| { |
| "model_dir": "models\\v6_code_aware_50k_oss_clean_benign_code", |
| "holdout": "data\\clf\\benign_code_holdout_lora_clean.jsonl", |
| "overall": { |
| "n": 10000, |
| "threshold": 0.5, |
| "false_positive_rate": 0.0097, |
| "flagged": 97, |
| "score_mean": 0.022216, |
| "score_p50": 0.000779, |
| "score_p90": 0.036148, |
| "score_p95": 0.103489, |
| "score_p99": 0.483205, |
| "score_max": 0.994358 |
| }, |
| "by_source": { |
| "local_project_code": { |
| "n": 160, |
| "threshold": 0.5, |
| "false_positive_rate": 0.0063, |
| "flagged": 1, |
| "score_mean": 0.027283, |
| "score_p50": 0.002633, |
| "score_p90": 0.034741, |
| "score_p95": 0.107271, |
| "score_p99": 0.437606, |
| "score_max": 0.955582 |
| }, |
| "local_repo_hs": { |
| "n": 14, |
| "threshold": 0.5, |
| "false_positive_rate": 0.1429, |
| "flagged": 2, |
| "score_mean": 0.234466, |
| "score_p50": 0.173636, |
| "score_p90": 0.50088, |
| "score_p95": 0.601973, |
| "score_p99": 0.732286, |
| "score_max": 0.764864 |
| }, |
| "local_repo_isre": { |
| "n": 173, |
| "threshold": 0.5, |
| "false_positive_rate": 0.0, |
| "flagged": 0, |
| "score_mean": 0.015629, |
| "score_p50": 0.000923, |
| "score_p90": 0.065123, |
| "score_p95": 0.111808, |
| "score_p99": 0.148813, |
| "score_max": 0.175909 |
| }, |
| "local_repo_job_application_pipeline": { |
| "n": 444, |
| "threshold": 0.5, |
| "false_positive_rate": 0.0023, |
| "flagged": 1, |
| "score_mean": 0.016508, |
| "score_p50": 0.001555, |
| "score_p90": 0.038672, |
| "score_p95": 0.117372, |
| "score_p99": 0.200662, |
| "score_max": 0.691934 |
| }, |
| "local_repo_llama_cpp": { |
| "n": 833, |
| "threshold": 0.5, |
| "false_positive_rate": 0.0228, |
| "flagged": 19, |
| "score_mean": 0.046812, |
| "score_p50": 0.004319, |
| "score_p90": 0.11022, |
| "score_p95": 0.229066, |
| "score_p99": 0.614219, |
| "score_max": 0.991824 |
| }, |
| "local_repo_math": { |
| "n": 6, |
| "threshold": 0.5, |
| "false_positive_rate": 0.0, |
| "flagged": 0, |
| "score_mean": 0.00212, |
| "score_p50": 0.001785, |
| "score_p90": 0.004231, |
| "score_p95": 0.004744, |
| "score_p99": 0.005155, |
| "score_max": 0.005257 |
| }, |
| "local_repo_olympiad_math": { |
| "n": 53, |
| "threshold": 0.5, |
| "false_positive_rate": 0.0189, |
| "flagged": 1, |
| "score_mean": 0.032375, |
| "score_p50": 0.001522, |
| "score_p90": 0.075568, |
| "score_p95": 0.202259, |
| "score_p99": 0.444325, |
| "score_max": 0.561933 |
| }, |
| "local_repo_pipeline": { |
| "n": 136, |
| "threshold": 0.5, |
| "false_positive_rate": 0.0074, |
| "flagged": 1, |
| "score_mean": 0.021312, |
| "score_p50": 0.001563, |
| "score_p90": 0.037614, |
| "score_p95": 0.080462, |
| "score_p99": 0.369778, |
| "score_max": 0.888886 |
| }, |
| "local_repo_repo": { |
| "n": 13, |
| "threshold": 0.5, |
| "false_positive_rate": 0.0, |
| "flagged": 0, |
| "score_mean": 0.049554, |
| "score_p50": 0.003904, |
| "score_p90": 0.15528, |
| "score_p95": 0.195039, |
| "score_p99": 0.231913, |
| "score_max": 0.241131 |
| }, |
| "local_repo_utils": { |
| "n": 114, |
| "threshold": 0.5, |
