{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:RKUUGUES4A2UHUOMG6DFV2APII","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"26a5b3b8e121bb32ff9e33db23a35afc1d2eea83bf7e2e11fc8b4f8e192f92dd","cross_cats_sorted":["cs.DB"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-18T07:57:31Z","title_canon_sha256":"5d8d85454bde5b419051dd087a0e048d0322674ad04c468eb03fb66b0efdca28"},"schema_version":"1.0","source":{"id":"2407.13244","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.13244","created_at":"2026-07-05T08:45:36Z"},{"alias_kind":"arxiv_version","alias_value":"2407.13244v1","created_at":"2026-07-05T08:45:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.13244","created_at":"2026-07-05T08:45:36Z"},{"alias_kind":"pith_short_12","alias_value":"RKUUGUES4A2U","created_at":"2026-07-05T08:45:36Z"},{"alias_kind":"pith_short_16","alias_value":"RKUUGUES4A2UHUOM","created_at":"2026-07-05T08:45:36Z"},{"alias_kind":"pith_short_8","alias_value":"RKUUGUES","created_at":"2026-07-05T08:45:36Z"}],"graph_snapshots":[{"event_id":"sha256:b3b3ca850c81ea720da2b156fe27a642f34bd3eaae1a16ecc14717f6585d18e6","target":"graph","created_at":"2026-07-05T08:45:36Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2407.13244/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Alessandro Berti, Humam Kourani, Wil M.P. van der Aalst","cross_cats":["cs.DB"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-18T07:57:31Z","title":"PM-LLM-Benchmark: Evaluating Large Language Models on Process Mining Tasks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.13244","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:01ea1f7608f7d53f9445d5d81a376d1dac0326ca0ea0820ec0e0ee967bf05a3d","target":"record","created_at":"2026-07-05T08:45:36Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"26a5b3b8e121bb32ff9e33db23a35afc1d2eea83bf7e2e11fc8b4f8e192f92dd","cross_cats_sorted":["cs.DB"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-18T07:57:31Z","title_canon_sha256":"5d8d85454bde5b419051dd087a0e048d0322674ad04c468eb03fb66b0efdca28"},"schema_version":"1.0","source":{"id":"2407.13244","kind":"arxiv","version":1}},"canonical_sha256":"8aa9435092e03543d1cc37865ae80f42204dfb5117aa40d49c5b18ade1375374","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8aa9435092e03543d1cc37865ae80f42204dfb5117aa40d49c5b18ade1375374","first_computed_at":"2026-07-05T08:45:36.336191Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:45:36.336191Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yTFhWQU3RW+Z/zCJUSb9kIKuIsBN9wEXF+APGdQWJyMSf0wnImQaXlBlK+afmuXcSklHU7ZqWR5ae4GBRoAzBw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:45:36.336616Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.13244","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:01ea1f7608f7d53f9445d5d81a376d1dac0326ca0ea0820ec0e0ee967bf05a3d","sha256:b3b3ca850c81ea720da2b156fe27a642f34bd3eaae1a16ecc14717f6585d18e6"],"state_sha256":"fafcda6ce07a9a54979f8f23f91661a2476286993650ce414cb621304a901381"}