Repository Public Research preview
1{2 "created_at": "2026-11-09T17:20:58Z",3 "git": {4 "commit": "HEAD",5 "branch": "HEAD",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": 12,34 "max_attempts": null,35 "seed": 1,36 "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": 12,47 "downloaded": 12,48 "already_present": 0,49 "not_found": 0,50 "too_large": 0,51 "copyrighted_header": 0,52 "no_pd_header": 0,53 "no_date": 1,54 "date_from_frontmatter": 10,55 "date_from_death_year": 1,56 "errors": 0,57 "by_locc": {58 "LH": 1,59 "TS": 1,60 "GT": 1,61 "RC": 1,62 "Z": 1,63 "BJ": 1,64 "QH": 1,65 "HB": 1,66 "LC": 1,67 "TJ": 1,68 "G": 1,69 "RT": 170 },71 "by_era": {72 "unknown": 1,73 "pre1900": 5,74 "1900-1949": 5,75 "1950-1979": 176 },77 "by_date_rule": {78 "none": 1,79 "frontmatter:imprint": 5,80 "frontmatter:copyright": 3,81 "frontmatter:published": 1,82 "frontmatter:roman": 1,83 "death_year": 184 },85 "pool_by_class": {86 "QH": 543,87 "QL": 491,88 "Z": 490,89 "BF": 372,90 "HV": 356,91 "B": 344,92 "HQ": 341,93 "G": 256,94 "BJ": 234,95 "Q": 202,96 "HD": 190,97 "RC": 190,98 "QC": 182,99 "QK": 180,100 "T": 167,101 "TT": 164,102 "QE": 161,103 "HE": 156,104 "QB": 139,105 "LB": 132,106 "TS": 130,107 "QA": 120,108 "RA": 112,109 "HX": 99,110 "GN": 99,111 "TL": 96,112 "TK": 89,113 "HF": 87,114 "RM": 84,115 "HB": 81,116 "GT": 81,117 "TP": 80,118 "QD": 78,119 "R": 77,120 "HG": 76,121 "TJ": 63,122 "HN": 62,123 "QP": 61,124 "HT": 55,125 "LC": 55,126 "TA": 50,127 "LA": 48,128 "HM": 47,129 "HC": 43,130 "TN": 42,131 "TH": 38,132 "TR": 37,133 "RD": 34,134 "LF": 33,135 "BD": 33,136 "RG": 32,137 "TC": 32,138 "TF": 27,139 "HS": 26,140 "TD": 25,141 "BC": 24,142 "GB": 19,143 "LD": 16,144 "RJ": 16,145 "H": 16,146 "RS": 16,147 "QR": 15,148 "HJ": 14,149 "QM": 14,150 "RT": 11,151 "RE": 11,152 "GA": 10,153 "BH": 9,154 "RZ": 8,155 "RK": 8,156 "RX": 7,157 "RB": 7,158 "LT": 7,159 "GC": 6,160 "TE": 6,161 "LH": 6,162 "GF": 5,163 "GR": 5,164 "TG": 5,165 "HA": 4,166 "L": 4,167 "RL": 3,168 "RF": 3,169 "RV": 1,170 "LE": 1171 },172 "catalog": {173 "url": "https://www.gutenberg.org/cache/epub/feeds/pg_catalog.csv",174 "path": "data/raw/books/_catalog/pg_catalog.csv",175 "cached": false,176 "last_modified": "Sun, 08 Nov 2026 22:43:51 GMT",177 "sha256": "8c06ec1c46751dc184b640b8a8ed5842c873ae3b621d575f8e76837f12f33eb6",178 "retrieved_or_cached_at": "2026-11-09T17:20:17Z"179 },180 "http": {181 "requests": 13,182 "retries": 0,183 "bytes": 25370564184 },185 "elapsed_s": 43.3186 }187}188