1089 lines
30 KiBLFS
JSON
1089 lines
30 KiBLFS
JSON
{
|
|
"schema_version": "skillsbench.agentbeats.task_set.v1",
|
|
"task_set": "skillsbench-v1.1",
|
|
"condition": "with_skills",
|
|
"allow_excluded_tasks": false,
|
|
"shard_index": 0,
|
|
"num_shards": 1,
|
|
"task_count": 87,
|
|
"tasks": [
|
|
{
|
|
"task_id": "3d-scan-calc",
|
|
"task_digest": "sha256:b25e882d1d3a44e4089cd3cea60ebfdfb1b5ac163b2cce0c5ab12a2d439ccf40",
|
|
"category": "industrial-physical-systems",
|
|
"difficulty": "hard",
|
|
"tags": [
|
|
"binary-parsing",
|
|
"algorithm",
|
|
"3d-geometry",
|
|
"stl"
|
|
]
|
|
},
|
|
{
|
|
"task_id": "ada-bathroom-plan-repair",
|
|
"task_digest": "sha256:9691aaf3db49f00ab64e9badaaf7e46d4283f36f47b6fc97b4425359264165ca",
|
|
"category": "industrial-physical-systems",
|
|
"difficulty": "hard",
|
|
"tags": [
|
|
"cad",
|
|
"dxf",
|
|
"accessibility",
|
|
"geometry",
|
|
"ada",
|
|
"spatial-reasoning"
|
|
]
|
|
},
|
|
{
|
|
"task_id": "adaptive-cruise-control",
|
|
"task_digest": "sha256:827d48c1c91dbcac670558b710f0ea6f76f9b5e6c531e4480a48cfe1c77c675c",
|
|
"category": "industrial-physical-systems",
|
|
"difficulty": "medium",
|
|
"tags": [
|
|
"python",
|
|
"pid-control",
|
|
"simulation",
|
|
"vehicle-dynamics",
|
|
"automotive",
|
|
"control-theory"
|
|
]
|
|
},
|
|
{
|
|
"task_id": "azure-bgp-oscillation-route-leak",
|
|
"task_digest": "sha256:58a862b7c0704fbe5ca545f18eeabac39599be94c857e0a7d80781dbbc0a52ef",
|
|
"category": "software-engineering",
|
|
"difficulty": "medium",
|
|
"tags": [
|
|
"bgp",
|
|
"oscillation",
|
|
"azure",
|
|
"network"
|
|
]
|
|
},
|
|
{
|
|
"task_id": "bike-rebalance",
|
|
"task_digest": "sha256:9366569f77d18bf7630a4ccdbad710c321374350c87e9d69746939432d2e0a7a",
|
|
"category": "mathematics-or-formal-reasoning",
|
|
"difficulty": "medium",
|
|
"tags": [
|
|
"bike-sharing",
|
|
"vehicle-routing",
|
|
"inventory-rebalancing",
|
|
"mixed-integer-program"
|
|
]
|
|
},
|
|
{
|
|
"task_id": "citation-check",
|
|
"task_digest": "sha256:d78c412f8d9f42b282c12fa009f76b0cda6d9da782ade315946dda747b71f252",
|
|
"category": "office-white-collar",
|
|
"difficulty": "medium",
|
|
"tags": [
|
|
"citation",
|
|
"bibtex",
|
|
"academic",
|
|
"verification",
|
|
"api",
|
|
"crossref",
|
|
"semantic-scholar"
|
|
]
|
|
},
|
|
{
|
|
"task_id": "civ6-adjacency-optimizer",
|
|
"task_digest": "sha256:5e3b398dd390add962fc8e0188734a725477fde38b9ad575f2fed60d91c2bef3",
|
|
"category": "mathematics-or-formal-reasoning",
|
|
"difficulty": "hard",
|
|
"tags": [
|
|
"optimization",
|
|
"constraint-satisfaction",
|
|
"game-mechanics",
|
|
"spatial understanding",
|
|
"civ6"
|
|
]
|
|
},
|
|
{
|
|
"task_id": "court-form-filling",
|
|
"task_digest": "sha256:2d4d4bd0a5fc64d0103592f3b571e0ec2ee6e9a2489d125b008cc69aef959f8f",
|
|
"category": "office-white-collar",
|
|
"difficulty": "easy",
|
|
"tags": [
|
|
"pdf",
|
|
"form-filling",
|
|
"legal",
|
|
"document-automation"
|
|
]
|
|
},
|
|
{
|
|
"task_id": "crystallographic-wyckoff-position-analysis",
|
|
"task_digest": "sha256:43cbf65a117d248693a81830500e8e9f5271da8c8c5e3374ade82f2c11e74dc9",
|
|
"category": "natural-science",
|
|
"difficulty": "medium",
|
|
"tags": [
|
|
"crystallography",
|
|
"pymatgen",
|
|
"sympy",
|
|
"wyckoff_positions",
|
|
"symmetry_analysis"
|
|
]
|
|
},
|
|
{
|
|
"task_id": "dapt-intrusion-detection",
|
|
"task_digest": "sha256:1d94af9e3b2e1c6703be4fa53b9f982a86ee45e39a7619bd07d04d6690870d24",
|
|
"category": "cybersecurity",
|
|
"difficulty": "hard",
