{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:YHEKI4XVV7WACF7SDM7XMWZVG2","short_pith_number":"pith:YHEKI4XV","schema_version":"1.0","canonical_sha256":"c1c8a472f5afec0117f21b3f765b35368a2f38935bf69c74f4e9be2d500f9f2a","source":{"kind":"arxiv","id":"2407.13647","version":2},"attestation_state":"computed","paper":{"title":"Weak-to-Strong Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Pengfei Liu, Yan Ma, Yuqing Yang","submitted_at":"2024-07-18T16:25:17Z","abstract_excerpt":"When large language models (LLMs) exceed human-level capabilities, it becomes increasingly challenging to provide full-scale and accurate supervision for these models. Weak-to-strong learning, which leverages a less capable model to unlock the latent abilities of a stronger model, proves valuable in this context. Yet, the efficacy of this approach for complex reasoning tasks is still untested. Furthermore, tackling reasoning tasks under the weak-to-strong setting currently lacks efficient methods to avoid blindly imitating the weak supervisor including its errors. In this paper, we introduce 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":"2407.13647","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-07-18T16:25:17Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"452437132bbd213798ca80831a029436ccdfc19a87a98bba91ba443adb83ba89","abstract_canon_sha256":"2d0d2c6100354e00c723c651f09f87f5a08e26e8d9c9f2d78bacdc8a55f65ed5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:13:55.025149Z","signature_b64":"Ht/oY6QkOto3u4viwhtZzMsDYpB/fB1mSVf29zqv0N7Mtc6GLelZDfxtOacl1jrUcToQS0fpfKdH3KYk+VsfCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c1c8a472f5afec0117f21b3f765b35368a2f38935bf69c74f4e9be2d500f9f2a","last_reissued_at":"2026-07-05T09:13:55.024685Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:13:55.024685Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Weak-to-Strong Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Pengfei Liu, Yan Ma, Yuqing Yang","submitted_at":"2024-07-18T16:25:17Z","abstract_excerpt":"When large language models (LLMs) exceed human-level capabilities, it becomes increasingly challenging to provide full-scale and accurate supervision for these models. Weak-to-strong learning, which leverages a less capable model to unlock the latent abilities of a stronger model, proves valuable in this context. Yet, the efficacy of this approach for complex reasoning tasks is still untested. Furthermore, tackling reasoning tasks under the weak-to-strong setting currently lacks efficient methods to avoid blindly imitating the weak supervisor including its errors. In this paper, we introduce a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.13647","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/2407.13647/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":"2407.13647","created_at":"2026-07-05T09:13:55.024741+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.13647v2","created_at":"2026-07-05T09:13:55.024741+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.13647","created_at":"2026-07-05T09:13:55.024741+00:00"},{"alias_kind":"pith_short_12","alias_value":"YHEKI4XVV7WA","created_at":"2026-07-05T09:13:55.024741+00:00"},{"alias_kind":"pith_short_16","alias_value":"YHEKI4XVV7WACF7S","created_at":"2026-07-05T09:13:55.024741+00:00"},{"alias_kind":"pith_short_8","alias_value":"YHEKI4XV","created_at":"2026-07-05T09:13:55.024741+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.05742","citing_title":"Weak-to-Strong Generalization is Nearly Inevitable (in Linear Models)","ref_index":23,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YHEKI4XVV7WACF7SDM7XMWZVG2","json":"https://pith.science/pith/YHEKI4XVV7WACF7SDM7XMWZVG2.json","graph_json":"https://pith.science/api/pith-number/YHEKI4XVV7WACF7SDM7XMWZVG2/graph.json","events_json":"https://pith.science/api/pith-number/YHEKI4XVV7WACF7SDM7XMWZVG2/events.json","paper":"https://pith.science/paper/YHEKI4XV"},"agent_actions":{"view_html":"https://pith.science/pith/YHEKI4XVV7WACF7SDM7XMWZVG2","download_json":"https://pith.science/pith/YHEKI4XVV7WACF7SDM7XMWZVG2.json","view_paper":"https://pith.science/paper/YHEKI4XV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.13647&json=true","fetch_graph":"https://pith.science/api/pith-number/YHEKI4XVV7WACF7SDM7XMWZVG2/graph.json","fetch_events":"https://pith.science/api/pith-number/YHEKI4XVV7WACF7SDM7XMWZVG2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YHEKI4XVV7WACF7SDM7XMWZVG2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YHEKI4XVV7WACF7SDM7XMWZVG2/action/storage_attestation","attest_author":"https://pith.science/pith/YHEKI4XVV7WACF7SDM7XMWZVG2/action/author_attestation","sign_citation":"https://pith.science/pith/YHEKI4XVV7WACF7SDM7XMWZVG2/action/citation_signature","submit_replication":"https://pith.science/pith/YHEKI4XVV7WACF7SDM7XMWZVG2/action/replication_record"}},"created_at":"2026-07-05T09:13:55.024741+00:00","updated_at":"2026-07-05T09:13:55.024741+00:00"}