| "false_positive_rate": 0.0088, |
| "flagged": 1, |
| "score_mean": 0.017779, |
| "score_p50": 0.000741, |
| "score_p90": 0.021215, |
| "score_p95": 0.039684, |
| "score_p99": 0.316717, |
| "score_max": 0.970841 |
| }, |
| "local_repo_vesuvius": { |
| "n": 730, |
| "threshold": 0.5, |
| "false_positive_rate": 0.0548, |
| "flagged": 40, |
| "score_mean": 0.103365, |
| "score_p50": 0.018504, |
| "score_p90": 0.349818, |
| "score_p95": 0.531822, |
| "score_p99": 0.915992, |
| "score_max": 0.994358 |
| }, |
| "python_stdlib": { |
| "n": 7324, |
| "threshold": 0.5, |
| "false_positive_rate": 0.0042, |
| "flagged": 31, |
| "score_mean": 0.011296, |
| "score_p50": 0.000434, |
| "score_p90": 0.015448, |
| "score_p95": 0.039071, |
| "score_p99": 0.230201, |
| "score_max": 0.97892 |
| } |
| }, |
| "flagged_examples": [ |
| { |
| "score": 0.955582, |
| "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": 0.586343, |
| "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": 0.863325, |
| "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": 0.991824, |
| "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": 0.60719, |
| "source": "local_repo_llama_cpp", |
| "path": "C:\\lora_training\\llama.cpp\\common\\arg.cpp", |
| "preview": "n_ubatch = 1024; params.n_batch = 1024; params.n_ctx = 0; params.n_cache_reuse = 256; } ).set_examples({LLAMA_EXAMPLE_SERVER})); add_opt(common_arg( {\"--fim-qwen-7b-spec\"}, string_format(\"use Qwen 2.5 Coder 7B + 0.5B draft for speculative d" |
| }, |
| { |
| "score": 0.827293, |
| "source": "local_repo_llama_cpp", |
| "path": "C:\\lora_training\\llama.cpp\\common\\arg.cpp", |
| "preview": "wen 3 Coder 30B A3B Instruct (note: can download weights from the internet)\"), [](common_params & params) { params.model.hf_repo = \"ggml-org/Qwen3-Coder-30B-A3B-Instruct-Q8_0-GGUF\"; params.model.hf_file = \"qwen3-coder-30b-a3b-instruct-q8_0." |
| }, |
| { |
| "score": 0.534571, |
| "source": "local_repo_llama_cpp", |
| "path": "C:\\lora_training\\llama.cpp\\common\\base64.hpp", |
| "preview": "; return 62; } else if (c == '_') { alphabet = alphabet::url_filename_safe; return 63; } } throw base64_error(\"invalid base64 character.\"); } }; #endif // !PUBLIC_DOMAIN_BASE64_HPP_" |
| }, |
| { |
| "score": 0.551723, |
| "source": "local_repo_llama_cpp", |
| "path": "C:\\lora_training\\llama.cpp\\common\\chat-parser.cpp", |
| "preview": "n_regex preamble_regex(\"<\\\\|channel\\\\|>commentary\"); static const common_regex tool_call1_regex(recipient + \"<\\\\|channel\\\\|>(analysis|commentary)\" + constraint + \"?\"); static const common_regex tool_call2_regex(\"<\\\\|channel\\\\|>(analysis|com" |
| }, |
| { |
| "score": 0.536037, |
| "source": "local_repo_llama_cpp", |
| "path": "C:\\lora_training\\llama.cpp\\common\\chat-parser.cpp", |
| "preview": "case COMMON_CHAT_FORMAT_DEEPSEEK_R1: common_chat_parse_deepseek_r1(builder); break; case COMMON_CHAT_FORMAT_DEEPSEEK_V3_1: common_chat_parse_deepseek_v3_1(builder); break; case COMMON_CHAT_FORMAT_FUNCTIONARY_V3_2: common_chat_parse_function" |
| }, |
| { |
| "score": 0.616117, |
