency log and verifiable by anyone.
+      - name: Sign artifacts
+        uses: sigstore/gh-action-sigstore-python@v3.0.0
+        with:
+          inputs: ./dist/*.tar.gz ./dist/*.whl ./sbom.cyclonedx.json
+
+      - name: Checksums
+        run: |
+          cd dist && sha256sum * > SHA256SUMS && cd ..
+          sha256sum sbom.cyclonedx.json >> dist/SHA256SUMS
+
+      - name: Publish release
+        uses: softprops/action-gh-release@v2
+        with:
+          files: |
+            dist/*
+            sbom.cyclonedx.json
+            *.sigstore.json
+          generate_release_notes: true
+
+      - name: Publish to PyPI
+        uses: pypa/gh-action-pypi-publish@release/v1
+        with:
+          skip-existing: true

attribution_suite-0.6.0/.gitignore

@@ -0,0 +1,15 @@
+__pycache__/
+*.py[cod]
+.venv/
+venv/
+dist/
+build/
+*.egg-info/
+.pytest_cache/
+.ruff_cache/
+.mypy_cache/
+.eae-cache/
+out/
+audit.jsonl
+case.yaml
+.DS_Store

attribution_suite-0.6.0/CHANGELOG.md

@@ -0,0 +1,13 @@
+# Changelog
+
+## [0.2.0] - 2026-08-18
+
+Initial release of the unification package.
+
+### Added
+- `attribution run` — full chain from one case file: import, collect, score,
+  resolve, verify, report
+- Passthrough commands for `index`, `portfolio`, `handles`, `registries`
+- `attribution verify` and `attribution version`
+- Non-zero exit when evidence verification fails, so scripted callers can detect
+  an unpresentable result

attribution_suite-0.6.0/CITATION.cff

@@ -0,0 +1,45 @@
+cff-version: 1.2.0
+title: "attribution-suite: unified CLI over the attribution toolchain"
+message: "If you use this software or the method it implements, please cite it."
+type: software
+cff-version: 1.2.0
+title: "adtx-attribution: ad-tech supply-chain collectors for entity attribution"
+message: "If you use this software or the method it implements, please cite it."
+type: software
+authors:
+  - family-names: Karumudi
+    given-names: Tushar
+    orcid: "https://orcid.org/0009-0005-0870-914X"
+repository-code: "https://github.com/OWNER/adtx-attribution"
+abstract: >-
+  Collectors and a reverse ads.txt/sellers.json index for attributing websites
+  to the legal entities paid for their advertising inventory. Chains IAB ads.txt
+  v1.1 and sellers.json declarations to statutory corporate registries (GLEIF,
+  SEC EDGAR, UK Companies House) and to infrastructure sources (RDAP,
+  Certificate Transparency, passive DNS), using only free and keyless endpoints.
+  The reverse index doubles as the selectivity corpus required to calibrate
+  attribution-graph confidence scores.
+keywords:
+  - ads.txt
+  - sellers.json
+  - ad fraud
+  - open source intelligence
+  - attribution
+  - corporate registries
+license: Apache-2.0
+version: 0.1.0
+repository-code: "https://github.com/OWNER/attribution-suite"
+abstract: >-
+  Meta-package providing a single install and a single command-line interface
+  over attribution-graph, adtx-attribution and handle-correlation. Runs the full
+  chain from one case file: import from SpiderFoot and OpenCTI, collect from
+  registries and ad-tech supply-chain sources, apply planted-identifier checks,
+  score and resolve, verify the evidence package, and report.
+keywords:
+  - open source intelligence
+  - entity resolution
+  - record linkage
+  - attribution
+  - threat intelligence
+license: Apache-2.0
+version: 0.1.0

attribution_suite-0.6.0/CODE_OF_CONDUCT.md

@@ -0,0 +1,17 @@
+# Code of Conduct
+
+This project follows the [Contributor Covenant v2.1](https://www.contributor-covenant.org/version/2/1/code_of_conduct/).
+
+In short: be respectful, assume good faith, and focus criticism on code and
+methods rather than people.
+
+## Additional expectation specific to this project
+
+This is attribution tooling. Do not use issues, discussions or pull requests to
+share attribution findings about identifiable private individuals, to request
+help attributing a specific person, or to post identifiers belonging to real
+people who are not parties to the discussion. Use synthetic or clearly fictional
+identifiers in bug reports and examples.
+
+Report conduct concerns through GitHub's private reporting or by contacting the
+maintainer directly.

