Seventh Lexis 360 intake (97 briefings, source Stands 2026-06 to
2026-08), extending the corpus to 374 curated entries in 56 clusters.
This batch opens five further briefings chapters ('Urlaub &
Karenzierung', 'Schwangerschaft & Elternkarenz', 'Krankenstand &
Arbeitsunfall', 'Dienstverhinderung', 'Ausserhalb des Betriebs-
standortes'; ten chapters in total now).
- 16 new clusters: urlaub (14), krankenstand (9), grenzeinsatz grz
(8: Ausland/Entsendung/Standortverlegung), karenzsonderformen
(7: Bildungs-/Hospiz-/Pflegekarenz), elternteilzeit (6), karenz
(6), kinderbetreuungsgeld (6), praesenzdienst (6), telearbeit
(6), mutterschutz msf (5: Schutzfristen/Wochengeld), dienst-
verhinderung dvh (4, incl. Streik), arbeitskraefteueberlassung
(2, AUEG), entgeltfortzahlung an Feiertagen efz (2), papamonat
(2), pflegefreistellung (2), wiedereingliederung (2); existing
clusters extended: arbeitnehmerschutz 12 -> 16 (Arbeitsunfall/
Berufskrankheit), schwangerschaft 1 -> 7
- documented gaps closed: Bildungskarenz (kzs), Abfertigung Alt
(lb-kar-01), Entgeltfortzahlung an Feiertagen (lb-efz-01/02),
Gefahrenevaluierung und Arbeitsverbote (lb-sch-04), Telearbeit
(tel cluster)
- three truncated duplicate export filenames (auslandstatigkeit_
sv_tatigkeit_in x3) renamed explicitly before extraction
- cross-batch reconciliations: lb-sch-01's Gefahrenevaluierung gap
now fully closed (-> lb-sch-04), lb-tzb-02's open Bildungskarenz
reference resolved (-> lb-kzs-01; terminology conflict with the
tzb briefing flagged for RIS)
- frontmatter fixes: seven entries of a stalled first curation
pass used invented topic values (papamonat-und-familienzeit-
bonus, geburt-schutzfrist, wochengeld) -> normalized to the
schema values (familienzeit, schutzfrist)
- flagged: asc-15 worked example draws a 42-day contingency
(1st-service-year pattern) against its own stage table (56
days), aug paragraph garble ('11503/1503 Abs 30 ABGB', likely
1153 Abs 30), grz-08 OGH follow-duty case law vs. explicit
source criticism, efz-01 36-hours compensatory time off,
dvh-04 pay claims of non-striking employees unsettled per
source
- note: the first curation pass stalled at 82/97 (no progress
from 14:43); the remaining 15 entries (asc-13..16, dvh/efz/pfl,
grz-08, aug) were re-run by three fresh parallel agents after
the user canceled the stuck one
Move the licensed PDF exports and the Layer-1 full texts from the
project root into the dot directory .lexis360/, keeping the root
listing to versioned content plus the tool checkouts.
The location also encodes provenance, distinct from .firecrawl/:
.lexis360/ holds user-supplied licensed exports that cannot be
re-fetched by an agent - if missing, stop and ask the user
(documented in MEMORY), whereas .firecrawl/ remains the home of
reconstructible web fetches.
- plain move of the unversioned directory (batch2/ subfolder spotted
and left untouched for its own intake run)
- .gitignore, tool constants/messages, source.pdf/source.text
frontmatter paths of all 55 curated entries, README/RUNBOOK/MEMORY
mentions; kb.json/INDEX.md regenerated
- batch 2 (53 PDFs) recorded in MEMORY as staged in .lexis360/batch2/
Validated end to end: --extract 55/55 with stable ids, --registry
55 entries/6 clusters, --check 0 problems (every frontmatter path
resolves at the new location), no stale path references remain.
Curated knowledge base from the first batch of Lexis 360 PDF exports
(LexisNexis "Lexis Briefings Personalrecht", 55 documents, source
Stands 2024-03 to 2026-09). Purpose: development reference alongside
RECHTSQUELLEN-*.md and a retrieval-ready corpus for a future
question-answering copilot.
Licensing split (decision D1): the PDF exports and the extracted full
texts stay local and unversioned (Lexis360/ gitignored, like
.firecrawl/); only the curation in own words with short quotes and
source citations is versioned.
- wissensbasis/dokumente/: one curated entry per briefing (55) with
approved frontmatter (frozen lb-<cluster>-<nn> ids, English
structural keys, German values, stand YYYY-MM, ASCII topic/tags
slugs) and sections Zusammenfassung, Kernwerte & Fristen (Stand
marked), Rechtsgrundlagen (only citations actually in the source,
verified/plausible/open marks), Payroll-Relevanz (Odoo), Verweise
- clusters: altersteilzeit 15, lehrlinge 15, jugendliche 7,
ferialpraktikanten 4, beschaftigungsformen 8, teilzeit 6
- kb.json + INDEX.md: generated from the frontmatter by --registry
(single source of truth, schema-validated)
- tools/build_lexis_kb.py: stdlib-only pipeline - --extract
(pdftotext, breadcrumb/stand parsing incl. dossier-style exports
with wrapped breadcrumbs), --registry (frontmatter validation:
required keys, id pattern, id prefix vs topic, stand format,
dangling cross_refs), --check (layer 1 <-> layer 2 completeness);
ids are frozen across batches, numbers never reused
- RUNBOOK.md: batch intake workflow, validation steps, known
limitations
Corpus contradictions flagged in the entries (not silently resolved):
AMS replacement rate for blocked Altersteilzeit 2026 (lb-atz-07 28.5%
vs lb-atz-09/12 27.5%), DAG limit 2023 (751.36 vs 751.37 EUR),
Kurzarbeit for Lehrlinge (lb-leh-11 vs lb-leh-07); lehrlinge cluster
partly older Stands (2024-03/2025-08).
Validated: extract 55/55, registry 55 entries/6 clusters, check 0
problems, structural scan of all 55 curated entries, py_compile.
fegger