Papers › Overview of the 2022 Validity and Novelty Prediction Shared Task

Overview of the 2022 Validity and Novelty Prediction Shared Task

1 Oct 2022ArgMining (ACL) 2022 10archive 2025-07-28

Philipp Heinisch, Anette Frank, Juri Opitz, Moritz Plenz, Philipp Cimiano

This paper provides an overview of the Argument Validity and Novelty Prediction Shared Task that was organized as part of the 9th Workshop on Argument Mining (ArgMining 2022). The task focused on the prediction of the validity and novelty of a conclusion given a textual premise. Validity is defined as the degree to which the conclusion is justified with respect to the given premise. Novelty defines the degree to which the conclusion contains content that is new in relation to the premise. Six groups participated in the task, submitting overall 13 system runs for the subtask of binary classification and 2 system runs for the subtask of relative classification. The results reveal that the task is challenging, with best results obtained for Validity prediction in the range of 75% F1 score, for Novelty prediction of 70% F1 score and for correctly predicting both Validity and Novelty of 45% F1 score. In this paper we summarize the task definition and dataset. We give an overview of the results obtained by the participating systems, as well as insights to be gained from the diverse contributions.

PaperPDFCode

Code

phhei/argsvalidnovel officialmentioned in paperpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Argument MiningBinary ClassificationPredictionValNov

Datasets

Introduced by this paper, per the archive.

ValNov Subtask AValNov Subtask B

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
ValNov ValNov Subtask A CLTeamL-3 JOINT-F1 45.16 #1 of 8 Archive leaderboard report
ValNov ValNov Subtask A CLTeamL-3 NOV-F1 61.75 #1 of 8 Archive leaderboard report
ValNov ValNov Subtask A CLTeamL-3 VAL-F1 74.64 #1 of 8 Archive leaderboard report
ValNov ValNov Subtask A ACCEPT-1 JOINT-F1 43.13 #3 of 8 Archive leaderboard report
ValNov ValNov Subtask A ACCEPT-1 NOV-F1 70.00 #3 of 8 Archive leaderboard report
ValNov ValNov Subtask A ACCEPT-1 VAL-F1 59.20 #3 of 8 Archive leaderboard report
ValNov ValNov Subtask A CSS JOINT-F1 42.40 #4 of 8 Archive leaderboard report
ValNov ValNov Subtask A CSS NOV-F1 59.86 #4 of 8 Archive leaderboard report
ValNov ValNov Subtask A CSS VAL-F1 70.76 #4 of 8 Archive leaderboard report
ValNov ValNov Subtask A System Average JOINT-F1 35.94 #5 of 8 Archive leaderboard report
ValNov ValNov Subtask A System Average NOV-F1 52.97 #5 of 8 Archive leaderboard report
ValNov ValNov Subtask A System Average VAL-F1 62.74 #5 of 8 Archive leaderboard report
ValNov ValNov Subtask A NLP@UIT JOINT-F1 25.89 #6 of 8 Archive leaderboard report
ValNov ValNov Subtask A NLP@UIT NOV-F1 43.36 #6 of 8 Archive leaderboard report
ValNov ValNov Subtask A NLP@UIT VAL-F1 61.72 #6 of 8 Archive leaderboard report
ValNov ValNov Subtask A Baseline JOINT-F1 23.90 #7 of 8 Archive leaderboard report
ValNov ValNov Subtask A Baseline NOV-F1 36.12 #7 of 8 Archive leaderboard report
ValNov ValNov Subtask A Baseline VAL-F1 59.96 #7 of 8 Archive leaderboard report
ValNov ValNov Subtask A Harshad JOINT-F1 17.35 #8 of 8 Archive leaderboard report
ValNov ValNov Subtask A Harshad NOV-F1 39.00 #8 of 8 Archive leaderboard report
ValNov ValNov Subtask A Harshad VAL-F1 56.31 #8 of 8 Archive leaderboard report
ValNov ValNov Subtask B NLP@UIT JOINT-F1 41.50 #1 of 3 Archive leaderboard report
ValNov ValNov Subtask B NLP@UIT NOV-F1 38.39 #1 of 3 Archive leaderboard report
ValNov ValNov Subtask B NLP@UIT VAL-F1 44.60 #1 of 3 Archive leaderboard report
ValNov ValNov Subtask B AXiS@EdUni JOINT-F1 29.16 #2 of 3 Archive leaderboard report
ValNov ValNov Subtask B AXiS@EdUni NOV-F1 25.86 #2 of 3 Archive leaderboard report
ValNov ValNov Subtask B AXiS@EdUni VAL-F1 32.47 #2 of 3 Archive leaderboard report
ValNov ValNov Subtask B Baseline JOINT-F1 21.46 #3 of 3 Archive leaderboard report
ValNov ValNov Subtask B Baseline NOV-F1 23.09 #3 of 3 Archive leaderboard report
ValNov ValNov Subtask B Baseline VAL-F1 19.82 #3 of 3 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections