{
  "data_status": "preview",
  "generated_at": "2026-09-22T04:51:07Z",
  "last_complete_month": "2026-08",
  "latest_data_date": "2026-09-21",
  "months": [
    {
      "any_llm_papers": 438,
      "family_papers": {
        "alpaca": 0,
        "arctic": 0,
        "aya": 0,
        "baichuan": 1,
        "bloom": 15,
        "claude": 1,
        "cog": 5,
        "cohere_command": 0,
        "dbrx": 0,
        "deepseek": 0,
        "ernie": 22,
        "exaone": 0,
        "falcon": 1,
        "gemini": 0,
        "gemma": 0,
        "glm": 4,
        "gpt_neo": 39,
        "gpt_oss": 0,
        "granite": 0,
        "hunyuan": 1,
        "internlm": 0,
        "internvl": 0,
        "jamba": 0,
        "kimi": 0,
        "lfm": 0,
        "llada": 0,
        "llama": 0,
        "llava": 0,
        "mimo": 0,
        "minicpm": 0,
        "minimax": 0,
        "mistral": 0,
        "molmo": 0,
        "mpt": 0,
        "nemotron": 0,
        "olmo": 0,
        "openai_gpt": 410,
        "openllama": 0,
        "opt": 20,
        "phi": 0,
        "pythia": 0,
        "qwen": 0,
        "redpajama": 0,
        "rwkv": 1,
        "seed_oss": 0,
        "smol": 0,
        "stablelm": 0,
        "starcoder": 1,
        "tulu": 0,
        "vicuna": 0,
        "yi": 0
      },
      "month": "2022-11",
      "papers_discovered": 5128,
      "papers_scanned": 5102,
      "source_counts": {
        "arxiv_bulk_pdf": 5102,
        "html": 0,
        "other": 0,
        "pdf": 0
      },
      "status": "final",
      "unscanned_by_reason": {
        "bulk_pdf_missing": 26
      }
    },
    {
      "any_llm_papers": 486,
      "family_papers": {
        "alpaca": 0,
        "arctic": 0,
        "aya": 0,
        "baichuan": 0,
        "bloom": 15,
        "claude": 0,
        "cog": 5,
        "cohere_command": 1,
        "dbrx": 0,
        "deepseek": 0,
        "ernie": 18,
        "exaone": 0,
        "falcon": 2,
        "gemini": 0,
        "gemma": 0,
        "glm": 0,
        "gpt_neo": 57,
        "gpt_oss": 0,
        "granite": 0,
        "hunyuan": 1,
        "internlm": 0,
        "internvl": 0,
        "jamba": 0,
        "kimi": 0,
        "lfm": 0,
        "llada": 0,
        "llama": 0,
        "llava": 1,
        "mimo": 0,
        "minicpm": 0,
        "minimax": 0,
        "mistral": 0,
        "molmo": 0,
        "mpt": 1,
        "nemotron": 0,
        "olmo": 0,
        "openai_gpt": 467,
        "openllama": 0,
        "opt": 28,
        "phi": 0,
        "pythia": 1,
        "qwen": 0,
        "redpajama": 0,
        "rwkv": 1,
        "seed_oss": 0,
        "smol": 0,
        "stablelm": 0,
        "starcoder": 2,
        "tulu": 0,
        "vicuna": 5,
        "yi": 0
      },
      "month": "2022-12",
      "papers_discovered": 4054,
      "papers_scanned": 4027,
      "source_counts": {
        "arxiv_bulk_pdf": 4027,
        "html": 0,
        "other": 0,
        "pdf": 0
      },
      "status": "final",
      "unscanned_by_reason": {
        "bulk_pdf_missing": 27
      }
    },
    {
      "any_llm_papers": 355,
      "family_papers": {
        "alpaca": 0,
        "arctic": 0,
        "aya": 0,
        "baichuan": 0,
        "bloom": 12,
        "claude": 1,
        "cog": 2,
        "cohere_command": 0,
        "dbrx": 0,
        "deepseek": 0,
        "ernie": 15,
        "exaone": 0,
        "falcon": 0,
        "gemini": 0,
        "gemma": 0,
        "glm": 4,
        "gpt_neo": 24,
        "gpt_oss": 0,
        "granite": 1,
        "hunyuan": 3,
        "internlm": 0,
        "internvl": 0,
        "jamba": 0,
        "kimi": 0,
        "lfm": 0,
        "llada": 0,
        "llama": 0,
        "llava": 1,
        "mimo": 0,
        "minicpm": 0,
        "minimax": 0,
        "mistral": 0,
        "molmo": 0,
        "mpt": 0,
        "nemotron": 0,
        "olmo": 0,
        "openai_gpt": 337,
        "openllama": 0,
        "opt": 15,
        "phi": 0,
        "pythia": 0,
        "qwen": 0,
        "redpajama": 0,
        "rwkv": 0,
        "seed_oss": 0,
        "smol": 0,
        "stablelm": 0,
        "starcoder": 0,
        "tulu": 0,
        "vicuna": 1,
        "yi": 0
      },
      "month": "2023-01",
      "papers_discovered": 3425,
      "papers_scanned": 3403,
      "source_counts": {
        "arxiv_bulk_pdf": 3403,
        "html": 0,
        "other": 0,
        "pdf": 0
      },
      "status": "final",
      "unscanned_by_reason": {
        "bulk_pdf_missing": 21,
        "pdftotext_exited_with_status_99_for_temporary_pdf": 1
      }
    },
    {
      "any_llm_papers": 522,
      "family_papers": {
        "alpaca": 0,
        "arctic": 0,
        "aya": 0,
        "baichuan": 1,
        "bloom": 13,
        "claude": 2,
        "cog": 3,
        "cohere_command": 1,
        "dbrx": 0,
        "deepseek": 0,
        "ernie": 21,
        "exaone": 0,
        "falcon": 2,
        "gemini": 3,
        "gemma": 0,
        "glm": 7,
        "gpt_neo": 44,
        "gpt_oss": 0,
        "granite": 0,
        "hunyuan": 1,
        "internlm": 0,
        "internvl": 0,
        "jamba": 0,
        "kimi": 0,
        "lfm": 1,
        "llada": 0,
        "llama": 4,
        "llava": 4,
        "mimo": 0,
        "minicpm": 0,
        "minimax": 0,
        "mistral": 0,
        "molmo": 0,
        "mpt": 0,
        "nemotron": 0,
        "olmo": 0,
        "openai_gpt": 497,
        "openllama": 0,
        "opt": 26,
        "phi": 0,
        "pythia": 2,
        "qwen": 0,
        "redpajama": 0,
        "rwkv": 2,
        "seed_oss": 0,
        "smol": 0,
        "stablelm": 1,
        "starcoder": 4,
        "tulu": 0,
        "vicuna": 6,
        "yi": 0
      },
      "month": "2023-02",
      "papers_discovered": 4494,
      "papers_scanned": 4472,
      "source_counts": {
        "arxiv_bulk_pdf": 4472,
        "html": 0,
        "other": 0,
        "pdf": 0
      },
      "status": "final",
      "unscanned_by_reason": {
        "bulk_pdf_missing": 22
      }
    },
    {
      "any_llm_papers": 716,
      "family_papers": {
        "alpaca": 9,
        "arctic": 0,
        "aya": 0,
        "baichuan": 1,
        "bloom": 27,
        "claude": 9,
        "cog": 20,
        "cohere_command": 2,
        "dbrx": 0,
        "deepseek": 0,
        "ernie": 11,
        "exaone": 0,
        "falcon": 2,
        "gemini": 6,
        "gemma": 0,
        "glm": 4,
        "gpt_neo": 48,
        "gpt_oss": 0,
        "granite": 1,
        "hunyuan": 1,
        "internlm": 1,
        "internvl": 0,
        "jamba": 0,
        "kimi": 0,
        "lfm": 1,
        "llada": 0,
        "llama": 89,
        "llava": 10,
        "mimo": 0,
        "minicpm": 1,
        "minimax": 0,
        "mistral": 0,
        "molmo": 0,
        "mpt": 0,
        "nemotron": 0,
        "olmo": 0,
        "openai_gpt": 673,
        "openllama": 0,
        "opt": 29,
        "phi": 0,
        "pythia": 1,
        "qwen": 0,
        "redpajama": 0,
        "rwkv": 1,
        "seed_oss": 0,
        "smol": 0,
        "stablelm": 1,
        "starcoder": 6,
        "tulu": 1,
        "vicuna": 8,
        "yi": 0
      },
      "month": "2023-03",
      "papers_discovered": 5795,
      "papers_scanned": 5778,
      "source_counts": {
        "arxiv_bulk_pdf": 5778,
        "html": 0,
        "other": 0,
        "pdf": 0
      },
      "status": "final",
      "unscanned_by_reason": {
        "bulk_pdf_missing": 17
      }
    },
    {
      "any_llm_papers": 706,
      "family_papers": {
        "alpaca": 38,
        "arctic": 0,
        "aya": 0,
        "baichuan": 1,
        "bloom": 24,
        "claude": 10,
        "cog": 9,
        "cohere_command": 0,
        "dbrx": 0,
        "deepseek": 0,
        "ernie": 10,
        "exaone": 0,
        "falcon": 7,
        "gemini": 2,
        "gemma": 0,
        "glm": 13,
        "gpt_neo": 52,
        "gpt_oss": 0,
        "granite": 0,
        "hunyuan": 2,
        "internlm": 2,
        "internvl": 0,
        "jamba": 0,
        "kimi": 0,
        "lfm": 0,
        "llada": 0,
        "llama": 129,
        "llava": 6,
        "mimo": 0,
        "minicpm": 0,
        "minimax": 0,
        "mistral": 0,
        "molmo": 0,
        "mpt": 1,
        "nemotron": 0,
        "olmo": 0,
        "openai_gpt": 687,
        "openllama": 1,
        "opt": 21,
        "phi": 0,
        "pythia": 7,
        "qwen": 0,
        "redpajama": 0,
        "rwkv": 1,
        "seed_oss": 0,
        "smol": 0,
        "stablelm": 0,
        "starcoder": 4,
        "tulu": 0,
        "vicuna": 18,
        "yi": 0
      },
      "month": "2023-04",
      "papers_discovered": 4611,
      "papers_scanned": 4586,
      "source_counts": {
        "arxiv_bulk_pdf": 4586,
        "html": 0,
        "other": 0,
        "pdf": 0
      },
      "status": "final",
      "unscanned_by_reason": {
        "bulk_pdf_missing": 25
      }
    },
    {
      "any_llm_papers": 1934,
      "family_papers": {
        "alpaca": 146,
        "arctic": 0,
        "aya": 1,
        "baichuan": 3,
        "bloom": 75,
        "claude": 42,
        "cog": 18,
        "cohere_command": 3,
        "dbrx": 0,
        "deepseek": 0,
        "ernie": 44,
        "exaone": 1,
        "falcon": 16,
        "gemini": 7,
        "gemma": 0,
        "glm": 26,
        "gpt_neo": 157,
        "gpt_oss": 0,
        "granite": 0,
        "hunyuan": 1,
        "internlm": 1,
        "internvl": 1,
        "jamba": 1,
        "kimi": 0,
        "lfm": 1,
        "llada": 0,
        "llama": 527,
        "llava": 44,
        "mimo": 0,
        "minicpm": 1,
        "minimax": 0,
        "mistral": 0,
        "molmo": 0,
        "mpt": 11,
        "nemotron": 1,
        "olmo": 0,
        "openai_gpt": 1853,
        "openllama": 4,
        "opt": 105,
