proof-citations 1.33.0__tar.gz

proof_citations-1.33.0/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2026 Yaniv Golan
+
+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.

proof_citations-1.33.0/PKG-INFO

@@ -0,0 +1,76 @@
+Metadata-Version: 2.4
+Name: proof-citations
+Version: 1.33.0
+Summary: Fetch URLs and verify that quoted text appears on the page. Extracted from proof-engine.
+Author-email: Yaniv Golan <yaniv@lool.vc>
+License: MIT License
+        
+        Copyright (c) 2026 Yaniv Golan
+        
+        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.
+        
+Project-URL: Homepage, https://proofengine.info
+Project-URL: Repository, https://github.com/yaniv-golan/proof-engine
+Project-URL: Documentation, https://github.com/yaniv-golan/proof-engine/blob/main/packages/proof-citations/README.md
+Project-URL: Issues, https://github.com/yaniv-golan/proof-engine/issues
+Project-URL: Changelog, https://github.com/yaniv-golan/proof-engine/blob/main/CHANGELOG.md
+Project-URL: Source, https://github.com/yaniv-golan/proof-engine/tree/main/packages/proof-citations
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Topic :: Text Processing
+Requires-Python: >=3.11
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: requests>=2.31
+Requires-Dist: pdfplumber>=0.10
+Requires-Dist: PyPDF2>=3.0
+Dynamic: license-file
+
+# proof-citations
+
+Fetch URLs and verify that quoted text appears on the page — the citation-verification
+primitive extracted from [Proof Engine](https://proofengine.info).
+
+## Install
+
+    pip install proof-citations
+
+## Library
+
+    from proof_citations import verify_citation
+
+    result = verify_citation(
+        "https://example.com/article",
+        "the exact quoted sentence",
+        "B1",                 # fact_id — used in messages
+    )
+    print(result["status"])   # "verified" | "partial" | "not_found" | "fetch_failed"
+    print(result["credibility"]["tier"])
+
+## CLI
+
+    proof-citations verify --url URL --quote "QUOTE TEXT" --fact-id B1
+    proof-citations verify --facts facts.json
+
+## Why
+
+LLMs hallucinate citations. This package does one job: fetch the URL, normalize
+unicode and HTML, and confirm the quoted text is actually on the page. It handles
+PDFs, Wayback fallback, and the unicode quirks (en-dash vs hyphen, curly quotes,
+non-breaking spaces, HTML-entity-encoded quotes) that real citations contain.

proof_citations-1.33.0/README.md

@@ -0,0 +1,32 @@
+# proof-citations
+
+Fetch URLs and verify that quoted text appears on the page — the citation-verification
+primitive extracted from [Proof Engine](https://proofengine.info).
+
+## Install
+
+    pip install proof-citations
+
+## Library
+
+    from proof_citations import verify_citation
+
+    result = verify_citation(
+        "https://example.com/article",
+        "the exact quoted sentence",
+        "B1",                 # fact_id — used in messages
+    )
+    print(result["status"])   # "verified" | "partial" | "not_found" | "fetch_failed"
+    print(result["credibility"]["tier"])
+
+## CLI
+
+    proof-citations verify --url URL --quote "QUOTE TEXT" --fact-id B1
+    proof-citations verify --facts facts.json
+
+## Why
+
+LLMs hallucinate citations. This package does one job: fetch the URL, normalize
+unicode and HTML, and confirm the quoted text is actually on the page. It handles
+PDFs, Wayback fallback, and the unicode quirks (en-dash vs hyphen, curly quotes,
+non-breaking spaces, HTML-entity-encoded quotes) that real citations contain.