attribution_suite-0.6.0/CONTRIBUTING.md

@@ -0,0 +1,22 @@
+# Contributing
+
+This package is thin by design: it wires the three component packages together
+and adds a CLI. It should stay that way.
+
+**Logic belongs in the component packages.** A PR adding scoring, collectors or
+signal analysis here will be redirected to `attribution-graph`,
+`adtx-attribution` or `handle-correlation` respectively. What belongs here is
+orchestration, argument plumbing, and anything that genuinely needs all three at
+once.
+
+The one substantive rule to preserve: **run ordering**. Imported claims seed the
+frontier before collection, adversarial checks run before scoring, and evidence
+verification runs before reporting. Each of those orderings prevents a specific
+failure — an unchecked planted identifier reaching the model at full weight, or
+findings being presented from a package whose integrity check failed. Changing
+the order needs an argument, not just passing tests.
+
+```bash
+pip install -e ".[dev]"
+pytest -q && ruff check .
+```

attribution_suite-0.6.0/LICENSE

@@ -0,0 +1,204 @@
+
+                                 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 [yyyy] [name of copyright owner]
+
+   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.
+
+Copyright 2026 Tushar Karumudi

attribution_suite-0.6.0/PKG-INFO

@@ -0,0 +1,127 @@
+Metadata-Version: 2.5
+Name: attribution-suite
+Version: 0.6.0
+Summary: One install and one CLI over the attribution-graph toolchain
+Project-URL: Homepage, https://github.com/OWNER/attribution-suite
+Author: Tushar Karumudi
+License-Expression: Apache-2.0
+License-File: LICENSE
+Keywords: attribution,entity-resolution,osint,threat-intelligence
+Classifier: Development Status :: 3 - Alpha
+Classifier: Intended Audience :: Information Technology
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Topic :: Security
+Requires-Python: >=3.11
+Requires-Dist: adtx-attribution>=0.6.0
+Requires-Dist: attribution-graph>=0.6.0
+Requires-Dist: handle-correlation>=0.6.0
+Provides-Extra: dev
+Requires-Dist: pytest-asyncio>=0.23; extra == 'dev'
+Requires-Dist: pytest>=8.0; extra == 'dev'
+Requires-Dist: ruff>=0.6; extra == 'dev'
+Description-Content-Type: text/markdown
+
+# attribution-suite
+
+[![License](https://img.shields.io/badge/license-Apache--2.0-blue.svg)](LICENSE)
+
+One install and one CLI over the attribution toolchain.
+
+```bash
+pip install attribution-suite
+attribution run --case case.yaml --index adtx.sqlite --out ./out
+```
+
+## Why the packages are separate at all
+
+[`attribution-graph`](https://github.com/OWNER/attribution-graph) is a pure
+inference library with no network I/O — that is what makes its scoring auditable,
+since every number is a function of claims plus index counts with no hidden
+network state. [`adtx-attribution`](https://github.com/OWNER/adtx-attribution)
+carries the collectors and their dependencies.
+[`handle-correlation`](https://github.com/OWNER/handle-correlation) is
+independent of both.
+
+Someone who only wants the scoring model should not have to install an HTTP
+client, and someone writing their own collectors should not inherit ours. This
+package exists for when you want all of it.
+
+## Unified run
+
+One case file drives the whole chain:
+
+```bash
+attribution run \
+  --case case.yaml \
+  --index adtx.sqlite \
+  --handles observed_handles.csv \
+  --spiderfoot scan.db \
+  --opencti bundle.json \
+  --robin investigations/kraken.json \
+  --out ./out
+```
+
+Robin handles feed the handle-correlation pass automatically, carrying the
+durable identifiers found alongside them. `.onion`-derived claims raise a warning
+in the run summary: those sources have no archive and no preserved body, so they
+cannot be verified after the fact by anyone, including you.
+
+Order is fixed, and the ordering is the point: imported claims seed the frontier
+before collection, adversarial checks run before scoring so a planted identifier
+never reaches the model at full weight, and evidence verification runs before
+reporting so findings from a package that failed its integrity check are never
+presented. **`attribution run` exits non-zero if verification fails**, so a
+scripted caller can detect an unpresentable result.
+
+## Passthrough commands
+
+```bash
+attribution index build --domains tranco.txt --db adtx.sqlite
+attribution portfolio scraper-site.example --index adtx.sqlite --registrants
+attribution handles --observations handles.csv --corpus usernames.txt
+attribution registries --jurisdiction IN
+attribution verify ./out/evidence
+attribution version
+```
+
+These delegate to the component CLIs rather than duplicating their flags.
+
+## Outputs
+
+| File | What it is |
+|---|---|
+| `attribution_report.md` / `.html` | Findings, ICD 203 language, source terms |
+| `verification_trail.md` | Ordered timestamped steps with numbered citations |
+| `investigation_graph.json` | Every claim with full provenance |
+| `entities.ftm.json` | FollowTheMoney — loads into yente / Aleph |
+| `graph.cypher` | Neo4j |
+| `evidence/evidence_manifest.json` | Hash-chained capture record |
+| `evidence/verify.py` | Standalone integrity checker, no dependencies |
+| `evidence/DECLARATION_DRAFT.md` | Qualified-person certification skeleton |
+
+## Collection policy
+
+`robots_policy` in the case file: `respect`, `record` (default), or `ignore`.
+
+There is no silent enforcement — robots.txt is routinely bypassed in practice and
+a library pretending otherwise would be enforcing an abandoned norm. What matters
+for this toolchain is different: the output is meant to survive review, and the
+question there is never "did the tool obey robots.txt" but "can you state what
+your collection policy was". Whichever setting you choose is written into the
+evidence manifest and the declaration draft.
+
+In practice it rarely bites. RDAP, crt.sh, GLEIF, EDGAR, `sellers.json` and
+`ads.txt` are all published for machine consumption; only imprint scraping and
+county-records HTML touch robots-relevant paths.
+
+## Version reporting
+
+Every run prints the version of each component, and `attribution version` reports
+them. A finding that cannot name its toolchain is hard to re-examine once the
+scoring model has moved.
+
+## License
+
+Apache-2.0.

attribution_suite-0.6.0/README.md

@@ -0,0 +1,102 @@
+# attribution-suite
+
+[![License](https://img.shields.io/badge/license-Apache--2.0-blue.svg)](LICENSE)
+
+One install and one CLI over the attribution toolchain.
+
+```bash
+pip install attribution-suite
+attribution run --case case.yaml --index adtx.sqlite --out ./out
+```
+
+## Why the packages are separate at all
+
+[`attribution-graph`](https://github.com/OWNER/attribution-graph) is a pure
+inference library with no network I/O — that is what makes its scoring auditable,
+since every number is a function of claims plus index counts with no hidden
+network state. [`adtx-attribution`](https://github.com/OWNER/adtx-attribution)
+carries the collectors and their dependencies.
+[`handle-correlation`](https://github.com/OWNER/handle-correlation) is
+independent of both.
+
+Someone who only wants the scoring model should not have to install an HTTP
+client, and someone writing their own collectors should not inherit ours. This
+package exists for when you want all of it.
+
+## Unified run
+
+One case file drives the whole chain:
+
+```bash
+attribution run \
+  --case case.yaml \
+  --index adtx.sqlite \
+  --handles observed_handles.csv \
+  --spiderfoot scan.db \
+  --opencti bundle.json \
+  --robin investigations/kraken.json \
+  --out ./out
+```
+
+Robin handles feed the handle-correlation pass automatically, carrying the
+durable identifiers found alongside them. `.onion`-derived claims raise a warning
+in the run summary: those sources have no archive and no preserved body, so they
+cannot be verified after the fact by anyone, including you.
+
+Order is fixed, and the ordering is the point: imported claims seed the frontier
+before collection, adversarial checks run before scoring so a planted identifier
+never reaches the model at full weight, and evidence verification runs before
+reporting so findings from a package that failed its integrity check are never
+presented. **`attribution run` exits non-zero if verification fails**, so a
+scripted caller can detect an unpresentable result.
+
+## Passthrough commands
+
+```bash
+attribution index build --domains tranco.txt --db adtx.sqlite
+attribution portfolio scraper-site.example --index adtx.sqlite --registrants
+attribution handles --observations handles.csv --corpus usernames.txt
+attribution registries --jurisdiction IN
+attribution verify ./out/evidence
+attribution version
+```
+
+These delegate to the component CLIs rather than duplicating their flags.
+
+## Outputs
+
+| File | What it is |
+|---|---|
+| `attribution_report.md` / `.html` | Findings, ICD 203 language, source terms |
+| `verification_trail.md` | Ordered timestamped steps with numbered citations |
+| `investigation_graph.json` | Every claim with full provenance |
+| `entities.ftm.json` | FollowTheMoney — loads into yente / Aleph |
+| `graph.cypher` | Neo4j |
+| `evidence/evidence_manifest.json` | Hash-chained capture record |
+| `evidence/verify.py` | Standalone integrity checker, no dependencies |
+| `evidence/DECLARATION_DRAFT.md` | Qualified-person certification skeleton |
+
+## Collection policy
+
+`robots_policy` in the case file: `respect`, `record` (default), or `ignore`.
+
+There is no silent enforcement — robots.txt is routinely bypassed in practice and
+a library pretending otherwise would be enforcing an abandoned norm. What matters
+for this toolchain is different: the output is meant to survive review, and the
+question there is never "did the tool obey robots.txt" but "can you state what
+your collection policy was". Whichever setting you choose is written into the
+evidence manifest and the declaration draft.
+
+In practice it rarely bites. RDAP, crt.sh, GLEIF, EDGAR, `sellers.json` and
+`ads.txt` are all published for machine consumption; only imprint scraping and
+county-records HTML touch robots-relevant paths.
+
+## Version reporting
+
+Every run prints the version of each component, and `attribution version` reports
+them. A finding that cannot name its toolchain is hard to re-examine once the
+scoring model has moved.
+
+## License
+
+Apache-2.0.