|
|
"tags": [
|
|
"security",
|
|
"network",
|
|
"pcap",
|
|
"intrusion-detection"
|
|
]
|
|
},
|
|
{
|
|
"task_id": "data-to-d3",
|
|
"task_digest": "sha256:6bd955ce55b21352a441a5706b0e3faaad42b37891145e614b27387f44d38808",
|
|
"category": "software-engineering",
|
|
"difficulty": "medium",
|
|
"tags": [
|
|
"d3.js",
|
|
"data-visualization",
|
|
"interactive-charts"
|
|
]
|
|
},
|
|
{
|
|
"task_id": "debug-trl-grpo",
|
|
"task_digest": "sha256:6224b1d6251416451c50c5f32436299d251945cd33bd5331c85bac9acb3b4dce",
|
|
"category": "software-engineering",
|
|
"difficulty": "hard",
|
|
"tags": [
|
|
"post-training",
|
|
"trl",
|
|
"debugging",
|
|
"reasoning-model",
|
|
"grpo"
|
|
]
|
|
},
|
|
{
|
|
"task_id": "dialogue-parser",
|
|
"task_digest": "sha256:4d48e3b0e7146cb3596bf3f56f9d37cecab57fcbb32058f229e5401182cd191d",
|
|
"category": "software-engineering",
|
|
"difficulty": "easy",
|
|
"tags": [
|
|
"game development",
|
|
"parsing"
|
|
]
|
|
},
|
|
{
|
|
"task_id": "drone-planning-control",
|
|
"task_digest": "sha256:a3959e17cf3f2e38e456898d804a105732ea09268feab0f0555216f9f830fcee",
|
|
"category": "industrial-physical-systems",
|
|
"difficulty": "medium",
|
|
"tags": [
|
|
"planning",
|
|
"control",
|
|
"robotics",
|
|
"simulation",
|
|
"dynamics"
|
|
]
|
|
},
|
|
{
|
|
"task_id": "dynamic-object-aware-egomotion",
|
|
"task_digest": "sha256:0028fd6bdc7dc8f792ff6f6e8bef7a901701fc10bb1cfb33054a991eb624c4b7",
|
|
"category": "industrial-physical-systems",
|
|
"difficulty": "medium",
|
|
"tags": [
|
|
"video",
|
|
"egomotion",
|
|
"spatial-reasoning"
|
|
]
|
|
},
|
|
{
|
|
"task_id": "earthquake-phase-association",
|
|
"task_digest": "sha256:a4bd363999e8b59b55bfe545f31aef3d6aec8b770a0fa63aa92a2b032de2210a",
|
|
"category": "natural-science",
|
|
"difficulty": "hard",
|
|
"tags": [
|
|
"science",
|
|
"earth-science",
|
|
"seismology",
|
|
"ai4science"
|
|
]
|
|
},
|
|
{
|
|
"task_id": "earthquake-plate-calculation",
|
|
"task_digest": "sha256:7174811da91ee6ee6dd52e8c5049307312ef7402e94c655516309c7c9a225cde",
|
|
"category": "natural-science",
|
|
"difficulty": "medium",
|
|
"tags": [
|
|
"geophysics",
|
|
"spatial-analysis",
|
|
"gis",
|
|
"plate-tectonics"
|
|
]
|
|
},
|
|
{
|
|
"task_id": "econ-detrending-correlation",
|
|
"task_digest": "sha256:9b238639d4d2c03792ec2bb0ccce3f43b63a91a030a614dadfc755be8ca747b9",
|
|
"category": "finance-economics",
|
|
"difficulty": "medium",
|
|
"tags": [
|
|
"economics",
|
|
"statistics",
|
|
"data-analysis",
|
|
"python",
|
|
"pandas",
|
|
"hp-filter",
|
|
"timeseries"
|
|
]
|
|
},
|
|
{
|
|
"task_id": "edit-pdf",
|
|
"task_digest": "sha256:94aeeab12884019d57f010967ae5162288dd1cc29197078517759f7bed45a93c",
|
|
"category": "office-white-collar",
|
|
"difficulty": "medium",
|
|
"tags": [
|
|
"pdf",
|
|
"document-editing",
|
|
"form-filling",
|
|
"natural-language"
|
|
]
|
|
},
|
|
{
|
|
"task_id": "energy-ac-optimal-power-flow",
|
|
"task_digest": "sha256:6c2795064b385c9aee5137169bd553adeda2df16e21b7f9e41854461b6218b3a",
|
|
"category": "industrial-physical-systems",
|
|
"difficulty": "medium",
|
|
"tags": [
|
|
"energy",
|
|
"system-operation",
|
|
"ac-optimal-power-flow",
|
|
"non-convex-optimization"
|
|
]
|
|
},
|
|
{
|
|
"task_id": "energy-market-pricing",
|
|
"task_digest": "sha256:57b3eee7ab0006de70664e6709cb7de5350bf7c64ea18b45ef202fafb4b78363",
|
|
"category": "industrial-physical-systems",
|
|
"difficulty": "hard",
|
|
"tags": [
|
|
"energy",
|
|
"market-pricing",
|
|
