{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:3XXAFU7O5V4YYIDGLUYXAPYH5G","short_pith_number":"pith:3XXAFU7O","schema_version":"1.0","canonical_sha256":"ddee02d3eeed798c20665d31703f07e9b48cc8325cf92279231c23693d1a542f","source":{"kind":"arxiv","id":"2408.11431","version":1},"attestation_state":"computed","paper":{"title":"Diagnosing and Remedying Knowledge Deficiencies in LLMs via Label-free Curricular Meaningful Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Bing Qin, Jiahao Ying, Kai Xiong, Li Du, Ting Liu, Xiao Ding, Yixin Cao","submitted_at":"2024-08-21T08:39:49Z","abstract_excerpt":"Large Language Models (LLMs) are versatile and demonstrate impressive generalization ability by mining and learning information from extensive unlabeled text. However, they still exhibit reasoning mistakes, often stemming from knowledge deficiencies, which can affect their trustworthiness and reliability. Although users can provide diverse and comprehensive queries, obtaining sufficient and effective feedback is demanding. Furthermore, evaluating LLMs comprehensively with limited labeled samples is difficult. This makes it a challenge to diagnose and remedy the deficiencies of LLMs through ric"},"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":"2408.11431","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-21T08:39:49Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"01747aa3d433156361dbb897588ccdcfe13489c40f30f51a0d335e2daf747d95","abstract_canon_sha256":"50be03f3049e102f647e044cc0d6728a545fb5c8415773f54ae179dc654566c5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:57:44.072416Z","signature_b64":"L+NZGRw99zsvXiqneztY6F9NW8sNDeOHXI4q8uV06cEczU/z22ti1E9kOGkyYt4vw8omKqhKiUcYmvTMh/dRDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ddee02d3eeed798c20665d31703f07e9b48cc8325cf92279231c23693d1a542f","last_reissued_at":"2026-07-05T08:57:44.071946Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:57:44.071946Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Diagnosing and Remedying Knowledge Deficiencies in LLMs via Label-free Curricular Meaningful Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Bing Qin, Jiahao Ying, Kai Xiong, Li Du, Ting Liu, Xiao Ding, Yixin Cao","submitted_at":"2024-08-21T08:39:49Z","abstract_excerpt":"Large Language Models (LLMs) are versatile and demonstrate impressive generalization ability by mining and learning information from extensive unlabeled text. However, they still exhibit reasoning mistakes, often stemming from knowledge deficiencies, which can affect their trustworthiness and reliability. Although users can provide diverse and comprehensive queries, obtaining sufficient and effective feedback is demanding. Furthermore, evaluating LLMs comprehensively with limited labeled samples is difficult. This makes it a challenge to diagnose and remedy the deficiencies of LLMs through ric"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.11431","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/2408.11431/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":"2408.11431","created_at":"2026-07-05T08:57:44.072001+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.11431v1","created_at":"2026-07-05T08:57:44.072001+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.11431","created_at":"2026-07-05T08:57:44.072001+00:00"},{"alias_kind":"pith_short_12","alias_value":"3XXAFU7O5V4Y","created_at":"2026-07-05T08:57:44.072001+00:00"},{"alias_kind":"pith_short_16","alias_value":"3XXAFU7O5V4YYIDG","created_at":"2026-07-05T08:57:44.072001+00:00"},{"alias_kind":"pith_short_8","alias_value":"3XXAFU7O","created_at":"2026-07-05T08:57:44.072001+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.07184","citing_title":"Structural Entropy Guided Agent for Detecting and Repairing Knowledge Deficiencies in LLMs","ref_index":47,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3XXAFU7O5V4YYIDGLUYXAPYH5G","json":"https://pith.science/pith/3XXAFU7O5V4YYIDGLUYXAPYH5G.json","graph_json":"https://pith.science/api/pith-number/3XXAFU7O5V4YYIDGLUYXAPYH5G/graph.json","events_json":"https://pith.science/api/pith-number/3XXAFU7O5V4YYIDGLUYXAPYH5G/events.json","paper":"https://pith.science/paper/3XXAFU7O"},"agent_actions":{"view_html":"https://pith.science/pith/3XXAFU7O5V4YYIDGLUYXAPYH5G","download_json":"https://pith.science/pith/3XXAFU7O5V4YYIDGLUYXAPYH5G.json","view_paper":"https://pith.science/paper/3XXAFU7O","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.11431&json=true","fetch_graph":"https://pith.science/api/pith-number/3XXAFU7O5V4YYIDGLUYXAPYH5G/graph.json","fetch_events":"https://pith.science/api/pith-number/3XXAFU7O5V4YYIDGLUYXAPYH5G/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3XXAFU7O5V4YYIDGLUYXAPYH5G/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3XXAFU7O5V4YYIDGLUYXAPYH5G/action/storage_attestation","attest_author":"https://pith.science/pith/3XXAFU7O5V4YYIDGLUYXAPYH5G/action/author_attestation","sign_citation":"https://pith.science/pith/3XXAFU7O5V4YYIDGLUYXAPYH5G/action/citation_signature","submit_replication":"https://pith.science/pith/3XXAFU7O5V4YYIDGLUYXAPYH5G/action/replication_record"}},"created_at":"2026-07-05T08:57:44.072001+00:00","updated_at":"2026-07-05T08:57:44.072001+00:00"}