{
  "lab": "EasyxLab",
  "publisher": "EasyByte Hub S. Coop. Mad.",
  "generated": "2026-10-03",
  "licence": "CC BY 4.0",
  "findings": [
    {
      "id": "S17",
      "title": "High-value datasets on data.europa.eu: what a machine sees, and what Member States say",
      "question": "What does a machine see about the EU's high-value datasets on data.europa.eu, and does it match what Member States report?",
      "headline": "On 2026-10-03, 28 months after the rules became applicable, the European data portal identified no high-value dataset for 7 of the 27 Member States, 3 of which had told the 2025 Open Data Maturity survey that their portal uses the DCAT-AP HVD tag; another 13,948 records (12,062 distinct datasets) carried an HVD category without the legal reference the portal needs to count them.",
      "figure": "7 of the 27",
      "label": "Member States for which the European data portal identifies no high-value dataset",
      "n": "27 Member States, 27,972 HVD records",
      "topics": [
        "open-data",
        "public-sector"
      ],
      "scope": "eu",
      "stage": "draft",
      "published": "2026-10-03",
      "updated": "2026-10-03",
      "url": "https://easybyte.es/lab/studies/s17/",
      "source": "https://github.com/easybytehub/easyxlab/tree/main/studies/s17-high-value-datasets",
      "paper": "https://easybyte.es/lab/studies/s17/paper/",
      "pdf": "https://easybyte.es/lab/studies/s17/paper.pdf"
    },
    {
      "id": "S11",
      "title": "Do the registration numbers on Airbnb listings exist in the official registries? Spain and New York around 20 May 2026",
      "question": "Do the registration numbers on Airbnb listings exist in the official registries?",
      "headline": "In June 2026, in five Spanish areas with an open registry, 2,066 of 31,222 listings showing a well-formed tourist-dwelling number (6.6%) showed one we could not trace to any registered dwelling; a further 557 (1.8%) showed a registered dwelling written in a recognisable wrong form.",
      "figure": "6.6%",
      "label": "of Airbnb listings in five Spanish areas with a well-formed tourist-dwelling number show one we could not trace to any registered dwelling",
      "n": "2,066 of 31,222",
      "topics": [
        "housing",
        "open-data"
      ],
      "scope": "es",
      "stage": "draft",
      "published": "2026-10-03",
      "updated": "2026-10-03",
      "url": "https://easybyte.es/lab/studies/s11/",
      "source": "https://github.com/easybytehub/easyxlab/tree/main/studies/s11-str-registration-numbers",
      "paper": "https://easybyte.es/lab/studies/s11/paper/",
      "pdf": "https://easybyte.es/lab/studies/s11/paper.pdf"
    },
    {
      "id": "S10",
      "title": "Past the static deadlines: NeTEx on five European access points, checked against open schemas",
      "question": "Are the public-transport NeTEx timetables on Europe's national access points valid against the open schemas?",
      "headline": "8 of 34 timetable datasets from five national access points are fully valid against the NeTEx XSD, all of them French; the static MMTIS deadlines passed in 2019–2025, and the 1 December 2026 date covers parking and vehicle sharing, not timetables.",
      "figure": "8 of 34",
      "label": "timetable datasets from five European national access points are fully valid against the NeTEx XSD, all of them French",
      "n": "34 datasets, 5 access points",
      "topics": [
        "transport",
        "open-data"
      ],
      "scope": "eu",
      "stage": "draft",
      "published": "2026-10-03",
      "updated": "2026-10-03",
      "url": "https://easybyte.es/lab/studies/s10/",
      "source": "https://github.com/easybytehub/easyxlab/tree/main/studies/s10-netex-naps",
      "paper": "https://easybyte.es/lab/studies/s10/paper/",
      "pdf": "https://easybyte.es/lab/studies/s10/paper.pdf"
    },
    {