        "phi": 0,
        "pythia": 22,
        "qwen": 0,
        "redpajama": 1,
        "rwkv": 4,
        "seed_oss": 0,
        "smol": 1,
        "stablelm": 12,
        "starcoder": 28,
        "tulu": 0,
        "vicuna": 84,
        "yi": 0
      },
      "month": "2023-05",
      "papers_discovered": 7333,
      "papers_scanned": 7306,
      "source_counts": {
        "arxiv_bulk_pdf": 7306,
        "html": 0,
        "other": 0,
        "pdf": 0
      },
      "status": "final",
      "unscanned_by_reason": {
        "bulk_pdf_missing": 27
      }
    },
    {
      "any_llm_papers": 1175,
      "family_papers": {
        "alpaca": 78,
        "arctic": 0,
        "aya": 0,
        "baichuan": 3,
        "bloom": 33,
        "claude": 21,
        "cog": 11,
        "cohere_command": 0,
        "dbrx": 0,
        "deepseek": 0,
        "ernie": 23,
        "exaone": 0,
        "falcon": 12,
        "gemini": 8,
        "gemma": 0,
        "glm": 34,
        "gpt_neo": 81,
        "gpt_oss": 0,
        "granite": 0,
        "hunyuan": 0,
        "internlm": 4,
        "internvl": 0,
        "jamba": 1,
        "kimi": 0,
        "lfm": 1,
        "llada": 0,
        "llama": 313,
        "llava": 38,
        "mimo": 0,
        "minicpm": 0,
        "minimax": 0,
        "mistral": 0,
        "molmo": 0,
        "mpt": 17,
        "nemotron": 0,
        "olmo": 0,
        "openai_gpt": 1120,
        "openllama": 3,
        "opt": 56,
        "phi": 1,
        "pythia": 20,
        "qwen": 0,
        "redpajama": 4,
        "rwkv": 7,
        "seed_oss": 0,
        "smol": 0,
        "stablelm": 9,
        "starcoder": 16,
        "tulu": 0,
        "vicuna": 60,
        "yi": 0
      },
      "month": "2023-06",
      "papers_discovered": 5939,
      "papers_scanned": 5914,
      "source_counts": {
        "arxiv_bulk_pdf": 5914,
        "html": 0,
        "other": 0,
        "pdf": 0
      },
      "status": "final",
      "unscanned_by_reason": {
        "bulk_pdf_missing": 25
      }
    },
    {
      "any_llm_papers": 935,
      "family_papers": {
        "alpaca": 68,
        "arctic": 1,
        "aya": 0,
        "baichuan": 8,
        "bloom": 38,
        "claude": 34,
        "cog": 6,
        "cohere_command": 0,
        "dbrx": 0,
        "deepseek": 0,
        "ernie": 17,
        "exaone": 0,
        "falcon": 12,
        "gemini": 7,
        "gemma": 0,
        "glm": 30,
        "gpt_neo": 55,
        "gpt_oss": 1,
        "granite": 0,
        "hunyuan": 1,
        "internlm": 3,
        "internvl": 0,
        "jamba": 0,
        "kimi": 0,
        "lfm": 1,
        "llada": 0,
        "llama": 289,
        "llava": 40,
        "mimo": 0,
        "minicpm": 2,
        "minimax": 1,
        "mistral": 0,
        "molmo": 0,
        "mpt": 16,
        "nemotron": 1,
        "olmo": 0,
        "openai_gpt": 897,
        "openllama": 6,
        "opt": 39,
        "phi": 2,
        "pythia": 11,
        "qwen": 0,
        "redpajama": 1,
        "rwkv": 12,
        "seed_oss": 0,
        "smol": 0,
        "stablelm": 8,
        "starcoder": 10,
        "tulu": 1,
        "vicuna": 55,
        "yi": 0
      },
      "month": "2023-07",
      "papers_discovered": 5019,
      "papers_scanned": 5004,
      "source_counts": {
        "arxiv_bulk_pdf": 5004,
        "html": 0,
        "other": 0,
        "pdf": 0
      },
      "status": "final",
      "unscanned_by_reason": {
        "bulk_pdf_missing": 15
      }
    },
    {
      "any_llm_papers": 1066,
      "family_papers": {
        "alpaca": 80,
        "arctic": 0,
        "aya": 0,
        "baichuan": 14,
        "bloom": 39,
        "claude": 49,
        "cog": 12,
        "cohere_command": 2,
        "dbrx": 0,
        "deepseek": 0,
        "ernie": 21,
        "exaone": 0,
        "falcon": 38,
        "gemini": 10,
        "gemma": 0,
        "glm": 48,
        "gpt_neo": 51,
        "gpt_oss": 0,
        "granite": 0,
        "hunyuan": 0,
        "internlm": 17,
        "internvl": 1,
        "jamba": 0,
        "kimi": 0,
        "lfm": 0,
        "llada": 0,
        "llama": 383,
        "llava": 46,
        "mimo": 0,
        "minicpm": 1,
        "minimax": 0,
        "mistral": 0,
        "molmo": 0,
        "mpt": 19,
        "nemotron": 0,
        "olmo": 0,
        "openai_gpt": 1014,
        "openllama": 5,
        "opt": 43,
        "phi": 5,
        "pythia": 11,
        "qwen": 20,
        "redpajama": 4,
        "rwkv": 8,
        "seed_oss": 0,
        "smol": 0,
        "stablelm": 7,
        "starcoder": 26,
        "tulu": 0,
        "vicuna": 76,
        "yi": 0
      },
      "month": "2023-08",
      "papers_discovered": 5306,
      "papers_scanned": 5280,
      "source_counts": {
        "arxiv_bulk_pdf": 5280,
        "html": 0,
        "other": 0,
        "pdf": 0
      },
      "status": "final",
      "unscanned_by_reason": {
        "bulk_pdf_missing": 26
      }
    },
    {
      "any_llm_papers": 1291,
      "family_papers": {
        "alpaca": 103,
        "arctic": 0,
        "aya": 0,
        "baichuan": 23,
        "bloom": 41,
        "claude": 72,
        "cog": 15,
        "cohere_command": 1,
        "dbrx": 0,
        "deepseek": 0,
        "ernie": 27,
        "exaone": 1,
        "falcon": 44,
        "gemini": 14,
        "gemma": 0,
        "glm": 45,
        "gpt_neo": 68,
        "gpt_oss": 0,
        "granite": 0,
        "hunyuan": 0,
        "internlm": 14,
        "internvl": 2,
        "jamba": 0,
        "kimi": 0,
        "lfm": 0,
        "llada": 0,
        "llama": 539,
        "llava": 51,
        "mimo": 0,
        "minicpm": 1,
        "minimax": 0,
        "mistral": 8,
        "molmo": 0,
        "mpt": 39,
        "nemotron": 0,
        "olmo": 0,
        "openai_gpt": 1226,
        "openllama": 16,
        "opt": 44,
        "phi": 12,
        "pythia": 17,
        "qwen": 30,
        "redpajama": 5,
        "rwkv": 12,
        "seed_oss": 0,
        "smol": 0,
        "stablelm": 10,
        "starcoder": 26,
        "tulu": 1,
        "vicuna": 96,
        "yi": 0
      },
      "month": "2023-09",
      "papers_discovered": 5519,
      "papers_scanned": 5487,
      "source_counts": {
        "arxiv_bulk_pdf": 5487,
        "html": 0,
        "other": 0,
        "pdf": 0
      },
      "status": "final",
      "unscanned_by_reason": {
        "bulk_pdf_missing": 32
      }
    },
    {
      "any_llm_papers": 2307,
      "family_papers": {
        "alpaca": 210,
        "arctic": 0,
        "aya": 0,
        "baichuan": 45,
        "bloom": 82,
        "claude": 120,
        "cog": 10,
        "cohere_command": 1,
        "dbrx": 0,
        "deepseek": 0,
        "ernie": 38,
        "exaone": 1,
        "falcon": 78,
        "gemini": 21,
        "gemma": 0,
        "glm": 91,
        "gpt_neo": 141,
        "gpt_oss": 0,
        "granite": 1,
        "hunyuan": 0,
        "internlm": 18,
        "internvl": 1,
        "jamba": 1,
        "kimi": 0,
        "lfm": 1,
        "llada": 0,
        "llama": 1057,
        "llava": 95,
        "mimo": 0,
        "minicpm": 4,
        "minimax": 1,
        "mistral": 77,
        "molmo": 1,
        "mpt": 42,
        "nemotron": 0,
        "olmo": 0,
        "openai_gpt": 2200,
        "openllama": 14,
        "opt": 123,
        "phi": 18,
        "pythia": 42,
        "qwen": 50,
        "redpajama": 10,
        "rwkv": 14,
        "seed_oss": 0,
        "smol": 1,
        "stablelm": 14,
        "starcoder": 51,
        "tulu": 9,
        "vicuna": 213,
        "yi": 0
      },
      "month": "2023-10",
      "papers_discovered": 7196,
      "papers_scanned": 7170,
      "source_counts": {
        "arxiv_bulk_pdf": 7170,
        "html": 0,
        "other": 0,
        "pdf": 0
      },
      "status": "final",
      "unscanned_by_reason": {
        "bulk_pdf_missing": 26
      }
    },
    {
      "any_llm_papers": 1867,
      "family_papers": {
        "alpaca": 125,
        "arctic": 0,
        "aya": 4,
        "baichuan": 46,
        "bloom": 49,
        "claude": 101,
        "cog": 45,
        "cohere_command": 4,
        "dbrx": 2,
        "deepseek": 14,
        "ernie": 33,
        "exaone": 0,
        "falcon": 64,
        "gemini": 37,
        "gemma": 0,
        "glm": 79,
        "gpt_neo": 82,
        "gpt_oss": 0,
        "granite": 1,
        "hunyuan": 3,
        "internlm": 37,
        "internvl": 4,
        "jamba": 0,
        "kimi": 0,
        "lfm": 1,
        "llada": 1,
        "llama": 875,
        "llava": 161,
        "mimo": 0,
        "minicpm": 1,
        "minimax": 0,
        "mistral": 122,
        "molmo": 0,
        "mpt": 44,
        "nemotron": 0,
        "olmo": 0,
        "openai_gpt": 1755,
        "openllama": 12,
        "opt": 65,
        "phi": 24,
        "pythia": 21,
        "qwen": 100,
        "redpajama": 4,
        "rwkv": 15,
        "seed_oss": 0,
        "smol": 0,
        "stablelm": 10,
        "starcoder": 32,
        "tulu": 8,
        "vicuna": 176,
        "yi": 15
      },
      "month": "2023-11",
      "papers_discovered": 6240,
      "papers_scanned": 6209,
      "source_counts": {
        "arxiv_bulk_pdf": 6209,
        "html": 0,
        "other": 0,
        "pdf": 0
      },
      "status": "final",
      "unscanned_by_reason": {
        "bulk_pdf_missing": 31
      }
    },
    {
      "any_llm_papers": 1612,
      "family_papers": {
        "alpaca": 113,
        "arctic": 0,
        "aya": 1,
        "baichuan": 45,
        "bloom": 40,
        "claude": 73,
        "cog": 51,
        "cohere_command": 0,
        "dbrx": 0,
        "deepseek": 20,
        "ernie": 23,
        "exaone": 0,
        "falcon": 41,
        "gemini": 41,
        "gemma": 0,
        "glm": 72,
        "gpt_neo": 70,
