fix(review): address PR #16 code-review findings

#1 ingest: normalize the pinned caller id (_norm_cited_id) so a non-bare DOI caller cannot store a URL-form papers.id that defeats DQ-5 idempotency / the startswith(10.) recovery gates. #2 quality.section_label: collapse to a controlled bucket only for an EXACT canonical heading; descriptive titles ('Abstract Nonsense...') keep their real title instead of being mislabelled. #4 ra_grobid_backfill: release the read connection before the slow GROBID network loop, fresh connection for the write (no idle-in-transaction across the loop over the flaky tunnel).

#5/#10 tex: flatten_inputs strips unresolved input/include at the depth cap (no literal leak on cycles); _norm_texkey strips only a single leading ./ . #6/#7 arxiv.fetch_source: keep non-.tex members resolvable for input; pick primary on an UN-commented documentclass line. #13 is_arxiv_id: also exclude http:// and arXiv-DOI forms. Tests added/updated for each.

Left as deliberate decisions: #3 (pre-section text drop is pre-existing in extract_sections; abstract stored separately), #8 (script normalizer is intentionally self-contained, already documented), #9/#11/#12 (no current trigger / tightening the gzip heuristic would reject valid old LaTeX like documentstyle / title truncation is by design on a write-only column). ruff + mypy clean.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

scripts/ra_grobid_backfill.py

@@ -142,6 +142,10 @@ def main(argv: list[str] | None = None) -> int:
     pdf_dir = Path(args.pdf_dir)
     pdfs = {p.stem: p for p in pdf_dir.glob("*.pdf")}
 
+    # Read the target list in a short-lived connection, then release it: the GROBID
+    # extraction below is a slow per-paper network loop and must NOT hold an
+    # idle-in-transaction connection open across it (a mid-loop SSH-tunnel drop would
+    # otherwise abort the whole batch — see docs/infra/jetson-ssh-stability.md).
     with get_conn() as conn:
         rows = conn.execute(
             """
@@ -152,46 +156,49 @@ def main(argv: list[str] | None = None) -> int:
             """
         ).fetchall()
 
-        targets: list[tuple[str, Path]] = []
-        for r in rows:
-            if args.only and r["id"] != args.only:
-                continue
-            if args.zero_edge_only and r["out_edges"] != 0:
-                continue
-            stem = Path(r["source_path"]).stem if r["source_path"] else None
-            pdf = pdfs.get(stem) if stem else None
-            if pdf is None:
-                logger.warning("no PDF for %s (stem=%s) — skipping", r["id"], stem)
-                continue
-            targets.append((r["id"], pdf))
-        if args.limit is not None:
-            targets = targets[: args.limit]
+    targets: list[tuple[str, Path]] = []
+    for r in rows:
+        if args.only and r["id"] != args.only:
+            continue
+        if args.zero_edge_only and r["out_edges"] != 0:
+            continue
+        stem = Path(r["source_path"]).stem if r["source_path"] else None
+        pdf = pdfs.get(stem) if stem else None
+        if pdf is None:
+            logger.warning("no PDF for %s (stem=%s) — skipping", r["id"], stem)
+            continue
+        targets.append((r["id"], pdf))
+    if args.limit is not None:
+        targets = targets[: args.limit]
 
-        logger.info(
-            "GROBID=%s | papers to process=%d | mode=%s",
-            grobid_url,
-            len(targets),
-            "WRITE" if args.write else "DRY-RUN",
-        )
+    logger.info(
+        "GROBID=%s | papers to process=%d | mode=%s",
+        grobid_url,
+        len(targets),
+        "WRITE" if args.write else "DRY-RUN",
+    )
 
-        all_citations: list[Citation] = []
-        for paper_id, pdf in targets:
-            try:
-                cits = build_grobid_citations(
-                    paper_id, pdf, grobid_url=grobid_url, timeout=args.timeout
-                )
-            except Exception as exc:
-                logger.warning("GROBID extraction failed for %s (%s): %s", paper_id, pdf.name, exc)
-                continue
-            logger.info("%-38s %3d refs  (%s)", paper_id, len(cits), pdf.name)
-            all_citations.extend(cits)
+    # GROBID extraction — no DB connection held during this slow network loop.
+    all_citations: list[Citation] = []
+    for paper_id, pdf in targets:
+        try:
+            cits = build_grobid_citations(
+                paper_id, pdf, grobid_url=grobid_url, timeout=args.timeout
+            )
+        except Exception as exc:
+            logger.warning("GROBID extraction failed for %s (%s): %s", paper_id, pdf.name, exc)
+            continue
+        logger.info("%-38s %3d refs  (%s)", paper_id, len(cits), pdf.name)
+        all_citations.extend(cits)
 
-        logger.info("total candidate citations: %d", len(all_citations))
+    logger.info("total candidate citations: %d", len(all_citations))
 
-        if not args.write:
-            logger.info("DRY-RUN — no rows written. Re-run with --write to apply.")
-            return 0
+    if not args.write:
+        logger.info("DRY-RUN — no rows written. Re-run with --write to apply.")
+        return 0
 
+    # Fresh connection for the write — the read connection was already released.
+    with get_conn() as conn:
         before = _coverage(conn)
         with conn.cursor() as cur:
             cur.executemany(
@@ -204,15 +211,15 @@ def main(argv: list[str] | None = None) -> int:
             )
         conn.commit()
         after = _coverage(conn)
-        logger.info(
-            "coverage papers=%d  citing %d->%d  edges %d->%d (+%d)",
-            after[0],
-            before[1],
-            after[1],
-            before[2],
-            after[2],
-            after[2] - before[2],
-        )
+    logger.info(
+        "coverage papers=%d  citing %d->%d  edges %d->%d (+%d)",
+        after[0],
+        before[1],
+        after[1],
+        before[2],
+        after[2],
+        after[2] - before[2],
+    )
     return 0