      "id": "S8",
      "title": "What can a machine verify on Spain's public-sector websites?",
      "question": "What can a machine verify on Spain's public-sector websites?",
      "headline": "Of 5,130 public-sector home pages served over HTTPS, 1,688 (32.9%) send HSTS; of 5,570 entities, 4 serve a security.txt that is strictly valid under RFC 9116.",
      "figure": "32.9%",
      "label": "of Spain's public-sector home pages on HTTPS send HSTS",
      "n": "1,688 of 5,130",
      "topics": [
        "public-sector",
        "web-security"
      ],
      "scope": "es",
      "stage": "draft",
      "published": "2026-10-03",
      "updated": "2026-10-03",
      "url": "https://easybyte.es/lab/studies/s8/",
      "source": "https://github.com/easybytehub/easyxlab/tree/main/studies/s8-spanish-public-sector-web",
      "paper": "https://easybyte.es/lab/studies/s8/paper/",
      "pdf": "https://easybyte.es/lab/studies/s8/paper.pdf"
    },
    {
      "id": "S7",
      "title": "Do Google's AI Overviews and AI Mode keep up with Spanish rule changes? About one answer in twenty did not",
      "question": "Do Google's AI Overviews and AI Mode keep up with Spanish rule changes?",
      "headline": "Judged against the consolidated law in force on 2 October 2026, 12 of 240 AI Overview answers (5.0%) and 13 of 291 AI Mode answers (4.5%) on 27 recently changed rules were outdated or wrong.",
      "figure": "5.0%",
      "label": "of Google AI Overview answers on recently changed Spanish rules were outdated or wrong",
      "n": "12 of 240",
      "topics": [
        "ai-and-search"
      ],
      "scope": "es",
      "stage": "draft",
      "published": "2026-10-03",
      "updated": "2026-10-03",
      "url": "https://easybyte.es/lab/studies/s7/",
      "source": "https://github.com/easybytehub/easyxlab/tree/main/studies/s7-aio-spanish-regulation",
      "paper": "https://easybyte.es/lab/studies/s7/paper/",
      "pdf": "https://easybyte.es/lab/studies/s7/paper.pdf"
    },
    {
      "id": "S6",
      "title": "Do AI-generated images on Wikimedia Commons carry provenance marks?",
      "question": "Do AI-generated images on Wikimedia Commons carry provenance marks?",
      "headline": "Files with a machine-readable AI mark rose from 25.8% of January–May 2026 uploads to 50.2% of June–July uploads; our own validator, ai-mark-lint 0.1.0, wrongly rejected 187 valid C2PA manifests (fixed in 0.1.1).",
      "figure": "50.2%",
      "label": "of AI images uploaded to Wikimedia Commons in June–July 2026 carry a machine-readable AI mark",
      "n": "313 uploads",
      "topics": [
        "ai-provenance"
      ],
      "scope": "global",
      "stage": "draft",
      "published": "2026-10-03",
      "updated": "2026-10-03",
      "url": "https://easybyte.es/lab/studies/s6/",
      "source": "https://github.com/easybytehub/easyxlab/tree/main/studies/s6-commons-ai-marks",
      "paper": "https://easybyte.es/lab/studies/s6/paper/",
      "pdf": "https://easybyte.es/lab/studies/s6/paper.pdf"
    },
    {
      "id": "S5",
      "title": "Who publishes attestations on PyPI and npm — and who stopped?",
      "question": "Who publishes PEP 740 attestations on PyPI and npm, and who stopped?",
      "headline": "The latest version is attested for 3,479 of 14,995 top PyPI projects (23.2%); 138 projects that once attested no longer do in the line pip installs, 96 of them after a change of publishing tool or workflow.",
      "figure": "23.2%",
      "label": "of the top PyPI projects attest their latest version",
      "n": "3,479 of 14,995",
      "topics": [
        "software-supply-chain"
      ],
      "scope": "global",
      "stage": "draft",
      "published": "2026-10-03",
      "updated": "2026-10-03",
      "url": "https://easybyte.es/lab/studies/s5/",
      "source": "https://github.com/easybytehub/easyxlab/tree/main/studies/s5-pypi-attestations",
