"""Audit fixed author tables and report aggregates, without publishing star rows.""" from pathlib import Path import argparse import collections import hashlib import json import numpy as np def read_benchmarks(path): result = [] lines = path.read_text().splitlines() data_start = max(index for index, line in enumerate(lines) if line.startswith('---')) + 1 for line in lines[data_start:]: if not line.strip(): continue assert 'Gaia DR2 ' in line, line prefix, remainder = line.split('Gaia DR2 ', 1) metadata = prefix.split() fields = remainder.split() assert fields[0].isdigit(), line # The author file's Ruprecht rows do not obey its advertised fixed widths. # Parse the explicit ID delimiter and eight terminal numeric columns; # validate every row instead of silently dropping parse failures. values = [float(value) for value in fields[-8:]] result.append({'cluster': ' '.join(metadata[:-2]), 'age_gyr': float(metadata[-2]), 'av_mag': float(metadata[-1]), 'source_id': 'Gaia DR2 ' + fields[0], 'teff_k': values[6], 'color0': values[3], 'period_days': values[7]}) assert all(row['age_gyr'] > 0 and row['period_days'] > 0 and row['teff_k'] > 0 and row['source_id'].startswith('Gaia DR2') for row in result) assert len(result) == len(set((row['cluster'], row['source_id']) for row in result)) return result def read_ruprecht(path): result = [] lines = path.read_text().splitlines() data_start = max(index for index, line in enumerate(lines) if line.startswith('---')) + 1 for line in lines[data_start:]: if not line.strip(): continue assert len(line) >= 606 and line[:28].strip(), line result.append({'source_id': line[:28].strip(), 'member': line[371:419].strip(), 'photometric_binary': line[420:423].strip(), 'wide_binary': line[424:427].strip(), 'spectroscopic_binary': line[428:437].strip(), 'teff_k': float(line[519:528]), 'period_days': float(line[548:559]), 'benchmark': line[587:606].strip()}) return result def main(): parser = argparse.ArgumentParser(description=__doc__) parser.add_argument('--inputs', type=Path, default=Path('inputs/curtis2020-source')) parser.add_argument('--output', type=Path, default=Path('results/cluster-sample-audit.json')) arguments = parser.parse_args() benchmark_path = arguments.inputs / 'Benchmark_Clusters.txt' ruprecht_path = arguments.inputs / 'Table_1-Ruprecht147_Catalog.txt' benchmarks = read_benchmarks(benchmark_path); ruprecht = read_ruprecht(ruprecht_path) naive_fixed_rows = 0 for line in benchmark_path.read_text().splitlines(): if len(line) < 144: continue try: [float(line[start:end]) for start, end in [(13,18),(19,24),(100,108),(127,134),(135,144)]] naive_fixed_rows += 1 except ValueError: continue # This deliberate failure reproducer does not feed the analysis. groups = [] for cluster in sorted(set(row['cluster'] for row in benchmarks)): stars = [row for row in benchmarks if row['cluster'] == cluster] groups.append({'cluster': cluster, 'rows': len(stars), 'fixed_age_gyr': sorted(set(row['age_gyr'] for row in stars)), 'fixed_av_mag': sorted(set(row['av_mag'] for row in stars)), 'temperature_range_k': [min(row['teff_k'] for row in stars), max(row['teff_k'] for row in stars)], 'period_range_days': [min(row['period_days'] for row in stars), max(row['period_days'] for row in stars)], 'temperature_bins': [{'range_k': [low, high], 'rows': len(selected), 'median_period_days': float(np.median([row['period_days'] for row in selected]))} for low, high in [(4200, 4500), (4500, 5000), (5000, 5500), (5500, 6000)] if (selected := [row for row in stars if low <= row['teff_k'] < high])]}) qualifying = [row for row in ruprecht if row['period_days'] > 0 and row['benchmark'] == 'Yes'] all_yes = [row for row in ruprecht if row['period_days'] > 0 and row['benchmark'].startswith('Yes')] authors_ruprecht = [row for row in benchmarks if row['cluster'] == 'Ruprecht 147'] source_names = {row['source_id'] for row in qualifying} benchmark_names = {row['source_id'] for row in authors_ruprecht} report = {'status': 'PASS delimiter/numeric-tail parsed author tables, positive units and unique IDs; all rows retained; exact selection flags reported', 'source_archive': 'https://arxiv.org/src/2010.02272v1', 'role': 'Local research inputs; explicit redistribution license unresolved, origin downloader route proposed', 'inputs': [{'member': path.name, 'bytes': path.stat().st_size, 'sha256': hashlib.sha256(path.read_bytes()).hexdigest()} for path in [benchmark_path, ruprecht_path]], 'author_format_warning': '35 Ruprecht rows violate the advertised fixed-width schema. Explicit Gaia DR2 delimiter plus eight numeric tail fields recover all923 rows; a naive fixed-width parser silently lost the entire old cluster.', 'naive_advertised_fixed_width_rows': naive_fixed_rows, 'recovered_rows_missing_from_naive_parser': len(benchmarks) - naive_fixed_rows, 'ruprecht_rows_without_gaia_identifier': sum(row['source_id'] == '...' for row in ruprecht), 'benchmark_rows': len(benchmarks), 'groups': groups, 'ruprecht_catalog_rows': len(ruprecht), 'ruprecht_benchmark_flags': dict(collections.Counter(row['benchmark'] for row in ruprecht)), 'ruprecht_period_positive_exact_yes': len(qualifying), 'ruprecht_period_positive_any_yes_prefix': len(all_yes), 'exact_yes_vs_figure12': {'exact_yes_ids': len(source_names), 'figure12_ids': len(benchmark_names), 'common_ids': len(source_names & benchmark_names), 'only_exact_yes': len(source_names - benchmark_names), 'only_figure12': len(benchmark_names - source_names)}, 'period_errors': 'Benchmark table gives periods without uncertainties; do not invent precise per-star Gaussian errors or count bootstrap scatter as absolute age accuracy', 'timing': 'Table entries are derived periods in days, not time-series epochs. Period timescale/reference-frame convention is not explicitly supplied here; raw K2/PTF cadence/exposure inference is not reproduced.'} arguments.output.parent.mkdir(parents=True, exist_ok=True) arguments.output.write_text(json.dumps(report, indent=2) + '\n') print(json.dumps(report, indent=2)) if __name__ == '__main__': main()