attribution_suite-0.6.0/SECURITY.md

@@ -0,0 +1,32 @@
+# Security policy
+
+## Reporting a vulnerability
+
+Report privately via GitHub Security Advisories ("Report a vulnerability" on the
+Security tab). Please do not open a public issue for security matters.
+
+Expect an acknowledgement within 5 working days.
+
+## Scope
+
+In scope:
+
+- Code execution or injection via crafted claim data, case files or graph JSON
+- Cypher or query injection in the unified runner
+- Bypass of the source-class deny list in `scope.check_source_class`
+- Leakage of unminimized identifiers when `minimize: true` is set
+- Path traversal in case-file or output handling
+
+Out of scope:
+
+- Misuse of the library for investigations the operator was not authorized to
+  conduct. Scope enforcement here is a guardrail against accident and drift, not
+  a security boundary against a determined operator who controls the code.
+- Vulnerabilities in downstream collector packages — report those to their
+  respective repositories.
+
+## Design note
+
+`AttributionGraph` and `Claim` objects deserialized from untrusted JSON should
+be treated as untrusted input. The library does not currently sandbox claim
+`raw` payloads.

attribution_suite-0.6.0/VERIFYING.md

@@ -0,0 +1,40 @@
+# Verifying a release
+
+Releases are signed with [Sigstore](https://www.sigstore.dev/) keyless signing.
+There is no long-lived signing key: the identity is the GitHub Actions workflow
+that built the artifact, and every signature is recorded in the public Rekor
+transparency log.
+
+## Verify a downloaded artifact
+
+```bash
+pip install sigstore
+
+sigstore verify identity \
+  --cert-identity "https://github.com/OWNER/REPO/.github/workflows/release.yml@refs/tags/vX.Y.Z" \
+  --cert-oidc-issuer "https://token.actions.githubusercontent.com" \
+  PACKAGE-X.Y.Z.tar.gz
+```
+
+Substitute the real owner, repo and tag. If verification fails, the artifact was
+not produced by that workflow at that tag — do not install it.
+
+## Checksums
+
+`SHA256SUMS` is published with each release and is itself signed.
+
+```bash
+sha256sum -c SHA256SUMS
+```
+
+## SBOM
+
+`sbom.cyclonedx.json` is a CycloneDX software bill of materials for the release,
+signed alongside the artifacts. Feed it to your own dependency scanner rather
+than trusting this project's assessment of its own supply chain.
+
+## What signing does and does not prove
+
+It proves the artifact came from this repository's release workflow at the stated
+tag and has not been altered since. It does not prove the code is correct, safe,
+or free of vulnerabilities. Read it.

attribution_suite-0.6.0/case.example.yaml

@@ -0,0 +1,26 @@
+# Drives the whole chain. attribution run --case this.yaml
+case_ref: SCRAPE-2026-0417
+authorization: "IR ticket SEC-88213 / preservation request 2026-08-02"
+contact_email: "threatintel@example.com"
+
+seeds:
+  - domain:scraper-site.example
+  - seller_id:pubmatic.com/156423
+
+pivot_radius: 3
+entity_types_allowed: [Company]
+jurisdictions: [US, EU, IN]
+
+# respect | record | ignore. Whichever you pick is written into the evidence
+# manifest and the declaration draft, so the run can state its own policy.
+robots_policy: record
+
+minimize: true
+retention_days: 180
+
+budget:
+  max_requests: 4000
+  max_nodes: 15000
+  max_runtime_s: 1800
+
+audit_path: audit.jsonl