      "paper": "https://easybyte.es/lab/studies/s5/paper/",
      "pdf": "https://easybyte.es/lab/studies/s5/paper.pdf"
    },
    {
      "id": "S4",
      "title": "Multilingual quality of drug names in Wikidata",
      "question": "How accurate are Wikidata's multilingual drug names?",
      "headline": "About 0.9% of 34,207 labels are wrong (a lower bound), concentrated in Urdu, Persian, Russian and Hindi; 135 proposed corrections, not applied.",
      "figure": "≈0.9%",
      "label": "of Wikidata's multilingual drug labels are wrong, a lower bound",
      "n": "34,207 labels",
      "topics": [
        "open-data"
      ],
      "scope": "global",
      "stage": "draft",
      "published": "2026-10-02",
      "updated": "2026-10-03",
      "url": "https://easybyte.es/lab/studies/s4/",
      "source": "https://github.com/easybytehub/easyxlab/tree/main/studies/s4-wikidata-drug-labels",
      "paper": "https://easybyte.es/lab/studies/s4/paper/",
      "pdf": "https://easybyte.es/lab/studies/s4/paper.pdf"
    },
    {
      "id": "S3",
      "title": "Do AI provenance marks survive common image, video and audio pipelines?",
      "question": "Do AI provenance marks (C2PA, IPTC, China's AIGC label) survive common image, video and audio pipelines?",
      "headline": "Every pixel or container rewrite removed the embedded C2PA manifest (124/124); editing one metadata field after signing left it present but invalid (6/6).",
      "figure": "124/124",
      "label": "pixel or container rewrites removed the embedded C2PA manifest",
      "n": "124 rewrites",
      "topics": [
        "ai-provenance"
      ],
      "scope": "global",
      "stage": "draft",
      "published": "2026-10-02",
      "updated": "2026-10-03",
      "url": "https://easybyte.es/lab/studies/s3/",
      "source": "https://github.com/easybytehub/easyxlab/tree/main/studies/s3-ai-marks-survival",
      "paper": "https://easybyte.es/lab/studies/s3/paper/",
      "pdf": "https://easybyte.es/lab/studies/s3/paper.pdf"
    },
    {
      "id": "S2",
      "title": "Spoofed AI crawlers",
      "question": "How much traffic that claims to be an AI or search crawler is real?",
      "headline": "39.3% of 16,548 claims on three small sites were spoofed; for user-initiated fetchers (ChatGPT-User, Claude-User, Perplexity-User…) 67.8%.",
      "figure": "39.3%",
      "label": "of requests claiming to be an AI or search crawler were spoofed",
      "n": "16,548 claims, 3 sites",
      "topics": [
        "ai-and-search",
        "web-security"
      ],
      "scope": "global",
      "stage": "draft",
      "published": "2026-10-02",
      "updated": "2026-10-03",
      "url": "https://easybyte.es/lab/studies/s2/",
      "source": "https://github.com/easybytehub/easyxlab/tree/main/studies/s2-spoofed-ai-crawlers",
      "paper": "https://easybyte.es/lab/studies/s2/paper/",
      "pdf": "https://easybyte.es/lab/studies/s2/paper.pdf"
    },
    {
      "id": "S1",
      "title": "Conformance of open-source Verifactu implementations",
      "question": "Do the XML records that open-source Verifactu implementations publish comply with Spain's rules?",
      "headline": "Of 35 files presented as valid records, 10 (28.6%) contain at least one error; the most frequent defect is a declared hash that does not match the record.",
      "figure": "28.6%",
      "label": "of the files presented as valid Verifactu records contain an error",
      "n": "35 files",
      "topics": [
        "tax-invoicing"
      ],
      "scope": "es",
      "stage": "draft",
      "published": "2026-10-02",
      "updated": "2026-10-03",
      "url": "https://easybyte.es/lab/studies/s1/",
      "source": "https://github.com/easybytehub/easyxlab/tree/main/studies/s1-verifactu-conformance",
      "paper": "https://easybyte.es/lab/studies/s1/paper/",
      "pdf": "https://easybyte.es/lab/studies/s1/paper.pdf"
    }
  ]
}