{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:FE55MM4RSLDNRKM6V6I3J6DOVR","short_pith_number":"pith:FE55MM4R","schema_version":"1.0","canonical_sha256":"293bd6339192c6d8a99eaf91b4f86eac51b160377ee5e049ec72ae53a8eedf38","source":{"kind":"arxiv","id":"2602.12996","version":2},"attestation_state":"computed","paper":{"title":"Know More, Know Clearer: A Meta-Cognitive Framework for Knowledge Augmentation in Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Hao Chen, Maosong Sun, Qingfu Zhu, Wanxiang Che, Ye He, Yuchun Fan, Yukun Yan, Zhenghao Liu","submitted_at":"2026-02-13T15:07:35Z","abstract_excerpt":"Knowledge augmentation has significantly enhanced the performance of Large Language Models (LLMs) in knowledge-intensive tasks. However, existing methods typically operate on the simplistic premise that model performance equates with internal knowledge, overlooking the knowledge-confidence gaps that lead to overconfident errors or uncertain truths. To bridge this gap, we propose a novel meta-cognitive framework for reliable knowledge augmentation via differentiated intervention and alignment. Our approach leverages internal cognitive signals to partition the knowledge space into mastered, conf"},"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":"2602.12996","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-02-13T15:07:35Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b359083f3bd5921308a911f702ddfa6f02fb2b0d62ef815fe2d1660c11576b5c","abstract_canon_sha256":"113e9a15a8877122fdc95b9951015e42001e7dc3528f101010456a5ea84a353c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-09T01:05:14.343604Z","signature_b64":"7egyPx6qDfsl8KOktAn9fnoXQZCnVbX33gN4Fr928X/40DQSVqJNw9O3SdYTvMy01fRU+s0dL+Daa/in0VMCDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"293bd6339192c6d8a99eaf91b4f86eac51b160377ee5e049ec72ae53a8eedf38","last_reissued_at":"2026-06-09T01:05:14.343068Z","signature_status":"signed_v1","first_computed_at":"2026-06-09T01:05:14.343068Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Know More, Know Clearer: A Meta-Cognitive Framework for Knowledge Augmentation in Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Hao Chen, Maosong Sun, Qingfu Zhu, Wanxiang Che, Ye He, Yuchun Fan, Yukun Yan, Zhenghao Liu","submitted_at":"2026-02-13T15:07:35Z","abstract_excerpt":"Knowledge augmentation has significantly enhanced the performance of Large Language Models (LLMs) in knowledge-intensive tasks. However, existing methods typically operate on the simplistic premise that model performance equates with internal knowledge, overlooking the knowledge-confidence gaps that lead to overconfident errors or uncertain truths. To bridge this gap, we propose a novel meta-cognitive framework for reliable knowledge augmentation via differentiated intervention and alignment. Our approach leverages internal cognitive signals to partition the knowledge space into mastered, conf"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.12996","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/2602.12996/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":"2602.12996","created_at":"2026-06-09T01:05:14.343130+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.12996v2","created_at":"2026-06-09T01:05:14.343130+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.12996","created_at":"2026-06-09T01:05:14.343130+00:00"},{"alias_kind":"pith_short_12","alias_value":"FE55MM4RSLDN","created_at":"2026-06-09T01:05:14.343130+00:00"},{"alias_kind":"pith_short_16","alias_value":"FE55MM4RSLDNRKM6","created_at":"2026-06-09T01:05:14.343130+00:00"},{"alias_kind":"pith_short_8","alias_value":"FE55MM4R","created_at":"2026-06-09T01:05:14.343130+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.22567","citing_title":"LANG: Reinforcement Learning for Multilingual Reasoning with Language-Adaptive Hint Guidance","ref_index":80,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FE55MM4RSLDNRKM6V6I3J6DOVR","json":"https://pith.science/pith/FE55MM4RSLDNRKM6V6I3J6DOVR.json","graph_json":"https://pith.science/api/pith-number/FE55MM4RSLDNRKM6V6I3J6DOVR/graph.json","events_json":"https://pith.science/api/pith-number/FE55MM4RSLDNRKM6V6I3J6DOVR/events.json","paper":"https://pith.science/paper/FE55MM4R"},"agent_actions":{"view_html":"https://pith.science/pith/FE55MM4RSLDNRKM6V6I3J6DOVR","download_json":"https://pith.science/pith/FE55MM4RSLDNRKM6V6I3J6DOVR.json","view_paper":"https://pith.science/paper/FE55MM4R","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.12996&json=true","fetch_graph":"https://pith.science/api/pith-number/FE55MM4RSLDNRKM6V6I3J6DOVR/graph.json","fetch_events":"https://pith.science/api/pith-number/FE55MM4RSLDNRKM6V6I3J6DOVR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FE55MM4RSLDNRKM6V6I3J6DOVR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FE55MM4RSLDNRKM6V6I3J6DOVR/action/storage_attestation","attest_author":"https://pith.science/pith/FE55MM4RSLDNRKM6V6I3J6DOVR/action/author_attestation","sign_citation":"https://pith.science/pith/FE55MM4RSLDNRKM6V6I3J6DOVR/action/citation_signature","submit_replication":"https://pith.science/pith/FE55MM4RSLDNRKM6V6I3J6DOVR/action/replication_record"}},"created_at":"2026-06-09T01:05:14.343130+00:00","updated_at":"2026-06-09T01:05:14.343130+00:00"}