attribution_suite-0.6.0/pyproject.toml

@@ -0,0 +1,49 @@
+[build-system]
+requires = ["hatchling"]
+build-backend = "hatchling.build"
+
+[project]
+name = "attribution-suite"
+version = "0.6.0"
+description = "One install and one CLI over the attribution-graph toolchain"
+readme = "README.md"
+requires-python = ">=3.11"
+license = "Apache-2.0"
+authors = [{ name = "Tushar Karumudi" }]
+keywords = ["osint", "attribution", "threat-intelligence", "entity-resolution"]
+classifiers = [
+  "Development Status :: 3 - Alpha",
+  "Intended Audience :: Information Technology",
+  "Topic :: Security",
+  "Programming Language :: Python :: 3.11",
+  "Programming Language :: Python :: 3.12",
+  "Programming Language :: Python :: 3.13",
+]
+dependencies = [
+  "attribution-graph>=0.6.0",
+  "adtx-attribution>=0.6.0",
+  "handle-correlation>=0.6.0",
+]
+
+[project.optional-dependencies]
+dev = ["pytest>=8.0", "pytest-asyncio>=0.23", "ruff>=0.6"]
+
+[project.scripts]
+attribution = "attribution_suite.cli:_cli"
+
+[project.urls]
+Homepage = "https://github.com/OWNER/attribution-suite"
+
+[tool.hatch.build.targets.wheel]
+packages = ["src/attribution_suite"]
+
+[tool.ruff]
+line-length = 100
+target-version = "py311"
+
+[tool.ruff.lint]
+select = ["E", "F", "W", "I", "UP", "B", "SIM"]
+ignore = ["B008", "UP017"]
+
+[tool.pytest.ini_options]
+testpaths = ["tests"]

attribution_suite-0.6.0/src/attribution_suite/__init__.py

@@ -0,0 +1,19 @@
+"""attribution-suite: one install and one CLI over the three attribution packages.
+
+The packages are separate on purpose. ``attribution-graph`` is a pure inference
+library with no network I/O, which is what makes its scoring auditable;
+``adtx-attribution`` carries the collectors and their dependencies;
+``handle-correlation`` is independent of both. Someone who only wants the scoring
+model should not have to install an HTTP client, and someone building their own
+collectors should not inherit ours.
+
+This package exists for the case where you want all of it: ``pip install
+attribution-suite`` and a single ``attribution`` command that runs the whole
+chain — collect, score, resolve, verify, report — with one case file.
+"""
+
+from .runner import SuiteResult, run_case
+from .version import PACKAGES, versions
+
+__version__ = "0.6.0"
+__all__ = ["run_case", "SuiteResult", "versions", "PACKAGES", "__version__"]