        "gpt_oss": 0,
        "granite": 0,
        "hunyuan": 2,
        "internlm": 36,
        "internvl": 6,
        "jamba": 0,
        "kimi": 1,
        "lfm": 1,
        "llada": 0,
        "llama": 718,
        "llava": 169,
        "mimo": 0,
        "minicpm": 1,
        "minimax": 1,
        "mistral": 108,
        "molmo": 0,
        "mpt": 36,
        "nemotron": 2,
        "olmo": 0,
        "openai_gpt": 1483,
        "openllama": 22,
        "opt": 67,
        "phi": 27,
        "pythia": 28,
        "qwen": 107,
        "redpajama": 4,
        "rwkv": 20,
        "seed_oss": 0,
        "smol": 0,
        "stablelm": 9,
        "starcoder": 44,
        "tulu": 2,
        "vicuna": 141,
        "yi": 12
      },
      "month": "2023-12",
      "papers_discovered": 6027,
      "papers_scanned": 6008,
      "source_counts": {
        "arxiv_bulk_pdf": 6008,
        "html": 0,
        "other": 0,
        "pdf": 0
      },
      "status": "final",
      "unscanned_by_reason": {
        "bulk_pdf_missing": 19
      }
    },
    {
      "any_llm_papers": 1547,
      "family_papers": {
        "alpaca": 99,
        "arctic": 1,
        "aya": 0,
        "baichuan": 44,
        "bloom": 48,
        "claude": 100,
        "cog": 36,
        "cohere_command": 3,
        "dbrx": 2,
        "deepseek": 37,
        "ernie": 29,
        "exaone": 1,
        "falcon": 52,
        "gemini": 92,
        "gemma": 0,
        "glm": 79,
        "gpt_neo": 78,
        "gpt_oss": 0,
        "granite": 1,
        "hunyuan": 2,
        "internlm": 35,
        "internvl": 3,
        "jamba": 1,
        "kimi": 1,
        "lfm": 0,
        "llada": 0,
        "llama": 791,
        "llava": 124,
        "mimo": 0,
        "minicpm": 3,
        "minimax": 0,
        "mistral": 185,
        "molmo": 0,
        "mpt": 28,
        "nemotron": 0,
        "olmo": 0,
        "openai_gpt": 1442,
        "openllama": 19,
        "opt": 54,
        "phi": 34,
        "pythia": 28,
        "qwen": 115,
        "redpajama": 8,
        "rwkv": 19,
        "seed_oss": 0,
        "smol": 0,
        "stablelm": 12,
        "starcoder": 38,
        "tulu": 5,
        "vicuna": 136,
        "yi": 27
      },
      "month": "2024-01",
      "papers_discovered": 5226,
      "papers_scanned": 5208,
      "source_counts": {
        "arxiv_bulk_pdf": 5208,
        "html": 0,
        "other": 0,
        "pdf": 0
      },
      "status": "final",
      "unscanned_by_reason": {
        "bulk_pdf_missing": 18
      }
    },
    {
      "any_llm_papers": 2824,
      "family_papers": {
        "alpaca": 207,
        "arctic": 1,
        "aya": 0,
        "baichuan": 64,
        "bloom": 71,
        "claude": 194,
        "cog": 46,
        "cohere_command": 4,
        "dbrx": 3,
        "deepseek": 87,
        "ernie": 37,
        "exaone": 1,
        "falcon": 82,
        "gemini": 200,
        "gemma": 14,
        "glm": 120,
        "gpt_neo": 133,
        "gpt_oss": 2,
        "granite": 5,
        "hunyuan": 2,
        "internlm": 60,
        "internvl": 9,
        "jamba": 2,
        "kimi": 3,
        "lfm": 3,
        "llada": 2,
        "llama": 1665,
        "llava": 226,
        "mimo": 0,
        "minicpm": 13,
        "minimax": 1,
        "mistral": 569,
        "molmo": 1,
        "mpt": 48,
        "nemotron": 3,
        "olmo": 44,
        "openai_gpt": 2652,
        "openllama": 24,
        "opt": 119,
        "phi": 94,
        "pythia": 47,
        "qwen": 211,
        "redpajama": 2,
        "rwkv": 36,
        "seed_oss": 0,
        "smol": 1,
        "stablelm": 17,
        "starcoder": 77,
        "tulu": 35,
        "vicuna": 278,
        "yi": 59
      },
      "month": "2024-02",
      "papers_discovered": 7265,
      "papers_scanned": 7235,
      "source_counts": {
        "arxiv_bulk_pdf": 7235,
        "html": 0,
        "other": 0,
        "pdf": 0
      },
      "status": "final",
      "unscanned_by_reason": {
        "bulk_pdf_missing": 29,
        "pdftotext_exited_with_status_1_for_temporary_pdf": 1
      }
    },
    {
      "any_llm_papers": 2403,
      "family_papers": {
        "alpaca": 137,
        "arctic": 0,
        "aya": 1,
        "baichuan": 61,
        "bloom": 51,
        "claude": 149,
        "cog": 56,
        "cohere_command": 5,
        "dbrx": 0,
        "deepseek": 77,
        "ernie": 36,
        "exaone": 1,
        "falcon": 66,
        "gemini": 154,
        "gemma": 69,
        "glm": 80,
        "gpt_neo": 92,
        "gpt_oss": 0,
        "granite": 2,
        "hunyuan": 6,
        "internlm": 54,
        "internvl": 22,
        "jamba": 4,
        "kimi": 1,
        "lfm": 0,
        "llada": 0,
        "llama": 1212,
        "llava": 225,
        "mimo": 0,
        "minicpm": 7,
        "minimax": 1,
        "mistral": 353,
        "molmo": 2,
        "mpt": 27,
        "nemotron": 1,
        "olmo": 39,
        "openai_gpt": 2208,
        "openllama": 16,
        "opt": 64,
        "phi": 69,
        "pythia": 38,
        "qwen": 196,
        "redpajama": 9,
        "rwkv": 33,
        "seed_oss": 0,
        "smol": 0,
        "stablelm": 25,
        "starcoder": 52,
        "tulu": 13,
        "vicuna": 194,
        "yi": 40
      },
      "month": "2024-03",
      "papers_discovered": 7478,
      "papers_scanned": 7439,
      "source_counts": {
        "arxiv_bulk_pdf": 7439,
        "html": 0,
        "other": 0,
        "pdf": 0
      },
      "status": "final",
      "unscanned_by_reason": {
        "bulk_pdf_missing": 39
      }
    },
    {
      "any_llm_papers": 2194,
      "family_papers": {
        "alpaca": 113,
        "arctic": 0,
        "aya": 1,
        "baichuan": 47,
        "bloom": 65,
        "claude": 196,
        "cog": 43,
        "cohere_command": 11,
        "dbrx": 6,
        "deepseek": 79,
        "ernie": 34,
        "exaone": 0,
        "falcon": 60,
        "gemini": 187,
        "gemma": 134,
        "glm": 75,
        "gpt_neo": 76,
        "gpt_oss": 0,
        "granite": 0,
        "hunyuan": 1,
        "internlm": 56,
        "internvl": 22,
        "jamba": 10,
        "kimi": 3,
        "lfm": 0,
        "llada": 0,
        "llama": 1152,
        "llava": 212,
        "mimo": 0,
        "minicpm": 14,
        "minimax": 1,
        "mistral": 441,
        "molmo": 0,
        "mpt": 36,
        "nemotron": 6,
        "olmo": 44,
        "openai_gpt": 2023,
        "openllama": 16,
        "opt": 77,
        "phi": 74,
        "pythia": 51,
        "qwen": 194,
        "redpajama": 3,
        "rwkv": 29,
        "seed_oss": 0,
        "smol": 0,
        "stablelm": 19,
        "starcoder": 58,
        "tulu": 18,
        "vicuna": 171,
        "yi": 33
      },
      "month": "2024-04",
      "papers_discovered": 6489,
      "papers_scanned": 6467,
      "source_counts": {
        "arxiv_bulk_pdf": 6467,
        "html": 0,
        "other": 0,
        "pdf": 0
      },
      "status": "final",
      "unscanned_by_reason": {
        "bulk_pdf_missing": 22
      }
    },
    {
      "any_llm_papers": 2585,
      "family_papers": {
        "alpaca": 141,
        "arctic": 5,
        "aya": 1,
        "baichuan": 59,
        "bloom": 53,
        "claude": 235,
        "cog": 66,
        "cohere_command": 24,
        "dbrx": 13,
        "deepseek": 146,
        "ernie": 29,
        "exaone": 0,
        "falcon": 61,
        "gemini": 262,
        "gemma": 188,
        "glm": 92,
        "gpt_neo": 108,
        "gpt_oss": 0,
        "granite": 6,
        "hunyuan": 7,
        "internlm": 80,
        "internvl": 42,
        "jamba": 19,
        "kimi": 4,
        "lfm": 1,
        "llada": 0,
        "llama": 1417,
        "llava": 271,
        "mimo": 0,
        "minicpm": 22,
        "minimax": 1,
        "mistral": 560,
        "molmo": 1,
        "mpt": 32,
        "nemotron": 7,
        "olmo": 41,
        "openai_gpt": 2341,
        "openllama": 20,
        "opt": 82,
        "phi": 129,
        "pythia": 55,
        "qwen": 280,
        "redpajama": 0,
        "rwkv": 44,
        "seed_oss": 0,
        "smol": 2,
        "stablelm": 19,
        "starcoder": 69,
        "tulu": 30,
        "vicuna": 219,
        "yi": 69
      },
      "month": "2024-05",
      "papers_discovered": 7539,
      "papers_scanned": 7508,
      "source_counts": {
        "arxiv_bulk_pdf": 7508,
        "html": 0,
        "other": 0,
        "pdf": 0
      },
      "status": "final",
      "unscanned_by_reason": {
        "bulk_pdf_missing": 31
      }
    },
    {
      "any_llm_papers": 3396,
      "family_papers": {
        "alpaca": 182,
        "arctic": 5,
        "aya": 20,
        "baichuan": 76,
        "bloom": 63,
        "claude": 419,
        "cog": 104,
        "cohere_command": 53,
        "dbrx": 29,
        "deepseek": 240,
        "ernie": 35,
        "exaone": 1,
        "falcon": 76,
        "gemini": 470,
        "gemma": 290,
        "glm": 132,
        "gpt_neo": 121,
        "gpt_oss": 2,
        "granite": 6,
        "hunyuan": 11,
        "internlm": 134,
        "internvl": 80,
        "jamba": 18,
        "kimi": 11,
        "lfm": 3,
        "llada": 0,
        "llama": 2106,
        "llava": 395,
        "mimo": 1,
        "minicpm": 50,
        "minimax": 1,
        "mistral": 878,
        "molmo": 5,
        "mpt": 32,
        "nemotron": 13,
        "olmo": 77,
        "openai_gpt": 3097,
        "openllama": 21,
        "opt": 107,
        "phi": 178,
        "pythia": 76,
        "qwen": 532,
        "redpajama": 4,
        "rwkv": 50,
        "seed_oss": 0,
        "smol": 4,
        "stablelm": 19,
        "starcoder": 86,
        "tulu": 52,
        "vicuna": 264,
        "yi": 104
      },
      "month": "2024-06",
      "papers_discovered": 8179,
      "papers_scanned": 8149,
