Swap archive and live URLs in recovered output

For any citation recovered via archive fallback, try_archive_fallback sets alt_request.source_url to the archive URL and stamps archive_of with the original unreachable live URL (crates/sp42-citation/src/citation/page.rs:231-255). This renderer uses archive_of as the URL to update the citation to and labels provenance.url as the live link, so recovered appendix lines tell reviewers to replace the citation with the dead URL while calling the actual archive the live link. Please render finding.provenance.url as the archive target and finding.archive_of as the live URL.

Useful? React with 👍 / 👎.

Gate panel-split copy on a real panel

For no-model disagreement findings, such as the book-lane book_searched_not_supported_outcome that records PanelAgreement::new(0, 0), this condition is true (0 * 2 <= 0) and the appendix says the review panel split even though no panel voted. That mislabels deterministic search-inside misses as low-confidence model disagreements; require a meaningful panel before applying the minority/no-majority annotation.

Useful? React with 👍 / 👎.

Distinguish failed book lookups from misses

When a skipped book ref comes from an Open Library transport failure, SkippedReason::BookSource is still used while the actual LookupFailed vs NotFound detail lives in report.book_resolutions. Rendering every BookSource skip as SKIPPED_BOOK_UNRESOLVED tells reviewers the identifier matched no usable catalog record even when the lookup never completed, so saved reports lose the failure disclosure and imply a catalog miss incorrectly.

Useful? React with 👍 / 👎.

Render book resolution outcomes

When a URL-less book citation resolves to an Open Library record but has no exact searchable scan, verify_page emits a SourceUnavailable/Unusable finding plus report.book_resolutions carrying the scan state (similar_only/none/unknown). This renderer only emits the finding buckets here and never renders a Books section, so that case becomes a generic unreadable-source line and the reviewer loses whether the book was resolved and why it could not be searched. Please render book_resolutions alongside the GA appendix’s book/offline section.

Useful? React with 👍 / 👎.

Match book lookup failures per source

Fresh evidence: the new fix keys failed lookups only by ref_id. extract_use_sites emits one BookUseSite per book source for a URL-less ref while reusing the same ref_id; if one cited book in that ref has LookupFailed and another has NotFound, both SkippedRef entries satisfy this contains(ref_id) check and the clean catalog miss is rendered as a tool failure. Join to the matching BookResolution (for example by ref id plus identifiers/order) before choosing the copy.

Useful? React with 👍 / 👎.

Avoid rewriting every failed unnamed ref as #1

When an extraction failure reason contains an unnamed cite id (for example extract_use_sites emits strings like ref cite_ref-64 has no resolvable claim text), this always calls ref_label(cite_id, 0). Numeric cite ids fall back to ordinal + 1, so any later failed unnamed ref is rendered as ref #1, pointing the reviewer at the wrong citation instead of the failing one.

Useful? React with 👍 / 👎.

Include identifiers for skipped book sources

When a single URL-less ref names multiple books, verify_book_use_site can produce multiple BookSource skips with the same ref_id, while the per-book identifiers are carried in SkippedRef.book_sources. This branch renders only the shared ref label plus generic failure/miss copy, so two failed/missed books in the same ref become indistinguishable and the appendix drops the only data that tells the reviewer which catalog lookup each line refers to. Include the book identifiers and/or cited page on BookSource skip lines.

Useful? React with 👍 / 👎.

Avoid using block indexes as ref numbers

When a skipped citation has an unnamed MediaWiki id such as cite_ref-9, this passes SkippedRef.block_ordinal into ref_label, but that field is the paragraph/block index from extraction, not the citation or use-site ordinal. For example, an anonymous non-URL ref in the first block renders as ref #1 even if the skipped ref id is cite_ref-9, so the GA appendix can point reviewers at the wrong citation; use block-anchored wording for skipped unnamed refs or carry the actual ref ordinal.

Useful? React with 👍 / 👎.

Remove pass/fail wording from lookup skips

When an Open Library transport error produces a BookSource skip, render_skipped_section emits this string, so the appendix contains the word failure. That violates the renderer's documented no pass/fail wording invariant for exactly the lookup-failed path that was added here, and it reintroduces verdict-sounding language for a tool transport problem; prefer neutral wording such as a lookup not completing or a tool limitation.

Useful? React with 👍 / 👎.