"optimization",
|
|
"duality",
|
|
"counterfactual-analysis"
|
|
]
|
|
},
|
|
{
|
|
"task_id": "energy-unit-commitment",
|
|
"task_digest": "sha256:cc22e69edc77c65ebda13671a98718c09085e55f3a88087d3cf6ae1cf095b61a",
|
|
"category": "industrial-physical-systems",
|
|
"difficulty": "hard",
|
|
"tags": [
|
|
"energy",
|
|
"unit-commitment",
|
|
"mixed-integer-optimization",
|
|
"day-ahead-scheduling",
|
|
"power-system-operations"
|
|
]
|
|
},
|
|
{
|
|
"task_id": "enterprise-information-search",
|
|
"task_digest": "sha256:57add4050ad2983534267dcc37a8155a29a5e4a305207cfb5b971330f1355d9c",
|
|
"category": "office-white-collar",
|
|
"difficulty": "hard",
|
|
"tags": [
|
|
"information-retrieval",
|
|
"question-answering",
|
|
"heterogeneous-data"
|
|
]
|
|
},
|
|
{
|
|
"task_id": "exam-block-sequencing",
|
|
"task_digest": "sha256:653a63535682be320086511f8ccde3671d3eb5f25d75fb36d78298ffc13f90cc",
|
|
"category": "mathematics-or-formal-reasoning",
|
|
"difficulty": "hard",
|
|
"tags": [
|
|
"scheduling",
|
|
"optimization",
|
|
"integer-programming",
|
|
"timetabling",
|
|
"education"
|
|
]
|
|
},
|
|
{
|
|
"task_id": "exceltable-in-ppt",
|
|
"task_digest": "sha256:dae3cb414f9ac36a40caf98a0af19ffc34c99f352645238dd53e0107d1fb66df",
|
|
"category": "office-white-collar",
|
|
"difficulty": "medium",
|
|
"tags": [
|
|
"excel",
|
|
"pptx",
|
|
"table-update"
|
|
]
|
|
},
|
|
{
|
|
"task_id": "exoplanet-detection-period",
|
|
"task_digest": "sha256:67bb300e81cee8649477be83aae60b4e145d41c5547694ee93b9bd6a1d6e33b4",
|
|
"category": "natural-science",
|
|
"difficulty": "medium",
|
|
"tags": [
|
|
"science",
|
|
"astronomy",
|
|
"planetary-science",
|
|
"timeseries",
|
|
"data-analysis",
|
|
"python"
|
|
]
|
|
},
|
|
{
|
|
"task_id": "financial-modeling-qa",
|
|
"task_digest": "sha256:c9fd9621f3d14dda5cb73b9d5e30ccdbfcc3c0311d51ab0502ef17065e14770f",
|
|
"category": "finance-economics",
|
|
"difficulty": "hard",
|
|
"tags": [
|
|
"data analysis",
|
|
"pdf parsing",
|
|
"financial knowledge"
|
|
]
|
|
},
|
|
{
|
|
"task_id": "fix-build-agentops",
|
|
"task_digest": "sha256:f03d658eee4f3f1e3ac7d91ad41cd63a8145759dc06281482efa7fe671d48edf",
|
|
"category": "software-engineering",
|
|
"difficulty": "easy",
|
|
"tags": [
|
|
"Python",
|
|
"agentops",
|
|
"AgentOps-AI/agentops",
|
|
"software",
|
|
"build",
|
|
"compilation",
|
|
"ci",
|
|
"github actions",
|
|
"debugging"
|
|
]
|
|
},
|
|
{
|
|
"task_id": "fix-build-google-auto",
|
|
"task_digest": "sha256:a71d138003aa4c28222d6877e0dd65c3ddfbd9f407d5878fd0a235a32e9df8a4",
|
|
"category": "software-engineering",
|
|
"difficulty": "easy",
|
|
"tags": [
|
|
"Java",
|
|
"maven",
|
|
"google/auto",
|
|
"software",
|
|
"build",
|
|
"compilation",
|
|
"ci",
|
|
"travis",
|
|
"debugging"
|
|
]
|
|
},
|
|
{
|
|
"task_id": "fix-druid-loophole-cve",
|
|
"task_digest": "sha256:a53aaa226bfcd53b928ef19364d7bec5da8e49f072c5ea71a323364bf07e3412",
|
|
"category": "cybersecurity",
|
|
"difficulty": "hard",
|
|
"tags": [
|
|
"Java",
|
|
"Security",
|
|
"Apache Druid",
|
|
"Vulnerability Fix"
|
|
]
|
|
},
|
|
{
|
|
"task_id": "fix-erlang-ssh-cve",
|
|
"task_digest": "sha256:81b3e7cdf8d40c99ecb6321e24759b0a3e78d136ab4fe83a8fec85197586e27c",
|
|
"category": "cybersecurity",
|
|
"difficulty": "hard",
|
|
"tags": [
|
|
"erlang",
|
|
"security"
|
|
]
|
|
},
|
|
{
|
|
"task_id": "fix-visual-stability",
|
|
"task_digest": "sha256:6f4f0977e3f06e6d3fb9b903966e1c1f0b3d1f9b2e3ac60aa7ed27f478a5252d",
|
|
"category": "software-engineering",