      "source_counts": {
        "arxiv_bulk_pdf": 8149,
        "html": 0,
        "other": 0,
        "pdf": 0
      },
      "status": "final",
      "unscanned_by_reason": {
        "bulk_pdf_missing": 30
      }
    },
    {
      "any_llm_papers": 2554,
      "family_papers": {
        "alpaca": 107,
        "arctic": 8,
        "aya": 14,
        "baichuan": 51,
        "bloom": 40,
        "claude": 313,
        "cog": 62,
        "cohere_command": 37,
        "dbrx": 16,
        "deepseek": 163,
        "ernie": 32,
        "exaone": 1,
        "falcon": 55,
        "gemini": 300,
        "gemma": 201,
        "glm": 91,
        "gpt_neo": 71,
        "gpt_oss": 0,
        "granite": 13,
        "hunyuan": 5,
        "internlm": 88,
        "internvl": 61,
        "jamba": 17,
        "kimi": 10,
        "lfm": 2,
        "llada": 2,
        "llama": 1419,
        "llava": 299,
        "mimo": 0,
        "minicpm": 37,
        "minimax": 1,
        "mistral": 577,
        "molmo": 4,
        "mpt": 31,
        "nemotron": 17,
        "olmo": 65,
        "openai_gpt": 2295,
        "openllama": 14,
        "opt": 60,
        "phi": 148,
        "pythia": 46,
        "qwen": 347,
        "redpajama": 3,
        "rwkv": 37,
        "seed_oss": 0,
        "smol": 4,
        "stablelm": 16,
        "starcoder": 64,
        "tulu": 27,
        "vicuna": 168,
        "yi": 59
      },
      "month": "2024-07",
      "papers_discovered": 7179,
      "papers_scanned": 7155,
      "source_counts": {
        "arxiv_bulk_pdf": 7155,
        "html": 0,
        "other": 0,
        "pdf": 0
      },
      "status": "final",
      "unscanned_by_reason": {
        "bulk_pdf_missing": 24
      }
    },
    {
      "any_llm_papers": 2158,
      "family_papers": {
        "alpaca": 80,
        "arctic": 5,
        "aya": 11,
        "baichuan": 49,
        "bloom": 38,
        "claude": 246,
        "cog": 58,
        "cohere_command": 17,
        "dbrx": 5,
        "deepseek": 149,
        "ernie": 32,
        "exaone": 2,
        "falcon": 33,
        "gemini": 258,
        "gemma": 188,
        "glm": 103,
        "gpt_neo": 62,
        "gpt_oss": 1,
        "granite": 3,
        "hunyuan": 11,
        "internlm": 71,
        "internvl": 62,
        "jamba": 11,
        "kimi": 6,
        "lfm": 0,
        "llada": 1,
        "llama": 1193,
        "llava": 266,
        "mimo": 0,
        "minicpm": 32,
        "minimax": 1,
        "mistral": 456,
        "molmo": 2,
        "mpt": 18,
        "nemotron": 13,
        "olmo": 35,
        "openai_gpt": 1914,
        "openllama": 12,
        "opt": 49,
        "phi": 147,
        "pythia": 24,
        "qwen": 356,
        "redpajama": 2,
        "rwkv": 22,
        "seed_oss": 0,
        "smol": 8,
        "stablelm": 8,
        "starcoder": 56,
        "tulu": 6,
        "vicuna": 157,
        "yi": 60
      },
      "month": "2024-08",
      "papers_discovered": 6071,
      "papers_scanned": 6054,
      "source_counts": {
        "arxiv_bulk_pdf": 6054,
        "html": 0,
        "other": 0,
        "pdf": 0
      },
      "status": "final",
      "unscanned_by_reason": {
        "bulk_pdf_missing": 17
      }
    },
    {
      "any_llm_papers": 2370,
      "family_papers": {
        "alpaca": 68,
        "arctic": 7,
        "aya": 12,
        "baichuan": 50,
        "bloom": 37,
        "claude": 318,
        "cog": 68,
        "cohere_command": 27,
        "dbrx": 10,
        "deepseek": 169,
        "ernie": 26,
        "exaone": 1,
        "falcon": 31,
        "gemini": 275,
        "gemma": 206,
        "glm": 96,
        "gpt_neo": 64,
        "gpt_oss": 0,
        "granite": 3,
        "hunyuan": 11,
        "internlm": 73,
        "internvl": 59,
        "jamba": 16,
        "kimi": 10,
        "lfm": 2,
        "llada": 0,
        "llama": 1360,
        "llava": 257,
        "mimo": 0,
        "minicpm": 47,
        "minimax": 0,
        "mistral": 507,
        "molmo": 4,
        "mpt": 13,
        "nemotron": 21,
        "olmo": 43,
        "openai_gpt": 2076,
        "openllama": 13,
        "opt": 56,
        "phi": 136,
        "pythia": 40,
        "qwen": 375,
        "redpajama": 2,
        "rwkv": 21,
        "seed_oss": 0,
        "smol": 10,
        "stablelm": 11,
        "starcoder": 50,
        "tulu": 19,
        "vicuna": 141,
        "yi": 47
      },
      "month": "2024-09",
      "papers_discovered": 6865,
      "papers_scanned": 6841,
      "source_counts": {
        "arxiv_bulk_pdf": 6841,
        "html": 0,
        "other": 0,
        "pdf": 0
      },
      "status": "final",
      "unscanned_by_reason": {
        "bulk_pdf_missing": 24
      }
    },
    {
      "any_llm_papers": 4248,
      "family_papers": {
        "alpaca": 163,
        "arctic": 12,
        "aya": 21,
        "baichuan": 44,
        "bloom": 61,
        "claude": 655,
        "cog": 110,
        "cohere_command": 44,
        "dbrx": 15,
        "deepseek": 384,
        "ernie": 36,
        "exaone": 3,
        "falcon": 59,
        "gemini": 591,
        "gemma": 504,
        "glm": 138,
        "gpt_neo": 132,
        "gpt_oss": 0,
        "granite": 11,
        "hunyuan": 11,
        "internlm": 146,
        "internvl": 140,
        "jamba": 43,
        "kimi": 15,
        "lfm": 3,
        "llada": 1,
        "llama": 2618,
        "llava": 494,
        "mimo": 1,
        "minicpm": 94,
        "minimax": 3,
        "mistral": 1116,
        "molmo": 16,
        "mpt": 40,
        "nemotron": 41,
        "olmo": 114,
        "openai_gpt": 3800,
        "openllama": 28,
        "opt": 107,
        "phi": 305,
        "pythia": 104,
        "qwen": 833,
        "redpajama": 8,
        "rwkv": 66,
        "seed_oss": 0,
        "smol": 8,
        "stablelm": 19,
        "starcoder": 88,
        "tulu": 43,
        "vicuna": 275,
        "yi": 94
      },
      "month": "2024-10",
      "papers_discovered": 9637,
      "papers_scanned": 9600,
      "source_counts": {
        "arxiv_bulk_pdf": 9600,
        "html": 0,
        "other": 0,
        "pdf": 0
      },
      "status": "final",
      "unscanned_by_reason": {
        "bulk_pdf_missing": 36,
        "pdftotext_stderr_exceeded_1048576_bytes_for_temporary_pdf": 1
      }
    },
    {
      "any_llm_papers": 2625,
      "family_papers": {
        "alpaca": 72,
        "arctic": 6,
        "aya": 14,
        "baichuan": 27,
        "bloom": 29,
        "claude": 364,
        "cog": 131,
        "cohere_command": 20,
        "dbrx": 11,
        "deepseek": 222,
        "ernie": 29,
        "exaone": 1,
        "falcon": 29,
        "gemini": 364,
        "gemma": 253,
        "glm": 103,
        "gpt_neo": 61,
        "gpt_oss": 3,
        "granite": 8,
        "hunyuan": 28,
        "internlm": 79,
        "internvl": 134,
        "jamba": 23,
        "kimi": 12,
        "lfm": 1,
        "llada": 0,
        "llama": 1455,
        "llava": 407,
        "mimo": 0,
        "minicpm": 60,
        "minimax": 1,
        "mistral": 542,
        "molmo": 19,
        "mpt": 26,
        "nemotron": 23,
        "olmo": 45,
        "openai_gpt": 2275,
        "openllama": 12,
        "opt": 52,
        "phi": 195,
        "pythia": 32,
        "qwen": 527,
        "redpajama": 4,
        "rwkv": 29,
        "seed_oss": 0,
        "smol": 10,
        "stablelm": 19,
        "starcoder": 49,
        "tulu": 14,
        "vicuna": 162,
        "yi": 41
      },
      "month": "2024-11",
      "papers_discovered": 6852,
      "papers_scanned": 6817,
      "source_counts": {
        "arxiv_bulk_pdf": 6817,
        "html": 0,
        "other": 0,
        "pdf": 0
      },
      "status": "final",
      "unscanned_by_reason": {
        "bulk_pdf_missing": 35
      }
    },
    {
      "any_llm_papers": 3166,
      "family_papers": {
        "alpaca": 99,
        "arctic": 15,
        "aya": 22,
        "baichuan": 55,
        "bloom": 30,
        "claude": 435,
        "cog": 179,
        "cohere_command": 36,
        "dbrx": 22,
        "deepseek": 323,
        "ernie": 22,
        "exaone": 2,
        "falcon": 52,
        "gemini": 456,
        "gemma": 315,
        "glm": 152,
        "gpt_neo": 57,
        "gpt_oss": 5,
        "granite": 13,
        "hunyuan": 39,
        "internlm": 127,
        "internvl": 179,
        "jamba": 24,
        "kimi": 12,
        "lfm": 1,
        "llada": 0,
        "llama": 1825,
        "llava": 518,
        "mimo": 0,
        "minicpm": 95,
        "minimax": 6,
        "mistral": 638,
        "molmo": 35,
        "mpt": 24,
        "nemotron": 31,
        "olmo": 64,
        "openai_gpt": 2756,
        "openllama": 12,
        "opt": 62,
        "phi": 209,
        "pythia": 30,
        "qwen": 770,
        "redpajama": 2,
        "rwkv": 34,
        "seed_oss": 0,
        "smol": 17,
        "stablelm": 19,
        "starcoder": 67,
        "tulu": 27,
        "vicuna": 172,
        "yi": 75
      },
      "month": "2024-12",
      "papers_discovered": 7879,
      "papers_scanned": 7850,
      "source_counts": {
        "arxiv_bulk_pdf": 7850,
        "html": 0,
        "other": 0,
        "pdf": 0
      },
      "status": "final",
      "unscanned_by_reason": {
        "bulk_pdf_missing": 29
      }
    },
    {
      "any_llm_papers": 2431,
      "family_papers": {
        "alpaca": 60,
        "arctic": 3,
        "aya": 14,
        "baichuan": 31,
        "bloom": 37,
        "claude": 347,
        "cog": 88,
        "cohere_command": 21,
        "dbrx": 3,
        "deepseek": 301,
        "ernie": 22,
        "exaone": 4,
        "falcon": 34,
        "gemini": 329,
        "gemma": 236,
        "glm": 93,
        "gpt_neo": 50,
        "gpt_oss": 0,
        "granite": 10,
        "hunyuan": 32,
        "internlm": 87,