| "source": "local_repo_llama_cpp", |
| "path": "C:\\lora_training\\llama.cpp\\common\\chat-parser.cpp", |
| "preview": "common_chat_parse_kimi_k2(builder); break; case COMMON_CHAT_FORMAT_QWEN3_CODER_XML: common_chat_parse_qwen3_coder_xml(builder); break; case COMMON_CHAT_FORMAT_APRIEL_1_5: common_chat_parse_apriel_1_5(builder); break; case COMMON_CHAT_FORMAT" |
| }, |
| { |
| "score": 0.609806, |
| "source": "local_repo_llama_cpp", |
| "path": "C:\\lora_training\\llama.cpp\\common\\chat.cpp", |
| "preview": "msg_new.tool_calls.size() < msg_prv.tool_calls.size()) { throw std::runtime_error(\"Invalid diff: now finding less tool calls!\"); } if (!msg_prv.tool_calls.empty()) { const auto idx = msg_prv.tool_calls.size() - 1; const auto & pref = msg_pr" |
| }, |
| { |
| "score": 0.876555, |
| "source": "local_repo_llama_cpp", |
| "path": "C:\\lora_training\\llama.cpp\\common\\chat.cpp", |
| "preview": "y v3.1 Llama 3.1\"; case COMMON_CHAT_FORMAT_DEEPSEEK_V3_1: return \"DeepSeek V3.1\"; case COMMON_CHAT_FORMAT_HERMES_2_PRO: return \"Hermes 2 Pro\"; case COMMON_CHAT_FORMAT_COMMAND_R7B: return \"Command R7B\"; case COMMON_CHAT_FORMAT_GRANITE: retur" |
| }, |
| { |
| "score": 0.610185, |
| "source": "local_repo_llama_cpp", |
| "path": "C:\\lora_training\\llama.cpp\\common\\chat.h", |
| "preview": "OMMON_CHAT_FORMAT_GRANITE, COMMON_CHAT_FORMAT_GPT_OSS, COMMON_CHAT_FORMAT_SEED_OSS, COMMON_CHAT_FORMAT_NEMOTRON_V2, COMMON_CHAT_FORMAT_APERTUS, COMMON_CHAT_FORMAT_LFM2_WITH_JSON_TOOLS, COMMON_CHAT_FORMAT_GLM_4_5, COMMON_CHAT_FORMAT_MINIMAX_" |
| }, |
| { |
| "score": 0.864733, |
| "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": 0.972733, |
| "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": 0.526275, |
| "source": "local_repo_llama_cpp", |
| "path": "C:\\lora_training\\llama.cpp\\common\\common.cpp", |
| "preview": "mmon_params_sampling_config::COMMON_PARAMS_SAMPLING_CONFIG_MIN_P); get_float(llama_model_meta_key_str(LLAMA_MODEL_META_KEY_SAMPLING_XTC_PROBABILITY), sparams.xtc_probability, common_params_sampling_config::COMMON_PARAMS_SAMPLING_CONFIG_XTC_" |
| }, |
| { |
| "score": 0.539756, |
| "source": "local_repo_llama_cpp", |
| "path": "C:\\lora_training\\llama.cpp\\common\\download.cpp", |
| "preview": "l_successful = common_pull_file(cli, parts.path, path_temporary, supports_ranges, existing_size, total_size); if (!was_pull_successful) { if (i + 1 < max_attempts) { const int exponential_backoff_delay = std::pow(retry_delay_seconds, i) * 1" |
| }, |
| { |
| "score": 0.530205, |
| "source": "local_repo_llama_cpp", |
| "path": "C:\\lora_training\\llama.cpp\\common\\download.cpp", |
| "preview": "size_t len) { buf.insert(buf.end(), data, data + len); return params.max_size == 0 || buf.size() <= static_cast<size_t>(params.max_size); }, nullptr ); if (!res) { throw std::runtime_error(\"error: cannot make GET request\"); } return { res->" |
| }, |
| { |
| "score": 0.882664, |
| "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": 0.765199, |
| "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 (" |
| } |
| ] |
| } |
