| { |
| "model_dir": "models\\v8_code_aware_50k_oss_clean_plus_fp_pool", |
| "holdout": "data\\clf\\benign_code_holdout_github_lora_clean.jsonl", |
| "overall": { |
| "n": 12000, |
| "threshold": 0.5, |
| "false_positive_rate": 0.0078, |
| "flagged": 94, |
| "score_mean": 0.021276, |
| "score_p50": 0.000913, |
| "score_p90": 0.035272, |
| "score_p95": 0.103479, |
| "score_p99": 0.46175, |
| "score_max": 0.973555 |
| }, |
| "by_source": { |
| "local_project_code": { |
| "n": 160, |
| "threshold": 0.5, |
| "false_positive_rate": 0.0063, |
| "flagged": 1, |
| "score_mean": 0.020748, |
| "score_p50": 0.002427, |
| "score_p90": 0.032955, |
| "score_p95": 0.04948, |
| "score_p99": 0.362833, |
| "score_max": 0.770936 |
| }, |
| "local_repo_hs": { |
| "n": 14, |
| "threshold": 0.5, |
| "false_positive_rate": 0.2143, |
| "flagged": 3, |
| "score_mean": 0.228853, |
| "score_p50": 0.142727, |
| "score_p90": 0.537983, |
| "score_p95": 0.563626, |
| "score_p99": 0.598728, |
| "score_max": 0.607504 |
| }, |
| "local_repo_isre": { |
| "n": 173, |
| "threshold": 0.5, |
| "false_positive_rate": 0.0, |
| "flagged": 0, |
| "score_mean": 0.010636, |
| "score_p50": 0.001124, |
| "score_p90": 0.025243, |
| "score_p95": 0.045867, |
| "score_p99": 0.159579, |
| "score_max": 0.214947 |
| }, |
| "local_repo_job_application_pipeline": { |
| "n": 444, |
| "threshold": 0.5, |
| "false_positive_rate": 0.0023, |
| "flagged": 1, |
| "score_mean": 0.01678, |
| "score_p50": 0.001522, |
| "score_p90": 0.027532, |
| "score_p95": 0.091225, |
| "score_p99": 0.264842, |
| "score_max": 0.682698 |
| }, |
| "local_repo_llama_cpp": { |
| "n": 1000, |
| "threshold": 0.5, |
| "false_positive_rate": 0.009, |
| "flagged": 9, |
| "score_mean": 0.035161, |
| "score_p50": 0.004799, |
| "score_p90": 0.073904, |
| "score_p95": 0.176423, |
| "score_p99": 0.490611, |
| "score_max": 0.960493 |
| }, |
| "local_repo_olympiad_math": { |
| "n": 53, |
| "threshold": 0.5, |
| "false_positive_rate": 0.0, |
| "flagged": 0, |
| "score_mean": 0.010182, |
| "score_p50": 0.001314, |
| "score_p90": 0.020649, |
| "score_p95": 0.058206, |
| "score_p99": 0.131524, |
| "score_max": 0.152684 |
| }, |
| "local_repo_packing": { |
| "n": 316, |
| "threshold": 0.5, |
| "false_positive_rate": 0.0032, |
| "flagged": 1, |
| "score_mean": 0.010008, |
| "score_p50": 0.000221, |
| "score_p90": 0.004749, |
| "score_p95": 0.024278, |
| "score_p99": 0.22543, |
| "score_max": 0.720243 |
| }, |
| "local_repo_pipeline": { |
| "n": 136, |
| "threshold": 0.5, |
| "false_positive_rate": 0.0074, |
| "flagged": 1, |
| "score_mean": 0.012794, |
| "score_p50": 0.001298, |
| "score_p90": 0.014629, |
| "score_p95": 0.035176, |
| "score_p99": 0.257477, |
| "score_max": 0.565864 |
| }, |
| "local_repo_repo": { |
| "n": 13, |
| "threshold": 0.5, |
| "false_positive_rate": 0.0, |
| "flagged": 0, |
| "score_mean": 0.050017, |
| "score_p50": 0.002628, |
| "score_p90": 0.143356, |
| "score_p95": 0.177811, |
| "score_p99": 0.216438, |
| "score_max": 0.226095 |