        "internvl": 117,
        "jamba": 18,
        "kimi": 14,
        "lfm": 0,
        "llada": 0,
        "llama": 1377,
        "llava": 315,
        "mimo": 2,
        "minicpm": 59,
        "minimax": 4,
        "mistral": 484,
        "molmo": 19,
        "mpt": 5,
        "nemotron": 17,
        "olmo": 45,
        "openai_gpt": 2112,
        "openllama": 12,
        "opt": 49,
        "phi": 131,
        "pythia": 23,
        "qwen": 577,
        "redpajama": 2,
        "rwkv": 30,
        "seed_oss": 0,
        "smol": 15,
        "stablelm": 13,
        "starcoder": 41,
        "tulu": 22,
        "vicuna": 106,
        "yi": 36
      },
      "month": "2025-01",
      "papers_discovered": 6230,
      "papers_scanned": 6196,
      "source_counts": {
        "arxiv_bulk_pdf": 6196,
        "html": 0,
        "other": 0,
        "pdf": 0
      },
      "status": "final",
      "unscanned_by_reason": {
        "bulk_pdf_missing": 34
      }
    },
    {
      "any_llm_papers": 4265,
      "family_papers": {
        "alpaca": 138,
        "arctic": 11,
        "aya": 46,
        "baichuan": 49,
        "bloom": 63,
        "claude": 748,
        "cog": 117,
        "cohere_command": 41,
        "dbrx": 10,
        "deepseek": 1047,
        "ernie": 21,
        "exaone": 7,
        "falcon": 59,
        "gemini": 680,
        "gemma": 564,
        "glm": 153,
        "gpt_neo": 87,
        "gpt_oss": 1,
        "granite": 24,
        "hunyuan": 55,
        "internlm": 142,
        "internvl": 172,
        "jamba": 47,
        "kimi": 76,
        "lfm": 2,
        "llada": 7,
        "llama": 2683,
        "llava": 448,
        "mimo": 1,
        "minicpm": 104,
        "minimax": 14,
        "mistral": 1022,
        "molmo": 35,
        "mpt": 23,
        "nemotron": 32,
        "olmo": 148,
        "openai_gpt": 3697,
        "openllama": 16,
        "opt": 98,
        "phi": 259,
        "pythia": 70,
        "qwen": 1390,
        "redpajama": 6,
        "rwkv": 51,
        "seed_oss": 0,
        "smol": 43,
        "stablelm": 15,
        "starcoder": 79,
        "tulu": 70,
        "vicuna": 217,
        "yi": 84
      },
      "month": "2025-02",
      "papers_discovered": 8729,
      "papers_scanned": 8672,
      "source_counts": {
        "arxiv_bulk_pdf": 8672,
        "html": 0,
        "other": 0,
        "pdf": 0
      },
      "status": "final",
      "unscanned_by_reason": {
        "bulk_pdf_missing": 57
      }
    },
    {
      "any_llm_papers": 4085,
      "family_papers": {
        "alpaca": 107,
        "arctic": 7,
        "aya": 30,
        "baichuan": 31,
        "bloom": 26,
        "claude": 642,
        "cog": 214,
        "cohere_command": 23,
        "dbrx": 6,
        "deepseek": 1036,
        "ernie": 26,
        "exaone": 7,
        "falcon": 45,
        "gemini": 684,
        "gemma": 410,
        "glm": 140,
        "gpt_neo": 64,
        "gpt_oss": 5,
        "granite": 22,
        "hunyuan": 128,
        "internlm": 147,
        "internvl": 316,
        "jamba": 25,
        "kimi": 82,
        "lfm": 0,
        "llada": 3,
        "llama": 2194,
        "llava": 681,
        "mimo": 3,
        "minicpm": 125,
        "minimax": 17,
        "mistral": 713,
        "molmo": 46,
        "mpt": 15,
        "nemotron": 28,
        "olmo": 117,
        "openai_gpt": 3465,
        "openllama": 18,
        "opt": 55,
        "phi": 222,
        "pythia": 45,
        "qwen": 1335,
        "redpajama": 1,
        "rwkv": 42,
        "seed_oss": 0,
        "smol": 43,
        "stablelm": 14,
        "starcoder": 71,
        "tulu": 54,
        "vicuna": 180,
        "yi": 55
      },
      "month": "2025-03",
      "papers_discovered": 9285,
      "papers_scanned": 9228,
      "source_counts": {
        "arxiv_bulk_pdf": 9228,
        "html": 0,
        "other": 0,
        "pdf": 0
      },
      "status": "final",
      "unscanned_by_reason": {
        "bulk_pdf_missing": 57
      }
    },
    {
      "any_llm_papers": 3315,
      "family_papers": {
        "alpaca": 67,
        "arctic": 13,
        "aya": 25,
        "baichuan": 31,
        "bloom": 23,
        "claude": 554,
        "cog": 127,
        "cohere_command": 31,
        "dbrx": 12,
        "deepseek": 960,
        "ernie": 12,
        "exaone": 8,
        "falcon": 33,
        "gemini": 581,
        "gemma": 376,
        "glm": 98,
        "gpt_neo": 56,
        "gpt_oss": 13,
        "granite": 20,
        "hunyuan": 79,
        "internlm": 85,
        "internvl": 202,
        "jamba": 21,
        "kimi": 111,
        "lfm": 1,
        "llada": 4,
        "llama": 1828,
        "llava": 434,
        "mimo": 2,
        "minicpm": 86,
        "minimax": 10,
        "mistral": 564,
        "molmo": 40,
        "mpt": 5,
        "nemotron": 36,
        "olmo": 70,
        "openai_gpt": 2822,
        "openllama": 4,
        "opt": 45,
        "phi": 151,
        "pythia": 31,
        "qwen": 1121,
        "redpajama": 1,
        "rwkv": 47,
        "seed_oss": 0,
        "smol": 35,
        "stablelm": 6,
        "starcoder": 51,
        "tulu": 49,
        "vicuna": 125,
        "yi": 42
      },
      "month": "2025-04",
      "papers_discovered": 7361,
      "papers_scanned": 7321,
      "source_counts": {
        "arxiv_bulk_pdf": 7321,
        "html": 0,
        "other": 0,
        "pdf": 0
      },
      "status": "final",
      "unscanned_by_reason": {
        "bulk_pdf_missing": 40
      }
    },
    {
      "any_llm_papers": 5800,
      "family_papers": {
        "alpaca": 132,
        "arctic": 15,
        "aya": 58,
        "baichuan": 57,
        "bloom": 47,
        "claude": 1096,
        "cog": 166,
        "cohere_command": 49,
        "dbrx": 9,
        "deepseek": 2098,
        "ernie": 31,
        "exaone": 8,
        "falcon": 71,
        "gemini": 1220,
        "gemma": 773,
        "glm": 172,
        "gpt_neo": 94,
        "gpt_oss": 32,
        "granite": 49,
        "hunyuan": 133,
        "internlm": 175,
        "internvl": 391,
        "jamba": 25,
        "kimi": 281,
        "lfm": 4,
        "llada": 21,
        "llama": 3361,
        "llava": 831,
        "mimo": 10,
        "minicpm": 141,
        "minimax": 26,
        "mistral": 1047,
        "molmo": 57,
        "mpt": 29,
        "nemotron": 82,
        "olmo": 141,
        "openai_gpt": 4971,
        "openllama": 10,
        "opt": 85,
        "phi": 274,
        "pythia": 69,
        "qwen": 2573,
        "redpajama": 2,
        "rwkv": 51,
        "seed_oss": 1,
        "smol": 50,
        "stablelm": 18,
        "starcoder": 89,
        "tulu": 95,
        "vicuna": 221,
        "yi": 66
      },
      "month": "2025-05",
      "papers_discovered": 11269,
      "papers_scanned": 11204,
      "source_counts": {
        "arxiv_bulk_pdf": 11204,
        "html": 0,
        "other": 0,
        "pdf": 0
      },
      "status": "final",
      "unscanned_by_reason": {
        "bulk_pdf_missing": 64,
        "pdftotext_exited_with_status_1_for_temporary_pdf": 1
      }
    },
    {
      "any_llm_papers": 4646,
      "family_papers": {
        "alpaca": 81,
        "arctic": 12,
        "aya": 29,
        "baichuan": 48,
        "bloom": 33,
        "claude": 860,
        "cog": 188,
        "cohere_command": 27,
        "dbrx": 10,
        "deepseek": 1487,
        "ernie": 11,
        "exaone": 13,
        "falcon": 43,
        "gemini": 975,
        "gemma": 610,
        "glm": 121,
        "gpt_neo": 69,
        "gpt_oss": 26,
        "granite": 20,
        "hunyuan": 141,
        "internlm": 131,
        "internvl": 340,
        "jamba": 21,
        "kimi": 176,
        "lfm": 0,
        "llada": 11,
        "llama": 2540,
        "llava": 670,
        "mimo": 9,
        "minicpm": 114,
        "minimax": 9,
        "mistral": 812,
        "molmo": 39,
        "mpt": 11,
        "nemotron": 60,
        "olmo": 136,
        "openai_gpt": 3868,
        "openllama": 9,
        "opt": 56,
        "phi": 193,
        "pythia": 54,
        "qwen": 1892,
        "redpajama": 0,
        "rwkv": 44,
        "seed_oss": 0,
        "smol": 51,
        "stablelm": 7,
        "starcoder": 61,
        "tulu": 69,
        "vicuna": 162,
        "yi": 40
      },
      "month": "2025-06",
      "papers_discovered": 9399,
      "papers_scanned": 9356,
      "source_counts": {
        "arxiv_bulk_pdf": 9356,
        "html": 0,
        "other": 0,
        "pdf": 0
      },
      "status": "final",
      "unscanned_by_reason": {
        "bulk_pdf_missing": 42,
        "pdf_extracted_170_characters_minimum_is_200": 1
      }
    },
    {
      "any_llm_papers": 3672,
      "family_papers": {
        "alpaca": 56,
        "arctic": 12,
        "aya": 20,
        "baichuan": 29,
        "bloom": 29,
        "claude": 619,
        "cog": 116,
        "cohere_command": 24,
        "dbrx": 7,
        "deepseek": 1102,
        "ernie": 24,
        "exaone": 13,
        "falcon": 32,
        "gemini": 765,
        "gemma": 459,
        "glm": 89,
        "gpt_neo": 49,
        "gpt_oss": 18,
        "granite": 28,
        "hunyuan": 86,
        "internlm": 81,
        "internvl": 205,
        "jamba": 26,
        "kimi": 125,
        "lfm": 0,
        "llada": 17,
        "llama": 1870,
        "llava": 482,
        "mimo": 13,
        "minicpm": 79,
        "minimax": 27,
        "mistral": 592,
        "molmo": 37,
        "mpt": 14,
        "nemotron": 55,
        "olmo": 71,
        "openai_gpt": 3006,
        "openllama": 11,
        "opt": 48,
        "phi": 122,
        "pythia": 27,
        "qwen": 1410,
        "redpajama": 2,
        "rwkv": 41,
        "seed_oss": 0,
        "smol": 28,
        "stablelm": 9,
        "starcoder": 63,
        "tulu": 59,
        "vicuna": 117,
        "yi": 31
