{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:SR32OD5JDXOG3TPZNUFVZTYVQC","short_pith_number":"pith:SR32OD5J","schema_version":"1.0","canonical_sha256":"9477a70fa91ddc6dcdf96d0b5ccf1580ae1e35fe39e52a3349cc44df209791e0","source":{"kind":"arxiv","id":"2607.04948","version":1},"attestation_state":"computed","paper":{"title":"Using Process Mining to Generate AI Agents from Software Engineering Process Records","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Andreas Metzger, Fabiana Fournier, Lior Limonad, Saimir Bala","submitted_at":"2026-07-06T11:22:25Z","abstract_excerpt":"Integrating AI agents into Software Engineering (SE) raises an important challenge: how can we specify and realize AI agents that work effectively alongside humans in hybrid SE teams? Determining the right granularity and separation of concerns for such agents is non-trivial. Coarse-grained agents may introduce unmanageable complexity, whereas micro-agents may create severe coordination overhead. Moreover, existing multi-agent SE frameworks typically rely on predefined role structures and do not account for project-specific characteristics or process adaptations. We address this by combining o"},"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":"2607.04948","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-07-06T11:22:25Z","cross_cats_sorted":[],"title_canon_sha256":"1388d8a43d0f1b9f623153367fd9d71d6196f2ea107dcb172db8775cf654920a","abstract_canon_sha256":"4ba4be6428394f03686798cab94ec2eec5b98733f1d0e0a7ba323a2873a09f56"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-07T02:20:14.932427Z","signature_b64":"a259AIX7Fufg5gS/nRpmRAIGFkcF0qOmySCMkGb/NFW08nX3OM89oX79ZezJlJUqmyMCXZ7ACYqa6gvCdmqJAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9477a70fa91ddc6dcdf96d0b5ccf1580ae1e35fe39e52a3349cc44df209791e0","last_reissued_at":"2026-07-07T02:20:14.931684Z","signature_status":"signed_v1","first_computed_at":"2026-07-07T02:20:14.931684Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Using Process Mining to Generate AI Agents from Software Engineering Process Records","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Andreas Metzger, Fabiana Fournier, Lior Limonad, Saimir Bala","submitted_at":"2026-07-06T11:22:25Z","abstract_excerpt":"Integrating AI agents into Software Engineering (SE) raises an important challenge: how can we specify and realize AI agents that work effectively alongside humans in hybrid SE teams? Determining the right granularity and separation of concerns for such agents is non-trivial. Coarse-grained agents may introduce unmanageable complexity, whereas micro-agents may create severe coordination overhead. Moreover, existing multi-agent SE frameworks typically rely on predefined role structures and do not account for project-specific characteristics or process adaptations. We address this by combining o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.04948","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/2607.04948/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":"2607.04948","created_at":"2026-07-07T02:20:14.931803+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.04948v1","created_at":"2026-07-07T02:20:14.931803+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.04948","created_at":"2026-07-07T02:20:14.931803+00:00"},{"alias_kind":"pith_short_12","alias_value":"SR32OD5JDXOG","created_at":"2026-07-07T02:20:14.931803+00:00"},{"alias_kind":"pith_short_16","alias_value":"SR32OD5JDXOG3TPZ","created_at":"2026-07-07T02:20:14.931803+00:00"},{"alias_kind":"pith_short_8","alias_value":"SR32OD5J","created_at":"2026-07-07T02:20:14.931803+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/SR32OD5JDXOG3TPZNUFVZTYVQC","json":"https://pith.science/pith/SR32OD5JDXOG3TPZNUFVZTYVQC.json","graph_json":"https://pith.science/api/pith-number/SR32OD5JDXOG3TPZNUFVZTYVQC/graph.json","events_json":"https://pith.science/api/pith-number/SR32OD5JDXOG3TPZNUFVZTYVQC/events.json","paper":"https://pith.science/paper/SR32OD5J"},"agent_actions":{"view_html":"https://pith.science/pith/SR32OD5JDXOG3TPZNUFVZTYVQC","download_json":"https://pith.science/pith/SR32OD5JDXOG3TPZNUFVZTYVQC.json","view_paper":"https://pith.science/paper/SR32OD5J","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.04948&json=true","fetch_graph":"https://pith.science/api/pith-number/SR32OD5JDXOG3TPZNUFVZTYVQC/graph.json","fetch_events":"https://pith.science/api/pith-number/SR32OD5JDXOG3TPZNUFVZTYVQC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SR32OD5JDXOG3TPZNUFVZTYVQC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SR32OD5JDXOG3TPZNUFVZTYVQC/action/storage_attestation","attest_author":"https://pith.science/pith/SR32OD5JDXOG3TPZNUFVZTYVQC/action/author_attestation","sign_citation":"https://pith.science/pith/SR32OD5JDXOG3TPZNUFVZTYVQC/action/citation_signature","submit_replication":"https://pith.science/pith/SR32OD5JDXOG3TPZNUFVZTYVQC/action/replication_record"}},"created_at":"2026-07-07T02:20:14.931803+00:00","updated_at":"2026-07-07T02:20:14.931803+00:00"}