attribution_suite-0.6.0/src/attribution_suite/cli.py

@@ -0,0 +1,131 @@
+"""Unified CLI.
+
+    attribution run       --case case.yaml [--index adtx.sqlite] [--handles h.csv]
+    attribution portfolio <domain> --index adtx.sqlite
+    attribution handles   --observations h.csv
+    attribution registries --jurisdiction IN
+    attribution verify    ./out/evidence
+    attribution version
+"""
+
+from __future__ import annotations
+
+import argparse
+import contextlib
+import os
+import subprocess
+import sys
+from pathlib import Path
+
+from .runner import run_case
+from .version import banner, versions
+
+
+def _run(a: argparse.Namespace) -> int:
+    from attribution_graph import PolicyError
+    try:
+        res = run_case(
+            a.case, a.out, corpus_index=a.index or None, blacklist=a.blacklist or None,
+            handles=a.handles or None, spiderfoot=a.spiderfoot or None,
+            opencti=a.opencti or None, robin=a.robin or None,
+            show_scores=not a.no_scores,
+            evidence=not a.no_evidence, concurrency=a.concurrency,
+        )
+    except PolicyError as e:
+        print(f"policy error: {e}", file=sys.stderr)
+        return 2
+
+    print(banner())
+    print(res.summary())
+    print()
+    for p in res.outputs:
+        print(f"  {p}")
+    # Non-zero when integrity failed: a caller scripting this must be able to
+    # detect that the findings are not presentable.
+    return 1 if res.stats.get("evidence_verified") is False else 0
+
+
+def _verify(a: argparse.Namespace) -> int:
+    v = Path(a.path) / "verify.py"
+    if not v.exists():
+        v = Path(a.path)
+    if not v.exists():
+        print(f"no verify.py at {a.path}", file=sys.stderr)
+        return 2
+    return subprocess.call([sys.executable, str(v)])
+
+
+def _delegate(module: str, argv: list[str]) -> int:
+    from importlib import import_module
+    return import_module(module).main(argv)
+
+
+def _version(_: argparse.Namespace) -> int:
+    for k, v in versions().items():
+        print(f"{k.replace('_', '-'):22} {v}")
+    return 0
+
+
+def main(argv: list[str] | None = None) -> int:
+    ap = argparse.ArgumentParser(
+        prog="attribution",
+        description="Unified entity attribution suite")
+    sub = ap.add_subparsers(dest="cmd", required=True)
+
+    r = sub.add_parser("run", help="full chain from one case file")
+    r.add_argument("--case", required=True)
+    r.add_argument("--out", default="./out")
+    r.add_argument("--index", default="", help="ads.txt corpus sqlite")
+    r.add_argument("--blacklist", default="")
+    r.add_argument("--handles", default="", help="observed-handle CSV/JSON")
+    r.add_argument("--spiderfoot", default="", help="SpiderFoot .csv or .db")
+    r.add_argument("--opencti", default="", help="STIX 2.1 bundle")
+    r.add_argument("--robin", default="", help="Robin dark web investigation JSON")
+    r.add_argument("--no-scores", action="store_true",
+                   help="omit confidence figures from the report")
+    r.add_argument("--no-evidence", action="store_true")
+    r.add_argument("--concurrency", type=int, default=6)
+    r.set_defaults(func=_run)
+
+    v = sub.add_parser("verify", help="check an evidence package's integrity")
+    v.add_argument("path", default="./out/evidence", nargs="?")
+    v.set_defaults(func=_verify)
+
+    sub.add_parser("version").set_defaults(func=_version)
+
+    known = {"run", "verify", "version"}
+    argv = list(sys.argv[1:] if argv is None else argv)
+
+    # Pass through to the component CLIs rather than duplicating their flags.
+    if argv and argv[0] not in known:
+        delegates = {
+            "portfolio": ("adtx_attribution.cli", argv),
+            "registries": ("adtx_attribution.cli", argv),
+            "index": ("adtx_attribution.index", argv[1:]),
+            "handles": ("handle_correlation.cli", ["score"] + argv[1:]),
+        }
+        if argv[0] in delegates:
+            mod, passthru = delegates[argv[0]]
+            if argv[0] == "index":
+                from adtx_attribution.index import _main
+                return _main(passthru)
+            return _delegate(mod, passthru)
+
+    args = ap.parse_args(argv)
+    return args.func(args)
+
+
+def _cli() -> int:
+    try:
+        return main()
+    except BrokenPipeError:
+        os.dup2(os.open(os.devnull, os.O_WRONLY), sys.stdout.fileno())
+        return 0
+    except KeyboardInterrupt:
+        with contextlib.suppress(Exception):
+            print("\ninterrupted", file=sys.stderr)
+        return 130
+
+
+if __name__ == "__main__":
+    raise SystemExit(_cli())

