{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:SIKL3NO57F4Q2R5NJS5E5CVGB7","short_pith_number":"pith:SIKL3NO5","schema_version":"1.0","canonical_sha256":"9214bdb5ddf9790d47ad4cba4e8aa60fe38dd553fa2971bc685becf992a1fce1","source":{"kind":"arxiv","id":"2306.09299","version":2},"attestation_state":"computed","paper":{"title":"Can Language Models Teach Weaker Agents? Teacher Explanations Improve Students via Personalization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Mohit Bansal, Peter Hase, Swarnadeep Saha","submitted_at":"2023-06-15T17:27:20Z","abstract_excerpt":"A hallmark property of explainable AI models is the ability to teach other agents, communicating knowledge of how to perform a task. While Large Language Models perform complex reasoning by generating explanations for their predictions, it is unclear whether they also make good teachers for weaker agents. To address this, we consider a student-teacher framework between two LLM agents and study if, when, and how the teacher should intervene with natural language explanations to improve the student's performance. Since communication is expensive, we define a budget such that the teacher only com"},"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":"2306.09299","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-06-15T17:27:20Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"e05b0d48197f7b30116903fb8d54eef4e5b83d494be8097ac84a1d63530a78f1","abstract_canon_sha256":"99dfd1529171cb776e9e2d9e840ba9a65132e02e5b5daaea68c0ab3e2f7d1998"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:12:17.168749Z","signature_b64":"zuSNx7LwgPAXOC8yzrrrEoEj+GJ2h58arFbra7up5WA1ri98t4EQlITLaFYQ/jfmEs+231nTMLY/x1F2xWezAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9214bdb5ddf9790d47ad4cba4e8aa60fe38dd553fa2971bc685becf992a1fce1","last_reissued_at":"2026-07-05T07:12:17.168264Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:12:17.168264Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Can Language Models Teach Weaker Agents? Teacher Explanations Improve Students via Personalization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Mohit Bansal, Peter Hase, Swarnadeep Saha","submitted_at":"2023-06-15T17:27:20Z","abstract_excerpt":"A hallmark property of explainable AI models is the ability to teach other agents, communicating knowledge of how to perform a task. While Large Language Models perform complex reasoning by generating explanations for their predictions, it is unclear whether they also make good teachers for weaker agents. To address this, we consider a student-teacher framework between two LLM agents and study if, when, and how the teacher should intervene with natural language explanations to improve the student's performance. Since communication is expensive, we define a budget such that the teacher only com"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.09299","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/2306.09299/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":"2306.09299","created_at":"2026-07-05T07:12:17.168321+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.09299v2","created_at":"2026-07-05T07:12:17.168321+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.09299","created_at":"2026-07-05T07:12:17.168321+00:00"},{"alias_kind":"pith_short_12","alias_value":"SIKL3NO57F4Q","created_at":"2026-07-05T07:12:17.168321+00:00"},{"alias_kind":"pith_short_16","alias_value":"SIKL3NO57F4Q2R5N","created_at":"2026-07-05T07:12:17.168321+00:00"},{"alias_kind":"pith_short_8","alias_value":"SIKL3NO5","created_at":"2026-07-05T07:12:17.168321+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2310.00754","citing_title":"Analyzing and Mitigating Object Hallucination in Large Vision-Language Models","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2308.11432","citing_title":"A Survey on Large Language Model based Autonomous Agents","ref_index":99,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SIKL3NO57F4Q2R5NJS5E5CVGB7","json":"https://pith.science/pith/SIKL3NO57F4Q2R5NJS5E5CVGB7.json","graph_json":"https://pith.science/api/pith-number/SIKL3NO57F4Q2R5NJS5E5CVGB7/graph.json","events_json":"https://pith.science/api/pith-number/SIKL3NO57F4Q2R5NJS5E5CVGB7/events.json","paper":"https://pith.science/paper/SIKL3NO5"},"agent_actions":{"view_html":"https://pith.science/pith/SIKL3NO57F4Q2R5NJS5E5CVGB7","download_json":"https://pith.science/pith/SIKL3NO57F4Q2R5NJS5E5CVGB7.json","view_paper":"https://pith.science/paper/SIKL3NO5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.09299&json=true","fetch_graph":"https://pith.science/api/pith-number/SIKL3NO57F4Q2R5NJS5E5CVGB7/graph.json","fetch_events":"https://pith.science/api/pith-number/SIKL3NO57F4Q2R5NJS5E5CVGB7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SIKL3NO57F4Q2R5NJS5E5CVGB7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SIKL3NO57F4Q2R5NJS5E5CVGB7/action/storage_attestation","attest_author":"https://pith.science/pith/SIKL3NO57F4Q2R5NJS5E5CVGB7/action/author_attestation","sign_citation":"https://pith.science/pith/SIKL3NO57F4Q2R5NJS5E5CVGB7/action/citation_signature","submit_replication":"https://pith.science/pith/SIKL3NO57F4Q2R5NJS5E5CVGB7/action/replication_record"}},"created_at":"2026-07-05T07:12:17.168321+00:00","updated_at":"2026-07-05T07:12:17.168321+00:00"}