{"paper":{"title":"Combining Abstract Argumentation and Machine Learning for Efficiently Analyzing Low-Level Process Event Streams","license":"http://creativecommons.org/licenses/by/4.0/","headline":"A neuro-symbolic approach uses machine learning to suggest event interpretations and argumentation to refine them with prior knowledge.","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Bettina Fazzinga, Filippo Furfaro, Francesco Scala, Luigi Pontieri, Sergio Flesca","submitted_at":"2025-05-09T08:45:07Z","abstract_excerpt":"Monitoring and analyzing process traces is a critical task for modern companies and organizations. In scenarios where there is a gap between trace events and reference business activities, this entails an interpretation problem, amounting to translating each event of any ongoing trace into the corresponding step of the activity instance. Building on a recent approach that frames the interpretation problem as an acceptance problem within an Abstract Argumentation Framework (AAF), one can elegantly analyze plausible event interpretations (possibly in an aggregated form), as well as offer explana"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"The proposed data-efficient neuro-symbolic approach, where candidate interpretations returned by the example-driven sequence tagger are refined by the AAF-based reasoner, allows leveraging prior knowledge to compensate for the scarcity of example data, as confirmed by experimental results.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the sequence-tagging model produces sufficiently accurate candidate interpretations even with limited training data, and that the AAF reasoner can reliably improve those candidates in highly uncertain mapping scenarios without introducing new inconsistencies.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"A neuro-symbolic approach trains a sequence tagger on limited examples to propose event interpretations and refines them via an Abstract Argumentation Framework to handle uncertain mappings in process streams.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A neuro-symbolic approach uses machine learning to suggest event interpretations and argumentation to refine them with prior knowledge.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"a525527ff306e69744c72ada751e1fcd6699cff59275a5942e779e4598f952cd"},"source":{"id":"2505.05880","kind":"arxiv","version":2},"verdict":{"id":"ec53caed-7b6b-47c3-98bc-b04dd046a52f","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-22T16:40:24.388138Z","strongest_claim":"The proposed data-efficient neuro-symbolic approach, where candidate interpretations returned by the example-driven sequence tagger are refined by the AAF-based reasoner, allows leveraging prior knowledge to compensate for the scarcity of example data, as confirmed by experimental results.","one_line_summary":"A neuro-symbolic approach trains a sequence tagger on limited examples to propose event interpretations and refines them via an Abstract Argumentation Framework to handle uncertain mappings in process streams.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the sequence-tagging model produces sufficiently accurate candidate interpretations even with limited training data, and that the AAF reasoner can reliably improve those candidates in highly uncertain mapping scenarios without introducing new inconsistencies.","pith_extraction_headline":"A neuro-symbolic approach uses machine learning to suggest event interpretations and argumentation to refine them with prior knowledge."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2505.05880/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":35,"sample":[{"doi":"","year":2021,"title":"J., Mannhardt, F., de Leoni, M","work_id":"073ddf7f-e77e-45fc-b4f0-8954fd7d9ae2","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2018,"title":"Tax, N. Human activity prediction in smart home environments with LSTM neural networks.14th International Conference on Intelligent Environments, IE 2018, Roma, Italy, June 25-28, 201840–47 (2018)","work_id":"1f020a45-9250-4909-906d-bedaf46a783a","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2016,"title":"& van der Aalst, W","work_id":"ca9305da-b0b2-4074-88a4-cffe2ee4b880","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2022,"title":"Fazzinga, B., Flesca, S., Furfaro, F. & Pontieri, L. Process mining meets argumen- tation: Explainable interpretations of low-level event logs via abstract argumentation. Information Systems107(2022)","work_id":"9bdc1b2b-b3fe-4cf6-a97c-163d1c20e81c","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2015,"title":"Baier, T., Di Ciccio, C., Mendling, J. & Weske, M. Gaaloul, K., Schmidt, R., Nurcan, S., Guerreiro, S. & Ma, Q. (eds)Matching of events and activities - an approach using declarative modeling constrai","work_id":"493ed57d-b672-4964-8f6f-32c0644059a1","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":35,"snapshot_sha256":"d0c3a1a9af2ddc4b9c0eb0551d4802e19d7474e056b2e48c0eecb2e50f257fed","internal_anchors":1},"formal_canon":{"evidence_count":2,"snapshot_sha256":"554f1af1ffba7718f1522dfbc18543984a8a6b35abeb171ef2d5c685c3de663d"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"}