| }, |
| "local_repo_utils": { |
| "n": 114, |
| "threshold": 0.5, |
| "false_positive_rate": 0.0088, |
| "flagged": 1, |
| "score_mean": 0.012336, |
| "score_p50": 0.000708, |
| "score_p90": 0.011919, |
| "score_p95": 0.036259, |
| "score_p99": 0.104212, |
| "score_max": 0.767851 |
| }, |
| "local_repo_vesuvius": { |
| "n": 730, |
| "threshold": 0.5, |
| "false_positive_rate": 0.074, |
| "flagged": 54, |
| "score_mean": 0.124375, |
| "score_p50": 0.024499, |
| "score_p90": 0.402151, |
| "score_p95": 0.62727, |
| "score_p99": 0.933021, |
| "score_max": 0.973555 |
| }, |
| "python_stdlib": { |
| "n": 8847, |
| "threshold": 0.5, |
| "false_positive_rate": 0.0026, |
| "flagged": 23, |
| "score_mean": 0.011986, |
| "score_p50": 0.000588, |
| "score_p90": 0.0194, |
| "score_p95": 0.047762, |
| "score_p99": 0.256061, |
| "score_max": 0.935251 |
| } |
| }, |
| "flagged_examples": [ |
| { |
| "score": 0.770936, |
| "source": "local_project_code", |
| "path": "C:\\GitHub\\Safety DS\\scripts\\build_malware_code_pool.py", |
| "preview": "def download_vxunderground( spec: dict, builder: PoolBuilder, chunk_cfg: dict, insecure: bool ) -> None: repo = spec[\"repo\"] cache = ROOT / spec.get(\"cache_dir\", \"data/external/vxunderground\") cache.mkdir(parents=True, exist_ok=True) for su" |
| }, |
| { |
| "score": 0.720243, |
| "source": "local_repo_packing", |
| "path": "C:\\GitHub\\packing\\core\\pack_cuda_primitives.py", |
| "preview": "ss) forward_counts[0] = n_subj; for (int i = 0; i < n_subj; ++i) { forward_polys[0][i] = subj[i]; } } else { // Initialize current buffer current_count = n_subj; for (int i = 0; i < n_subj; ++i) { current_poly[i] = subj[i]; } } // Apply eac" |
| }, |
| { |
| "score": 0.53516, |
| "source": "local_repo_llama_cpp", |
| "path": "C:\\lora_training\\llama.cpp\\convert_hf_to_gguf.py", |
| "preview": "def __init__(self, *args, **kwargs): super().__init__(*args, **kwargs) # SwigLU activation assert self.hparams[\"activation_function\"] == \"swiglu\" # ALiBi position embedding assert self.hparams[\"position_embedding_type\"] == \"alibi\" # Embeddi" |
| }, |
| { |
| "score": 0.659107, |
| "source": "local_repo_llama_cpp", |
| "path": "C:\\lora_training\\llama.cpp\\common\\arg.cpp", |
| "preview": "_ARG_NO_KV_OFFLOAD\")); add_opt(common_arg( {\"-nr\", \"--no-repack\"}, \"disable weight repacking\", [](common_params & params) { params.no_extra_bufts = true; } ).set_env(\"LLAMA_ARG_NO_REPACK\")); add_opt(common_arg( {\"--no-host\"}, \"bypass host b" |
| }, |
| { |
| "score": 0.960493, |
| "source": "local_repo_llama_cpp", |
| "path": "C:\\lora_training\\llama.cpp\\common\\arg.cpp", |
| "preview": "nd_dev_t> devices; for (size_t i = 0; i < ggml_backend_dev_count(); ++i) { auto * dev = ggml_backend_dev_get(i); if (ggml_backend_dev_type(dev) != GGML_BACKEND_DEVICE_TYPE_CPU) { devices.push_back(dev); } } printf(\"Available devices:\\n\"); f" |
| }, |
| { |
| "score": 0.772781, |
| "source": "local_repo_llama_cpp", |
