Repository Public Research preview
1{2 "created_at": "2026-11-09T17:19:27Z",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_pmc",31 "args": {32 "candidates": 6000,33 "max_docs": 1200,34 "seed": 2,35 "out": "data/raw/pmc",36 "codes": "CC0,PUBLIC-DOMAIN,CC-BY,CC-BY-SA,CC-BY-NC,CC-BY-NC-SA",37 "report": null38 },39 "stats": {40 "candidates": 4187,41 "missing": 2367,42 "not_open_access": 395,43 "retracted": 1,44 "license_excluded": 210,45 "manuscript": 14,46 "fetched": 1200,47 "md5_fail": 0,48 "errors": 0,49 "by_license": {50 "CC0": 26,51 "CC-BY": 842,52 "CC-BY-NC": 210,53 "TDM": 405,54 "CC-BY-NC-SA": 126,55 "UNKNOWN": 137,56 "CC-BY-NC-ND": 73,57 "CC-BY-ND": 158 },59 "http": {60 "requests": 5387,61 "retries": 0,62 "bytes": 10419922963 },64 "elapsed_s": 391.165 }66}67