      },
      "month": "2025-07",
      "papers_discovered": 8207,
      "papers_scanned": 8171,
      "source_counts": {
        "arxiv_bulk_pdf": 8171,
        "html": 0,
        "other": 0,
        "pdf": 0
      },
      "status": "final",
      "unscanned_by_reason": {
        "bulk_pdf_missing": 36
      }
    },
    {
      "any_llm_papers": 4193,
      "family_papers": {
        "alpaca": 68,
        "arctic": 6,
        "aya": 33,
        "baichuan": 39,
        "bloom": 21,
        "claude": 754,
        "cog": 132,
        "cohere_command": 19,
        "dbrx": 6,
        "deepseek": 1338,
        "ernie": 23,
        "exaone": 11,
        "falcon": 38,
        "gemini": 949,
        "gemma": 478,
        "glm": 155,
        "gpt_neo": 58,
        "gpt_oss": 64,
        "granite": 28,
        "hunyuan": 103,
        "internlm": 86,
        "internvl": 256,
        "jamba": 9,
        "kimi": 183,
        "lfm": 1,
        "llada": 25,
        "llama": 2051,
        "llava": 510,
        "mimo": 26,
        "minicpm": 95,
        "minimax": 23,
        "mistral": 615,
        "molmo": 21,
        "mpt": 9,
        "nemotron": 60,
        "olmo": 73,
        "openai_gpt": 3431,
        "openllama": 6,
        "opt": 45,
        "phi": 144,
        "pythia": 29,
        "qwen": 1834,
        "redpajama": 0,
        "rwkv": 21,
        "seed_oss": 0,
        "smol": 48,
        "stablelm": 8,
        "starcoder": 42,
        "tulu": 47,
        "vicuna": 120,
        "yi": 39
      },
      "month": "2025-08",
      "papers_discovered": 8725,
      "papers_scanned": 8673,
      "source_counts": {
        "arxiv_bulk_pdf": 8673,
        "html": 0,
        "other": 0,
        "pdf": 0
      },
      "status": "final",
      "unscanned_by_reason": {
        "bulk_pdf_missing": 51,
        "pdftotext_exceeded_120_0_seconds_for_temporary_pdf": 1
      }
    },
    {
      "any_llm_papers": 4800,
      "family_papers": {
        "alpaca": 68,
        "arctic": 8,
        "aya": 33,
        "baichuan": 34,
        "bloom": 40,
        "claude": 787,
        "cog": 122,
        "cohere_command": 23,
        "dbrx": 1,
        "deepseek": 1596,
        "ernie": 21,
        "exaone": 14,
        "falcon": 53,
        "gemini": 1145,
        "gemma": 626,
        "glm": 185,
        "gpt_neo": 62,
        "gpt_oss": 138,
        "granite": 33,
        "hunyuan": 118,
        "internlm": 100,
        "internvl": 321,
        "jamba": 10,
        "kimi": 245,
        "lfm": 4,
        "llada": 52,
        "llama": 2370,
        "llava": 590,
        "mimo": 26,
        "minicpm": 114,
        "minimax": 29,
        "mistral": 735,
        "molmo": 56,
        "mpt": 17,
        "nemotron": 97,
        "olmo": 107,
        "openai_gpt": 3867,
        "openllama": 4,
        "opt": 41,
        "phi": 165,
        "pythia": 46,
        "qwen": 2193,
        "redpajama": 2,
        "rwkv": 35,
        "seed_oss": 4,
        "smol": 73,
        "stablelm": 7,
        "starcoder": 53,
        "tulu": 92,
        "vicuna": 124,
        "yi": 48
      },
      "month": "2025-09",
      "papers_discovered": 9741,
      "papers_scanned": 9717,
      "source_counts": {
        "arxiv_bulk_pdf": 9717,
        "html": 0,
        "other": 0,
        "pdf": 0
      },
      "status": "final",
      "unscanned_by_reason": {
        "bulk_pdf_missing": 24
      }
    },
    {
      "any_llm_papers": 5725,
      "family_papers": {
        "alpaca": 90,
        "arctic": 13,
        "aya": 46,
        "baichuan": 45,
        "bloom": 29,
        "claude": 1077,
        "cog": 149,
        "cohere_command": 45,
        "dbrx": 5,
        "deepseek": 2026,
        "ernie": 26,
        "exaone": 18,
        "falcon": 50,
        "gemini": 1457,
        "gemma": 817,
        "glm": 235,
        "gpt_neo": 70,
        "gpt_oss": 275,
        "granite": 52,
        "hunyuan": 139,
        "internlm": 117,
        "internvl": 378,
        "jamba": 29,
        "kimi": 337,
        "lfm": 4,
        "llada": 67,
        "llama": 2757,
        "llava": 625,
        "mimo": 37,
        "minicpm": 113,
        "minimax": 39,
        "mistral": 857,
        "molmo": 51,
        "mpt": 15,
        "nemotron": 129,
        "olmo": 141,
        "openai_gpt": 4577,
        "openllama": 8,
        "opt": 74,
        "phi": 184,
        "pythia": 65,
        "qwen": 2807,
        "redpajama": 2,
        "rwkv": 44,
        "seed_oss": 14,
        "smol": 84,
        "stablelm": 8,
        "starcoder": 62,
        "tulu": 133,
        "vicuna": 131,
        "yi": 41
      },
      "month": "2025-10",
      "papers_discovered": 10733,
      "papers_scanned": 10696,
      "source_counts": {
        "arxiv_bulk_pdf": 10696,
        "html": 0,
        "other": 0,
        "pdf": 0
      },
      "status": "final",
      "unscanned_by_reason": {
        "bulk_pdf_missing": 37
      }
    },
    {
      "any_llm_papers": 4246,
      "family_papers": {
        "alpaca": 46,
        "arctic": 11,
        "aya": 20,
        "baichuan": 24,
        "bloom": 15,
        "claude": 736,
        "cog": 142,
        "cohere_command": 18,
        "dbrx": 3,
        "deepseek": 1337,
        "ernie": 24,
        "exaone": 4,
        "falcon": 34,
        "gemini": 1059,
        "gemma": 528,
        "glm": 158,
        "gpt_neo": 41,
        "gpt_oss": 169,
        "granite": 40,
        "hunyuan": 141,
        "internlm": 69,
        "internvl": 347,
        "jamba": 25,
        "kimi": 211,
        "lfm": 9,
        "llada": 33,
        "llama": 1905,
        "llava": 613,
        "mimo": 31,
        "minicpm": 73,
        "minimax": 30,
        "mistral": 590,
        "molmo": 47,
        "mpt": 6,
        "nemotron": 60,
        "olmo": 76,
        "openai_gpt": 3326,
        "openllama": 7,
        "opt": 41,
        "phi": 119,
        "pythia": 27,
        "qwen": 1974,
        "redpajama": 1,
        "rwkv": 38,
        "seed_oss": 3,
        "smol": 55,
        "stablelm": 9,
        "starcoder": 38,
        "tulu": 55,
        "vicuna": 104,
        "yi": 20
      },
      "month": "2025-11",
      "papers_discovered": 9146,
      "papers_scanned": 9111,
      "source_counts": {
        "arxiv_bulk_pdf": 9111,
        "html": 0,
        "other": 0,
        "pdf": 0
      },
      "status": "final",
      "unscanned_by_reason": {
        "bulk_pdf_missing": 35
      }
    },
    {
      "any_llm_papers": 3912,
      "family_papers": {
        "alpaca": 44,
        "arctic": 10,
        "aya": 16,
        "baichuan": 21,
        "bloom": 16,
        "claude": 685,
        "cog": 196,
        "cohere_command": 10,
        "dbrx": 4,
        "deepseek": 1201,
        "ernie": 21,
        "exaone": 9,
        "falcon": 26,
        "gemini": 1050,
        "gemma": 459,
        "glm": 188,
        "gpt_neo": 44,
        "gpt_oss": 178,
        "granite": 37,
        "hunyuan": 207,
        "internlm": 79,
        "internvl": 321,
        "jamba": 14,
        "kimi": 203,
        "lfm": 8,
        "llada": 44,
        "llama": 1591,
        "llava": 526,
        "mimo": 31,
        "minicpm": 79,
        "minimax": 31,
        "mistral": 448,
        "molmo": 36,
        "mpt": 3,
        "nemotron": 68,
        "olmo": 61,
        "openai_gpt": 2978,
        "openllama": 11,
        "opt": 40,
        "phi": 113,
        "pythia": 23,
        "qwen": 1851,
        "redpajama": 2,
        "rwkv": 33,
        "seed_oss": 11,
        "smol": 51,
        "stablelm": 6,
        "starcoder": 44,
        "tulu": 61,
        "vicuna": 84,
        "yi": 20
      },
      "month": "2025-12",
      "papers_discovered": 8020,
      "papers_scanned": 7993,
      "source_counts": {
        "arxiv_bulk_pdf": 7993,
        "html": 0,
        "other": 0,
        "pdf": 0
      },
      "status": "final",
      "unscanned_by_reason": {
        "bulk_pdf_missing": 27
      }
    },
    {
      "any_llm_papers": 5041,
      "family_papers": {
        "alpaca": 62,
        "arctic": 12,
        "aya": 36,
        "baichuan": 32,
        "bloom": 25,
        "claude": 992,
        "cog": 122,
        "cohere_command": 21,
        "dbrx": 4,
        "deepseek": 1794,
        "ernie": 23,
        "exaone": 16,
        "falcon": 37,
        "gemini": 1343,
        "gemma": 651,
        "glm": 283,
        "gpt_neo": 40,
        "gpt_oss": 307,
        "granite": 49,
        "hunyuan": 144,
        "internlm": 80,
        "internvl": 297,
        "jamba": 22,
        "kimi": 342,
        "lfm": 8,
        "llada": 63,
        "llama": 2321,
        "llava": 504,
        "mimo": 46,
        "minicpm": 109,
        "minimax": 70,
        "mistral": 702,
        "molmo": 27,
        "mpt": 7,
        "nemotron": 116,
        "olmo": 125,
        "openai_gpt": 3916,
        "openllama": 5,
        "opt": 36,
        "phi": 103,
        "pythia": 46,
        "qwen": 2744,
        "redpajama": 1,
        "rwkv": 52,
        "seed_oss": 8,
        "smol": 63,
        "stablelm": 10,
        "starcoder": 53,
        "tulu": 81,
        "vicuna": 91,
        "yi": 33
      },
      "month": "2026-01",
      "papers_discovered": 9106,
      "papers_scanned": 9084,
      "source_counts": {
        "arxiv_bulk_pdf": 9084,
        "html": 0,
        "other": 0,
        "pdf": 0
      },
      "status": "final",
      "unscanned_by_reason": {
        "bulk_pdf_missing": 22
      }
    },
    {
      "any_llm_papers": 5370,
      "family_papers": {
        "alpaca": 76,
        "arctic": 7,
        "aya": 21,
        "baichuan": 31,
        "bloom": 15,
        "claude": 1082,
        "cog": 130,
        "cohere_command": 29,
        "dbrx": 4,
        "deepseek": 1828,
        "ernie": 31,
        "exaone": 7,
        "falcon": 31,
        "gemini": 1476,