| "path": "C:\\lora_training\\llama.cpp\\common\\chat-parser-xml-toolcall.cpp", |
| "preview": "int i = l; while (i < r) { const std::string &s = forbids[i]; if ((int)s.size() == depth) { ++i; continue; } unsigned char c = (unsigned char)s[depth]; int j = i; while (j < r && (int)forbids[j].size() > depth && (unsigned char)forbids[j][d" |
| }, |
| { |
| "score": 0.783634, |
| "source": "local_repo_llama_cpp", |
| "path": "C:\\lora_training\\llama.cpp\\common\\common.cpp", |
| "preview": "d-%H_%M_%S\", std::localtime(&as_time_t)); const int64_t ns = std::chrono::duration_cast<std::chrono::nanoseconds>( current_time.time_since_epoch() % 1000000000).count(); char timestamp_ns[11]; snprintf(timestamp_ns, 11, \"%09\" PRId64, ns); r" |
| }, |
| { |
| "score": 0.837582, |
| "source": "local_repo_llama_cpp", |
| "path": "C:\\lora_training\\llama.cpp\\common\\common.cpp", |
| "preview": "ARATOR; } return p; }; if (getenv(\"LLAMA_CACHE\")) { cache_directory = std::getenv(\"LLAMA_CACHE\"); } else { #if defined(__linux__) || defined(__FreeBSD__) || defined(_AIX) || defined(__OpenBSD__) if (std::getenv(\"XDG_CACHE_HOME\")) { cache_di" |
| }, |
| { |
| "score": 0.695738, |
| "source": "local_repo_llama_cpp", |
| "path": "C:\\lora_training\\llama.cpp\\common\\download.cpp", |
| "preview": "local_path, token, false)) { throw std::runtime_error(\"Failed to download Docker Model\"); } LOG_INF(\"%s: Downloaded Docker Model to: %s\\n\", __func__, local_path.c_str()); return local_path; } catch (const std::exception & e) { LOG_ERR(\"%s: " |
| }, |
| { |
| "score": 0.602298, |
| "source": "local_repo_llama_cpp", |
| "path": "C:\\lora_training\\llama.cpp\\common\\json-partial.cpp", |
| "preview": "last_non_sp_char == 'E' || last_non_sp_char == '-'; }; std::string closing; for (size_t i = err_loc.stack.size(); i > 0; i--) { auto & el = err_loc.stack[i - 1]; if (el.type == COMMON_JSON_STACK_ELEMENT_OBJECT) { closing += \"}\"; } else if (" |
| }, |
| { |
| "score": 0.558078, |
| "source": "local_repo_llama_cpp", |
| "path": "C:\\lora_training\\llama.cpp\\common\\speculative.cpp", |
| "preview": "} { const int n_vocab_tgt = llama_vocab_n_tokens(vocab_tgt); const int n_vocab_dft = llama_vocab_n_tokens(vocab_dft); const int vocab_diff = n_vocab_tgt > n_vocab_dft ? n_vocab_tgt - n_vocab_dft : n_vocab_dft - n_vocab_tgt; if (vocab_diff >" |
| }, |
| { |
| "score": 0.565864, |
| "source": "local_repo_pipeline", |
| "path": "C:\\lora_training\\math_professor_sft\\pipeline\\run_llama32_1b_train_clean_v1.ps1", |
| "preview": "$ErrorActionPreference = \"Stop\" $ProjectRoot = \"C:\\lora_training\\math_professor_sft\" $Script = Join-Path $ProjectRoot \"pipeline\\train_llama32_1b_math_sft.py\" $Dataset = \"C:\\lora_training\\OLympiad\\final_sft_train_math_strict_v2_plus_openrout" |
| }, |
| { |
| "score": 0.767851, |
| "source": "local_repo_utils", |
| "path": "C:\\lora_training\\utils\\generate_variants.py", |
