{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:TJBW3EG3CMVS5ZUAGO4TDQTBCO","short_pith_number":"pith:TJBW3EG3","schema_version":"1.0","canonical_sha256":"9a436d90db132b2ee68033b931c26113afc15f200db99170d95a9c1aa17888e8","source":{"kind":"arxiv","id":"2607.22571","version":1},"attestation_state":"computed","paper":{"title":"SCAIR: Schema-Conditioned Agentic Iterative Reasoning for Enterprise Knowledge Graphs","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Dongzhuoran Zhou, Evgeny Kharlamov, Fei Du, Hongkuan Zhou, Jie Tang, Prateek Chaturvedi, Steffen Staab, Yunjie He, Yuqicheng Zhu","submitted_at":"2026-06-02T16:14:23Z","abstract_excerpt":"Knowledge Graph-based Retrieval-Augmented Generation (KG-RAG) enables natural language interaction with structured enterprise knowledge, yet existing agentic approaches that perform well on public benchmarks often fail to generalize to real-world enterprise Knowledge Graphs (KGs), which are dense, schema-driven, and operationally constrained. To address these limitations, we propose SCAIR (Schema-Conditioned Agentic Iterative Reasoning), a training-free framework that integrates structured planning with controlled iterative reasoning by injecting schema-conditioned structural priors and enforc"},"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":"2607.22571","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-02T16:14:23Z","cross_cats_sorted":[],"title_canon_sha256":"79929e785f950e5ca603611bfe5589b856bffc87c3523f46dcbd7e4554d27d14","abstract_canon_sha256":"6e1b2615cf2af1b27d83dbf6bbcbb25e1799867a2436ad02994d3f5b375de065"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-28T00:21:42.901487Z","signature_b64":"Fq5CXFKcxHXhX5irapdEz7lsDk6jDfmfK07qWa31qIyQkIZF96A90HffggX5Jr47BBynQ7kuy/fO2qwxBXXwBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9a436d90db132b2ee68033b931c26113afc15f200db99170d95a9c1aa17888e8","last_reissued_at":"2026-07-28T00:21:42.900662Z","signature_status":"signed_v1","first_computed_at":"2026-07-28T00:21:42.900662Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SCAIR: Schema-Conditioned Agentic Iterative Reasoning for Enterprise Knowledge Graphs","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Dongzhuoran Zhou, Evgeny Kharlamov, Fei Du, Hongkuan Zhou, Jie Tang, Prateek Chaturvedi, Steffen Staab, Yunjie He, Yuqicheng Zhu","submitted_at":"2026-06-02T16:14:23Z","abstract_excerpt":"Knowledge Graph-based Retrieval-Augmented Generation (KG-RAG) enables natural language interaction with structured enterprise knowledge, yet existing agentic approaches that perform well on public benchmarks often fail to generalize to real-world enterprise Knowledge Graphs (KGs), which are dense, schema-driven, and operationally constrained. To address these limitations, we propose SCAIR (Schema-Conditioned Agentic Iterative Reasoning), a training-free framework that integrates structured planning with controlled iterative reasoning by injecting schema-conditioned structural priors and enforc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.22571","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/2607.22571/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":"2607.22571","created_at":"2026-07-28T00:21:42.901079+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.22571v1","created_at":"2026-07-28T00:21:42.901079+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.22571","created_at":"2026-07-28T00:21:42.901079+00:00"},{"alias_kind":"pith_short_12","alias_value":"TJBW3EG3CMVS","created_at":"2026-07-28T00:21:42.901079+00:00"},{"alias_kind":"pith_short_16","alias_value":"TJBW3EG3CMVS5ZUA","created_at":"2026-07-28T00:21:42.901079+00:00"},{"alias_kind":"pith_short_8","alias_value":"TJBW3EG3","created_at":"2026-07-28T00:21:42.901079+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/TJBW3EG3CMVS5ZUAGO4TDQTBCO","json":"https://pith.science/pith/TJBW3EG3CMVS5ZUAGO4TDQTBCO.json","graph_json":"https://pith.science/api/pith-number/TJBW3EG3CMVS5ZUAGO4TDQTBCO/graph.json","events_json":"https://pith.science/api/pith-number/TJBW3EG3CMVS5ZUAGO4TDQTBCO/events.json","paper":"https://pith.science/paper/TJBW3EG3"},"agent_actions":{"view_html":"https://pith.science/pith/TJBW3EG3CMVS5ZUAGO4TDQTBCO","download_json":"https://pith.science/pith/TJBW3EG3CMVS5ZUAGO4TDQTBCO.json","view_paper":"https://pith.science/paper/TJBW3EG3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.22571&json=true","fetch_graph":"https://pith.science/api/pith-number/TJBW3EG3CMVS5ZUAGO4TDQTBCO/graph.json","fetch_events":"https://pith.science/api/pith-number/TJBW3EG3CMVS5ZUAGO4TDQTBCO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TJBW3EG3CMVS5ZUAGO4TDQTBCO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TJBW3EG3CMVS5ZUAGO4TDQTBCO/action/storage_attestation","attest_author":"https://pith.science/pith/TJBW3EG3CMVS5ZUAGO4TDQTBCO/action/author_attestation","sign_citation":"https://pith.science/pith/TJBW3EG3CMVS5ZUAGO4TDQTBCO/action/citation_signature","submit_replication":"https://pith.science/pith/TJBW3EG3CMVS5ZUAGO4TDQTBCO/action/replication_record"}},"created_at":"2026-07-28T00:21:42.901079+00:00","updated_at":"2026-07-28T00:21:42.901079+00:00"}