        "gemma": 716,
        "glm": 273,
        "gpt_neo": 42,
        "gpt_oss": 341,
        "granite": 31,
        "hunyuan": 189,
        "internlm": 86,
        "internvl": 351,
        "jamba": 25,
        "kimi": 400,
        "lfm": 12,
        "llada": 80,
        "llama": 2291,
        "llava": 558,
        "mimo": 61,
        "minicpm": 114,
        "minimax": 112,
        "mistral": 687,
        "molmo": 46,
        "mpt": 4,
        "nemotron": 146,
        "olmo": 141,
        "openai_gpt": 4013,
        "openllama": 9,
        "opt": 62,
        "phi": 107,
        "pythia": 44,
        "qwen": 2920,
        "redpajama": 0,
        "rwkv": 55,
        "seed_oss": 12,
        "smol": 89,
        "stablelm": 6,
        "starcoder": 44,
        "tulu": 107,
        "vicuna": 103,
        "yi": 24
      },
      "month": "2026-02",
      "papers_discovered": 9908,
      "papers_scanned": 9881,
      "source_counts": {
        "arxiv_bulk_pdf": 9881,
        "html": 0,
        "other": 0,
        "pdf": 0
      },
      "status": "final",
      "unscanned_by_reason": {
        "bulk_pdf_missing": 27
      }
    },
    {
      "any_llm_papers": 6011,
      "family_papers": {
        "alpaca": 72,
        "arctic": 8,
        "aya": 17,
        "baichuan": 19,
        "bloom": 17,
        "claude": 1255,
        "cog": 210,
        "cohere_command": 27,
        "dbrx": 3,
        "deepseek": 1783,
        "ernie": 22,
        "exaone": 8,
        "falcon": 32,
        "gemini": 1726,
        "gemma": 769,
        "glm": 301,
        "gpt_neo": 48,
        "gpt_oss": 338,
        "granite": 42,
        "hunyuan": 249,
        "internlm": 87,
        "internvl": 515,
        "jamba": 26,
        "kimi": 394,
        "lfm": 14,
        "llada": 60,
        "llama": 2322,
        "llava": 780,
        "mimo": 62,
        "minicpm": 129,
        "minimax": 98,
        "mistral": 722,
        "molmo": 71,
        "mpt": 6,
        "nemotron": 125,
        "olmo": 150,
        "openai_gpt": 4388,
        "openllama": 7,
        "opt": 34,
        "phi": 99,
        "pythia": 37,
        "qwen": 3123,
        "redpajama": 0,
        "rwkv": 59,
        "seed_oss": 5,
        "smol": 71,
        "stablelm": 7,
        "starcoder": 56,
        "tulu": 95,
        "vicuna": 106,
        "yi": 16
      },
      "month": "2026-03",
      "papers_discovered": 11396,
      "papers_scanned": 11361,
      "source_counts": {
        "arxiv_bulk_pdf": 11361,
        "html": 0,
        "other": 0,
        "pdf": 0
      },
      "status": "final",
      "unscanned_by_reason": {
        "bulk_pdf_missing": 35
      }
    },
    {
      "any_llm_papers": 6175,
      "family_papers": {
        "alpaca": 69,
        "arctic": 12,
        "aya": 17,
        "baichuan": 25,
        "bloom": 16,
        "claude": 1585,
        "cog": 152,
        "cohere_command": 29,
        "dbrx": 3,
        "deepseek": 1902,
        "ernie": 22,
        "exaone": 12,
        "falcon": 47,
        "gemini": 1796,
        "gemma": 848,
        "glm": 320,
        "gpt_neo": 54,
        "gpt_oss": 397,
        "granite": 60,
        "hunyuan": 163,
        "internlm": 82,
        "internvl": 438,
        "jamba": 35,
        "kimi": 476,
        "lfm": 20,
        "llada": 65,
        "llama": 2548,
        "llava": 656,
        "mimo": 80,
        "minicpm": 103,
        "minimax": 116,
        "mistral": 891,
        "molmo": 52,
        "mpt": 12,
        "nemotron": 146,
        "olmo": 175,
        "openai_gpt": 4645,
        "openllama": 7,
        "opt": 47,
        "phi": 125,
        "pythia": 64,
        "qwen": 3320,
        "redpajama": 0,
        "rwkv": 53,
        "seed_oss": 8,
        "smol": 82,
        "stablelm": 8,
        "starcoder": 46,
        "tulu": 80,
        "vicuna": 101,
        "yi": 28
      },
      "month": "2026-04",
      "papers_discovered": 10811,
      "papers_scanned": 10784,
      "source_counts": {
        "arxiv_bulk_pdf": 10784,
        "html": 0,
        "other": 0,
        "pdf": 0
      },
      "status": "final",
      "unscanned_by_reason": {
        "bulk_pdf_missing": 27
      }
    },
    {
      "any_llm_papers": 8485,
      "family_papers": {
        "alpaca": 97,
        "arctic": 19,
        "aya": 20,
        "baichuan": 35,
        "bloom": 30,
        "claude": 2211,
        "cog": 218,
        "cohere_command": 35,
        "dbrx": 7,
        "deepseek": 2800,
        "ernie": 33,
        "exaone": 15,
        "falcon": 49,
        "gemini": 2361,
        "gemma": 1291,
        "glm": 519,
        "gpt_neo": 71,
        "gpt_oss": 532,
        "granite": 75,
        "hunyuan": 282,
        "internlm": 97,
        "internvl": 523,
        "jamba": 35,
        "kimi": 757,
        "lfm": 18,
        "llada": 116,
        "llama": 3304,
        "llava": 748,
        "mimo": 155,
        "minicpm": 147,
        "minimax": 239,
        "mistral": 1089,
        "molmo": 64,
        "mpt": 4,
        "nemotron": 259,
        "olmo": 294,
        "openai_gpt": 5936,
        "openllama": 8,
        "opt": 69,
        "phi": 153,
        "pythia": 96,
        "qwen": 4879,
        "redpajama": 2,
        "rwkv": 66,
        "seed_oss": 10,
        "smol": 113,
        "stablelm": 9,
        "starcoder": 58,
        "tulu": 135,
        "vicuna": 118,
        "yi": 39
      },
      "month": "2026-05",
      "papers_discovered": 15002,
      "papers_scanned": 14960,
      "source_counts": {
        "arxiv_bulk_pdf": 14960,
        "html": 0,
        "other": 0,
        "pdf": 0
      },
      "status": "final",
      "unscanned_by_reason": {
        "bulk_pdf_missing": 41,
        "pdftotext_exited_with_status_1_for_temporary_pdf": 1
      }
    },
    {
      "any_llm_papers": 6615,
      "family_papers": {
        "alpaca": 73,
        "arctic": 10,
        "aya": 18,
        "baichuan": 23,
        "bloom": 24,
        "claude": 1774,
        "cog": 165,
        "cohere_command": 24,
        "dbrx": 3,
        "deepseek": 2096,
        "ernie": 18,
        "exaone": 13,
        "falcon": 49,
        "gemini": 1820,
        "gemma": 993,
        "glm": 422,
        "gpt_neo": 59,
        "gpt_oss": 389,
        "granite": 58,
        "hunyuan": 234,
        "internlm": 63,
        "internvl": 411,
        "jamba": 28,
        "kimi": 556,
        "lfm": 15,
        "llada": 84,
        "llama": 2385,
        "llava": 611,
        "mimo": 128,
        "minicpm": 103,
        "minimax": 199,
        "mistral": 745,
        "molmo": 65,
        "mpt": 10,
        "nemotron": 191,
        "olmo": 211,
        "openai_gpt": 4545,
        "openllama": 3,
        "opt": 39,
        "phi": 124,
        "pythia": 61,
        "qwen": 3744,
        "redpajama": 3,
        "rwkv": 45,
        "seed_oss": 6,
        "smol": 95,
        "stablelm": 4,
        "starcoder": 54,
        "tulu": 93,
        "vicuna": 94,
        "yi": 24
      },
      "month": "2026-06",
      "papers_discovered": 11888,
      "papers_scanned": 11870,
      "source_counts": {
        "arxiv_bulk_pdf": 11870,
        "html": 0,
        "other": 0,
        "pdf": 0
      },
      "status": "final",
      "unscanned_by_reason": {
        "bulk_pdf_missing": 18
      }
    },
    {
      "any_llm_papers": 5007,
      "family_papers": {
        "alpaca": 36,
        "arctic": 7,
        "aya": 14,
        "baichuan": 13,
        "bloom": 13,
        "claude": 1347,
        "cog": 146,
        "cohere_command": 17,
        "dbrx": 1,
        "deepseek": 1480,
        "ernie": 13,
        "exaone": 6,
        "falcon": 36,
        "gemini": 1290,
        "gemma": 744,
        "glm": 349,
        "gpt_neo": 46,
        "gpt_oss": 235,
        "granite": 46,
        "hunyuan": 205,
        "internlm": 54,
        "internvl": 357,
        "jamba": 21,
        "kimi": 412,
        "lfm": 16,
        "llada": 39,
        "llama": 1569,
        "llava": 495,
        "mimo": 90,
        "minicpm": 79,
        "minimax": 147,
        "mistral": 545,
        "molmo": 32,
        "mpt": 2,
        "nemotron": 143,
        "olmo": 124,
        "openai_gpt": 3341,
        "openllama": 6,
        "opt": 30,
        "phi": 94,
        "pythia": 53,
        "qwen": 2695,
        "redpajama": 2,
        "rwkv": 40,
        "seed_oss": 1,
        "smol": 66,
        "stablelm": 6,
        "starcoder": 29,
        "tulu": 52,
        "vicuna": 64,
        "yi": 24
      },
      "month": "2026-07",
      "papers_discovered": 9438,
      "papers_scanned": 9422,
      "source_counts": {
        "arxiv_bulk_pdf": 9422,
        "html": 0,
        "other": 0,
        "pdf": 0
      },
      "status": "final",
      "unscanned_by_reason": {
        "bulk_pdf_missing": 16
      }
    },
    {
      "any_llm_papers": 6238,
      "family_papers": {
        "alpaca": 45,
        "arctic": 10,
        "aya": 27,
        "baichuan": 22,
        "bloom": 27,
        "claude": 1731,
        "cog": 130,
        "cohere_command": 13,
        "dbrx": 2,
        "deepseek": 1909,
        "ernie": 22,
        "exaone": 13,
        "falcon": 30,
        "gemini": 1611,
        "gemma": 981,
        "glm": 513,
        "gpt_neo": 45,
        "gpt_oss": 325,
        "granite": 62,
        "hunyuan": 206,
        "internlm": 62,
        "internvl": 400,
        "jamba": 25,
        "kimi": 606,
        "lfm": 21,
        "llada": 64,
        "llama": 2045,
        "llava": 573,
        "mimo": 106,
        "minicpm": 111,
        "minimax": 176,
        "mistral": 759,
        "molmo": 43,
        "mpt": 4,
        "nemotron": 178,
        "olmo": 196,
        "openai_gpt": 4160,
        "openllama": 6,
        "opt": 39,
        "phi": 98,
        "pythia": 64,
        "qwen": 3717,
        "redpajama": 0,
