Repository Public Research preview
1{2 "created_at": "2026-11-09T18:38:44Z",3 "git": {4 "commit": "e4eec911d74f1ec613a2572cb35afde77ec2bdcc",5 "branch": "main",6 "dirty": true7 },8 "libraries": {9 "python": "3.14.4",10 "torch": "2.12.0",11 "numpy": "2.5.4",12 "anthropic": "2.3.0",13 "transformers": "5.8.1",14 "sentencepiece": "0.2.2",15 "lxml": "6.1.3",16 "pyarrow": "24.0.0",17 "sacrebleu": "2.6.0",18 "datasketch": "2.0.0",19 "rapidfuzz": "3.14.6"20 },21 "hardware": {22 "platform": "macOS-27.0-arm64-arm-64bit-Mach-O",23 "machine": "arm64",24 "cpu_count": 18,25 "chip": "Apple M5 Max",26 "ram_gb": 48.0,27 "torch_mps": true,28 "torch_cuda": false29 },30 "script": "discover_books",31 "args": {32 "source": "gutenberg",33 "max_docs": 500,34 "max_attempts": 700,35 "seed": 2,36 "out": "data/raw/books",37 "codes": "CC0,PUBLIC-DOMAIN,CC-BY,CC-BY-SA,CC-BY-NC,CC-BY-NC-SA",38 "locc": "Q,R,T,H,G,B,L,Z",39 "max_mb": 25.0,40 "pool_only": false,41 "report": null42 },43 "stats": {44 "catalog_rows": 79769,45 "candidates": 7799,46 "attempted": 517,47 "downloaded": 500,48 "already_present": 0,49 "not_found": 5,50 "too_large": 3,51 "copyrighted_header": 9,52 "no_pd_header": 0,53 "no_date": 60,54 "date_from_frontmatter": 370,55 "date_from_death_year": 70,56 "errors": 0,57 "by_locc": {58 "RC": 23,59 "LT": 2,60 "QH": 11,61 "GT": 17,62 "HV": 13,63 "TD": 3,64 "BF": 26,65 "RS": 1,66 "LB": 28,67 "QA": 1,68 "GN": 11,69 "HS": 1,70 "TN": 3,71 "Z": 62,72 "QL": 13,73 "G": 32,74 "HX": 3,75 "TA": 3,76 "BJ": 14,77 "LD": 4,78 "TL": 6,79 "B": 19,80 "RZ": 2,81 "LA": 12,82 "QR": 1,83 "HD": 4,84 "TS": 3,85 "GC": 1,86 "HN": 3,87 "T": 16,88 "RM": 8,89 "QK": 5,90 "HE": 7,91 "R": 12,92 "QE": 6,93 "H": 2,94 "Q": 11,95 "RA": 12,96 "HQ": 13,97 "TJ": 4,98 "HF": 3,99 "TT": 9,100 "HM": 1,101 "TC": 1,102 "QP": 4,103 "HT": 2,104 "QC": 3,105 "HG": 4,106 "RG": 4,107 "TP": 5,108 "LF": 4,109 "HB": 2,110 "LC": 14,111 "TH": 2,112 "QB": 4,113 "HC": 2,114 "RJ": 2,115 "TK": 4,116 "BD": 3,117 "HJ": 1,118 "RD": 1,119 "BC": 1,120 "QD": 1,121 "TF": 1,122 "LH": 1,123 "HA": 1,124 "QM": 1,125 "GB": 1126 },127 "by_era": {128 "pre1900": 178,129 "1950-1979": 20,130 "1900-1949": 236,131 "unknown": 60,132 "1980-1999": 2,133 "2000-2009": 4134 },135 "by_date_rule": {136 "frontmatter:imprint": 164,137 "frontmatter:copyright": 140,138 "death_year": 70,139 "frontmatter:published": 41,140 "none": 60,141 "frontmatter:roman": 25142 },143 "pool_by_class": {144 "QH": 543,145 "QL": 491,146 "Z": 490,147 "BF": 372,148 "HV": 356,149 "B": 344,150 "HQ": 341,151 "G": 256,152 "BJ": 234,153 "Q": 202,154 "HD": 190,155 "RC": 190,156 "QC": 182,157 "QK": 180,158 "T": 167,159 "TT": 164,160 "QE": 161,161 "HE": 156,162 "QB": 139,163 "LB": 132,164 "TS": 130,165 "QA": 120,166 "RA": 112,167 "HX": 99,168 "GN": 99,169 "TL": 96,170 "TK": 89,171 "HF": 87,172 "RM": 84,173 "HB": 81,174 "GT": 81,175 "TP": 80,176 "QD": 78,177 "R": 77,178 "HG": 76,179 "TJ": 63,180 "HN": 62,181 "QP": 61,182 "HT": 55,183 "LC": 55,184 "TA": 50,185 "LA": 48,186 "HM": 47,187 "HC": 43,188 "TN": 42,189 "TH": 38,190 "TR": 37,191 "RD": 34,192 "LF": 33,193 "BD": 33,194 "RG": 32,195 "TC": 32,196 "TF": 27,197 "HS": 26,198 "TD": 25,199 "BC": 24,200 "GB": 19,201 "LD": 16,202 "RJ": 16,203 "H": 16,204 "RS": 16,205 "QR": 15,206 "HJ": 14,207 "QM": 14,208 "RT": 11,209 "RE": 11,210 "GA": 10,211 "BH": 9,212 "RZ": 8,213 "RK": 8,214 "RX": 7,215 "RB": 7,216 "LT": 7,217 "GC": 6,218 "TE": 6,219 "LH": 6,220 "GF": 5,221 "GR": 5,222 "TG": 5,223 "HA": 4,224 "L": 4,225 "RL": 3,226 "RF": 3,227 "RV": 1,228 "LE": 1229 },230 "catalog": {231 "url": "https://www.gutenberg.org/cache/epub/feeds/pg_catalog.csv",232 "path": "data/raw/books/_catalog/pg_catalog.csv",233 "cached": true,234 "sha256": "8c06ec1c46751dc184b640b8a8ed5842c873ae3b621d575f8e76837f12f33eb6",235 "retrieved_or_cached_at": "2026-11-09T17:57:39Z"236 },237 "http": {238 "requests": 527,239 "retries": 0,240 "bytes": 284820446241 },242 "elapsed_s": 2465.3243 }244}245