cxcscmu/SkillLearnBench - Página 17

greedy-point-matching

Match clustered centroids to expert annotations using greedy nearest-neighbor matching with distance constraints. Compute F1 scores and delta metrics for clustering quality assessment.

Idioma do texto original: inglês

mars-cloud-data-loading-matching

Load citizen science and expert annotation datasets, match them by image using file_rad column, handle missing data, and prepare data for clustering evaluation.

Idioma do texto original: inglês

output-formatting-pareto-results

Format and write Pareto frontier results to CSV file with proper rounding and column ordering.

Idioma do texto original: inglês

pareto-frontier-optimization

Execute grid search over DBSCAN hyperparameters, evaluate each combination across all images, filter by F1 threshold, and identify Pareto-optimal solutions balancing F1 score and delta metric.

Idioma do texto original: inglês

deduplicate-and-order-vulnerability-records

Ensure vulnerability records are deduplicated and ordered according to ground-truth requirements.

Idioma do texto original: inglês

extract-cvss-score-with-correct-priority

Extract CVSS score from vulnerability data using the correct priority order (NVD → GHSA → RedHat) and handle nested JSON structure properly. Use case-insensitive field access and correct JSON path navigation.

Idioma do texto original: inglês

filter-vulnerabilities-by-severity-level

Filter vulnerability records to include only HIGH and CRITICAL severity levels with case-sensitive exact matching.

Idioma do texto original: inglês

format-and-write-csv-with-proper-escaping

Write CSV output with correct field quoting and escaping for special characters, using standard CSV formatting.

Idioma do texto original: inglês

handle-null-and-missing-values-in-vulnerability-data

Properly handle null, missing, and empty values in vulnerability records with appropriate fallback values.

Idioma do texto original: inglês

map-trivy-json-fields-to-csv-columns-accurately

Correctly identify and extract Trivy vulnerability JSON field names and map them to the required CSV output columns in exact order.

Idioma do texto original: inglês

calculate-distance-to-nearest-pacific-boundary

Combine all Pacific plate boundary geometries using `.unary_union` and calculate the distance from each earthquake to this combined boundary geometry. Returns the minimum distance in kilometers for each earthquake.

Idioma do texto original: inglês

execute-complete-geospatial-analysis-pipeline

Orchestrate the full analysis workflow: load data, identify Pacific plate, filter earthquakes and boundaries, project to EPSG:4087, calculate distances, find the furthest earthquake, and save results. Use this as the main execution skill.

Idioma do texto original: inglês

filter-earthquakes-within-pacific-plate

Use the `.within()` geometric method to identify earthquakes that are contained inside the Pacific plate polygon. Use this skill to ensure only earthquakes actually inside the Pacific plate are analyzed.

Idioma do texto original: inglês

filter-pacific-plate-boundaries

Filter the boundary dataset to include only boundaries relevant to the Pacific plate (where PlateA or PlateB equals the Pacific plate identifier). Use this skill to exclude irrelevant boundaries before distance calculations.

Idioma do texto original: inglês

find-earthquake-furthest-from-pacific-boundary

Identify the earthquake with the maximum distance to the Pacific plate boundary from the earthquakes within the Pacific plate. Use this skill to locate the target earthquake for final output.

Idioma do texto original: inglês

identify-pacific-plate-identifier

Examine the plates dataset to find the exact identifier used for the Pacific plate (e.g., "PA", "Pacific", etc.). Use this skill early in the analysis to ensure consistent filtering across boundaries and plates.

Idioma do texto original: inglês

load-and-parse-plate-boundary-data

Load plate boundary GeoJSON and create a GeoDataFrame with proper geometry parsing. Verify column names (PlateA, PlateB) match the dataset structure. Use this skill to prepare boundary data before filtering for Pacific plate relevance.

Idioma do texto original: inglês

load-and-parse-plate-polygon-data

Load plate polygon GeoJSON and parse geometries correctly. Verify the column name used for plate identifiers (e.g., 'PlateName' or similar). Use this skill to prepare plate polygon data for containment checks.

Idioma do texto original: inglês

load-and-validate-earthquake-data

Load earthquake data from GeoJSON format and validate that it contains required fields (id, time, magnitude, latitude, longitude, place). Use this skill when initializing the analysis to ensure data integrity before processing.

Idioma do texto original: inglês

output-result-to-json-file

Write the final result dictionary to a JSON file at `/root/answer.json` with proper formatting and field validation. Use this skill as the final step to save the analysis result.

