Experiment design

This is a reproduction of 20140314-NOOR

Hypothesis: Confirm where the process converges and that it provide a better F-measure than logical repair.

Experimental setting: As of 20140314-NOOR;


Experimenter: Jérôme Euzenat (INRIA)

Date: 2015-02-19 (started 2015-02-18 finished 2015-02-20)

Lazy lavender hash: dd79573c717614724f74740d3d0004faab071c19

Parameters: params.sh

Command line (script.sh):

java -Xms500M -Xmx1G -cp lib/lazylav/ll.jar:lib/slf4j/logback-classic-1.0.9.jar:lib/slf4j/logback-core-1.0.9.jar:. fr.inria.exmo.lazylavender.engine.Monitor -DrevisionModality=add -DnbRuns=10 -DnbAgents=6 -DnbIterations=100000 > log6-100000.txt 

Class used: NOOEnvironment, AlignmentAdjustingAgent, AlignmentRevisionExperiment, ActionLogger, AverageLogger, Monitor.

Execution environment: Debian Linux virtual machine configured with four processors and 20GB of RAM running under a Dell PowerEdge T610 with 2*Intel Xeon 1.9GHz processors and 32GB of RAM, under Linux ProxMox 2 (Debian). - Java 1.7.0 HotSpot

It took roughly 43h30: It may be due to a slower virtual machine or the new implementation.

Raw results

20150219-NOOR-Log6-100000.tsv 20150219-NOOR-Log6-100000.txt

Result exploration

modality size success convergence Incoherence degree F-measure
Reference 783 0.00 1.00
Initial 495 0.63 0.06
Add 200 0.97 17398 0.0 0.17
Alcomo 184 1 0.0 0.11
LogMap 231 1 0.0 0.12

In addition here are the last games in which F-measure changed, i.e., a failure has occurred (reverse order). This combines 10 rounds:


(same results as 20140314-NOOR)

Key points:

Further experiments:

This file can be retrieved from URL https://sake.re/20150219-NOOR

It is possible to check out the repository by cloning https://felapton.inrialpes.fr/cakes/20150219-NOOR.git

This experiment has been transferred from its initial location at https://gforge.inria.fr (not available any more)