{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:SES2ZQC3MR3QX3URRPMSLLYJ2J","short_pith_number":"pith:SES2ZQC3","schema_version":"1.0","canonical_sha256":"9125acc05b64770bee918bd925af09d26a15ba2e5575dcae50a85f39e09e5f00","source":{"kind":"arxiv","id":"2503.13520","version":1},"attestation_state":"computed","paper":{"title":"Evaluating the Process Modeling Abilities of Large Language Models -- Preliminary Foundations and Results","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG","cs.SE"],"primary_cat":"cs.CL","authors_text":"Constantin Houy, Peter Fettke","submitted_at":"2025-03-14T18:52:18Z","abstract_excerpt":"Large language models (LLM) have revolutionized the processing of natural language. Although first benchmarks of the process modeling abilities of LLM are promising, it is currently under debate to what extent an LLM can generate good process models. In this contribution, we argue that the evaluation of the process modeling abilities of LLM is far from being trivial. Hence, available evaluation results must be taken carefully. For example, even in a simple scenario, not only the quality of a model should be taken into account, but also the costs and time needed for generation. Thus, an LLM doe"},"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":"2503.13520","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-14T18:52:18Z","cross_cats_sorted":["cs.LG","cs.SE"],"title_canon_sha256":"02d3667c073102adcf691b3f61db6873d7d2682e330a909eea5ab049598ce8a9","abstract_canon_sha256":"1e049f5a7ecaa1188adfa81dbee79a000327d51819c0af1209280e3c75e5215d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:33:12.074089Z","signature_b64":"vSWHYA8BV7+1l7G+DVre5bZFig/TAk5ju1cHx0wWQAbwv3FPSy6Vs9Ljzra4uz5g+hvmWfvwJyIbcr9j9FiyBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9125acc05b64770bee918bd925af09d26a15ba2e5575dcae50a85f39e09e5f00","last_reissued_at":"2026-07-05T10:33:12.073667Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:33:12.073667Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Evaluating the Process Modeling Abilities of Large Language Models -- Preliminary Foundations and Results","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG","cs.SE"],"primary_cat":"cs.CL","authors_text":"Constantin Houy, Peter Fettke","submitted_at":"2025-03-14T18:52:18Z","abstract_excerpt":"Large language models (LLM) have revolutionized the processing of natural language. Although first benchmarks of the process modeling abilities of LLM are promising, it is currently under debate to what extent an LLM can generate good process models. In this contribution, we argue that the evaluation of the process modeling abilities of LLM is far from being trivial. Hence, available evaluation results must be taken carefully. For example, even in a simple scenario, not only the quality of a model should be taken into account, but also the costs and time needed for generation. Thus, an LLM doe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.13520","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/2503.13520/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":"2503.13520","created_at":"2026-07-05T10:33:12.073722+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.13520v1","created_at":"2026-07-05T10:33:12.073722+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.13520","created_at":"2026-07-05T10:33:12.073722+00:00"},{"alias_kind":"pith_short_12","alias_value":"SES2ZQC3MR3Q","created_at":"2026-07-05T10:33:12.073722+00:00"},{"alias_kind":"pith_short_16","alias_value":"SES2ZQC3MR3QX3UR","created_at":"2026-07-05T10:33:12.073722+00:00"},{"alias_kind":"pith_short_8","alias_value":"SES2ZQC3","created_at":"2026-07-05T10:33:12.073722+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.11356","citing_title":"What is the Best Process Model Representation? A Comparative Analysis for Process Modeling with Large Language Models","ref_index":4,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SES2ZQC3MR3QX3URRPMSLLYJ2J","json":"https://pith.science/pith/SES2ZQC3MR3QX3URRPMSLLYJ2J.json","graph_json":"https://pith.science/api/pith-number/SES2ZQC3MR3QX3URRPMSLLYJ2J/graph.json","events_json":"https://pith.science/api/pith-number/SES2ZQC3MR3QX3URRPMSLLYJ2J/events.json","paper":"https://pith.science/paper/SES2ZQC3"},"agent_actions":{"view_html":"https://pith.science/pith/SES2ZQC3MR3QX3URRPMSLLYJ2J","download_json":"https://pith.science/pith/SES2ZQC3MR3QX3URRPMSLLYJ2J.json","view_paper":"https://pith.science/paper/SES2ZQC3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.13520&json=true","fetch_graph":"https://pith.science/api/pith-number/SES2ZQC3MR3QX3URRPMSLLYJ2J/graph.json","fetch_events":"https://pith.science/api/pith-number/SES2ZQC3MR3QX3URRPMSLLYJ2J/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SES2ZQC3MR3QX3URRPMSLLYJ2J/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SES2ZQC3MR3QX3URRPMSLLYJ2J/action/storage_attestation","attest_author":"https://pith.science/pith/SES2ZQC3MR3QX3URRPMSLLYJ2J/action/author_attestation","sign_citation":"https://pith.science/pith/SES2ZQC3MR3QX3URRPMSLLYJ2J/action/citation_signature","submit_replication":"https://pith.science/pith/SES2ZQC3MR3QX3URRPMSLLYJ2J/action/replication_record"}},"created_at":"2026-07-05T10:33:12.073722+00:00","updated_at":"2026-07-05T10:33:12.073722+00:00"}