{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:V7ZPVZPIDFPVHQVAF4PCYLW4HP","short_pith_number":"pith:V7ZPVZPI","schema_version":"1.0","canonical_sha256":"aff2fae5e8195f53c2a02f1e2c2edc3bd19e79ec6c7007077f3c94b8f1752ced","source":{"kind":"arxiv","id":"2501.11551","version":4},"attestation_state":"computed","paper":{"title":"PIKE-RAG: sPecIalized KnowledgE and Rationale Augmented Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jiang Bian, Jingjing Fu, Jinyu Wang, Lei Song, Rui Wang","submitted_at":"2025-01-20T15:39:39Z","abstract_excerpt":"Despite notable advancements in Retrieval-Augmented Generation (RAG) systems that expand large language model (LLM) capabilities through external retrieval, these systems often struggle to meet the complex and diverse needs of real-world industrial applications. The reliance on retrieval alone proves insufficient for extracting deep, domain-specific knowledge performing in logical reasoning from specialized corpora. To address this, we introduce sPecIalized KnowledgE and Rationale Augmentation Generation (PIKE-RAG), focusing on extracting, understanding, and applying specialized knowledge, whi"},"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":"2501.11551","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-01-20T15:39:39Z","cross_cats_sorted":[],"title_canon_sha256":"53886c01d4d5bcf4c7c40f6be23f96c5a2521274c922182776edfe472868dae8","abstract_canon_sha256":"35af17daeeceaac906bd1305eaa38f57018bf24eff6fdcae483508f37155cf04"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:29:32.978893Z","signature_b64":"dBIPQ2q1YKa0KAvEmc4ZL8aAzv3KzTxIyCPuLaL8QgQBmBbD+KCPXoe40T1GtnPf2VWgNYT0i6TApYQbxS8LDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aff2fae5e8195f53c2a02f1e2c2edc3bd19e79ec6c7007077f3c94b8f1752ced","last_reissued_at":"2026-07-05T10:29:32.977756Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:29:32.977756Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PIKE-RAG: sPecIalized KnowledgE and Rationale Augmented Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jiang Bian, Jingjing Fu, Jinyu Wang, Lei Song, Rui Wang","submitted_at":"2025-01-20T15:39:39Z","abstract_excerpt":"Despite notable advancements in Retrieval-Augmented Generation (RAG) systems that expand large language model (LLM) capabilities through external retrieval, these systems often struggle to meet the complex and diverse needs of real-world industrial applications. The reliance on retrieval alone proves insufficient for extracting deep, domain-specific knowledge performing in logical reasoning from specialized corpora. To address this, we introduce sPecIalized KnowledgE and Rationale Augmentation Generation (PIKE-RAG), focusing on extracting, understanding, and applying specialized knowledge, whi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.11551","kind":"arxiv","version":4},"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/2501.11551/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":"2501.11551","created_at":"2026-07-05T10:29:32.977903+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.11551v4","created_at":"2026-07-05T10:29:32.977903+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.11551","created_at":"2026-07-05T10:29:32.977903+00:00"},{"alias_kind":"pith_short_12","alias_value":"V7ZPVZPIDFPV","created_at":"2026-07-05T10:29:32.977903+00:00"},{"alias_kind":"pith_short_16","alias_value":"V7ZPVZPIDFPVHQVA","created_at":"2026-07-05T10:29:32.977903+00:00"},{"alias_kind":"pith_short_8","alias_value":"V7ZPVZPI","created_at":"2026-07-05T10:29:32.977903+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.13669","citing_title":"Agents-K1: Towards Agent-native Knowledge Orchestration","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2606.13669","citing_title":"Agents-K1: Towards Agent-native Knowledge Orchestration","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2605.29742","citing_title":"Citation-Closure Retrieval and Per-Rule Attribution for Real-World Regulatory Compliance Question Answering","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2502.09891","citing_title":"ArchRAG: Attributed Community-based Hierarchical Retrieval-Augmented Generation","ref_index":57,"is_internal_anchor":false},{"citing_arxiv_id":"2601.19827","citing_title":"When Iterative RAG Beats Ideal Evidence: A Diagnostic Study in Scientific Multi-hop Question Answering","ref_index":27,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/V7ZPVZPIDFPVHQVAF4PCYLW4HP","json":"https://pith.science/pith/V7ZPVZPIDFPVHQVAF4PCYLW4HP.json","graph_json":"https://pith.science/api/pith-number/V7ZPVZPIDFPVHQVAF4PCYLW4HP/graph.json","events_json":"https://pith.science/api/pith-number/V7ZPVZPIDFPVHQVAF4PCYLW4HP/events.json","paper":"https://pith.science/paper/V7ZPVZPI"},"agent_actions":{"view_html":"https://pith.science/pith/V7ZPVZPIDFPVHQVAF4PCYLW4HP","download_json":"https://pith.science/pith/V7ZPVZPIDFPVHQVAF4PCYLW4HP.json","view_paper":"https://pith.science/paper/V7ZPVZPI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.11551&json=true","fetch_graph":"https://pith.science/api/pith-number/V7ZPVZPIDFPVHQVAF4PCYLW4HP/graph.json","fetch_events":"https://pith.science/api/pith-number/V7ZPVZPIDFPVHQVAF4PCYLW4HP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/V7ZPVZPIDFPVHQVAF4PCYLW4HP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/V7ZPVZPIDFPVHQVAF4PCYLW4HP/action/storage_attestation","attest_author":"https://pith.science/pith/V7ZPVZPIDFPVHQVAF4PCYLW4HP/action/author_attestation","sign_citation":"https://pith.science/pith/V7ZPVZPIDFPVHQVAF4PCYLW4HP/action/citation_signature","submit_replication":"https://pith.science/pith/V7ZPVZPIDFPVHQVAF4PCYLW4HP/action/replication_record"}},"created_at":"2026-07-05T10:29:32.977903+00:00","updated_at":"2026-07-05T10:29:32.977903+00:00"}