proof_citations-1.33.0/pyproject.toml

@@ -0,0 +1,42 @@
+[build-system]
+requires = ["setuptools>=68", "wheel"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "proof-citations"
+version = "1.33.0"
+description = "Fetch URLs and verify that quoted text appears on the page. Extracted from proof-engine."
+readme = "README.md"
+license = { file = "LICENSE" }
+authors = [{ name = "Yaniv Golan", email = "yaniv@lool.vc" }]
+requires-python = ">=3.11"
+dependencies = [
+  "requests>=2.31",
+  "pdfplumber>=0.10",
+  "PyPDF2>=3.0",
+]
+classifiers = [
+  "License :: OSI Approved :: MIT License",
+  "Programming Language :: Python :: 3.11",
+  "Topic :: Text Processing",
+]
+
+[project.scripts]
+proof-citations = "proof_citations.cli:main"
+
+[project.urls]
+Homepage = "https://proofengine.info"
+Repository = "https://github.com/yaniv-golan/proof-engine"
+Documentation = "https://github.com/yaniv-golan/proof-engine/blob/main/packages/proof-citations/README.md"
+Issues = "https://github.com/yaniv-golan/proof-engine/issues"
+Changelog = "https://github.com/yaniv-golan/proof-engine/blob/main/CHANGELOG.md"
+Source = "https://github.com/yaniv-golan/proof-engine/tree/main/packages/proof-citations"
+
+[tool.setuptools.packages.find]
+where = ["src"]
+
+[tool.setuptools.package-data]
+proof_citations = ["data/*.json"]
+
+[tool.pytest.ini_options]
+testpaths = ["tests"]

proof_citations-1.33.0/setup.cfg

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

proof_citations-1.33.0/src/proof_citations/__init__.py

@@ -0,0 +1,10 @@
+"""proof-citations — fetch URLs and verify quoted text appears on the page."""
+
+__version__ = "1.33.0"
+
+from proof_citations.verify import (
+    verify_citation,
+    verify_all_citations,
+)
+
+__all__ = ["verify_citation", "verify_all_citations"]

proof_citations-1.33.0/src/proof_citations/cli.py

@@ -0,0 +1,67 @@
+"""Command-line entry point for proof-citations.
+
+    proof-citations verify --url URL --quote "QUOTE" --fact-id B1
+    proof-citations verify --facts facts.json
+"""
+
+import argparse
+import json
+import sys
+
+from proof_citations import verify_citation, verify_all_citations
+
+
+def _cmd_verify(args) -> int:
+    if args.facts:
+        with open(args.facts) as f:
+            facts = json.load(f)
+        results = verify_all_citations(facts)
+        # verify_all_citations returns a dict (per verify_citations.py).
+        # Emit as-is, and compute exit from statuses.
+        sys.stdout.write(
+            json.dumps(results, indent=2 if args.pretty else None) + "\n"
+        )
+        statuses = [r.get("status") for r in results.values()] \
+            if isinstance(results, dict) else []
+        return 0 if statuses and all(s == "verified" for s in statuses) else 1
+
+    if not args.url or not args.quote:
+        sys.stderr.write("error: --url and --quote are required (or --facts)\n")
+        return 2
+
+    result = verify_citation(args.url, args.quote, args.fact_id)
+    if args.json:
+        sys.stdout.write(
+            json.dumps(result, indent=2 if args.pretty else None, default=str)
+            + "\n"
+        )
+    else:
+        sys.stdout.write(f"{result.get('status')}: {args.url}\n")
+    return 0 if result.get("status") == "verified" else 1
+
+
+def build_parser() -> argparse.ArgumentParser:
+    parser = argparse.ArgumentParser(prog="proof-citations")
+    sub = parser.add_subparsers(dest="cmd", required=True)
+
+    verify = sub.add_parser("verify", help="Verify a quote appears at a URL.")
+    verify.add_argument("--url")
+    verify.add_argument("--quote")
+    verify.add_argument("--fact-id", default="B1",
+                        help="Identifier used in messages (default: B1).")
+    verify.add_argument("--facts", help="Path to JSON file of facts to verify.")
+    verify.add_argument("--json", action="store_true", help="Emit JSON.")
+    verify.add_argument("--pretty", action="store_true", help="Pretty-print JSON.")
+    verify.set_defaults(func=_cmd_verify)
+
+    return parser
+
+
+def main(argv=None) -> int:
+    parser = build_parser()
+    args = parser.parse_args(argv)
+    return args.func(args)
+
+
+if __name__ == "__main__":
+    raise SystemExit(main())