        "rwkv": 51,
        "seed_oss": 4,
        "smol": 96,
        "stablelm": 7,
        "starcoder": 35,
        "tulu": 73,
        "vicuna": 80,
        "yi": 19
      },
      "month": "2026-08",
      "papers_discovered": 10756,
      "papers_scanned": 10748,
      "source_counts": {
        "arxiv_bulk_pdf": 0,
        "html": 10180,
        "other": 0,
        "pdf": 568
      },
      "status": "final",
      "unscanned_by_reason": {
        "html_404": 8
      }
    },
    {
      "any_llm_papers": 3615,
      "family_papers": {
        "alpaca": 34,
        "arctic": 5,
        "aya": 15,
        "baichuan": 12,
        "bloom": 16,
        "claude": 1006,
        "cog": 57,
        "cohere_command": 16,
        "dbrx": 0,
        "deepseek": 1037,
        "ernie": 11,
        "exaone": 15,
        "falcon": 26,
        "gemini": 906,
        "gemma": 641,
        "glm": 259,
        "gpt_neo": 26,
        "gpt_oss": 219,
        "granite": 45,
        "hunyuan": 92,
        "internlm": 33,
        "internvl": 190,
        "jamba": 14,
        "kimi": 312,
        "lfm": 11,
        "llada": 37,
        "llama": 1180,
        "llava": 264,
        "mimo": 65,
        "minicpm": 63,
        "minimax": 106,
        "mistral": 459,
        "molmo": 25,
        "mpt": 2,
        "nemotron": 128,
        "olmo": 126,
        "openai_gpt": 2380,
        "openllama": 3,
        "opt": 30,
        "phi": 50,
        "pythia": 40,
        "qwen": 2135,
        "redpajama": 0,
        "rwkv": 24,
        "seed_oss": 3,
        "smol": 75,
        "stablelm": 4,
        "starcoder": 16,
        "tulu": 53,
        "vicuna": 40,
        "yi": 12
      },
      "month": "2026-09",
      "papers_discovered": 6429,
      "papers_scanned": 6428,
      "source_counts": {
        "arxiv_bulk_pdf": 0,
        "html": 6055,
        "other": 0,
        "pdf": 373
      },
      "status": "partial",
      "unscanned_by_reason": {
        "html_404": 1
      }
    }
  ],
  "preview_provenance": {
    "archive_plans_expected": 6711,
    "archive_plans_verified": 6711,
    "archive_sparse_bundle_identity": "643fe8f405c20477ecfe02fc1ded8fca6e43b6f315060d14459c9683cea2ec0c",
    "bootstrap_receipt_sha256": "152779ed4420ea968a5ac0cd7d99e863a4e355eb885cdb61172b82e1c697c4b6",
    "cutoff_exclusive": "2026-09-22T00:00:00Z",
    "handoff_manifest_sha256": "6a43ff111a732ad1a48d81885dbf218f1deb660d3415e2f38f0a9eeab723ff6b",
    "handoff_sha256": "0bda1d55606a4bb2b86bbc4f9a475f42d5b1a8e2394363399ac83da2f0be27c5",
    "kind": "daily_ledger_preview",
    "llm_denominator_family_count": 51,
    "llm_denominator_method": "unique_versionless_papers_with_any_release_eligible_kept_family",
    "monthly_any_llm_papers_sha256": "45aa49cbeb67ef32672c468589a68d34246518e5133fe12e5393c38816e09cf3",
    "oai_from_inclusive": "2026-09-20",
    "oai_next_from": "2026-09-21",
    "precision_policy_sha256": "b086781fa1ae86883b41fc3ce8edf9e800055b86c26b37b48266d03e37d82476",
    "precision_policy_version": "2026-08-21.2",
    "production_publishable": false,
    "publication_blockers": [
      "archive_sparse_not_production_publishable",
      "chart_date_basis_not_selected"
    ],
    "release_gate_rule": "submitted_at_at_or_after_verified_family_eligible_from",
    "retry_queue_closure_receipt_sha256": "0f8a6a24f20c4b04408a36349fcecf76301a37f4419994a22e069f3d87115c3c",
    "retry_queue_oldest_first_seen_date": "2026-08-23",
    "retry_queue_rows": 9,
    "retry_queue_sha256": "6ff1e796232e2008580f390395a137b3610a194da4b50b834f37b1e854b3224f",
    "retry_queue_unattempted_rows": 0,
    "run_id": "90ca0bc71eb89c21ac25",
    "scanner_commit": "67ef2169185bcad6ed1a2eec1570d854f9fd35d5",
    "scanner_interface_version": "arxiv-daily-state-v1",
    "state_generation_id": "4c48993416a219e2b351edeb3d64a0c60c922f72279751079496f7b481396ff0",
    "unresolved_temporal_families": [
      "deepseek",
      "kimi"
    ]
  },
  "schema_version": 2,
  "scope": {
    "categories": [
      "cs.AI",
      "cs.CL",
      "cs.CV",
      "cs.LG",
      "stat.ML"
    ],
    "co_mentions": "independent",
    "content_sources": [
      "arxiv_bulk_pdf",
      "html",
      "other",
      "pdf"
    ],
    "date_basis": "first_submission",
    "includes_bibliography": true,
    "llm_denominator": "unique_versionless_papers_with_any_release_eligible_kept_family",
    "mention_unit": "paper_presence",
    "version_policy": "latest_available_at_scan"
  },
  "taxonomy": {
    "families": [
      {
        "default_visible": true,
        "key": "qwen",
        "label": "Qwen"
      },
      {
        "default_visible": true,
        "key": "llama",
        "label": "Llama"
      },
      {
        "default_visible": true,
        "key": "deepseek",
        "label": "DeepSeek"
      },
      {
        "default_visible": false,
        "key": "mistral",
        "label": "Mistral"
      },
      {
        "default_visible": false,
        "key": "gemma",
        "label": "Gemma"
      },
      {
        "default_visible": false,
        "key": "kimi",
        "label": "Kimi"
      },
      {
        "default_visible": false,
        "key": "glm",
        "label": "GLM"
      },
      {
        "default_visible": false,
        "key": "olmo",
        "label": "OLMo"
      },
      {
        "default_visible": false,
        "key": "nemotron",
        "label": "Nemotron"
      },
      {
        "default_visible": false,
        "key": "phi",
        "label": "Phi"
      },
      {
        "default_visible": false,
        "key": "gpt_oss",
        "label": "GPT-OSS"
      },
      {
        "default_visible": false,
        "key": "hunyuan",
        "label": "Hunyuan"
      },
      {
        "default_visible": false,
        "key": "internvl",
        "label": "InternVL"
      },
      {
        "default_visible": false,
        "key": "llava",
        "label": "LLaVA"
      },
      {
        "default_visible": false,
        "key": "minimax",
        "label": "MiniMax"
      },
      {
        "default_visible": false,
        "key": "mimo",
        "label": "MiMo"
      },
      {
        "default_visible": false,
        "key": "granite",
        "label": "Granite"
      },
      {
        "default_visible": false,
        "key": "minicpm",
        "label": "MiniCPM"
      },
      {
        "default_visible": false,
        "key": "smol",
        "label": "SmolLM/SmolVLM"
      },
      {
        "default_visible": false,
        "key": "molmo",
        "label": "Molmo"
      },
      {
        "default_visible": false,
        "key": "falcon",
        "label": "Falcon"
      },
      {
        "default_visible": false,
        "key": "cohere_command",
        "label": "Command"
      },
      {
        "default_visible": false,
        "key": "aya",
        "label": "Aya"
      },
      {
        "default_visible": false,
        "key": "tulu",
        "label": "Tulu"
      },
      {
        "default_visible": false,
        "key": "internlm",
        "label": "InternLM"
      },
      {
        "default_visible": false,
        "key": "yi",
        "label": "Yi"
      },
      {
        "default_visible": false,
        "key": "dbrx",
        "label": "DBRX"
      },
      {
        "default_visible": false,
        "key": "jamba",
        "label": "Jamba"
      },
      {
        "default_visible": false,
        "key": "arctic",
        "label": "Arctic"
      },
      {
        "default_visible": false,
        "key": "lfm",
        "label": "LFM"
      },
      {
        "default_visible": false,
        "key": "seed_oss",
        "label": "Seed-OSS"
      },
      {
        "default_visible": false,
        "key": "vicuna",
        "label": "Vicuna"
      },
      {
        "default_visible": false,
        "key": "alpaca",
        "label": "Alpaca"
      },
      {
        "default_visible": false,
        "key": "bloom",
        "label": "BLOOM/BLOOMZ"
      },
      {
        "default_visible": false,
        "key": "opt",
        "label": "OPT"
      },
      {
        "default_visible": false,
        "key": "gpt_neo",
        "label": "GPT-J/Neo/NeoX"
      },
      {
        "default_visible": false,
        "key": "pythia",
        "label": "Pythia"
      },
      {
        "default_visible": false,
        "key": "mpt",
        "label": "MPT"
      },
      {
        "default_visible": false,
        "key": "stablelm",
        "label": "StableLM"
      },
      {
        "default_visible": false,
        "key": "redpajama",
        "label": "RedPajama"
      },
      {
        "default_visible": false,
        "key": "openllama",
        "label": "OpenLLaMA"
      },
      {
        "default_visible": false,
        "key": "rwkv",
        "label": "RWKV"
      },
      {
        "default_visible": false,
        "key": "starcoder",
        "label": "StarCoder"
      },
      {
        "default_visible": false,
        "key": "baichuan",
        "label": "Baichuan"
      },
      {
        "default_visible": false,
        "key": "ernie",
        "label": "ERNIE"
      },
      {
        "default_visible": false,
        "key": "exaone",
        "label": "EXAONE"
      },
      {
        "default_visible": false,
        "key": "llada",
        "label": "LLaDA"
      },
      {
        "default_visible": false,
        "key": "cog",
        "label": "CogVLM/CogVideo"
      },
      {
        "default_visible": true,
        "key": "openai_gpt",
        "label": "OpenAI GPT"
      },
      {
        "default_visible": true,
        "key": "claude",
        "label": "Claude"
      },
      {
        "default_visible": true,
        "key": "gemini",
        "label": "Gemini"
      }
    ],
    "sha256": "004f9c7e35504130d057dc926c9415ffa61cce0af2d896bf2316e68f448649b5",
    "version": "2026-08-21.4"
  }
}
