Repository Public Research preview
1{2 "created_at": "2026-11-09T17:21:53Z",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": true,41 "report": null42 },43 "stats": {44 "catalog": {45 "url": "https://www.gutenberg.org/cache/epub/feeds/pg_catalog.csv",46 "path": "data/raw/books/_catalog/pg_catalog.csv",47 "cached": true,48 "sha256": "8c06ec1c46751dc184b640b8a8ed5842c873ae3b621d575f8e76837f12f33eb6",49 "retrieved_or_cached_at": "2026-11-09T17:21:52Z"50 },51 "catalog_rows": 79769,52 "text_en": 61977,53 "eligible_pool": 7799,54 "pool_by_letter": {55 "Q": 2186,56 "H": 1653,57 "T": 1051,58 "B": 1016,59 "R": 620,60 "Z": 490,61 "G": 481,62 "L": 30263 },64 "pool_by_class": {65 "QH": 543,66 "QL": 491,67 "Z": 490,68 "BF": 372,69 "HV": 356,70 "B": 344,71 "HQ": 341,72 "G": 256,73 "BJ": 234,74 "Q": 202,75 "HD": 190,76 "RC": 190,77 "QC": 182,78 "QK": 180,79 "T": 167,80 "TT": 164,81 "QE": 161,82 "HE": 156,83 "QB": 139,84 "LB": 132,85 "TS": 130,86 "QA": 120,87 "RA": 112,88 "HX": 99,89 "GN": 99,90 "TL": 96,91 "TK": 89,92 "HF": 87,93 "RM": 84,94 "HB": 81,95 "GT": 81,96 "TP": 80,97 "QD": 78,98 "R": 77,99 "HG": 76,100 "TJ": 63,101 "HN": 62,102 "QP": 61,103 "HT": 55,104 "LC": 55,105 "TA": 50,106 "LA": 48,107 "HM": 47,108 "HC": 43,109 "TN": 42,110 "TH": 38,111 "TR": 37,112 "RD": 34,113 "LF": 33,114 "BD": 33,115 "RG": 32,116 "TC": 32,117 "TF": 27,118 "HS": 26,119 "TD": 25,120 "BC": 24,121 "GB": 19,122 "LD": 16,123 "RJ": 16,124 "H": 16,125 "RS": 16,126 "QR": 15,127 "HJ": 14,128 "QM": 14,129 "RT": 11,130 "RE": 11,131 "GA": 10,132 "BH": 9,133 "RZ": 8,134 "RK": 8,135 "RX": 7,136 "RB": 7,137 "LT": 7,138 "GC": 6,139 "TE": 6,140 "LH": 6,141 "GF": 5,142 "GR": 5,143 "TG": 5,144 "HA": 4,145 "L": 4,146 "RL": 3,147 "RF": 3,148 "RV": 1,149 "LE": 1150 },151 "pool_with_any_author_life_dates": 5929,152 "elapsed_s": 0.3153 }154}155