SPB Git

Repository Public Research preview

discover_books_bookshelf_seed1.json 1.6 KB 75 lines json

1{2  "created_at": "2026-11-09T17:29:55Z",3  "git": {4    "commit": "43899c8924172a93eb7fdb44567c22c0c6bb1e47",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": "bookshelf",33    "max_docs": 3,34    "max_attempts": 12,35    "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    "list_rows": 9733,45    "pre2018_rows": 3941,46    "attempted": 4,47    "too_large": 0,48    "books_kept": 3,49    "chapters_written": 17,50    "license_excluded": 0,51    "license_unknown": 1,52    "not_pre2018_xml": 0,53    "no_body_chapters": 0,54    "errors": 0,55    "by_license": {56      "PUBLIC-DOMAIN": 2,57      "UNKNOWN": 1,58      "CC-BY": 159    },60    "by_publisher": {61      "Agency for Healthcare Research and Quality (US)": 2,62      "Springer": 163    },64    "by_era": {65      "2010-2017": 366    },67    "ftp": {68      "requests": 8,69      "retries": 0,70      "bytes": 852923071    },72    "elapsed_s": 14.573  }74}75
Files main
Menu

Theme