{ "schema_version": 1, "collection": "reference-lists", "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/reference-lists.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", "/lists/*/citations/*/graph_edges/*/source_snapshot", "/observed_at" ], "publisher-words": [ "/lists/*/heading", "/lists/*/number", "/lists/*/marker_form", "/lists/*/entries/*/marker", "/lists/*/entry_not_read/marker", "/lists/*/citations/*/printed", "/lists/*/citations/*/quote", "/lists/*/citations/*/entry", "/headings_not_read/*/heading" ], "entry": [ "/lists/*/citations/*/designator", "/lists/*/citations/*/graph_edges/*/designator" ], "computed": [ "/derivation_version", "/derived_on", "/state", "/lists/*/at", "/lists/*/anchor_state", "/lists/*/read_to", "/lists/*/entries", "/lists/*/entry_not_read", "/lists/*/citations", "/lists/*/not_taken", "/lists/*/entries/*/at", "/lists/*/entries/*/end", "/lists/*/entry_not_read/at", "/lists/*/citations/*/at", "/lists/*/citations/*/quote_at", "/lists/*/citations/*/entry_at", "/lists/*/citations/*/anchor_state", "/lists/*/citations/*/graph_edges", "/lists/*/not_taken/*/count", "/lists/*/not_taken/*/at", "/headings_not_read/*/at", "/list_count", "/citation_count", "/citations_held_by_graph", "/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", "/lists/*/anchor", "/lists/*/citations/*/to", "/lists/*/citations/*/anchor", "/rights_of", "/source" ], "statement": [ "/why", "/lists/*/anchor_withheld", "/lists/*/entry_not_read/why", "/lists/*/citations/*/anchor_withheld", "/lists/*/not_taken/*/why", "/headings_not_read/*/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": "/lists/*/heading", "holds": "whole" }, { "pointer": "/lists/*/number", "holds": "whole" }, { "pointer": "/lists/*/marker_form", "holds": "whole" }, { "pointer": "/lists/*/entries/*/marker", "holds": "whole" }, { "pointer": "/lists/*/entry_not_read/marker", "holds": "whole" }, { "pointer": "/lists/*/citations/*/printed", "holds": "whole" }, { "pointer": "/lists/*/citations/*/quote", "holds": "whole" }, { "pointer": "/lists/*/citations/*/entry", "holds": "whole" }, { "pointer": "/headings_not_read/*/heading", "holds": "whole" } ] } }, "population": "one item per (tracked row, content hash) named by an observation, under the current derivation version", "store_read_from": "state/reference-lists.jsonl", "store_read": true, "method_read_from": "state/reference-lists-method.jsonl", "graph_read_from": "state/citations.json", "graph_read": true, "derivation": { "version": "reference-lists/79d8a041a1e6", "first_derived_on": "2026-10-28", "rule_text": "L1 HEADING. A heading is one of HEADINGS, in the case it is listed in, printed\n directly after a section number of the text's own and one space. A section\n number is an arabic number of one to three digits, with or without a\n trailing dot, or such numbers joined by dots (\"8\", \"8.\" or \"4.2\"); an\n upper-case roman numeral with a dot (\"IV.\"); or \"Appendix\" or \"Annex\", in\n either of their listed cases, with a label and a dash or a colon. So a\n draft's line number or a page number printed directly before a listed\n heading is read as a section number. The heading is followed by one\n whitespace character and then a capital letter, a digit, an opening square\n bracket or an entry marker; a bracketed number (\"(11)\") between them is\n passed over. A heading form followed by a run of dots (a table of\n contents) or by a lower-case word (\"References to the repealed\n Directive\") is not a heading.\nL2 ENTRIES. A heading is read as a list only where its first entry marker\n follows it, with at most LINE_NUMBERS_MAX bare numbers between them (the\n line numbers a draft prints). An entry marker is \"1.\" for a numbered list,\n or one of BULLETS. Each later entry is the next marker of the same form\n (\"2.\" after \"1.\"; the same bullet), printed after whitespace and followed\n by a space, within ENTRY_MAX code points of the marker before it. An entry\n runs from its marker to the next marker. The list ends at the first entry\n after which no next marker is found, and THAT LAST ENTRY IS NOT READ: the\n text prints no mark where it ends, so where a later passage begins is not\n a thing the text states. It is counted, and named, as not read.\n A heading whose first entry marker is not found is listed under\n `headings_not_read`, with that reason, and nothing after it is read.\nL3 NAMES. Inside each entry read, after its marker, every designator that\n `designator_rules()` admits is matched as the citation graph matches it:\n the form as published, any case, no word character on either side,\n LONGEST FIRST so a span is consumed by the most specific form, never the\n citing document's own forms, and a concept-titled form only where another\n form of the same document is printed within the citation graph's radius.\n The furniture test (`content_region.is_evidence()`), the letter-run test\n (`citations.words_lost()`) and the radius are applied as the graph applies\n them: on the span `citations.quote_at()` gives, over the text with every\n whitespace run made one space. A match one of them refuses is not taken,\n and is counted by that reason with its offset. A span already consumed is\n not matched again. The graph's outlier hold is not applied here: it is a\n property of the graph's whole edge set, and `scripts/citations.py` applies\n it to every edge it takes from this store.\nL4 CONTEXT. The served quote is whole whitespace-delimited words around the\n match, its own words included, at most the quote cap, centred on it, by\n `concordance_fulltext.context()`, read WITHIN THE MATCH'S ENTRY (from its\n marker to the next), so it never holds another entry's words; byte-exact\n at `quote_at`. A match whose served quote is itself furniture or holds a\n letter run too long to be a word is not taken, and is counted.\nL5 ANCHOR. A heading's clause anchor is read from the clause-anchor store by\n `concordance_fulltext.anchor_for()`: the last heading those rules read at\n or before the offset; its id where placed, no id where it is withheld or\n where none is read before it. A MATCH IS PLACED WHERE ITS LIST IS: it\n carries its list's anchor, because an entry number the clause-anchor rules\n read as a heading (\"10.\" in a numbered list) is an entry of this list and\n not a clause the match is printed under.\nL6 OVERLAP. A heading printed at or after a list's heading and before the\n marker of that list's last entry (the entry not read) is not read again.\n A heading printed inside that last entry is read.", "rules": { "bullets": [ "•", "−" ], "entry_marker_pattern": "(?<=\\s)N\\.(?= )", "entry_max": 600, "heading_pattern": "((?:(?