Novel Mechanisms for Online Crowdsourcing with Unreliable, Strategic Agents
Authors: Praphul Chandra, Yadati Narahari, Debmalya Mandal, Prasenjit Dey
AAAI 2015 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | The section on Simulation presents pertinent experimental results. We use simulations to demonstrate the effectiveness of our proposed mechanisms with varying arrival rate and agent reliability. We compare DPM with FP which is currently the defacto mechanism on crowdsourcing platforms today. |
| Researcher Affiliation | Collaboration | 1Indian Institute of Science, Bangalore, India, 2Hewlett Packard, Bangalore, India, 3SEAS, Harvard University, Cambrige, MA, USA, 4IBM Research, Bangalore, India |
| Pseudocode | No | The paper describes the DPM and ABM mechanisms using mathematical equations and textual explanations, but it does not include formal pseudocode blocks or algorithm listings. |
| Open Source Code | No | The paper does not contain any statement about releasing source code or provide any links to a code repository. |
| Open Datasets | No | The paper uses a simulation setup with predefined parameters (e.g., 50 tasks, 25 hours deadline, 2 agents/hour arrival rate) rather than external, publicly available datasets. Therefore, no concrete access information for a dataset is provided. |
| Dataset Splits | No | The paper describes a simulation setup and performs comparisons of mechanisms within that simulation. It does not involve dataset splitting for training, validation, and testing, as would be common in machine learning experiments. |
| Hardware Specification | No | The paper describes the simulation setup (e.g., number of tasks, deadline, arrival rates) but provides no details regarding the specific hardware (CPU, GPU, memory, etc.) used to perform these simulations. |
| Software Dependencies | No | The paper describes the mechanisms and simulation scenarios but does not specify any software dependencies, programming languages, or library versions used for implementation or simulation. |
| Experiment Setup | Yes | We consider the following setup. At t = 0, a requester posts h0 = 50 tasks on the platform with a deadline of T = 25 hours. On-time completion of these tasks generates a requester value of ϑ = 20. The posted price attracts qualified agents to service the task at µ = 2 per hour (Poisson process) so that tasks will complete in expectation ( µT = 50 = h0). |