Idioma do texto original: inglês

project-data-to-epsg-4087-for-distance-calculation

Reproject earthquake points and boundary geometries to EPSG:4087 (World Equidistant Cylindrical) before calculating distances. Use this skill to ensure accurate distance measurements in kilometers.

Idioma do texto original: inglês

evidence-validation-checkpoint

Before writing final answers, validate that all required evidence has been extracted, multi-hop traversal was executed, and answers are complete against expected values.

Idioma do texto original: inglês

multi-hop-evidence-extraction

Extract evidence from all three tiers (explicit reviewers, substantive feedback contributors from Slack and transcripts, and other identifiable contributors). Follow artifact references and traverse relationships to collect complete answer sets.

Idioma do texto original: inglês

product-grounded-artifact-retrieval

Load enterprise data from /root/DATA, identify the correct artifact version for each product mentioned in questions, and reject cross-product distractors. Apply strict 2-signal product grounding (artifact metadata + question context).

Idioma do texto original: inglês

question-parsing

Load and parse questions from /root/question.txt, extract question IDs and their artifact/product context. Validate that all questions are correctly mapped before proceeding to data retrieval.

Idioma do texto original: inglês

token-counting-and-output

Count tokens consumed during data retrieval operations, validate numeric format, and write results to /root/answer.json with proper structure.

Idioma do texto original: inglês

aggregate-holdings-across-multiple-funds

Search multiple funds' holdings data for a specific security (by CUSIP) and aggregate the total share values held by each fund manager. Use this to rank fund managers by their investment in a particular security.

Idioma do texto original: inglês

calculate-aum-from-holdings

Sum the market values of all holdings to derive the Assets Under Management (AUM) for a fund as of a specific report date. Use this to answer questions about fund size in a given quarter.

Idioma do texto original: inglês

compare-holdings-between-quarters

Load holdings for the same fund in two different quarters, match positions by security identifier, and calculate the change in shares and market values. Use this to identify which securities received increased investment between reporting periods.

Idioma do texto original: inglês

examine-raw-holdings-data-structure

Inspect the actual holdings dataset to understand its schema, field names, and data patterns before applying filters. Use this to identify the correct field name that distinguishes equity securities from bonds, options, warrants, and other non-stock…

Idioma do texto original: inglês

filter-holdings-by-security-type-stocks-only

Remove non-equity securities (bonds, options, warrants, preferred shares, funds) from holdings data, keeping only common stock positions. Use the correct security type field identified from the raw data structure inspection.

Idioma do texto original: inglês

fuzzy-search-coverpage-for-fund-identification

Search the COVERPAGE dataset using fuzzy matching to locate a specific fund by name and extract its accession_number for subsequent analysis. Use this when you need to identify a fund's filing by partial or approximate name matching.

Idioma do texto original: inglês

load-holdings-data-by-accession-number

Retrieve and load the complete holdings dataset for a specific fund using its accession_number. Use this to access position-level details needed for AUM, stock count, and comparative analysis.

Idioma do texto original: inglês

search-cusip-for-security

Find the CUSIP identifier for a specific security (e.g., Palantir) by searching across all holdings data or a security master file. Use this when you need to locate a specific stock across multiple fund positions.

Idioma do texto original: inglês

validate-accession-number-and-report-date

Confirm that the accession_number retrieved corresponds to the correct quarter and report date before using it for analysis. Use this to prevent analyzing data from the wrong quarter.

Idioma do texto original: inglês

create-and-apply-git-patch-files-for-druid-security-fixes

Generate proper git-compatible patch files that address the empty key validation and JavaScript filter disabling vulnerabilities, then apply them to the Druid 0.20.0 source repository.

Idioma do texto original: inglês

disable-javascript-execution-in-druid-filters

Configure and enforce a security policy that completely disables JavaScript filter evaluation in Apache Druid, preventing arbitrary code execution through the javascript filter type even if structural validation is bypassed.

Idioma do texto original: inglês

input-stream-validation-before-jackson-deserialization

Validate and sanitize raw JSON input at the point where it enters Jackson's deserialization pipeline, before any ObjectMapper.readValue() call processes it, to prevent bypass attacks using empty keys.

Idioma do texto original: inglês

locate-jackson-deserialization-entry-points-in-druid

Find the exact code locations where user-supplied JSON is deserialized into DimFilter and other security-sensitive objects in Apache Druid's indexing pipeline, to identify where raw input validation must occur before Jackson processes it.

Idioma do texto original: inglês

calculate-average-pr-merge-time

Compute the average number of days from PR creation to merge for all merged PRs in December 2024, using correct timestamp parsing and filtering.

Idioma do texto original: inglês