proof_citations-1.33.0/src/proof_citations/data/academic_domains.json

@@ -0,0 +1,97 @@
+{
+    "_comment": "Academic/research TLDs and known scholarly publisher domains. Tier 4 (peer-reviewed/institutional).",
+    "tld_suffixes": [
+        ".edu",
+        ".edu.au",
+        ".edu.br",
+        ".edu.cn",
+        ".edu.hk",
+        ".edu.sg",
+        ".edu.tw",
+        ".edu.mx",
+        ".edu.ar",
+        ".edu.co",
+        ".edu.pe",
+        ".ac.uk",
+        ".ac.jp",
+        ".ac.kr",
+        ".ac.il",
+        ".ac.in",
+        ".ac.nz",
+        ".ac.za",
+        ".ac.id",
+        ".ac.th",
+        ".uni.edu",
+        ".edu.pl",
+        ".edu.tr"
+    ],
+    "known_domains": [
+        "nature.com",
+        "science.org",
+        "sciencemag.org",
+        "thelancet.com",
+        "bmj.com",
+        "nejm.org",
+        "cell.com",
+        "pnas.org",
+        "plos.org",
+        "plosone.org",
+        "plosmedicine.org",
+        "springer.com",
+        "link.springer.com",
+        "wiley.com",
+        "onlinelibrary.wiley.com",
+        "sciencedirect.com",
+        "elsevier.com",
+        "tandfonline.com",
+        "taylorandfrancis.com",
+        "oxfordacademic.com",
+        "academic.oup.com",
+        "cambridge.org",
+        "journals.sagepub.com",
+        "sagepub.com",
+        "jstor.org",
+        "arxiv.org",
+        "biorxiv.org",
+        "medrxiv.org",
+        "ssrn.com",
+        "pubmed.ncbi.nlm.nih.gov",
+        "ncbi.nlm.nih.gov",
+        "scholar.google.com",
+        "semanticscholar.org",
+        "researchgate.net",
+        "doi.org",
+        "crossref.org",
+        "cochranelibrary.com",
+        "annualreviews.org",
+        "frontiersin.org",
+        "mdpi.com",
+        "ieee.org",
+        "ieeexplore.ieee.org",
+        "acm.org",
+        "dl.acm.org",
+        "aps.org",
+        "aaas.org",
+        "royalsocietypublishing.org",
+        "worldscientific.com",
+        "degruyter.com",
+        "karger.com",
+        "biomedcentral.com",
+        "iopscience.iop.org",
+        "aanda.org",
+        "journals.aps.org",
+        "physrev.org",
+        "aip.org",
+        "scitation.org",
+        "projecteuclid.org",
+        "msp.org",
+        "ams.org",
+        "zbmath.org"
+    ],
+    "doi_prefixes": [
+        "https://doi.org/",
+        "http://doi.org/",
+        "https://dx.doi.org/",
+        "http://dx.doi.org/"
+    ]
+}

