spb/wpai0002_uqo

1{2  "created_at": "2026-11-09T17:31:54Z",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_arxiv",31  "args": {32    "sets": [33      "q-fin",34      "econ"35    ],36    "date_from": "2008-01-01",37    "date_until": "2017-12-31",38    "datestamp_until": null,39    "max_docs": 12,40    "seed": 1,41    "out": "data/raw/arxiv",42    "codes": "CC0,CC-BY,CC-BY-SA,CC-BY-NC,CC-BY-NC-SA",43    "metadata_only": false,44    "metadata_out": null,45    "report": null,46    "max_minutes": null47  },48  "stats": {49    "records_seen": 1544,50    "duplicates": 0,51    "license_excluded": 1496,52    "no_versions": 0,53    "before_window": 0,54    "not_pre2018": 0,55    "eligible": 48,56    "pdf_only": 3,57    "fetched": 12,58    "errors": 0,59    "by_license": {60      "CC-BY": 24,61      "ARXIV-NONEXCLUSIVE": 1450,62      "UNKNOWN": 46,63      "CC-BY-NC-SA": 19,64      "CC0": 4,65      "CC-BY-SA": 166    },67    "by_set": {68      "q-fin": 46,69      "econ": 270    },71    "by_v1_year_eligible": {72      "2013": 6,73      "2014": 18,74      "2015": 3,75      "2016": 18,76      "2009": 1,77      "2017": 278    },79    "by_license_eligible": {80      "CC-BY": 24,81      "CC-BY-NC-SA": 19,82      "CC0": 4,83      "CC-BY-SA": 184    },85    "windows_harvested": [86      {87        "set": "q-fin",88        "from": "2014-01-01",89        "until": "2014-12-31",90        "pages_total": 1,91        "records_seen_total": 67392      },93      {94        "set": "q-fin",95        "from": "2016-01-01",96        "until": "2016-12-31",97        "pages_total": 2,98        "records_seen_total": 147099      },100      {101        "set": "econ",102        "from": "2017-09-01",103        "until": "2017-12-31",104        "pages_total": 3,105        "records_seen_total": 1544106      }107    ],108    "truncated_at": null,109    "candidate_pool": 48,110    "oai_endpoint": "https://oaipmh.arxiv.org/oai",111    "oai_pages": 3,112    "http": {113      "requests": 25,114      "retries": 6,115      "bytes": 24328619116    },117    "elapsed_s": 203.8118  }119}120