|
|
"difficulty": "hard",
|
|
"tags": [
|
|
"react",
|
|
"nextjs",
|
|
"cls",
|
|
"flickering",
|
|
"visual-stability"
|
|
]
|
|
},
|
|
{
|
|
"task_id": "flink-query",
|
|
"task_digest": "sha256:9c47e12a691f2bc0b94941962ee9b7878b2a2f8edf6aec30f02dd602cdc81850",
|
|
"category": "software-engineering",
|
|
"difficulty": "hard",
|
|
"tags": [
|
|
"flink",
|
|
"java",
|
|
"data engineer"
|
|
]
|
|
},
|
|
{
|
|
"task_id": "flood-risk-analysis",
|
|
"task_digest": "sha256:2f817566346351ad6fe354c228b720062715527e4089dfcf816f967c9313ae70",
|
|
"category": "natural-science",
|
|
"difficulty": "medium",
|
|
"tags": [
|
|
"hydrology",
|
|
"geospatial",
|
|
"csv",
|
|
"json",
|
|
"flood-monitoring"
|
|
]
|
|
},
|
|
{
|
|
"task_id": "glm-lake-mendota",
|
|
"task_digest": "sha256:2cffc4a969b971f64b6558de140baaffe663a19dc2e58fc4c6d9c43cafd995ae",
|
|
"category": "natural-science",
|
|
"difficulty": "hard",
|
|
"tags": [
|
|
"hydrology",
|
|
"lake-modeling",
|
|
"parameter-calibration"
|
|
]
|
|
},
|
|
{
|
|
"task_id": "gravitational-wave-detection",
|
|
"task_digest": "sha256:473c6c69fe42578e2fa476f8a0c2250ce87a6318def1f77b59f4f516972bd56f",
|
|
"category": "natural-science",
|
|
"difficulty": "medium",
|
|
"tags": [
|
|
"science",
|
|
"astronomy",
|
|
"physics",
|
|
"gravitational-waves",
|
|
"signal-processing",
|
|
"python",
|
|
"pycbc"
|
|
]
|
|
},
|
|
{
|
|
"task_id": "grid-dispatch-operator",
|
|
"task_digest": "sha256:60c5bca1ec15bdb2053dd672016f8153ce6e64c922f8b0fc0a73228ff24e25b4",
|
|
"category": "industrial-physical-systems",
|
|
"difficulty": "medium",
|
|
"tags": [
|
|
"energy",
|
|
"large-scale-energy-market-clearing",
|
|
"optimization",
|
|
"power-flow",
|
|
"dc-opf"
|
|
]
|
|
},
|
|
{
|
|
"task_id": "hvac-control",
|
|
"task_digest": "sha256:fd4a8c1ffc1b9f5826407486012d96b89a574d4bcb09bdb5075fbe0542ad99e8",
|
|
"category": "industrial-physical-systems",
|
|
"difficulty": "medium",
|
|
"tags": [
|
|
"hvac",
|
|
"control-theory",
|
|
"system-identification",
|
|
"pid",
|
|
"python",
|
|
"thermal-modeling"
|
|
]
|
|
},
|
|
{
|
|
"task_id": "invoice-fraud-detection",
|
|
"task_digest": "sha256:7355f35c7a0bd44ad9f4dd933a357c49d1b4906679ccd7e822e98c8909d237ec",
|
|
"category": "finance-economics",
|
|
"difficulty": "hard",
|
|
"tags": [
|
|
"pdf",
|
|
"excel",
|
|
"fraud-detection",
|
|
"fuzzy-matching",
|
|
"finance"
|
|
]
|
|
},
|
|
{
|
|
"task_id": "jax-computing-basics",
|
|
"task_digest": "sha256:85f8adc808c68bfacd1fa06b17b91bb82b09aac0848c2ba55e512feb84137b35",
|
|
"category": "software-engineering",
|
|
"difficulty": "medium",
|
|
"tags": [
|
|
"jax-language",
|
|
"numerical-computing"
|
|
]
|
|
},
|
|
{
|
|
"task_id": "jpg-ocr-stat",
|
|
"task_digest": "sha256:7a6137d973f6ddd03ec7fbce9a11f95be9c8ca553efdf681e35d3a186184f968",
|
|
"category": "office-white-collar",
|
|
"difficulty": "hard",
|
|
"tags": [
|
|
"image ocr",
|
|
"data statistics"
|
|
]
|
|
},
|
|
{
|
|
"task_id": "lab-unit-harmonization",
|
|
"task_digest": "sha256:c30aa90c0483f090aa0cba86dd68fdc92f3eb5a2dd0b35eaed2ef94a9134a236",
|
|
"category": "natural-science",
|
|
"difficulty": "medium",
|
|
"tags": [
|
|
"bioinformatics",
|
|
"clinical",
|
|
"unit-conversion",
|
|
"data-harmonization",
|
|
"chronic-kidney-disease"
|
|
]
|
|
},
|
|
{
|
|
"task_id": "lake-warming-attribution",
|
|
"task_digest": "sha256:32d3699e6348478971e08322e28b52bd6396d11fa4908f3ad113485730ac956f",
|
|
"category": "natural-science",
|
|
"difficulty": "medium",
