{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:NDRRMDKCSEICIRMIWKCZCKGKIH","short_pith_number":"pith:NDRRMDKC","schema_version":"1.0","canonical_sha256":"68e3160d429110244588b2859128ca41d54cc898825ada89a4d369c5e613ce59","source":{"kind":"arxiv","id":"2508.16741","version":1},"attestation_state":"computed","paper":{"title":"WST: Weak-to-Strong Knowledge Transfer via Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Haosen Ge, Lianghuan Huang, Shuo Li","submitted_at":"2025-08-22T18:33:06Z","abstract_excerpt":"Effective prompt engineering remains a challenging task for many applications. We introduce Weak-to-Strong Transfer (WST), an automatic prompt engineering framework where a small \"Teacher\" model generates instructions that enhance the performance of a much larger \"Student\" model. Unlike prior work, WST requires only a weak teacher, making it efficient and broadly applicable in settings where large models are closed-source or difficult to fine-tune. Using reinforcement learning, the Teacher Model's instructions are iteratively improved based on the Student Model's outcomes, yielding substantial"},"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":"2508.16741","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-08-22T18:33:06Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"12615163841bf650ff0dec8305710c818c58b493752e54dce9a817e7bb749dc0","abstract_canon_sha256":"6c575528cc42228f8dfa7ec8d9e18a33f6536cb78a8e2df5d0a6a7d21b800102"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:58:02.756060Z","signature_b64":"Bjh1qeszYIzPU/386m8CvJxFx6KFvUM46/aQpidZEfRdaNEnFSxueJcQzzf9YVVnHbC+UfBvPOApFNAod4xUDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"68e3160d429110244588b2859128ca41d54cc898825ada89a4d369c5e613ce59","last_reissued_at":"2026-07-05T11:58:02.755606Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:58:02.755606Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"WST: Weak-to-Strong Knowledge Transfer via Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Haosen Ge, Lianghuan Huang, Shuo Li","submitted_at":"2025-08-22T18:33:06Z","abstract_excerpt":"Effective prompt engineering remains a challenging task for many applications. We introduce Weak-to-Strong Transfer (WST), an automatic prompt engineering framework where a small \"Teacher\" model generates instructions that enhance the performance of a much larger \"Student\" model. Unlike prior work, WST requires only a weak teacher, making it efficient and broadly applicable in settings where large models are closed-source or difficult to fine-tune. Using reinforcement learning, the Teacher Model's instructions are iteratively improved based on the Student Model's outcomes, yielding substantial"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.16741","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/2508.16741/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":"2508.16741","created_at":"2026-07-05T11:58:02.755669+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.16741v1","created_at":"2026-07-05T11:58:02.755669+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.16741","created_at":"2026-07-05T11:58:02.755669+00:00"},{"alias_kind":"pith_short_12","alias_value":"NDRRMDKCSEIC","created_at":"2026-07-05T11:58:02.755669+00:00"},{"alias_kind":"pith_short_16","alias_value":"NDRRMDKCSEICIRMI","created_at":"2026-07-05T11:58:02.755669+00:00"},{"alias_kind":"pith_short_8","alias_value":"NDRRMDKC","created_at":"2026-07-05T11:58:02.755669+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NDRRMDKCSEICIRMIWKCZCKGKIH","json":"https://pith.science/pith/NDRRMDKCSEICIRMIWKCZCKGKIH.json","graph_json":"https://pith.science/api/pith-number/NDRRMDKCSEICIRMIWKCZCKGKIH/graph.json","events_json":"https://pith.science/api/pith-number/NDRRMDKCSEICIRMIWKCZCKGKIH/events.json","paper":"https://pith.science/paper/NDRRMDKC"},"agent_actions":{"view_html":"https://pith.science/pith/NDRRMDKCSEICIRMIWKCZCKGKIH","download_json":"https://pith.science/pith/NDRRMDKCSEICIRMIWKCZCKGKIH.json","view_paper":"https://pith.science/paper/NDRRMDKC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.16741&json=true","fetch_graph":"https://pith.science/api/pith-number/NDRRMDKCSEICIRMIWKCZCKGKIH/graph.json","fetch_events":"https://pith.science/api/pith-number/NDRRMDKCSEICIRMIWKCZCKGKIH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NDRRMDKCSEICIRMIWKCZCKGKIH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NDRRMDKCSEICIRMIWKCZCKGKIH/action/storage_attestation","attest_author":"https://pith.science/pith/NDRRMDKCSEICIRMIWKCZCKGKIH/action/author_attestation","sign_citation":"https://pith.science/pith/NDRRMDKCSEICIRMIWKCZCKGKIH/action/citation_signature","submit_replication":"https://pith.science/pith/NDRRMDKCSEICIRMIWKCZCKGKIH/action/replication_record"}},"created_at":"2026-07-05T11:58:02.755669+00:00","updated_at":"2026-07-05T11:58:02.755669+00:00"}