Repository Public Research preview
1{2 "created_at": "2026-11-09T17:28:50Z",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": "openstax",33 "max_docs": 5,34 "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": 60.0,40 "pool_only": false,41 "report": null42 },43 "stats": {44 "search_hits": {45 "openstax_college": 6,46 "cnx_ost": 16447 },48 "candidates": 170,49 "attempted": 8,50 "no_pdf": 0,51 "too_large": 3,52 "md5_fail": 0,53 "no_infile_date": 0,54 "date_after_2017": 0,55 "license_unverified": 0,56 "license_excluded": 0,57 "downloaded": 5,58 "errors": 0,59 "by_license": {60 "CC-BY": 561 },62 "by_era": {63 "2010-2017": 564 },65 "by_query": {66 "openstax_college": 3,67 "cnx_ost": 268 },69 "http": {70 "requests": 15,71 "retries": 0,72 "bytes": 12379631573 },74 "elapsed_s": 59.275 }76}77