spb/wpai0002_uqo

1{2  "created_at": "2026-11-09T18:28:01Z",3  "git": {4    "commit": "e4eec911d74f1ec613a2572cb35afde77ec2bdcc",5    "branch": "main",6    "dirty": false7  },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": "bookshelf",33    "max_docs": 300,34    "max_attempts": 450,35    "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": 80.0,40    "pool_only": false,41    "report": null42  },43  "stats": {44    "list_rows": 9733,45    "pre2018_rows": 3941,46    "attempted": 450,47    "too_large": 9,48    "books_kept": 163,49    "chapters_written": 1351,50    "license_excluded": 99,51    "license_unknown": 142,52    "not_pre2018_xml": 0,53    "no_body_chapters": 37,54    "errors": 0,55    "by_license": {56      "PUBLIC-DOMAIN": 169,57      "CC-BY-NC-ND": 98,58      "CC0": 25,59      "UNKNOWN": 142,60      "CC-BY-NC-SA": 1,61      "CC-BY-ND": 1,62      "CC-BY-NC": 3,63      "CC-BY": 264    },65    "by_publisher": {66      "Agency for Healthcare Research and Quality (US)": 109,67      "Centers for Disease Control and Prevention (US)": 19,68      "Substance Abuse and Mental Health Services Administration (US)": 10,69      "Office of the Surgeon General (US)": 2,70      "Department of Veterans Affairs (US)": 13,71      "American Epilepsy Society": 1,72      "National Center for Biotechnology Information (US)": 3,73      "Springer": 3,74      "The International Bank for Reconstruction and Development / The World Bank": 1,75      "National Institute of Environmental Health Sciences": 276    },77    "by_era": {78      "2010-2017": 92,79      "2000-2009": 57,80      "1980-1999": 1481    },82    "ftp": {83      "requests": 895,84      "retries": 4,85      "bytes": 231028754586    },87    "elapsed_s": 1822.488  }89}90