{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:RKUUGUES4A2UHUOMG6DFV2APII","short_pith_number":"pith:RKUUGUES","schema_version":"1.0","canonical_sha256":"8aa9435092e03543d1cc37865ae80f42204dfb5117aa40d49c5b18ade1375374","source":{"kind":"arxiv","id":"2407.13244","version":1},"attestation_state":"computed","paper":{"title":"PM-LLM-Benchmark: Evaluating Large Language Models on Process Mining Tasks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DB"],"primary_cat":"cs.CL","authors_text":"Alessandro Berti, Humam Kourani, Wil M.P. van der Aalst","submitted_at":"2024-07-18T07:57:31Z","abstract_excerpt":"Large Language Models (LLMs) have the potential to semi-automate some process mining (PM) analyses. While commercial models are already adequate for many analytics tasks, the competitive level of open-source LLMs in PM tasks is unknown. In this paper, we propose PM-LLM-Benchmark, the first comprehensive benchmark for PM focusing on domain knowledge (process-mining-specific and process-specific) and on different implementation strategies. We focus also on the challenges in creating such a benchmark, related to the public availability of the data and on evaluation biases by the LLMs. Overall, we"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2407.13244","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-18T07:57:31Z","cross_cats_sorted":["cs.DB"],"title_canon_sha256":"5d8d85454bde5b419051dd087a0e048d0322674ad04c468eb03fb66b0efdca28","abstract_canon_sha256":"26a5b3b8e121bb32ff9e33db23a35afc1d2eea83bf7e2e11fc8b4f8e192f92dd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:45:36.336616Z","signature_b64":"yTFhWQU3RW+Z/zCJUSb9kIKuIsBN9wEXF+APGdQWJyMSf0wnImQaXlBlK+afmuXcSklHU7ZqWR5ae4GBRoAzBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8aa9435092e03543d1cc37865ae80f42204dfb5117aa40d49c5b18ade1375374","last_reissued_at":"2026-07-05T08:45:36.336191Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:45:36.336191Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PM-LLM-Benchmark: Evaluating Large Language Models on Process Mining Tasks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DB"],"primary_cat":"cs.CL","authors_text":"Alessandro Berti, Humam Kourani, Wil M.P. van der Aalst","submitted_at":"2024-07-18T07:57:31Z","abstract_excerpt":"Large Language Models (LLMs) have the potential to semi-automate some process mining (PM) analyses. While commercial models are already adequate for many analytics tasks, the competitive level of open-source LLMs in PM tasks is unknown. In this paper, we propose PM-LLM-Benchmark, the first comprehensive benchmark for PM focusing on domain knowledge (process-mining-specific and process-specific) and on different implementation strategies. We focus also on the challenges in creating such a benchmark, related to the public availability of the data and on evaluation biases by the LLMs. Overall, we"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.13244","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2407.13244/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2407.13244","created_at":"2026-07-05T08:45:36.336250+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.13244v1","created_at":"2026-07-05T08:45:36.336250+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.13244","created_at":"2026-07-05T08:45:36.336250+00:00"},{"alias_kind":"pith_short_12","alias_value":"RKUUGUES4A2U","created_at":"2026-07-05T08:45:36.336250+00:00"},{"alias_kind":"pith_short_16","alias_value":"RKUUGUES4A2UHUOM","created_at":"2026-07-05T08:45:36.336250+00:00"},{"alias_kind":"pith_short_8","alias_value":"RKUUGUES","created_at":"2026-07-05T08:45:36.336250+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RKUUGUES4A2UHUOMG6DFV2APII","json":"https://pith.science/pith/RKUUGUES4A2UHUOMG6DFV2APII.json","graph_json":"https://pith.science/api/pith-number/RKUUGUES4A2UHUOMG6DFV2APII/graph.json","events_json":"https://pith.science/api/pith-number/RKUUGUES4A2UHUOMG6DFV2APII/events.json","paper":"https://pith.science/paper/RKUUGUES"},"agent_actions":{"view_html":"https://pith.science/pith/RKUUGUES4A2UHUOMG6DFV2APII","download_json":"https://pith.science/pith/RKUUGUES4A2UHUOMG6DFV2APII.json","view_paper":"https://pith.science/paper/RKUUGUES","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.13244&json=true","fetch_graph":"https://pith.science/api/pith-number/RKUUGUES4A2UHUOMG6DFV2APII/graph.json","fetch_events":"https://pith.science/api/pith-number/RKUUGUES4A2UHUOMG6DFV2APII/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RKUUGUES4A2UHUOMG6DFV2APII/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RKUUGUES4A2UHUOMG6DFV2APII/action/storage_attestation","attest_author":"https://pith.science/pith/RKUUGUES4A2UHUOMG6DFV2APII/action/author_attestation","sign_citation":"https://pith.science/pith/RKUUGUES4A2UHUOMG6DFV2APII/action/citation_signature","submit_replication":"https://pith.science/pith/RKUUGUES4A2UHUOMG6DFV2APII/action/replication_record"}},"created_at":"2026-07-05T08:45:36.336250+00:00","updated_at":"2026-07-05T08:45:36.336250+00:00"}