proof_citations-1.33.0/src/proof_citations/data/government_tlds.json

@@ -0,0 +1,114 @@
+{
+    "_comment": "Government and intergovernmental TLDs and domain suffixes. Tier 5 (primary official source).",
+    "_comment_un_agencies": "UN subsidiary organs and specialized agencies. un.int excluded — subdomain matching would promote all *.un.int hosts (including member-state mission sites) to tier 5.",
+    "tld_suffixes": [
+        ".gov",
+        ".gov.uk",
+        ".gov.au",
+        ".gov.ca",
+        ".gov.nz",
+        ".gov.za",
+        ".gov.in",
+        ".gov.sg",
+        ".gov.ie",
+        ".gov.il",
+        ".gc.ca",
+        ".gouv.fr",
+        ".gouv.qc.ca",
+        ".gob.mx",
+        ".gob.es",
+        ".gob.ar",
+        ".gob.cl",
+        ".gob.pe",
+        ".gobierno.ar",
+        ".go.jp",
+        ".go.kr",
+        ".go.id",
+        ".go.th",
+        ".gov.br",
+        ".gov.cn",
+        ".gov.tw",
+        ".gov.ph",
+        ".gov.my",
+        ".gov.eg",
+        ".gov.ng",
+        ".gov.gh",
+        ".gov.ke",
+        ".govt.nz",
+        ".bund.de",
+        ".admin.ch",
+        ".overheid.nl",
+        ".regeringen.se",
+        ".mil",
+        ".mil.br"
+    ],
+    "known_domains": [
+        "europa.eu",
+        "un.org",
+        "who.int",
+        "worldbank.org",
+        "imf.org",
+        "oecd.org",
+        "nato.int",
+        "wto.org",
+        "iaea.org",
+        "unicef.org",
+        "unhcr.org",
+        "icj-cij.org",
+        "icc-cpi.int",
+        "ilo.org",
+        "fao.org",
+        "wipo.int",
+        "itu.int",
+        "unep.org",
+        "undp.org",
+        "unfccc.int",
+        "ipcc.ch",
+        "data.worldbank.org",
+        "data.un.org",
+        "stats.oecd.org",
+        "federalreserve.gov",
+        "bls.gov",
+        "census.gov",
+        "cdc.gov",
+        "nih.gov",
+        "nasa.gov",
+        "noaa.gov",
+        "epa.gov",
+        "fda.gov",
+        "sec.gov",
+        "treasury.gov",
+        "state.gov",
+        "justice.gov",
+        "uscourts.gov",
+        "congress.gov",
+        "whitehouse.gov",
+        "ons.gov.uk",
+        "bankofengland.co.uk",
+        "abs.gov.au",
+        "rba.gov.au",
+        "statcan.gc.ca",
+        "bankofcanada.ca",
+        "destatis.de",
+        "bundesbank.de",
+        "insee.fr",
+        "banque-france.fr",
+        "istat.it",
+        "stats.govt.nz",
+        "ecb.europa.eu",
+        "eurostat.ec.europa.eu",
+        "unrwa.org",
+        "ungeneva.org",
+        "wfp.org",
+        "unesco.org",
+        "unodc.org",
+        "unhabitat.org",
+        "unwomen.org",
+        "unaids.org",
+        "unido.org",
+        "unctad.org",
+        "unops.org",
+        "reliefweb.int",
+        "ohchr.org"
+    ]
+}

proof_citations-1.33.0/src/proof_citations/data/major_news.json

@@ -0,0 +1,69 @@
+{
+    "_comment": "Major news organizations with established editorial standards. Tier 3 (major news). Based on Wikipedia's Perennial Sources list (generally reliable).",
+    "_comment_newer_outlets": "Established newer outlets with editorial standards, added 2026-04.",
+    "known_domains": [
+        "apnews.com",
+        "reuters.com",
+        "bbc.com",
+        "bbc.co.uk",
+        "nytimes.com",
+        "washingtonpost.com",
+        "wsj.com",
+        "economist.com",
+        "ft.com",
+        "theguardian.com",
+        "aljazeera.com",
+        "npr.org",
+        "pbs.org",
+        "abcnews.go.com",
+        "cbsnews.com",
+        "nbcnews.com",
+        "cnn.com",
+        "usatoday.com",
+        "latimes.com",
+        "chicagotribune.com",
+        "bostonglobe.com",
+        "politico.com",
+        "thehill.com",
+        "bloomberg.com",
+        "cnbc.com",
+        "time.com",
+        "newsweek.com",
+        "theatlantic.com",
+        "newyorker.com",
+        "propublica.org",
+        "theintercept.com",
+        "foreignaffairs.com",
+        "foreignpolicy.com",
+        "deseret.com",
+        "dw.com",
+        "france24.com",
+        "scmp.com",
+        "abc.net.au",
+        "cbc.ca",
+        "rte.ie",
+        "irishtimes.com",
+        "smh.com.au",
+        "nzherald.co.nz",
+        "japantimes.co.jp",
+        "haaretz.com",
+        "jpost.com",
+        "timesofisrael.com",
+        "hindustantimes.com",
+        "thehindu.com",
+        "scientificamerican.com",
+        "newscientist.com",
+        "nationalgeographic.com",
+        "smithsonianmag.com",
+        "popsci.com",
+        "livescience.com",
+        "sciencenews.org",
+        "theconversation.com",
+        "semafor.com",
+        "axios.com",
+        "themarkup.org",
+        "restofworld.org",
+        "defector.com",
+        "theinformation.com"
+    ]
+}

