{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:T5XM3O4S2C4GFBXJRHP62DEFPN","short_pith_number":"pith:T5XM3O4S","schema_version":"1.0","canonical_sha256":"9f6ecdbb92d0b86286e989dfed0c857b533fd030f0d46b0ce0c9d43553a2d519","source":{"kind":"arxiv","id":"2505.16849","version":2},"attestation_state":"computed","paper":{"title":"Walk&Retrieve: Simple Yet Effective Zero-shot Retrieval-Augmented Generation via Knowledge Graph Walks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.IR","authors_text":"Andreea Iana, Heiko Paulheim, Martin B\\\"ockling","submitted_at":"2025-05-22T16:11:35Z","abstract_excerpt":"Large Language Models (LLMs) have showcased impressive reasoning abilities, but often suffer from hallucinations or outdated knowledge. Knowledge Graph (KG)-based Retrieval-Augmented Generation (RAG) remedies these shortcomings by grounding LLM responses in structured external information from a knowledge base. However, many KG-based RAG approaches struggle with (i) aligning KG and textual representations, (ii) balancing retrieval accuracy and efficiency, and (iii) adapting to dynamically updated KGs. In this work, we introduce Walk&Retrieve, a simple yet effective KG-based framework that leve"},"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":"2505.16849","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-05-22T16:11:35Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"bfa2f9c05139cc227f782830b00857bc2085201f752271adb7ae69fce4656f3c","abstract_canon_sha256":"30ffac7fb56180259cce3af033e62d61e1258f0ff6b6ac0535747afb0fc1d889"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:10:57.468352Z","signature_b64":"sDZgGmkox49LJ25msxD5aRhR9ZH8Ruzb51gli1Tfl0qn8rwPaZ9hNKfDABD6UKhFV1GkdrOwJMyXE57Mz80ZCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9f6ecdbb92d0b86286e989dfed0c857b533fd030f0d46b0ce0c9d43553a2d519","last_reissued_at":"2026-07-05T11:10:57.467831Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:10:57.467831Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Walk&Retrieve: Simple Yet Effective Zero-shot Retrieval-Augmented Generation via Knowledge Graph Walks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.IR","authors_text":"Andreea Iana, Heiko Paulheim, Martin B\\\"ockling","submitted_at":"2025-05-22T16:11:35Z","abstract_excerpt":"Large Language Models (LLMs) have showcased impressive reasoning abilities, but often suffer from hallucinations or outdated knowledge. Knowledge Graph (KG)-based Retrieval-Augmented Generation (RAG) remedies these shortcomings by grounding LLM responses in structured external information from a knowledge base. However, many KG-based RAG approaches struggle with (i) aligning KG and textual representations, (ii) balancing retrieval accuracy and efficiency, and (iii) adapting to dynamically updated KGs. In this work, we introduce Walk&Retrieve, a simple yet effective KG-based framework that leve"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.16849","kind":"arxiv","version":2},"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/2505.16849/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":"2505.16849","created_at":"2026-07-05T11:10:57.467893+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.16849v2","created_at":"2026-07-05T11:10:57.467893+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.16849","created_at":"2026-07-05T11:10:57.467893+00:00"},{"alias_kind":"pith_short_12","alias_value":"T5XM3O4S2C4G","created_at":"2026-07-05T11:10:57.467893+00:00"},{"alias_kind":"pith_short_16","alias_value":"T5XM3O4S2C4GFBXJ","created_at":"2026-07-05T11:10:57.467893+00:00"},{"alias_kind":"pith_short_8","alias_value":"T5XM3O4S","created_at":"2026-07-05T11:10:57.467893+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06641","citing_title":"Healthier LLMs: Retrieval-Augmented Generation for Public Health Question Answering","ref_index":27,"is_internal_anchor":true},{"citing_arxiv_id":"2605.01484","citing_title":"Evaluating LLMs on Large-Scale Graph Property Estimation via Random Walks","ref_index":32,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/T5XM3O4S2C4GFBXJRHP62DEFPN","json":"https://pith.science/pith/T5XM3O4S2C4GFBXJRHP62DEFPN.json","graph_json":"https://pith.science/api/pith-number/T5XM3O4S2C4GFBXJRHP62DEFPN/graph.json","events_json":"https://pith.science/api/pith-number/T5XM3O4S2C4GFBXJRHP62DEFPN/events.json","paper":"https://pith.science/paper/T5XM3O4S"},"agent_actions":{"view_html":"https://pith.science/pith/T5XM3O4S2C4GFBXJRHP62DEFPN","download_json":"https://pith.science/pith/T5XM3O4S2C4GFBXJRHP62DEFPN.json","view_paper":"https://pith.science/paper/T5XM3O4S","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.16849&json=true","fetch_graph":"https://pith.science/api/pith-number/T5XM3O4S2C4GFBXJRHP62DEFPN/graph.json","fetch_events":"https://pith.science/api/pith-number/T5XM3O4S2C4GFBXJRHP62DEFPN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/T5XM3O4S2C4GFBXJRHP62DEFPN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/T5XM3O4S2C4GFBXJRHP62DEFPN/action/storage_attestation","attest_author":"https://pith.science/pith/T5XM3O4S2C4GFBXJRHP62DEFPN/action/author_attestation","sign_citation":"https://pith.science/pith/T5XM3O4S2C4GFBXJRHP62DEFPN/action/citation_signature","submit_replication":"https://pith.science/pith/T5XM3O4S2C4GFBXJRHP62DEFPN/action/replication_record"}},"created_at":"2026-07-05T11:10:57.467893+00:00","updated_at":"2026-07-05T11:10:57.467893+00:00"}