Stop treating punctuated unnamed refs as ref #1

Fresh evidence: page verification errors are formatted as verify failed for {ref_id}: {error}, so an unnamed id is seen here as cite_ref-64: because the tokenizer stops only at whitespace. The colon makes rest non-numeric, which sends the value through ref_label(cite_id, 0) and renders it as ref #1 instead of the block-anchored unnamed-ref label, so later failed anonymous refs are again misidentified; strip trailing punctuation or parse the numeric prefix before this check.

Useful? React with 👍 / 👎.

Render book-scan provenance on findings

When a book citation is verified through Internet Archive search-inside, the report sets finding.book_scan with scanned_page, cited_page, and note; this line reduces a supported book finding to just “quote located.” If whole-book search finds the passage on page 32 while the citation says page=42, the GA appendix loses that page-mismatch disclosure and makes an imprecise page citation look cleanly supported, so the book-scan details/note should be rendered on finding lines.

Useful? React with 👍 / 👎.

Avoid using block ordinal as a book ref number

Fresh evidence: the skipped-ref path now avoids this, but the Books consulted section still passes BookResolution.block_ordinal to ref_label as if it were the citation ordinal. For unnamed book refs such as cite_ref-9, a book cited in block 0 renders as ref #1 even when the actual citation marker is not #1, pointing reviewers at the wrong footnote; use block-anchored wording here too or carry the real use-site/ref ordinal.

Useful? React with 👍 / 👎.

Escape cited book pages in scan annotations

When a book citation's cited page differs from the scanned page, cited_page comes directly from the cite template and can contain arbitrary wikitext; this path formats it through book_scan_pages and later writes the returned annotation without escape_verbatim. A page value such as 42</nowiki>{{...}} would break out of the pasted appendix even though other verbatim fields are nowiki-escaped, so escape the cited page before putting it in the annotation.

Useful? React with 👍 / 👎.

Append book-scan notes outside supported lines

Fresh evidence: book_scan_annotation is now only appended in the dead-link, unreadable, and supported render paths. Book search-inside results can also land in this disagreement path, for example NoMatches creates a NotSupported finding with a book_scan.note of “searched, no matching passage”, and model Partial/NotSupported book findings carry scanned-vs-cited page provenance; those appendix lines currently drop the only disclosure that the book scan was searched and whether the cited page matched. Please append the book-scan annotation in the disagreement and unconfirmed render paths too.

Useful? React with 👍 / 👎.

Neutralize failure wording in extraction reasons

When a URL or book use-site verification errors, verify_page records BlockFailure.reason strings such as verify failed for {ref_id}: ... and book verify failed for ...; this line only rewrites cite IDs and then emits the reason verbatim. Those reports therefore produce GA appendix bullets containing failed, which breaks the renderer's no pass/fail wording guarantee and makes a tool error read like a citation verdict, so the reason should be mapped through neutral copy before rendering.

Useful? React with 👍 / 👎.

Scrub transport-failure wording from scan notes

When Internet Archive metadata or search-inside requests hit a transport error, prepare_book_grounding stores error.to_string() in book_scan.note, and HttpClientError formats those as transport failed: .... Appending that note verbatim here means dead/unreadable book lines can still leak banned failure wording despite the copy invariant; render these tool notes through neutral wording rather than the raw error string.

Useful? React with 👍 / 👎.

Escape derived ref names before emitting labels

When a named ref id contains markup-like characters, this returns that derived name directly (for example cite_ref-{{x}}_1-0 becomes a live ref "{{x}}" label), and every bucket writes the label into pasteable wikitext without escape_verbatim. Because ref names come from article content or saved report JSON while claims/quotes are explicitly escaped, a named ref with wikitext in its name can transclude or break the pasted appendix; encode or nowiki-wrap the derived name before returning the label.

Useful? React with 👍 / 👎.

Escape book identifier values

When render-report deserializes a saved PageVerificationReport, BookIdentifier variants are accepted from JSON directly, so values do not necessarily pass the constructor validation used by live extraction. These raw format! arms are later pasted into the GA wikitext for skipped book refs without escape_verbatim; a crafted saved report with an ISBN value like {{...}} would transclude or break markup even though claims and pages are nowiki-escaped. Escape the identifier value before returning the label.

Useful? React with 👍 / 👎.

