{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:HI4LFBUAGR75RYNKY64IVOHLA3","short_pith_number":"pith:HI4LFBUA","schema_version":"1.0","canonical_sha256":"3a38b28680347fd8e1aac7b88ab8eb06ca496ce93e98960f01010280abb5e912","source":{"kind":"arxiv","id":"2407.05682","version":2},"attestation_state":"computed","paper":{"title":"Retrieved In-Context Principles from Previous Mistakes","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bo Wang, Fei Huang, Hao Sun, Pengjun Xie, Yan Zhang, Yingyan Hou, Yong Jiang","submitted_at":"2024-07-08T07:32:26Z","abstract_excerpt":"In-context learning (ICL) has been instrumental in adapting Large Language Models (LLMs) to downstream tasks using correct input-output examples. Recent advances have attempted to improve model performance through principles derived from mistakes, yet these approaches suffer from lack of customization and inadequate error coverage. To address these limitations, we propose Retrieved In-Context Principles (RICP), a novel teacher-student framework. In RICP, the teacher model analyzes mistakes from the student model to generate reasons and insights for preventing similar mistakes. These mistakes a"},"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":"2407.05682","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-08T07:32:26Z","cross_cats_sorted":[],"title_canon_sha256":"554e9c2931bad3057ef912ba24c3bfb287eccd22a4c7ca6d9da8571783c929a9","abstract_canon_sha256":"5b27d3b2ef53ec3af13a1b81fb2b0432171a6f5edbd81904c9ef43755bf56f0e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T01:03:08.862292Z","signature_b64":"SSBl9rSWPxsE6l98gnA6x2S+4KGEYwDtmPkSvnCerFX0NrOhkuc8L6MfftTTXJVV/hWDZIiVnppmQ/9xOjbcDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3a38b28680347fd8e1aac7b88ab8eb06ca496ce93e98960f01010280abb5e912","last_reissued_at":"2026-05-26T01:03:08.861417Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T01:03:08.861417Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Retrieved In-Context Principles from Previous Mistakes","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bo Wang, Fei Huang, Hao Sun, Pengjun Xie, Yan Zhang, Yingyan Hou, Yong Jiang","submitted_at":"2024-07-08T07:32:26Z","abstract_excerpt":"In-context learning (ICL) has been instrumental in adapting Large Language Models (LLMs) to downstream tasks using correct input-output examples. Recent advances have attempted to improve model performance through principles derived from mistakes, yet these approaches suffer from lack of customization and inadequate error coverage. To address these limitations, we propose Retrieved In-Context Principles (RICP), a novel teacher-student framework. In RICP, the teacher model analyzes mistakes from the student model to generate reasons and insights for preventing similar mistakes. These mistakes a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.05682","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/2407.05682/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":"2407.05682","created_at":"2026-05-26T01:03:08.861545+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.05682v2","created_at":"2026-05-26T01:03:08.861545+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.05682","created_at":"2026-05-26T01:03:08.861545+00:00"},{"alias_kind":"pith_short_12","alias_value":"HI4LFBUAGR75","created_at":"2026-05-26T01:03:08.861545+00:00"},{"alias_kind":"pith_short_16","alias_value":"HI4LFBUAGR75RYNK","created_at":"2026-05-26T01:03:08.861545+00:00"},{"alias_kind":"pith_short_8","alias_value":"HI4LFBUA","created_at":"2026-05-26T01:03:08.861545+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2410.13181","citing_title":"AdaSwitch: Adaptive Switching between Small and Large Agents for Effective Cloud-Local Collaborative Learning","ref_index":22,"is_internal_anchor":true},{"citing_arxiv_id":"2604.03245","citing_title":"FVRuleLearner: Operator-Level Reasoning Tree (OP-Tree)-Based Rules Learning for Formal Verification","ref_index":54,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HI4LFBUAGR75RYNKY64IVOHLA3","json":"https://pith.science/pith/HI4LFBUAGR75RYNKY64IVOHLA3.json","graph_json":"https://pith.science/api/pith-number/HI4LFBUAGR75RYNKY64IVOHLA3/graph.json","events_json":"https://pith.science/api/pith-number/HI4LFBUAGR75RYNKY64IVOHLA3/events.json","paper":"https://pith.science/paper/HI4LFBUA"},"agent_actions":{"view_html":"https://pith.science/pith/HI4LFBUAGR75RYNKY64IVOHLA3","download_json":"https://pith.science/pith/HI4LFBUAGR75RYNKY64IVOHLA3.json","view_paper":"https://pith.science/paper/HI4LFBUA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.05682&json=true","fetch_graph":"https://pith.science/api/pith-number/HI4LFBUAGR75RYNKY64IVOHLA3/graph.json","fetch_events":"https://pith.science/api/pith-number/HI4LFBUAGR75RYNKY64IVOHLA3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HI4LFBUAGR75RYNKY64IVOHLA3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HI4LFBUAGR75RYNKY64IVOHLA3/action/storage_attestation","attest_author":"https://pith.science/pith/HI4LFBUAGR75RYNKY64IVOHLA3/action/author_attestation","sign_citation":"https://pith.science/pith/HI4LFBUAGR75RYNKY64IVOHLA3/action/citation_signature","submit_replication":"https://pith.science/pith/HI4LFBUAGR75RYNKY64IVOHLA3/action/replication_record"}},"created_at":"2026-05-26T01:03:08.861545+00:00","updated_at":"2026-05-26T01:03:08.861545+00:00"}