Round 8 Train DatasetThis is the training data used to construct and evaluate trojan detection software solutions. This data, generated at NIST, consists of natural language processing (NLP) AIs trained to perform extractive question answering (QA on English text. A known percentage of these trained AI models have been poisoned with a known trigger which induces incorrect behavior. This data will be used to develop software solutions for detecting which trained AI models have been poisoned via embedded triggers.

Round 1 Training DatasetThe data being generated and disseminated is the training data used to construct trojan detection software solutions. This data, generated at NIST, consists of human level AIs trained to perform a variety of tasks (image classification, natural language processing, etc.). A known percentage of these trained AI models have been poisoned with a known trigger which induces incorrect behavior. This data will be used to develop software solutions for detecting which trained AI models have been poisoned via embedded triggers.

Data for mass concentration analysis and spectral analysis for the paper titled, "Comparison of primary laser spectroscopy and mass spectrometry methods for measuring mass concentration of gaseous elemental mercury"

Round 1 Test DatasetThe data being generated and disseminated is the test data used to evaluate trojan detection software solutions. This data, generated at NIST, consists of human level AIs trained to perform a variety of tasks (image classification, natural language processing, etc.). A known percentage of these trained AI models have been poisoned with a known trigger which induces incorrect behavior. This data will be used to develop software solutions for detecting which trained AI models have been poisoned via embedded triggers.

Round1 Holdout DatasetThe data being generated and disseminated is the holdout data used to evaluate trojan detection software solutions. This data, generated at NIST, consists of human level AIs trained to perform a variety of tasks (image classification, natural language processing, etc.). A known percentage of these trained AI models have been poisoned with a known trigger which induces incorrect behavior. This data will be used to develop software solutions for detecting which trained AI models have been poisoned via embedded triggers.

Round 2 Training DatasetThe data being generated and disseminated is the training data used to construct trojan detection software solutions. This data, generated at NIST, consists of human level AIs trained to perform image classification. A known percentage of these trained AI models have been poisoned with a known trigger which induces incorrect behavior. This data will be used to develop software solutions for detecting which trained AI models have been poisoned via embedded triggers.

This Standard Reference Material (SRM) is intended for use as a primary calibration standard for the quantitative determination of mercury. A unit of SRM 3133 consists of five 10 mL sealed borosilicate glass ampoules of an acidified aqueous solution prepared gravimetrically to contain a known mass fraction of mercury. The solution contains nitric acid at an approximate mass fraction of 10 %. This data is public in the Certificate of Analysis for this material.

This Standard Reference Material (SRM) is intended for use as a primary calibration standard for the quantitative determination of iodide. A unit of SRM 3180 consists of five 5 mL, sealed, amber, borosilicate glass ampoules of solution prepared gravimetrically to contain a known mass fraction of iodide. The matrix of the solution is water containing sodium sulfite at a concentration of approximately 0.01 mol/L and sodium hydroxide at a concentration of approximately 0.005 mol/L. This data is public in the Certificate of Analysis for this material.

This Standard Reference Material (SRM) is intended for use as a primary calibration standard for the quantitative determination of sulfate using anion ion chromatography (IC) or other methods. A unit of SRM 3181 consists of five 10 mL sealed borosilicate glass ampoules of solution prepared gravimetrically to contain a known mass fraction of sulfate dissolved in filtered (0.22 ?m) water having a minimum resistivity of 18 megaohm centimeters. This data is public in the Certificate of Analysis for this material.

This Standard Reference Material (SRM) is intended as a primary standard for the quantitative determination of chloride using anion ion chromatography (IC) or other methods. A unit of SRM 3182 consists of five 10 mL sealed borosilicate glass ampoules of solution. The solution is prepared gravimetrically to contain a known mass fraction of chloride dissolved in filtered (0.22 µm) water having a minimum resistivity of 18 megaohm centimeters. This data is public in the Certificate of Analysis for this material.