{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:PTHKMKNXENYGTO6CYW3LXBUTJM","short_pith_number":"pith:PTHKMKNX","schema_version":"1.0","canonical_sha256":"7ccea629b7237069bbc2c5b6bb86934b298d3e9a067db877c713c242272a305b","source":{"kind":"arxiv","id":"2504.10498","version":3},"attestation_state":"computed","paper":{"title":"CCSK:Cognitive Convection of Self-Knowledge Based Retrieval Augmentation for Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.IR","authors_text":"Jianling Lu, Mingqi Lv, Tieming Chen","submitted_at":"2025-04-07T13:43:53Z","abstract_excerpt":"The performance of large language models (LLMs) in Q&A task increased substantially through Retrieval-Augmented Generation (RAG) which brings in external knowledge. However, the main difficulty lies in balancing the inherent self-knowledge of LLMs with external information retrieval (IR). The current threshold-based methods apply one-dimensional static mechanisms with single criterion. As a result, their IR decisions might be irrelevant to the LLMs' response under difficult queries. To alleviate this problem, we propose Cognitive Convection of Self-Knowledge (CCSK). Different from traditional "},"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":"2504.10498","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2025-04-07T13:43:53Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"dac50a6a3105cd5ea4250ba1125e6dcfe77f2e81600f6a9ceb937703ce50a9ee","abstract_canon_sha256":"fa60c8b4a0f611c38f4ae6da6ba6e490b5d13dd854fb6f10e27503b041b7ab2a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:59:09.376858Z","signature_b64":"otcRFkIB2gfBxqR6SGfzB89CugBPwOyoRPzAFB862VYnOIkKrAD5Uc88adN0HSRoZqeP77BYOfOjyWx6Lhw0DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7ccea629b7237069bbc2c5b6bb86934b298d3e9a067db877c713c242272a305b","last_reissued_at":"2026-07-05T10:59:09.376353Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:59:09.376353Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CCSK:Cognitive Convection of Self-Knowledge Based Retrieval Augmentation for Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.IR","authors_text":"Jianling Lu, Mingqi Lv, Tieming Chen","submitted_at":"2025-04-07T13:43:53Z","abstract_excerpt":"The performance of large language models (LLMs) in Q&A task increased substantially through Retrieval-Augmented Generation (RAG) which brings in external knowledge. However, the main difficulty lies in balancing the inherent self-knowledge of LLMs with external information retrieval (IR). The current threshold-based methods apply one-dimensional static mechanisms with single criterion. As a result, their IR decisions might be irrelevant to the LLMs' response under difficult queries. To alleviate this problem, we propose Cognitive Convection of Self-Knowledge (CCSK). Different from traditional "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.10498","kind":"arxiv","version":3},"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/2504.10498/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":"2504.10498","created_at":"2026-07-05T10:59:09.376414+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.10498v3","created_at":"2026-07-05T10:59:09.376414+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.10498","created_at":"2026-07-05T10:59:09.376414+00:00"},{"alias_kind":"pith_short_12","alias_value":"PTHKMKNXENYG","created_at":"2026-07-05T10:59:09.376414+00:00"},{"alias_kind":"pith_short_16","alias_value":"PTHKMKNXENYGTO6C","created_at":"2026-07-05T10:59:09.376414+00:00"},{"alias_kind":"pith_short_8","alias_value":"PTHKMKNX","created_at":"2026-07-05T10:59:09.376414+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/PTHKMKNXENYGTO6CYW3LXBUTJM","json":"https://pith.science/pith/PTHKMKNXENYGTO6CYW3LXBUTJM.json","graph_json":"https://pith.science/api/pith-number/PTHKMKNXENYGTO6CYW3LXBUTJM/graph.json","events_json":"https://pith.science/api/pith-number/PTHKMKNXENYGTO6CYW3LXBUTJM/events.json","paper":"https://pith.science/paper/PTHKMKNX"},"agent_actions":{"view_html":"https://pith.science/pith/PTHKMKNXENYGTO6CYW3LXBUTJM","download_json":"https://pith.science/pith/PTHKMKNXENYGTO6CYW3LXBUTJM.json","view_paper":"https://pith.science/paper/PTHKMKNX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.10498&json=true","fetch_graph":"https://pith.science/api/pith-number/PTHKMKNXENYGTO6CYW3LXBUTJM/graph.json","fetch_events":"https://pith.science/api/pith-number/PTHKMKNXENYGTO6CYW3LXBUTJM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PTHKMKNXENYGTO6CYW3LXBUTJM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PTHKMKNXENYGTO6CYW3LXBUTJM/action/storage_attestation","attest_author":"https://pith.science/pith/PTHKMKNXENYGTO6CYW3LXBUTJM/action/author_attestation","sign_citation":"https://pith.science/pith/PTHKMKNXENYGTO6CYW3LXBUTJM/action/citation_signature","submit_replication":"https://pith.science/pith/PTHKMKNXENYGTO6CYW3LXBUTJM/action/replication_record"}},"created_at":"2026-07-05T10:59:09.376414+00:00","updated_at":"2026-07-05T10:59:09.376414+00:00"}