{
  "title_ro": "Inventarul public Moldoveni: fotografie tehnică din 1 noiembrie 2026",
  "site": "https://moldoveni.co.uk",
  "snapshot_date": "2026-11-01",
  "source_capture_started_utc": "2026-11-01T23:36:13.684734+00:00",
  "source_capture_finished_utc": "2026-11-01T23:42:15.222942+00:00",
  "first_included_page_observed_utc": "2026-11-01T23:36:15.073118+00:00",
  "last_included_page_observed_utc": "2026-11-01T23:41:38.860261+00:00",
  "input_sha256": "87290cf3113f6a8cace86962fac2802067e4e7eadd898800484e9a66ea1ba868",
  "sample": {
    "design": "Census of URLs in the captured public sitemap; not a random sample of UK adverts or a market survey.",
    "n_urls": 294,
    "n_advert_pages": 276,
    "n_articles": 8,
    "n_hubs_or_policy_pages": 10
  },
  "collection": "Recorded sequential public GET requests, approximately one request per 1.05 seconds. The source crawl also fetched bounded utilities and pagination, but only captured sitemap URLs enter this dataset. Redirects were not followed automatically.",
  "unit_of_analysis": "One public canonical sitemap URL observed at its recorded time.",
  "metrics": {
    "sitemap_urls": 294,
    "page_types": {
      "hub_or_policy": 10,
      "article": 8,
      "advert": 276
    },
    "http_statuses": {
      "200": 294
    },
    "http_200": 294,
    "single_h1": 294,
    "self_canonical": 294,
    "meta_description_present": 294,
    "title_present": 294,
    "jsonld_present": 294,
    "jsonld_syntax_valid": 294,
    "public_indexable_signal_recorded": 294,
    "click_depth_counts": {
      "0": 1,
      "1": 14,
      "2": 59,
      "3": 220
    },
    "maximum_observed_click_depth": 3,
    "advert_pages": 276,
    "advert_distinct_exact_titles": 226,
    "advert_repeated_title_groups": 26,
    "advert_pages_in_repeated_title_groups": 76,
    "advert_pages_in_repeated_title_groups_percent": 27.5,
    "advert_title_count_beyond_one_per_exact_string": 50,
    "advert_full_title_character_median": 36.0,
    "advert_click_depth_counts": {
      "2": 56,
      "3": 220
    }
  },
  "metric_definitions": {
    "title_present": "The parsed HTML title contains non-whitespace text. Presence is not a relevance or quality judgment.",
    "single_h1": "The source parser counted exactly one H1 in the returned HTML.",
    "self_canonical": "The canonical array is exactly the observed URL. This does not report the Google-selected canonical.",
    "meta_description_present": "At least one non-empty parsed meta description; no length or quality threshold.",
    "jsonld_present": "At least one parsed application/ld+json block; not proof of eligibility for a rich result.",
    "jsonld_syntax_valid": "Every recorded JSON-LD block parsed as JSON; not a schema semantics or Google validator result.",
    "public_indexable_signal_recorded": "The existing crawler recorded its public indexability signal as true. Not confirmation of actual Google or Bing indexing.",
    "observed_click_depth": "Minimum hyperlink distance from the homepage in the bounded public graph recorded by the source crawler. The graph includes fetched pagination/filter routes; the report rows include only sitemap URLs.",
    "exact_title_group_size_within_adverts": "Count of advert URLs with the exact same parsed full HTML title string, including brand suffix. Case and accents are preserved; no fuzzy matching. A repeat does not establish duplicate text, seller, transaction, fraud or offer.",
    "title_character_count": "Python Unicode character count of the parsed full HTML title, including the brand suffix. No recommended length threshold is imposed.",
    "title_sha256": "SHA-256 of the UTF-8 full parsed title. This enables exact duplicate aggregation without republishing advertiser names, titles or contact text."
  },
  "limitations": [
    "Historical observation from 1 November 2026, not a live inventory count or claim that an offer is still available.",
    "The 276 advert URLs are pages preserved in the public inventory, not 276 independently verified active opportunities.",
    "No advertiser identity, location, price, business licence, contact channel, media permission or offer availability was validated.",
    "No private accounts, messages, business records or user database were accessed for this dataset.",
    "No category-level market statistics: the public category mapping was incomplete and title-based category inferences would not be authoritative.",
    "Title repetitions alone cannot determine whether two adverts describe the same offer; no duplicate advert was deleted or rewritten.",
    "Shared templates influence metadata. Technical completeness is not a score of usefulness, accuracy, legal compliance, accessibility or Core Web Vitals.",
    "No UK-wide market, Moldovan population, demand, rent, wage, conversion, Google rank, traffic or backlink inference is supported.",
    "The later 23:45 UTC Self Assessment article correction and any 2 November continuation changes are outside this source capture. This dataset deliberately describes the earlier fixed snapshot.",
    "The frozen crawl and reproducibility script are retained in the site-maintenance handover. This public aggregate download records their fingerprints and method; fetching the live site later produces a different dated observation."
  ],
  "data_minimisation": "Public output contains aggregate counts, method, dates and source archive fingerprint only. No individual advert routes, raw titles, descriptions, names, contact details, photographs, account identifiers or emails are republished.",
  "proposed_public_context_url": "https://moldoveni.co.uk/surse#inventar-public-2026-11-01",
  "refresh_policy": {
    "next_review_proposed": "2027-11-01",
    "status": "Proposed editorial review date, not a scheduled automation or promise.",
    "method": "Publish each new snapshot with a new date and denominator; retain old versions and log any methodological changes."
  },
  "research_claim": "An original, reproducible descriptive measurement of the platform public pages. It is not proprietary field research, a representative market survey or one research dataset for each of the six pillars.",
  "dataset_scope": "Aggregate counts and methodology only; no row-level URLs, advertiser names, contact information, account information or advert bodies.",
  "method_version": "1.0",
  "method_sha256": "702f338846a07b8accc7d1265804808c5e7eaf875012a0c468922af1f178797c",
  "recalculation": "Select the 294 sitemap URLs in the frozen input crawl; classify paths /anunt/ as advert, /articol/ as article, others as hub_or_policy; count recorded fields. Group adverts by exact parsed full HTML title and count groups of size greater than one. No fuzzy matching, inferred categories or current-offer validation."
}
