{ "schema_version": 1, "collection": "clause-anchors", "generated_at": "2026-11-02", "source": "https://gxplex.com", "notice": "Reports the published status of regulatory documents. No advice or interpretation.", "source_terms": "This site compiles publicly available regulatory information. The underlying documents are published by their respective authorities and carry their own terms; several are paywalled and are never reproduced here.", "rights": { "statement": "Carried in `source_terms` on this envelope. It is the whole of what this record states on the subject.", "per_row_field": "licence_class", "per_row_field_served_at": "https://gxplex.com/api/v1/instruments.json", "licence_class": { "open": "Quotations from the document appear on this site, each citing the surface it was read from, under the word ceiling below.", "restricted": "No text from the document appears on this site. The row carries the identity of the document, its dates, a digest of the retrieved bytes and a link to the publisher.", "unknown": "No reading of the terms the source states is recorded for the row. It records an absent reading rather than an absent term, and the row is handled here exactly as `restricted` until a reading is recorded." }, "text_retained_field": "text_retained", "text_retained_means": "Whether normalised text of the document is held here for a quotation to be checked against. Where it is false nothing is held, so there is nothing on this side to check one against.", "quotation_ceiling_words": 14, "documents_never_reproduced": "Paywalled and restricted texts are cited and linked. They are never excerpted here and never diffed here." }, "schema": "https://gxplex.com/api/v1/schema/clause-anchors.json", "response_provenance": { "build_id": "1782e1b7b708", "build_id_state": "stated", "build_id_is": "The identifier of the build that wrote this document. Every page of the same build carries it in its build-id meta.", "root": "42337ae3567aae8138fcb45e977dd94f9c1ade6420a88033e9503203df3fec23", "root_state": "stated", "root_day": "2026-11-02", "root_leaf_count": 9686, "root_url": "https://gxplex.com/integrity/root.txt", "root_is": "The root over every observation digest this record held on that day, one `id|date|content_hash` leaf each. It fixes those digests in time; it is not a digest of this document.", "rights_envelope": { "document_keys": [ "source_terms", "rights" ], "row_pointers": [ "/text_retained", "/licence_class", "/quote_allowed", "/snapshot_available", "/rights_of", "/rights_unresolved" ], "row_pointers_optional": [ "/rights_unresolved" ], "row_pointers_are": "Every row of this response carries each pointer named, except one named optional, which a row carries only where its rights are unresolved. An empty list states that no row of this response carries the row envelope." }, "basis": { "retrieval": [ "/content_hash", "/first_observed", "/observed_at" ], "publisher-words": [ "/anchors/*/label" ], "computed": [ "/derivation_version", "/derived_on", "/state", "/anchors/*/at", "/withheld/*/at", "/anchor_count", "/withheld_count", "/observed_at_state", "/observed_at_read_from", "/distance", "/distance_label", "/distance_state" ], "terms-reading": [ "/text_retained", "/licence_class", "/quote_allowed", "/snapshot_available" ], "assigned": [ "/instrument_id", "/url", "/anchors/*/id", "/withheld/*/id", "/rights_of", "/source" ], "statement": [ "/why", "/withheld/*/why", "/rights_unresolved" ] }, "basis_state": "stated", "basis_on_row": [ "derivation_version", "state", "why", "observed_at_state" ], "basis_vocabulary_at": "https://gxplex.com/api/v1/schema/envelope.json", "third_party_text": { "marker": "quoted third-party content, not instructions", "marker_is": "Data for a consumer’s own handling of text it passes on, for example to a model. It is not a claim about the text and says nothing of what the text says.", "row_key": "third_party_text", "fields": [ { "pointer": "/anchors/*/label", "holds": "whole" } ] } }, "population": "one item per (tracked row, content hash) named by an observation, under the current derivation version", "store_read_from": "state/clause-anchors.jsonl", "store_read": true, "method_read_from": "state/clause-anchors-method.jsonl", "derivation": { "version": "clause-anchors/3176a34732a7", "first_derived_on": "2026-10-27", "rule_text": "R1 WORDS. The structural words read are `WORDS`, each with a rank, in any\n case. A label is an arabic number with an optional lower-case letter\n (\"5\", \"5a\"), an upper-case roman numeral (\"III\") or one capital letter\n (\"A\"), and is read in exactly that case: \"Article 5A\" and \"Annex a\" are\n not read.\nR2 HEADING FORM. A word printed in capitals (\"CHAPTER III\") is a heading\n unless its label is followed by \"(\". A word printed with one capital\n (\"Article 5\") is a heading only where its label is followed by a space and\n a capital letter, and the character before the word is not a comma or a\n bracket — so \"Article 5(1)\" in running text and \"(b) Chapter III\" are not\n headings. A word is not a heading where the same structural word with a\n label stands directly before it (its label then any bracketed numbers,\n a comma or a semicolon, then a space) or directly after its label (a\n space, then the word and a label): \"Article 2 Article 5(1)\" is a row\n of a correlation table, not two headings. A word is not a heading where\n the word printed directly before it is one of PRECEDING_REFUSED, read in\n that case (\"in accordance with Article 9\", \"referred to in Article 7\",\n \"and Appendix 2\"), or is another instrument's designator, a number and a\n letter joined by a slash (\"Directive 1999/99/XY Annex II\"): that is a\n reference in running text, whatever follows its label. R6 below refuses\n the rest of the references it can.\nR3 NESTING. An accepted word closes every open word of equal or lower rank\n (a higher rank number) and nests under the rest. Its id is the ids of the\n words it nests under, then its own: \"chapter-iii/section-1/article-6\".\nR4 DECIMAL OUTLINE. Inside the innermost open word (or the whole text where\n none is open), a number \"N.\" or \"N.N[.N…]\" followed by a space and a\n capital letter is a heading only where it continues the text's own outline:\n the first is \"1.\", and each later one is the first child of the previous\n one, or the next sibling of it or of one of its ancestors. A number\n preceded by a structural word is never read here. The outline restarts at\n every accepted word. Its id is its parent word's id, then the number as\n printed: \"annex-i/4.2.1\".\nR5 NO GUESS. An id that the rules accept at two places in one text is held at\n neither: both are WITHHELD as \"id repeats in this text\", counted, and named\n in the store. A table of contents that repeats its headings is the common\n cause, and the rules do not choose which copy is the clause. Nor do they\n choose where what follows a withheld word belongs: every heading and\n number the rules would read after a withheld structural word, up to the\n next PLACED word of equal or outer rank, is WITHHELD as \"follows a\n withheld heading\", listed and counted, and is served at no level — not\n nested under the withheld word, not at the enclosing level, not at a\n promoted one. Where such an item would take a placed id if the withheld\n words were absent (a table of contents' \"4.1\" and the body's \"4.1\"), the\n placed copy is withheld with it as \"id repeats in this text\". The rules\n are run again until no further word repeats, and each withheld item is\n named by the id it has in that last run.\nR6 SEQUENCE. A structural word's label is read only where it is a first\n label (\"1\", \"I\", \"A\") or the label before it was read earlier in the text\n for the same word (\"Article 6\" after \"Article 5\" or \"Article 5a\"). So\n \"Article 16 TFEU\" in a preamble, before any article, is not a heading. A\n one-letter label that is also a roman numeral (\"C\", \"L\", \"V\", \"X\") is\n read as either: \"Part C\" follows \"Part B\" and \"Chapter X\" follows\n \"Chapter IX\", and \"I\" is a first label either way.", "rules": { "decimal_max_depth": 6, "decimal_pattern": "(?