{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:I5UHXSDQIR3Z5OPSPMBISBFRGL","short_pith_number":"pith:I5UHXSDQ","schema_version":"1.0","canonical_sha256":"47687bc87044779eb9f27b028904b132e12d9f5f07b50848515232c2adf322e1","source":{"kind":"arxiv","id":"2505.07184","version":1},"attestation_state":"computed","paper":{"title":"Structural Entropy Guided Agent for Detecting and Repairing Knowledge Deficiencies in LLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Angsheng Li, Li Du, Tengfei Pan, Xiaoyan Yu, Yifan Wei","submitted_at":"2025-05-12T02:21:36Z","abstract_excerpt":"Large language models (LLMs) have achieved unprecedented performance by leveraging vast pretraining corpora, yet their performance remains suboptimal in knowledge-intensive domains such as medicine and scientific research, where high factual precision is required. While synthetic data provides a promising avenue for augmenting domain knowledge, existing methods frequently generate redundant samples that do not align with the model's true knowledge gaps. To overcome this limitation, we propose a novel Structural Entropy-guided Knowledge Navigator (SENATOR) framework that addresses the intrinsic"},"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":"2505.07184","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-12T02:21:36Z","cross_cats_sorted":[],"title_canon_sha256":"581991591c229cbb3a832f2a3bafa81a66fe4bdd4d238e6712c2aaaed52ae25d","abstract_canon_sha256":"3b6f2938d17994e756f7e57c3d146f8a9abb5655e070945887a6aeb76fbbbee0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:01:43.944593Z","signature_b64":"/MKDiOTdpHB/pqyIsqWfm4EmdK9eyT8syrmwtdswsCuRdr+HWJhyQe/eeybGRwBIlqExrgkdu2gOHXhusv82CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"47687bc87044779eb9f27b028904b132e12d9f5f07b50848515232c2adf322e1","last_reissued_at":"2026-07-05T11:01:43.944221Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:01:43.944221Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Structural Entropy Guided Agent for Detecting and Repairing Knowledge Deficiencies in LLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Angsheng Li, Li Du, Tengfei Pan, Xiaoyan Yu, Yifan Wei","submitted_at":"2025-05-12T02:21:36Z","abstract_excerpt":"Large language models (LLMs) have achieved unprecedented performance by leveraging vast pretraining corpora, yet their performance remains suboptimal in knowledge-intensive domains such as medicine and scientific research, where high factual precision is required. While synthetic data provides a promising avenue for augmenting domain knowledge, existing methods frequently generate redundant samples that do not align with the model's true knowledge gaps. To overcome this limitation, we propose a novel Structural Entropy-guided Knowledge Navigator (SENATOR) framework that addresses the intrinsic"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.07184","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/2505.07184/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":"2505.07184","created_at":"2026-07-05T11:01:43.944275+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.07184v1","created_at":"2026-07-05T11:01:43.944275+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.07184","created_at":"2026-07-05T11:01:43.944275+00:00"},{"alias_kind":"pith_short_12","alias_value":"I5UHXSDQIR3Z","created_at":"2026-07-05T11:01:43.944275+00:00"},{"alias_kind":"pith_short_16","alias_value":"I5UHXSDQIR3Z5OPS","created_at":"2026-07-05T11:01:43.944275+00:00"},{"alias_kind":"pith_short_8","alias_value":"I5UHXSDQ","created_at":"2026-07-05T11:01:43.944275+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.21836","citing_title":"AutoTIR: Autonomous Tools Integrated Reasoning via Reinforcement Learning","ref_index":58,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/I5UHXSDQIR3Z5OPSPMBISBFRGL","json":"https://pith.science/pith/I5UHXSDQIR3Z5OPSPMBISBFRGL.json","graph_json":"https://pith.science/api/pith-number/I5UHXSDQIR3Z5OPSPMBISBFRGL/graph.json","events_json":"https://pith.science/api/pith-number/I5UHXSDQIR3Z5OPSPMBISBFRGL/events.json","paper":"https://pith.science/paper/I5UHXSDQ"},"agent_actions":{"view_html":"https://pith.science/pith/I5UHXSDQIR3Z5OPSPMBISBFRGL","download_json":"https://pith.science/pith/I5UHXSDQIR3Z5OPSPMBISBFRGL.json","view_paper":"https://pith.science/paper/I5UHXSDQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.07184&json=true","fetch_graph":"https://pith.science/api/pith-number/I5UHXSDQIR3Z5OPSPMBISBFRGL/graph.json","fetch_events":"https://pith.science/api/pith-number/I5UHXSDQIR3Z5OPSPMBISBFRGL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/I5UHXSDQIR3Z5OPSPMBISBFRGL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/I5UHXSDQIR3Z5OPSPMBISBFRGL/action/storage_attestation","attest_author":"https://pith.science/pith/I5UHXSDQIR3Z5OPSPMBISBFRGL/action/author_attestation","sign_citation":"https://pith.science/pith/I5UHXSDQIR3Z5OPSPMBISBFRGL/action/citation_signature","submit_replication":"https://pith.science/pith/I5UHXSDQIR3Z5OPSPMBISBFRGL/action/replication_record"}},"created_at":"2026-07-05T11:01:43.944275+00:00","updated_at":"2026-07-05T11:01:43.944275+00:00"}