{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:JRANFODLQP4KVIFYZBEIAEED2F","short_pith_number":"pith:JRANFODL","schema_version":"1.0","canonical_sha256":"4c40d2b86b83f8aaa0b8c848801083d15d716bd3310b60787f954c16faa298ce","source":{"kind":"arxiv","id":"2406.04959","version":1},"attestation_state":"computed","paper":{"title":"Leveraging Generative AI for Extracting Process Models from Multimodal Documents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Manfred Reichert, Marius Breitmayer, Marvin Voelter, Raheleh Hadian, Timotheus Kampik","submitted_at":"2024-06-07T14:24:05Z","abstract_excerpt":"This paper presents an investigation of the capabilities of Generative Pre-trained Transformers (GPTs) to auto-generate graphical process models from multi-modal (i.e., text- and image-based) inputs. More precisely, we first introduce a small dataset as well as a set of evaluation metrics that allow for a ground truth-based evaluation of multi-modal process model generation capabilities. We then conduct an initial evaluation of commercial GPT capabilities using zero-, one-, and few-shot prompting strategies. Our results indicate that GPTs can be useful tools for semi-automated process modeling"},"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":"2406.04959","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2024-06-07T14:24:05Z","cross_cats_sorted":[],"title_canon_sha256":"96dbd2b392b1985014b9275158e82b14c518aaff8104593bf76bf23e82a0d33f","abstract_canon_sha256":"9348d6bf6565bfa15aab9ed2c9131a39c1faab85104e7a54715184e74ac6b9fc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:28:51.488669Z","signature_b64":"SBM6wfiaagtmVn5HvIkFXqdB7Q8EAJM19VcTumFEbppxbxXv1yyVqyVj+97mZghXoofwRFb90ifVblIqwN8ADg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4c40d2b86b83f8aaa0b8c848801083d15d716bd3310b60787f954c16faa298ce","last_reissued_at":"2026-07-05T08:28:51.488138Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:28:51.488138Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Leveraging Generative AI for Extracting Process Models from Multimodal Documents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Manfred Reichert, Marius Breitmayer, Marvin Voelter, Raheleh Hadian, Timotheus Kampik","submitted_at":"2024-06-07T14:24:05Z","abstract_excerpt":"This paper presents an investigation of the capabilities of Generative Pre-trained Transformers (GPTs) to auto-generate graphical process models from multi-modal (i.e., text- and image-based) inputs. More precisely, we first introduce a small dataset as well as a set of evaluation metrics that allow for a ground truth-based evaluation of multi-modal process model generation capabilities. We then conduct an initial evaluation of commercial GPT capabilities using zero-, one-, and few-shot prompting strategies. Our results indicate that GPTs can be useful tools for semi-automated process modeling"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.04959","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/2406.04959/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":"2406.04959","created_at":"2026-07-05T08:28:51.488195+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.04959v1","created_at":"2026-07-05T08:28:51.488195+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.04959","created_at":"2026-07-05T08:28:51.488195+00:00"},{"alias_kind":"pith_short_12","alias_value":"JRANFODLQP4K","created_at":"2026-07-05T08:28:51.488195+00:00"},{"alias_kind":"pith_short_16","alias_value":"JRANFODLQP4KVIFY","created_at":"2026-07-05T08:28:51.488195+00:00"},{"alias_kind":"pith_short_8","alias_value":"JRANFODL","created_at":"2026-07-05T08:28:51.488195+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.12105","citing_title":"Automated BPMN Model Generation from Textual Process Descriptions: A Multi-Stage LLM-Driven Approach","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07817","citing_title":"Automatic Generation of Executable BPMN Models from Medical Guidelines","ref_index":22,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JRANFODLQP4KVIFYZBEIAEED2F","json":"https://pith.science/pith/JRANFODLQP4KVIFYZBEIAEED2F.json","graph_json":"https://pith.science/api/pith-number/JRANFODLQP4KVIFYZBEIAEED2F/graph.json","events_json":"https://pith.science/api/pith-number/JRANFODLQP4KVIFYZBEIAEED2F/events.json","paper":"https://pith.science/paper/JRANFODL"},"agent_actions":{"view_html":"https://pith.science/pith/JRANFODLQP4KVIFYZBEIAEED2F","download_json":"https://pith.science/pith/JRANFODLQP4KVIFYZBEIAEED2F.json","view_paper":"https://pith.science/paper/JRANFODL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.04959&json=true","fetch_graph":"https://pith.science/api/pith-number/JRANFODLQP4KVIFYZBEIAEED2F/graph.json","fetch_events":"https://pith.science/api/pith-number/JRANFODLQP4KVIFYZBEIAEED2F/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JRANFODLQP4KVIFYZBEIAEED2F/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JRANFODLQP4KVIFYZBEIAEED2F/action/storage_attestation","attest_author":"https://pith.science/pith/JRANFODLQP4KVIFYZBEIAEED2F/action/author_attestation","sign_citation":"https://pith.science/pith/JRANFODLQP4KVIFYZBEIAEED2F/action/citation_signature","submit_replication":"https://pith.science/pith/JRANFODLQP4KVIFYZBEIAEED2F/action/replication_record"}},"created_at":"2026-07-05T08:28:51.488195+00:00","updated_at":"2026-07-05T08:28:51.488195+00:00"}