|
|
"tags": [
|
|
"hydrology",
|
|
"trend-analysis",
|
|
"contribution-analysis"
|
|
]
|
|
},
|
|
{
|
|
"task_id": "latex-formula-extraction",
|
|
"task_digest": "sha256:49df78d85f4e04b51db20f17bdfcfb479f19b2e1c8acaf2090a03f8b85c78238",
|
|
"category": "office-white-collar",
|
|
"difficulty": "medium",
|
|
"tags": [
|
|
"pdf",
|
|
"latex",
|
|
"latex-extraction"
|
|
]
|
|
},
|
|
{
|
|
"task_id": "lean4-proof",
|
|
"task_digest": "sha256:0a37922e73bb30f32f7f345874d5259b2fbc1c4543fa58a5886329e386a2f962",
|
|
"category": "mathematics-or-formal-reasoning",
|
|
"difficulty": "medium",
|
|
"tags": [
|
|
"formal method",
|
|
"lean4"
|
|
]
|
|
},
|
|
{
|
|
"task_id": "llm-prefix-cache-replay",
|
|
"task_digest": "sha256:ac5d31f79c6fb25306e9e7216ccf56407f637a12097f31930ed494c0cada5deb",
|
|
"category": "software-engineering",
|
|
"difficulty": "medium",
|
|
"tags": [
|
|
"llm-serving",
|
|
"kv-cache",
|
|
"trace-replay",
|
|
"prefix-cache",
|
|
"s3fifo",
|
|
"performance"
|
|
]
|
|
},
|
|
{
|
|
"task_id": "manufacturing-codebook-normalization",
|
|
"task_digest": "sha256:07f8f87ed53b8224fefc65dc220537572980e0794970db30e3873aebd063c9d3",
|
|
"category": "industrial-physical-systems",
|
|
"difficulty": "medium",
|
|
"tags": [
|
|
"test failure reason codebook",
|
|
"defect reason standardization",
|
|
"testing remarks analysis"
|
|
]
|
|
},
|
|
{
|
|
"task_id": "manufacturing-equipment-maintenance",
|
|
"task_digest": "sha256:477f88b04a7a8c6a2de0d05a1bc4f3e0336a9170ea745dfca4b4b2ff33f5fdfd",
|
|
"category": "industrial-physical-systems",
|
|
"difficulty": "medium",
|
|
"tags": [
|
|
"question and answer",
|
|
"reflow machine maintenance",
|
|
"data analysis",
|
|
"reasoning"
|
|
]
|
|
},
|
|
{
|
|
"task_id": "manufacturing-fjsp-optimization",
|
|
"task_digest": "sha256:7b1e01c2d74c6333e629c63c09d963eff9f846b5ac96318d13cc0cde95a3d444",
|
|
"category": "industrial-physical-systems",
|
|
"difficulty": "medium",
|
|
"tags": [
|
|
"optimization",
|
|
"manufacturing",
|
|
"flexible job shop planning"
|
|
]
|
|
},
|
|
{
|
|
"task_id": "mario-coin-counting",
|
|
"task_digest": "sha256:e66bd69fb226e0ae23563f535b952ea66d6f49e2bf0e315f7d95acf035acce2f",
|
|
"category": "media-content-production",
|
|
"difficulty": "medium",
|
|
"tags": [
|
|
"video-processing",
|
|
"image-processing",
|
|
"computer-vision"
|
|
]
|
|
},
|
|
{
|
|
"task_id": "mars-clouds-clustering",
|
|
"task_digest": "sha256:df164f340bb3df4ef99997a5fca44fec0c36f4f11c34762a9a1da87cac05dc68",
|
|
"category": "natural-science",
|
|
"difficulty": "hard",
|
|
"tags": [
|
|
"science",
|
|
"astronomy",
|
|
"planetary-science",
|
|
"clustering",
|
|
"optimization",
|
|
"parallelization",
|
|
"python"
|
|
]
|
|
},
|
|
{
|
|
"task_id": "multilingual-video-dubbing",
|
|
"task_digest": "sha256:8947bde71c1cb7d9652daf827bd979e9f09d14b5e89941871d4cdc895646d81a",
|
|
"category": "media-content-production",
|
|
"difficulty": "medium",
|
|
"tags": [
|
|
"video dubbing",
|
|
"speech",
|
|
"text-to-speech",
|
|
"alignment"
|
|
]
|
|
},
|
|
{
|
|
"task_id": "offer-letter-generator",
|
|
"task_digest": "sha256:c9b406ec4509a0742d54add417d145913d1f0273e01b1735c4607f777b7cffbc",
|
|
"category": "office-white-collar",
|
|
"difficulty": "easy",
|
|
"tags": [
|
|
"docx",
|
|
"word",
|
|
"template",
|
|
"office",
|
|
"mail-merge"
|
|
]
|
|
},
|
|
{
|
|
"task_id": "organize-messy-files",
|
|
"task_digest": "sha256:09f43f6b7454bd68b186948550155a1b26310d8e047cd43834af46795e7fcf43",
|
|
"category": "office-white-collar",
