LIVEdataset aec-bench@releasetasks 552models 18last submission … · built …
electricalwith-tool

Cctv Storage Calculation

Calculates surveillance video storage from camera count, average bitrate, recording hours, retention period, and storage overhead. The template converts Mbps to daily gigabytes per camera, then reports usable retained storage and raw storage including overhead.

with-tool: The model is given an executable Python calculator script.

Standards

IEC 62676-4

Tags

cctvdeterministicelectricalsecuritystoragevideo

How this task is generated

One template produces many comparable benchmark tasks while keeping the scoring contract fixed.

  1. 01

    Template

    The reusable contract shown on this page.

  2. 02

    Scenario

    An archetype and site context are sampled.

  3. 03

    Difficulty tier

    Inputs may be hidden at harder tiers.

  4. 04

    Task prompt

    The model responds with the declared outputs.

Parameters

Inputs the model receives, and the outputs it is scored on.

Inputs

5 inputs

Always given

Included directly in every task prompt.

4

  • Camera count

    camera_count

    Number of cameras

    1 – 1000

  • Average bitrate

    average_bitrate_mbps

    Average video bitrate per camera

    0.1 – 50 Mbps

  • Recording hours per day

    recording_hours_per_day

    Recording hours per day

    1 – 24 h/day

  • Storage overhead pct

    storage_overhead_pct

    Storage overhead for RAID, filesystem, or spare capacity

    0 – 100 %

Hidden at higher difficulty

Visible in easier tasks and withheld in one or more harder tiers.

1

  • Retention

    retention_days

    Required retention period

    Hidden at hard difficulty.

    1 – 365 days

Scored outputs

3 outputs

Daily storage per camera gb

daily_storage_per_camera_gb

Daily storage per camera

Scores if within ±3% of the reference value.

Usable storage required tb

usable_storage_required_tb

Usable retained storage required

Scores if within ±3% of the reference value.

Raw storage with overhead tb

raw_storage_with_overhead_tb

Raw storage after overhead allowance

Scores if within ±3% of the reference value.

Difficulty

Each template is sampled at three tiers. Harder tiers may hide inputs, forcing the model to infer them from the scenario description.

easy

All inputs given

Small site storage calculation

medium

All inputs given

Small or large CCTV storage calculation

hard

Some inputs hidden

Retention hidden in the site security context

Hidden inputs

  • Retention daysretention_days

Prompt replacement text

Use the retention period implied by {{ archetype.description }}.

Retention days restricted to: 30

Task bundle

The exact instruction and parameter contract used to generate this task, pinned to the published library source.

/workspace

  • instruction.md
  • cctv-storage-calculation_calc.py

Teal lines show Jinja input conditions, not task visibility policy. A line renders only when that input or tool is visible.

1You are a senior security systems engineer sizing CCTV storage.2 3## Given4 5| Parameter | Value | Unit |6|-----------|-------|------|7| Camera count | {{ camera_count }} | count |8| Average bitrate | {{ average_bitrate_mbps }} | Mbps per camera |9| Recording hours per day | {{ recording_hours_per_day }} | h/day |10{% if retention_days is defined %}11| Retention period | {{ retention_days }} | days |12{% endif %}13| Storage overhead | {{ storage_overhead_pct }} | % |14 15## Constraints16 17- Convert Mbps to GB using `bitrate x hours x 3600 / 8 / 1000`.18- Total usable storage equals daily storage per camera times camera count times retention days.19- Raw storage equals usable storage times the overhead factor.20 21## Output Format22 23Include a JSON block with exactly these keys:24 25```json26{27 "daily_storage_per_camera_gb": <numeric_value>,28 "usable_storage_required_tb": <numeric_value>,29 "raw_storage_with_overhead_tb": <numeric_value>30}31```32 33Write your complete solution to `/workspace/output.md`.34

Scenario archetypes

Each generated task is drawn from one of these realistic scenario bands.

Site contexts ground each scenario in a real locale the model can use to infer hidden values.

Small site

small_site

Small CCTV site with continuous or business-hours recording

building-securitycar-park
Parameter ranges
camera_count
2 – 24
average_bitrate_mbps
1 – 8
recording_hours_per_day
8 – 24
retention_days
7 – 60
storage_overhead_pct
10 – 30

Large precinct

large_precinct

Large surveillance precinct with many IP cameras

transport-hubcampus-security
Parameter ranges
camera_count
25 – 300
average_bitrate_mbps
2 – 12
recording_hours_per_day
12 – 24
retention_days
14 – 120
storage_overhead_pct
15 – 50

Example task

transport-hub-large-precinct-preview — hard difficulty, some inputs hidden.

Large surveillance precinct with many IP cameras. transport-hub. Required outputs: daily_storage_per_camera_gb, usable_storage_required_tb, raw_storage_with_overhead_tb

The model sees

Scenario context and visible inputs.

camera_count
25 to 300
average_bitrate_mbps
2 to 12 Mbps
recording_hours_per_day
12 to 24 h/day
storage_overhead_pct
15 to 50 %

Executable tool: cctv-storage-calculation_calc.py

The model must infer

Inputs withheld at this difficulty.

  • Retention days

    retention_days

Stand-in text in the prompt

Use the retention period implied by {{ archetype.description }}.

The model must produce

The scored JSON answer schema.

{
  "daily_storage_per_camera_gb": <number>,
  "usable_storage_required_tb": <number>,
  "raw_storage_with_overhead_tb": <number>
}
  • daily_storage_per_camera_gb · scored within ±3%
  • usable_storage_required_tb · scored within ±3%
  • raw_storage_with_overhead_tb · scored within ±3%