| "preview": "from transformers import AutoModelForCausalLM, AutoTokenizer from peft import PeftModel import torch import json # Загрузка модели (как в telegram_bot.py) base_model = AutoModelForCausalLM.from_pretrained( \"./solar_model\", device_map=\"auto\"" |
| }, |
| { |
| "score": 0.54, |
| "source": "local_repo_hs", |
| "path": "C:\\GitHub\\HS\\assets\\glitch.js", |
| "preview": "(function () { var padp = document.querySelector(\".vis-padp\"); if (!padp) return; var bars = padp.querySelectorAll(\".p-bar\"); var vals = padp.querySelectorAll(\".p-val\"); var steps = padp.querySelectorAll(\".p-step\"); var title = padp.querySe" |
| }, |
| { |
| "score": 0.607504, |
| "source": "local_repo_hs", |
| "path": "C:\\GitHub\\HS\\assets\\lora-anim.js", |
| "preview": "(nx*2 + t*0.10, ny*2 + t*0.07, 8); var ang = noise(nx*1.2, ny*1.2 + t*0.06, 9) * Math.PI * 4; var rot = { x: Math.cos(ang), y: Math.sin(ang) }; tvx = lerp(c3.x, rot.x, 0.55) * 5; tvy = lerp(c3.y, rot.y, 0.55) * 5; var cl = noise(nx*1.4, ny*" |
| }, |
| { |
| "score": 0.533278, |
| "source": "local_repo_hs", |
| "path": "C:\\GitHub\\HS\\assets\\sphere.js", |
| "preview": "var fx = (d.ox - d.x) * SPRING; var fy = (d.oy - d.y) * SPRING; if (mouse.active) { var ddx = mx - d.x, ddy = my - d.y; var dist2 = ddx*ddx + ddy*ddy; if (dist2 < pullR2 && dist2 > 0.01) { var dist = Math.sqrt(dist2); var t = 1 - dist/pullR" |
| }, |
| { |
| "score": 0.682698, |
| "source": "local_repo_job_application_pipeline", |
| "path": "C:\\GitHub\\Job Application Pipeline\\scripts\\run_daily_report.ps1", |
| "preview": "param( [string]$Date = \"\", [string]$SourcesConfig = \"\", [string]$Profile = \"\", [int]$MaxPackets = 1, [switch]$SkipPackets, [switch]$SkipTelegram ) $ErrorActionPreference = \"Stop\" $repoRoot = Split-Path -Parent $PSScriptRoot $env:PYTHONPATH " |
| }, |
| { |
| "score": 0.605122, |
| "source": "local_repo_vesuvius", |
| "path": "C:\\GitHub\\Vesuvius\\tools\\convert_gn_to_bn.py", |
| "preview": "class VesuviusEncoderGN(nn.Module): def __init__(self, in_channels=1, base_channels=32): super().__init__() c = base_channels self.enc2_0 = ConvBlockGN(in_channels, c) self.enc2_1 = ConvBlockGN(c * 1, c * 2) self.enc2_2 = ConvBlockGN(c * 4," |
| }, |
| { |
| "score": 0.606929, |
| "source": "local_repo_vesuvius", |
| "path": "C:\\GitHub\\Vesuvius\\tools\\convert_gn_to_bn.py", |
| "preview": "class VesuviusEncoderBN(nn.Module): def __init__(self, in_channels=1, base_channels=32): super().__init__() c = base_channels self.enc2_0 = ConvBlockBN(in_channels, c) self.enc2_1 = ConvBlockBN(c * 1, c * 2) self.enc2_2 = ConvBlockBN(c * 4," |
| }, |
| { |
| "score": 0.905741, |
| "source": "local_repo_vesuvius", |
| "path": "C:\\GitHub\\Vesuvius\\metric\\topological-metrics-kaggle\\external\\Betti-Matching-3D\\src\\main.cpp", |
| "preview": "; string unmatched0Filename = \"unmatched_0.csv\"; string unmatched1Filename = \"unmatched_1.csv\"; fileFormat format0; fileFormat format1; bool print = false; bool saveResult = false; for (int i = 1; i < argc; ++i) { const string arg(argv[i]);" |
| } |
| ] |
| } |
