{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:M5FOC2FGO6O3DVFUCUKG3DAYAR","short_pith_number":"pith:M5FOC2FG","schema_version":"1.0","canonical_sha256":"674ae168a6779db1d4b415146d8c180445c7a1c0223540c4ea0839e4fa11e448","source":{"kind":"arxiv","id":"2509.03626","version":1},"attestation_state":"computed","paper":{"title":"Explainable Knowledge Graph Retrieval-Augmented Generation (KG-RAG) with KG-SMILE","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Bhupesh Kumar Mishra, Dhavalkumar Thakker, Koorosh Aslansefat, Maneeha Rani, Rameez Raja Kureshi, Zahra Zehtabi Sabeti Moghaddam, Zeinab Dehghani","submitted_at":"2025-09-03T18:29:30Z","abstract_excerpt":"Generative AI, such as Large Language Models (LLMs), has achieved impressive progress but still produces hallucinations and unverifiable claims, limiting reliability in sensitive domains. Retrieval-Augmented Generation (RAG) improves accuracy by grounding outputs in external knowledge, especially in domains like healthcare, where precision is vital. However, RAG remains opaque and essentially a black box, heavily dependent on data quality. We developed a method-agnostic, perturbation-based framework that provides token and component-level interoperability for Graph RAG using SMILE and named it"},"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":"2509.03626","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2025-09-03T18:29:30Z","cross_cats_sorted":[],"title_canon_sha256":"44f9277c88bf2d079d4ec1b8f9896d38fec1845380efd93588cd62bf01770e16","abstract_canon_sha256":"3b1a0a0f72a0f99693af246d3c03245b1be7712db7fc4edddbae213c954c9438"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:04:43.463660Z","signature_b64":"PqzLGKHjV0ACkR5zHYmQHqaTRHabB/hMSMphBIzAsmxs3l7/BOMI0fEfgnKv1c9r9qBT8ngOOhp/fHYTlPPhAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"674ae168a6779db1d4b415146d8c180445c7a1c0223540c4ea0839e4fa11e448","last_reissued_at":"2026-07-05T12:04:43.463179Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:04:43.463179Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Explainable Knowledge Graph Retrieval-Augmented Generation (KG-RAG) with KG-SMILE","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Bhupesh Kumar Mishra, Dhavalkumar Thakker, Koorosh Aslansefat, Maneeha Rani, Rameez Raja Kureshi, Zahra Zehtabi Sabeti Moghaddam, Zeinab Dehghani","submitted_at":"2025-09-03T18:29:30Z","abstract_excerpt":"Generative AI, such as Large Language Models (LLMs), has achieved impressive progress but still produces hallucinations and unverifiable claims, limiting reliability in sensitive domains. Retrieval-Augmented Generation (RAG) improves accuracy by grounding outputs in external knowledge, especially in domains like healthcare, where precision is vital. However, RAG remains opaque and essentially a black box, heavily dependent on data quality. We developed a method-agnostic, perturbation-based framework that provides token and component-level interoperability for Graph RAG using SMILE and named it"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.03626","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/2509.03626/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":"2509.03626","created_at":"2026-07-05T12:04:43.463234+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.03626v1","created_at":"2026-07-05T12:04:43.463234+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.03626","created_at":"2026-07-05T12:04:43.463234+00:00"},{"alias_kind":"pith_short_12","alias_value":"M5FOC2FGO6O3","created_at":"2026-07-05T12:04:43.463234+00:00"},{"alias_kind":"pith_short_16","alias_value":"M5FOC2FGO6O3DVFU","created_at":"2026-07-05T12:04:43.463234+00:00"},{"alias_kind":"pith_short_8","alias_value":"M5FOC2FG","created_at":"2026-07-05T12:04:43.463234+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.03140","citing_title":"Evaluating Retrieval-Augmented Generation for Explainable Malware Analysis","ref_index":5,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/M5FOC2FGO6O3DVFUCUKG3DAYAR","json":"https://pith.science/pith/M5FOC2FGO6O3DVFUCUKG3DAYAR.json","graph_json":"https://pith.science/api/pith-number/M5FOC2FGO6O3DVFUCUKG3DAYAR/graph.json","events_json":"https://pith.science/api/pith-number/M5FOC2FGO6O3DVFUCUKG3DAYAR/events.json","paper":"https://pith.science/paper/M5FOC2FG"},"agent_actions":{"view_html":"https://pith.science/pith/M5FOC2FGO6O3DVFUCUKG3DAYAR","download_json":"https://pith.science/pith/M5FOC2FGO6O3DVFUCUKG3DAYAR.json","view_paper":"https://pith.science/paper/M5FOC2FG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.03626&json=true","fetch_graph":"https://pith.science/api/pith-number/M5FOC2FGO6O3DVFUCUKG3DAYAR/graph.json","fetch_events":"https://pith.science/api/pith-number/M5FOC2FGO6O3DVFUCUKG3DAYAR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/M5FOC2FGO6O3DVFUCUKG3DAYAR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/M5FOC2FGO6O3DVFUCUKG3DAYAR/action/storage_attestation","attest_author":"https://pith.science/pith/M5FOC2FGO6O3DVFUCUKG3DAYAR/action/author_attestation","sign_citation":"https://pith.science/pith/M5FOC2FGO6O3DVFUCUKG3DAYAR/action/citation_signature","submit_replication":"https://pith.science/pith/M5FOC2FGO6O3DVFUCUKG3DAYAR/action/replication_record"}},"created_at":"2026-07-05T12:04:43.463234+00:00","updated_at":"2026-07-05T12:04:43.463234+00:00"}