|
|
"difficulty": "medium",
|
|
"tags": [
|
|
"file-management",
|
|
"pdf"
|
|
]
|
|
},
|
|
{
|
|
"task_id": "paper-anonymizer",
|
|
"task_digest": "sha256:be99a90a20f308e3e5349bed9800a087b4bdf62517e37d54c67e934e55176357",
|
|
"category": "office-white-collar",
|
|
"difficulty": "medium",
|
|
"tags": [
|
|
"pdf",
|
|
"redaction",
|
|
"anonymization",
|
|
"blind-review"
|
|
]
|
|
},
|
|
{
|
|
"task_id": "parallel-tfidf-search",
|
|
"task_digest": "sha256:482f37d1b1cb39de2c6dcfe36ad1db5b5594ebf0ca76abb9c504d061a27e3b02",
|
|
"category": "software-engineering",
|
|
"difficulty": "medium",
|
|
"tags": [
|
|
"parallel"
|
|
]
|
|
},
|
|
{
|
|
"task_id": "paratransit-routing",
|
|
"task_digest": "sha256:839b0c7b035503e9b70f8901b69f47e70f7f790b961cabfeb8e8ccc417a27500",
|
|
"category": "mathematics-or-formal-reasoning",
|
|
"difficulty": "hard",
|
|
"tags": [
|
|
"paratransit",
|
|
"dial-a-ride",
|
|
"routing",
|
|
"operations-research",
|
|
"schedule-audit"
|
|
]
|
|
},
|
|
{
|
|
"task_id": "pddl-airport-planning",
|
|
"task_digest": "sha256:d4994f5b27d70de16342f7f3d2a9a2d2ad8d3701edefd2fc23ce36ff82f37d3e",
|
|
"category": "mathematics-or-formal-reasoning",
|
|
"difficulty": "medium",
|
|
"tags": [
|
|
"dsl",
|
|
"planning"
|
|
]
|
|
},
|
|
{
|
|
"task_id": "pddl-tpp-planning",
|
|
"task_digest": "sha256:536ad41c86db02eea73da1483768f55f68cd53fc91b74c38cffb38ea4f2445f0",
|
|
"category": "mathematics-or-formal-reasoning",
|
|
"difficulty": "medium",
|
|
"tags": [
|
|
"dsl",
|
|
"planning"
|
|
]
|
|
},
|
|
{
|
|
"task_id": "pdf-excel-diff",
|
|
"task_digest": "sha256:555a80997825f9258d023aeb53df148d54a41a93833d970bcd6ff417adb63667",
|
|
"category": "office-white-collar",
|
|
"difficulty": "medium",
|
|
"tags": [
|
|
"pdf",
|
|
"excel",
|
|
"data-extraction",
|
|
"diff",
|
|
"table-parsing",
|
|
"office"
|
|
]
|
|
},
|
|
{
|
|
"task_id": "powerlifting-coef-calc",
|
|
"task_digest": "sha256:23be68ce08baceae83a988ac9e3803ea65d8d2f2d7c3dfdb84fd6a4ceff278d1",
|
|
"category": "office-white-collar",
|
|
"difficulty": "easy",
|
|
"tags": [
|
|
"excel",
|
|
"sports",
|
|
"excel-index-match",
|
|
"statistics",
|
|
"excel-formula"
|
|
]
|
|
},
|
|
{
|
|
"task_id": "pptx-reference-formatting",
|
|
"task_digest": "sha256:25c81ae61ac4623ab9acaa3c5dbb68969973cc959c29ea4fd15db1c24d4fceb4",
|
|
"category": "office-white-collar",
|
|
"difficulty": "medium",
|
|
"tags": [
|
|
"pptx",
|
|
"ppt",
|
|
"slides",
|
|
"formatting"
|
|
]
|
|
},
|
|
{
|
|
"task_id": "protein-expression-analysis",
|
|
"task_digest": "sha256:dd81d820bc8dfd9a6cb8a48e7eafa72a7bf430b65a3bb4948a359573174df196",
|
|
"category": "natural-science",
|
|
"difficulty": "medium",
|
|
"tags": [
|
|
"xlsx",
|
|
"proteomics",
|
|
"excel",
|
|
"data-analysis",
|
|
"statistics",
|
|
"bioinformatics"
|
|
]
|
|
},
|
|
{
|
|
"task_id": "python-scala-translation",
|
|
"task_digest": "sha256:d84a2aae85cce5480402fed5095a06495efa07a4ca458505171515d7707fc013",
|
|
"category": "software-engineering",
|
|
"difficulty": "medium",
|
|
"tags": [
|
|
"translation",
|
|
"scala",
|
|
"python"
|
|
]
|
|
},
|
|
{
|
|
"task_id": "quantum-numerical-simulation",
|
|
"task_digest": "sha256:434e1ac9ffe67525341b8f90d16657dcdaa3a21cf4e56466ef15e754df10e659",
|
|
"category": "natural-science",
|
|
"difficulty": "medium",
|
|
"tags": [
|
|
"quantum",
|
|
"quantum-simulation"
|
|
]
|
|
},
|
|
{
|
|
"task_id": "r2r-mpc-control",
|
|
"task_digest": "sha256:1b0b77e7fccaa8a88e763cb5fd39e32f1d439dceef3b971f18beee224a7ffeac",