proof_citations-1.33.0/src/proof_citations/data/reference_domains.json

@@ -0,0 +1,44 @@
+{
+    "_comment": "Established reference sources, encyclopedias, major data aggregators, and known-good government data republishers. Tier 3 (established reference).",
+    "known_domains": [
+        "en.wikipedia.org",
+        "wikipedia.org",
+        "britannica.com",
+        "merriam-webster.com",
+        "dictionary.com",
+        "encyclopedia.com",
+        "plato.stanford.edu",
+        "investopedia.com",
+        "webmd.com",
+        "mayoclinic.org",
+        "clevelandclinic.org",
+        "statista.com",
+        "tradingeconomics.com",
+        "macrotrends.net",
+        "ourworldindata.org",
+        "gapminder.org",
+        "wolframalpha.com",
+        "mathworld.wolfram.com",
+        "khanacademy.org",
+        "coursera.org",
+        "rateinflation.com",
+        "inflationdata.com",
+        "measuringworth.com",
+        "usinflationcalculator.com",
+        "multpl.com",
+        "fred.stlouisfed.org",
+        "minneapolisfed.org",
+        "bea.gov",
+        "numbeo.com",
+        "countryeconomy.com",
+        "officialdata.org",
+        "brainfacts.org",
+        "simplypsychology.org",
+        "physicsworld.com",
+        "sciencebasedmedicine.org",
+        "amnh.org",
+        "burkemuseum.org",
+        "snopes.com",
+        "factcheck.org"
+    ]
+}

proof_citations-1.33.0/src/proof_citations/data/unreliable_domains.json

@@ -0,0 +1,54 @@
+{
+    "_comment": "Known unreliable, fake news, conspiracy, or junk science domains. Tier 1 (flagged unreliable). Sourced from OpenSources, Iffy.news, and Wikipedia Perennial Sources (deprecated/generally unreliable). This is intentionally a conservative list — only domains with broad consensus on unreliability.",
+    "known_domains": [
+        "infowars.com",
+        "naturalnews.com",
+        "beforeitsnews.com",
+        "globalresearch.ca",
+        "zerohedge.com",
+        "breitbart.com",
+        "dailycaller.com",
+        "thegatewaypundit.com",
+        "oann.com",
+        "newsmax.com",
+        "rt.com",
+        "sputniknews.com",
+        "tass.com",
+        "presstv.ir",
+        "globalresearch.ca",
+        "collective-evolution.com",
+        "davidicke.com",
+        "mercola.com",
+        "greenmedinfo.com",
+        "activistpost.com",
+        "lewrockwell.com",
+        "worldtruth.tv",
+        "yournewswire.com",
+        "neonnettle.com",
+        "newspunch.com",
+        "theepochtimes.com",
+        "dailywire.com",
+        "occupydemocrats.com",
+        "bipartisanreport.com",
+        "palmerreport.com",
+        "addictinginfo.com",
+        "conservativetribune.com",
+        "freedomdaily.com",
+        "worldnewsdailyreport.com",
+        "empirenews.net",
+        "nationalreport.net",
+        "huzlers.com",
+        "theonion.com",
+        "babylonbee.com",
+        "clickhole.com",
+        "borowitz.com",
+        "waterfordwhispersnews.com"
+    ],
+    "satire_domains": [
+        "theonion.com",
+        "babylonbee.com",
+        "clickhole.com",
+        "borowitz.com",
+        "waterfordwhispersnews.com"
+    ]
+}