attribution_suite-0.6.0/src/attribution_suite/runner.py

@@ -0,0 +1,205 @@
+"""Unified run: collect, score, resolve, verify, report.
+
+One case file drives everything. The sequence is fixed because the ordering
+matters: adversarial checks must run before scoring (a planted identifier must
+not reach the model at full weight), and evidence verification must run before
+reporting (findings from a package that failed its integrity check should never
+be presented).
+"""
+
+from __future__ import annotations
+
+import asyncio
+from dataclasses import dataclass, field
+from pathlib import Path
+from typing import Any
+
+from attribution_graph import (
+    AttributionGraph,
+    CaseScope,
+    CompositeIndex,
+    Engine,
+    EvidenceLog,
+    InMemoryIndex,
+    PolicyEngine,
+    ResolutionResult,
+    RobotsPolicy,
+    StepKind,
+    Trail,
+    load_blacklist,
+    write_all,
+    write_evidence_package,
+)
+
+
+@dataclass
+class SuiteResult:
+    scope: CaseScope
+    graph: AttributionGraph
+    resolution: ResolutionResult | None
+    trail: Trail
+    evidence: EvidenceLog | None
+    outputs: list[Path] = field(default_factory=list)
+    warnings: list[str] = field(default_factory=list)
+    stats: dict[str, Any] = field(default_factory=dict)
+
+    def summary(self) -> str:
+        L = [f"case {self.scope.case_ref}",
+             f"  {len(self.graph.identifiers)} identifiers, "
+             f"{len(self.graph.claims)} claims, {len(self.graph.entities)} entities"]
+        for k, v in self.stats.items():
+            L.append(f"  {k}: {v}")
+        if self.warnings:
+            L.append("  warnings:")
+            L += [f"    - {w}" for w in self.warnings]
+        return "\n".join(L)
+
+
+def run_case(
+    case_path: str | Path,
+    outdir: str | Path = "./out",
+    *,
+    corpus_index: str | Path | None = None,
+    blacklist: str | Path | None = None,
+    handles: str | Path | None = None,
+    spiderfoot: str | Path | None = None,
+    opencti: str | Path | None = None,
+    robin: str | Path | None = None,
+    show_scores: bool = True,
+    evidence: bool = True,
+    concurrency: int = 6,
+) -> SuiteResult:
+    """Run the full chain from one case file."""
+    from adtx_attribution import AdsTxtIndex, Fetcher
+    from adtx_attribution.collectors import build_all
+
+    scope = CaseScope.load(case_path)
+    out = Path(outdir)
+    out.mkdir(parents=True, exist_ok=True)
+
+    trail = Trail(scope.case_ref, scope.authorization)
+    warnings: list[str] = []
+    stats: dict[str, Any] = {}
+
+    if blacklist:
+        load_blacklist(str(blacklist))
+
+    ua = (f"attribution-suite/0.2 (case {scope.case_ref}; "
+          f"{scope.contact_email or 'no-contact-configured'})")
+    fetcher = Fetcher(user_agent=ua, max_requests=scope.max_requests)
+    policy = PolicyEngine(policy=RobotsPolicy(scope.robots_policy), user_agent=ua)
+    ev = EvidenceLog(scope, out / "evidence") if evidence else None
+
+    collectors = build_all(fetcher, scope)
+    engine = Engine(scope, collectors=collectors, concurrency=concurrency)
+
+    if corpus_index:
+        engine.index = CompositeIndex(AdsTxtIndex(str(corpus_index)),
+                                      InMemoryIndex(engine.graph))
+    else:
+        warnings.append(
+            "no corpus index supplied — selectivity counts come from this case "
+            "only, so confidence figures are upper bounds, not assessments")
+
+    for s in scope.seeds:
+        trail.seed(s)
+
+    # --- imported claims, before collection, so they seed the frontier ------ #
+    if spiderfoot:
+        from adtx_attribution import from_spiderfoot_csv, from_spiderfoot_db
+        p = Path(spiderfoot)
+        imported = (from_spiderfoot_db(p) if p.suffix in (".db", ".sqlite")
+                    else from_spiderfoot_csv(p))
+        for c in imported:
+            engine.ingest(c, depth=1)
+        stats["spiderfoot_claims"] = len(imported)
+        trail.add_imported("SpiderFoot", str(p), len(imported))
+
+    if opencti:
+        from adtx_attribution import from_opencti_bundle
+        imported = from_opencti_bundle(Path(opencti))
+        for c in imported:
+            engine.ingest(c, depth=1)
+        stats["opencti_claims"] = len(imported)
+        trail.add_imported("OpenCTI", str(opencti), len(imported))
+
+    robin_claims: list = []
+    if robin:
+        from adtx_attribution import from_robin
+        robin_claims = from_robin(Path(robin))
+        for c in robin_claims:
+            engine.ingest(c, depth=1)
+        stats["robin_claims"] = len(robin_claims)
+        onion = sum(1 for c in robin_claims if c.raw.get("onion"))
+        llm = sum(1 for c in robin_claims if c.raw.get("llm_derived"))
+        stats["robin_onion_sources"] = onion
+        trail.add_imported("Robin", str(robin), len(robin_claims))
+        trail.add(
+            StepKind.FILTER,
+            f"Marked {len(robin_claims)} Robin claim(s) as derived text",
+            detail=("Robin truncates scraped content and does not retain response "
+                    "bodies, so these are leads rather than captures. "
+                    f"{onion} came from .onion sources, which cannot be re-fetched "
+                    f"or archived; {llm} were asserted by a language model and are "
+                    "capped at UNCERTAIN."))
+        if onion:
+            warnings.append(
+                f"{onion} claim(s) derive from .onion sources with no preserved "
+                "response body — unverifiable after the fact by anyone, including you")
+
+    # --- collect ------------------------------------------------------------ #
+    resolution = asyncio.run(engine.run())
+    asyncio.run(fetcher.aclose())
+    stats["requests"] = fetcher.count
+
+    # --- handles ------------------------------------------------------------ #
+    if handles or robin_claims:
+        from handle_correlation import HandleCorpus, Observation, all_claims, correlation_points
+        from handle_correlation import load as load_handles
+
+        obs = load_handles(handles) if handles else []
+
+        # Handles Robin surfaced join the same correlation pass, carrying the
+        # durable identifiers found on the same page -- which is what can lift
+        # them above the correlation-point floor.
+        if robin_claims:
+            from adtx_attribution import to_handle_observations
+            for row in to_handle_observations(robin_claims, scope.case_ref):
+                obs.append(Observation(
+                    handle=row["handle"], platform=row["platform"],
+                    linked={k[5:]: v for k, v in row.items() if k.startswith("link_")},
+                    source_url=row.get("source_url", ""),
+                    case_ref=row.get("case_ref", ""),
+                ))
+        corpus = HandleCorpus()
+        for o in obs:
+            corpus.observe(o.qualified)
+        hclaims = all_claims(obs, corpus)
+        for c in hclaims:
+            engine.graph.add_claim(c)
+        hc = correlation_points(hclaims)
+        stats["handle_observations"] = len(obs)
+        stats["handle_confidence"] = f"{hc.level.value} ({hc.points} points)"
+        warnings.append(f"handle correlation: {hc.caveat}")
+        trail.infer(f"Handle correlation assessed: {hc.level.value}",
+                    basis=hc.caveat)
+
+    # --- evidence policy block ---------------------------------------------- #
+    if ev is not None:
+        ev.fetch_policy = policy.summary([])
+        paths = write_evidence_package(ev)
+        ok, problems = ev.verify()
+        stats["evidence_verified"] = ok
+        if not ok:
+            warnings.append(
+                "EVIDENCE VERIFICATION FAILED — do not present these findings: "
+                + "; ".join(problems[:3]))
+
+    outputs = write_all(engine.graph, resolution, scope, out,
+                        show_scores=show_scores, trail=trail)
+    if ev is not None:
+        outputs += paths
+
+    return SuiteResult(scope=scope, graph=engine.graph, resolution=resolution,
+                       trail=trail, evidence=ev, outputs=outputs,
+                       warnings=warnings, stats=stats)