|
|
"category": "industrial-physical-systems",
|
|
"difficulty": "medium",
|
|
"tags": [
|
|
"mpc",
|
|
"manufacturing",
|
|
"tension-control",
|
|
"lqr",
|
|
"python",
|
|
"state-space",
|
|
"r2r"
|
|
]
|
|
},
|
|
{
|
|
"task_id": "radar-vital-signs",
|
|
"task_digest": "sha256:a0cd2e92dfb6933cff15749879de04566c496051f7560bf05a998b6b93ed1b18",
|
|
"category": "natural-science",
|
|
"difficulty": "medium",
|
|
"tags": [
|
|
"radar",
|
|
"signal-processing",
|
|
"biomedical",
|
|
"vital-signs",
|
|
"python"
|
|
]
|
|
},
|
|
{
|
|
"task_id": "react-performance-debugging",
|
|
"task_digest": "sha256:598d880dbacaa43e05cd93786ab88d424690c47fd2636b41f2e6602fb385d4d8",
|
|
"category": "software-engineering",
|
|
"difficulty": "hard",
|
|
"tags": [
|
|
"react",
|
|
"nextjs",
|
|
"performance",
|
|
"debugging",
|
|
"bundle-optimization"
|
|
]
|
|
},
|
|
{
|
|
"task_id": "reserves-at-risk-calc",
|
|
"task_digest": "sha256:bbf57b1a76688f2877c29db1bbcfed818acd9cda238a25d76fedd6bdbbadbd55",
|
|
"category": "finance-economics",
|
|
"difficulty": "medium",
|
|
"tags": [
|
|
"excel",
|
|
"finance",
|
|
"macrofinance",
|
|
"office"
|
|
]
|
|
},
|
|
{
|
|
"task_id": "sales-pivot-analysis",
|
|
"task_digest": "sha256:d904b56d07ee53b5d6f2784409d877143b9137b14b7a0c6885895c28cb0be764",
|
|
"category": "office-white-collar",
|
|
"difficulty": "medium",
|
|
"tags": [
|
|
"excel",
|
|
"pivot-tables",
|
|
"pdf",
|
|
"aggregation",
|
|
"data-integration"
|
|
]
|
|
},
|
|
{
|
|
"task_id": "sec-financial-report",
|
|
"task_digest": "sha256:2274c6f554782e3061a3ff7d076362501617dd744d1286c7889188a003d62b2d",
|
|
"category": "finance-economics",
|
|
"difficulty": "hard",
|
|
"tags": [
|
|
"data processing",
|
|
"financial analysis"
|
|
]
|
|
},
|
|
{
|
|
"task_id": "seismic-phase-picking",
|
|
"task_digest": "sha256:7f906f01a7f5217ca67ccb15fd53725375b97bd774c8980fe96f7ce6fc7c3118",
|
|
"category": "natural-science",
|
|
"difficulty": "hard",
|
|
"tags": [
|
|
"science",
|
|
"earth-science",
|
|
"seismology",
|
|
"ai4science"
|
|
]
|
|
},
|
|
{
|
|
"task_id": "setup-fuzzing-py",
|
|
"task_digest": "sha256:ac70897b525ee19474225247a9132f4beaa9365ad8a4af064305321997147c0d",
|
|
"category": "cybersecurity",
|
|
"difficulty": "medium",
|
|
"tags": [
|
|
"security",
|
|
"build",
|
|
"vulnerability",
|
|
"continuous-integration",
|
|
"python"
|
|
]
|
|
},
|
|
{
|
|
"task_id": "shock-analysis-demand",
|
|
"task_digest": "sha256:6d1ee94a0c9ce1bec020b115022208f889111d70cb8eb2acd4521c2368a176dd",
|
|
"category": "finance-economics",
|
|
"difficulty": "medium",
|
|
"tags": [
|
|
"excel",
|
|
"finance",
|
|
"macrofinance",
|
|
"office"
|
|
]
|
|
},
|
|
{
|
|
"task_id": "shock-analysis-supply",
|
|
"task_digest": "sha256:b3ef079863d7cadf258e7f388229248e3bf42e06e5d6b0196656b0d186dec8f5",
|
|
"category": "finance-economics",
|
|
"difficulty": "hard",
|
|
"tags": [
|
|
"excel",
|
|
"finance",
|
|
"macrofinance",
|
|
"office",
|
|
"production-function"
|
|
]
|
|
},
|
|
{
|
|
"task_id": "simpo-code-reproduction",
|
|
"task_digest": "sha256:a436e280e9d3aabba9486530d1c10fc1ebcfa4f883bc4b9765259300767568af",
|
|
"category": "software-engineering",
|
|
"difficulty": "hard",
|
|
"tags": [
|
|
"code-reproduction",
|
|
"nlp",
|
|
"paper-to-code",
|
|
"unit-tests"
|
|
]
|
|
},
|
|
{
|
|
"task_id": "software-dependency-audit",
|
|
"task_digest": "sha256:806b47bea8b86a370c18dee279f6322da3a9b23026287876c2e9ffbfac855ec3",
|
|
"category": "cybersecurity",
|
|
