Repository Public Research preview
1{2 "created_at": "2026-11-09T18:22:03Z",3 "git": {4 "commit": "e5b9872e8ec134616aca832cf77f5ed5f73008af",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_pmc",31 "args": {32 "candidates": 40000,33 "max_docs": 10000,34 "seed": 3,35 "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": 35117,41 "missing": 20114,42 "not_open_access": 3218,43 "retracted": 21,44 "license_excluded": 1653,45 "manuscript": 111,46 "fetched": 10000,47 "md5_fail": 0,48 "errors": 0,49 "by_license": {50 "UNKNOWN": 954,51 "TDM": 3302,52 "CC-BY-NC": 1704,53 "CC-BY": 7213,54 "CC-BY-NC-SA": 911,55 "CC0": 211,56 "CC-BY-NC-ND": 694,57 "CC-BY-ND": 12,58 "CC-BY-SA": 259 },60 "http": {61 "requests": 45117,62 "retries": 0,63 "bytes": 86509283964 },65 "elapsed_s": 3371.166 }67}68