attribution_suite-0.6.0/src/attribution_suite/version.py

@@ -0,0 +1,32 @@
+"""Version reporting across the suite.
+
+Every report and evidence manifest should be able to state which versions
+produced it. A finding that cannot name its toolchain is hard to re-examine
+later, especially once the scoring model has moved.
+"""
+
+from __future__ import annotations
+
+import importlib
+import importlib.metadata
+
+PACKAGES = ("attribution_graph", "adtx_attribution", "handle_correlation")
+
+
+def versions() -> dict[str, str]:
+    out: dict[str, str] = {}
+    for name in PACKAGES:
+        try:
+            mod = importlib.import_module(name)
+            out[name] = getattr(mod, "__version__", "unknown")
+        except ImportError:
+            out[name] = "not installed"
+    try:
+        out["attribution_suite"] = importlib.metadata.version("attribution-suite")
+    except importlib.metadata.PackageNotFoundError:
+        out["attribution_suite"] = "dev"
+    return out
+
+
+def banner() -> str:
+    return " | ".join(f"{k.replace('_', '-')} {v}" for k, v in versions().items())

attribution_suite-0.6.0/tests/test_suite.py

@@ -0,0 +1,34 @@
+"""Suite wiring."""
+
+
+from attribution_suite import PACKAGES, versions
+from attribution_suite.cli import main
+
+
+def test_all_component_packages_import():
+    v = versions()
+    for p in PACKAGES:
+        assert v[p] != "not installed", p
+
+
+def test_versions_are_aligned():
+    v = versions()
+    reported = {v[p] for p in PACKAGES}
+    assert len(reported) == 1, f"component versions diverge: {v}"
+
+
+def test_version_command_runs(capsys):
+    assert main(["version"]) == 0
+    assert "attribution-graph" in capsys.readouterr().out
+
+
+def test_run_refuses_a_case_without_authorization(tmp_path, capsys):
+    c = tmp_path / "bad.yaml"
+    c.write_text("case_ref: X\nseeds: [domain:a.example]\n")
+    assert main(["run", "--case", str(c), "--out", str(tmp_path / "o")]) == 2
+    assert "authorization" in capsys.readouterr().err
+
+
+def test_registries_delegates_to_component_cli(capsys):
+    assert main(["registries", "--jurisdiction", "GB"]) == 0
+    assert "Companies House" in capsys.readouterr().out