Keep book scan outages out of dead-link bucket

When a resolved book's Internet Archive metadata/search-inside request cannot be reached, ground_resolved_book's BookGroundingPreparation::Unreachable arm creates a SourceUnavailable finding with book_scan provenance and a status-0 provenance; this branch then files it under DeadLink. In that scenario the GA appendix tells reviewers the citation link may be dead even though only the scan/search tool request failed, so route book-scan transport outages to the tool-limitation/book path instead of the dead-link bucket.

Useful? React with 👍 / 👎.

Escape the report title in the footer

When render-report renders a saved report, report.title is deserialized file data but is written directly into live italic wikitext here. A title/value containing wiki markup such as '' or {{...}} can break the footer formatting or transclude when the appendix is pasted, while the other verbatim report fields are nowiki-escaped; escape the title before appending it.

Useful? React with 👍 / 👎.

Keep book-scan outages out of the summary

When a resolved book's Internet Archive metadata/search request is unreachable, bucket_for now correctly routes the book_scan finding to the unreadable/tool-limitation bucket, but the summary still prints report.stats.source_unavailable_unreachable as dead links. tally_stats counts those status-0 book-scan outages as source_unavailable_unreachable, so the appendix can say there is a dead link even though the only outage was the scan/search tool request; derive the dead/unreadable counts with the same book-scan override used for buckets or adjust the stats before rendering.

Useful? React with 👍 / 👎.

Distinguish ungroundable exact scans

When Open Library reports an exact-edition scan but the scan identity could not be recovered (ScanAvailability.exact is non-empty and all ocaids are None), the references code deliberately keeps that as an exact item while groundable_scan() returns None. This condition treats it as if no exact scan exists, so with no similar items the Books consulted section says the book is “not scanned in the tool's catalog” even though the actual reason is that the reported exact scan could not be grounded; reviewers lose the correct explanation for why the citation was not searched.

Useful? React with 👍 / 👎.

Include identifiers for consulted books

When a resolved Open Library edition has no title (or two resolved cited books share the same title), this Books consulted line renders only (untitled book)/the title plus scan state, dropping the BookResolution identifiers and cited page that distinguish which book was actually consulted. In that scenario the appendix can contain indistinguishable book lines and gives the reviewer no way to map the scan-state disclosure back to the cited source; include the resolved/cited identifier and page here as the skipped-book section does.

Useful? React with 👍 / 👎.

Anchor unparseable skipped ref ids by block

Fresh evidence: sp42-parsoid preserves marker ids verbatim and its unnamed-ref fixture uses a non-numeric id like cite_ref-test-1 with no ref name. For skipped/book refs with that shape, this call passes ordinal 0 into ref_label; the parse misses the named-ref pattern and renders ref #1, even when the skipped citation is later in the article. Since these paths do not have a real use-site ordinal, parse-miss cite_ref-* labels should stay block-anchored instead of fabricating footnote #1.

Useful? React with 👍 / 👎.

Avoid attributing no-model book misses to the panel

When Internet Archive search-inside returns no matches, book_searched_not_supported_outcome creates a NotSupported finding with PanelAgreement::new(0, 0), so no model panel voted. This copy is still used for that finding and tells reviewers that “the panel found” no support, misrepresenting a deterministic book-search miss as a panel judgment; branch the wording for no-panel findings or avoid panel attribution here.

Useful? React with 👍 / 👎.

Use outage-specific copy for unreachable book scans

When ground_resolved_book hits BookGroundingPreparation::Unreachable, it emits a SourceUnavailable finding with book_scan and status 0, and bucket_for routes every book_scan finding into this unreadable path. In that scenario the appendix says the tool fetched the scan URL and read an unusable page, even though the metadata/search request never completed; render a separate book-scan outage message for book_scan + unreachable/status-0 findings.

Useful? React with 👍 / 👎.

Escape URLs before embedding external links

When a citation URL contains a literal ] in its query or fragment, writing as_str() inside MediaWiki's [url] syntax closes the external link early; for example, a saved report URL like https://example.test/?q=]''x would leave ''x as live wikitext in the pasted appendix. The same raw-URL pattern is used in the other buckets too, so route these through a wikitext-link escaping helper (at least percent-encode ]) before emitting them.

Useful? React with 👍 / 👎.