1import duckdb, sys2con = duckdb.connect(sys.argv[1] + "/data/processed/wp44.duckdb", read_only=True)3q = lambda s: con.execute(s).fetchall()4print("2026 eligible by first_month:", q("select first_month, count(*) from corpus_works where eligible and publication_year=2026 group by 1 order by 1"))5print("2026 by type:", q("select type, count(*) from corpus_works where eligible and publication_year=2026 group by 1 order by 2 desc limit 6"))6print("2026 top sources:", q("select source_name, count(*) from corpus_works where eligible and publication_year=2026 group by 1 order by 2 desc limit 10"))7print("2025 top sources:", q("select source_name, count(*) from corpus_works where eligible and publication_year=2025 group by 1 order by 2 desc limit 10"))8print("2026 pub_date day-01 share:", q("select sum((substr(publication_date,9,2)='01')::int)*1.0/count(*) from corpus_works where eligible and publication_year=2026"))9print("2025 pub_date day-01 share:", q("select sum((substr(publication_date,9,2)='01')::int)*1.0/count(*) from corpus_works where eligible and publication_year=2025"))10print("2026 created_date months:", q("select substr(created_date,1,7), count(*) from corpus_works where eligible and publication_year=2026 group by 1 order by 1"))11print("other-type dblp sample:", q("select id, doi, source_name, publication_year, n_refs from corpus_works where in_dblp and type='other' limit 4"))12