"difficulty": "medium",
|
|
"tags": [
|
|
"security",
|
|
"vulnerability-scanning",
|
|
"dependencies"
|
|
]
|
|
},
|
|
{
|
|
"task_id": "spring-boot-jakarta-migration",
|
|
"task_digest": "sha256:2f5a32911b6e7bba86a6eb94e012e088f536d13ea823e7d0760b6ea93de51fba",
|
|
"category": "software-engineering",
|
|
"difficulty": "hard",
|
|
"tags": [
|
|
"migration",
|
|
"compilation"
|
|
]
|
|
},
|
|
{
|
|
"task_id": "suricata-custom-exfil",
|
|
"task_digest": "sha256:1a282d9d2283b8def6105a1e9e2ac1eb8eb30eeba79b452f6276d77a2197c986",
|
|
"category": "cybersecurity",
|
|
"difficulty": "medium",
|
|
"tags": [
|
|
"suricata",
|
|
"dpi",
|
|
"pcap",
|
|
"ids",
|
|
"rule-writing"
|
|
]
|
|
},
|
|
{
|
|
"task_id": "syzkaller-ppdev-syzlang",
|
|
"task_digest": "sha256:428a0a71086a6e1f537e0da43a65fa64d2c7e5545777cddbac611de90ad1b133",
|
|
"category": "cybersecurity",
|
|
"difficulty": "medium",
|
|
"tags": [
|
|
"security",
|
|
"fuzzing",
|
|
"kernel",
|
|
"syzkaller",
|
|
"syzlang"
|
|
]
|
|
},
|
|
{
|
|
"task_id": "threejs-structure-parser",
|
|
"task_digest": "sha256:adb134c373db87374ed4231a4c7bb0efe4bd012737e6ef2989e7a71fed677aad",
|
|
"category": "media-content-production",
|
|
"difficulty": "medium",
|
|
"tags": [
|
|
"threejs",
|
|
"json",
|
|
"3d",
|
|
"3D parts understanding",
|
|
"javascript"
|
|
]
|
|
},
|
|
{
|
|
"task_id": "threejs-to-obj",
|
|
"task_digest": "sha256:a6685ad8902228229c50d82684f0600fbc9a387f96e19378b4bfc8de150ff268",
|
|
"category": "media-content-production",
|
|
"difficulty": "medium",
|
|
"tags": [
|
|
"threejs",
|
|
"obj",
|
|
"3d",
|
|
"node",
|
|
"javascript"
|
|
]
|
|
},
|
|
{
|
|
"task_id": "tictoc-unnecessary-abort-detection",
|
|
"task_digest": "sha256:2142ae37cde1142f7ffbe4be59107d94171221d28ed6d390c4ec736bf26d2906",
|
|
"category": "software-engineering",
|
|
"difficulty": "hard",
|
|
"tags": [
|
|
"concurrency-control",
|
|
"transactions",
|
|
"tictoc",
|
|
"trace-analysis"
|
|
]
|
|
},
|
|
{
|
|
"task_id": "travel-planning",
|
|
"task_digest": "sha256:99dd2da5c704914c52b220c9d26366e0ebf04e15ce24ac07635c9dc2c58d48bd",
|
|
"category": "mathematics-or-formal-reasoning",
|
|
"difficulty": "medium",
|
|
"tags": [
|
|
"travel",
|
|
"planning",
|
|
"constraints"
|
|
]
|
|
},
|
|
{
|
|
"task_id": "video-silence-remover",
|
|
"task_digest": "sha256:66efcc64a2f38eaf183af213cff15b3dcb2119a33e20bde86024b5bf7a4b71bb",
|
|
"category": "media-content-production",
|
|
"difficulty": "hard",
|
|
"tags": [
|
|
"video",
|
|
"audio-analysis",
|
|
"ffmpeg",
|
|
"signal-processing"
|
|
]
|
|
},
|
|
{
|
|
"task_id": "weighted-gdp-calc",
|
|
"task_digest": "sha256:3a0f4971eb3f2407df8a60a156d847f0290c9dd1709a596aa5b9d13713f57d2f",
|
|
"category": "finance-economics",
|
|
"difficulty": "medium",
|
|
"tags": [
|
|
"excel",
|
|
"finance",
|
|
"macrofinance",
|
|
"office",
|
|
"excel-index-match",
|
|
"statistics"
|
|
]
|
|
},
|
|
{
|
|
"task_id": "xlsx-recover-data",
|
|
"task_digest": "sha256:5461eb5dec0c941670dd59e103a1cdbe826da6824c66de0334f65c031690299d",
|
|
"category": "finance-economics",
|
|
"difficulty": "medium",
|
|
"tags": [
|
|
"excel",
|
|
"data-recovery",
|
|
"financial-analysis",
|
|
"cross-sheet-dependencies"
|
|
]
|
|
}
|
|
],
|
|
"task_set_digest": "sha256:3c9432bb1a4bd1b66ddbc175bb1f43bf546f7de663d1b2aa0327a88bff7ecd39",
|
|
"source_registry": {
|
|
"name": "skillsbench",
|
|
"version": "1.1",
|
|
"git_tag": "v1.1",
|
|
"bench_version": ">=0.6.3,<0.7",
|
|
"registry_path": "registry.json"
|
|
}
|
|
}
|