{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:63RDQTHZ3GG6GFHGVBSLATVQMI","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"fb5669e5a22b4b0bd49910573156d1aec18cad25a75de8660e792a43944cf505","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-03T18:35:52Z","title_canon_sha256":"f2a55410e31bf4fe532c797624ffec6c5a1206067436a51d5cd591b1350cd7a9"},"schema_version":"1.0","source":{"id":"2506.03295","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.03295","created_at":"2026-07-05T11:16:09Z"},{"alias_kind":"arxiv_version","alias_value":"2506.03295v2","created_at":"2026-07-05T11:16:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.03295","created_at":"2026-07-05T11:16:09Z"},{"alias_kind":"pith_short_12","alias_value":"63RDQTHZ3GG6","created_at":"2026-07-05T11:16:09Z"},{"alias_kind":"pith_short_16","alias_value":"63RDQTHZ3GG6GFHG","created_at":"2026-07-05T11:16:09Z"},{"alias_kind":"pith_short_8","alias_value":"63RDQTHZ","created_at":"2026-07-05T11:16:09Z"}],"graph_snapshots":[{"event_id":"sha256:07050783a47ac646c3baa3f6e949f36ef47e171dc4fc379aef92c00f1f3a2a72","target":"graph","created_at":"2026-07-05T11:16:09Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2506.03295/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We have witnessed that strong LLMs like Qwen-Math, MiMo, and Phi-4 possess immense reasoning potential inherited from the pre-training stage. With reinforcement learning (RL), these models can improve dramatically on reasoning tasks. Recent studies have shown that even RL on a single problem can unleash these models' reasoning capabilities. However, RL is not only expensive but also unstable. Even one-shot RL requires hundreds of GPU hours. This raises a critical question: Is there a more efficient way to unleash the reasoning potential of these powerful base LLMs? In this work, we demonstrate","authors_text":"Kai Zou, Lijun Wu, Ping Nie, Wenhu Chen, Yubo Wang","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-03T18:35:52Z","title":"Unleashing the Reasoning Potential of Pre-trained LLMs by Critique Fine-Tuning on One Problem"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.03295","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:d88d6bc280139d4e2bf1a885ae772efbc14cf66185442ac83ab71a1d7b4ac594","target":"record","created_at":"2026-07-05T11:16:09Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"fb5669e5a22b4b0bd49910573156d1aec18cad25a75de8660e792a43944cf505","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-03T18:35:52Z","title_canon_sha256":"f2a55410e31bf4fe532c797624ffec6c5a1206067436a51d5cd591b1350cd7a9"},"schema_version":"1.0","source":{"id":"2506.03295","kind":"arxiv","version":2}},"canonical_sha256":"f6e2384cf9d98de314e6a864b04eb0622b08b5451158aead79099fec2b1695bd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f6e2384cf9d98de314e6a864b04eb0622b08b5451158aead79099fec2b1695bd","first_computed_at":"2026-07-05T11:16:09.797663Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:16:09.797663Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hCVhaCArrqUdIDTU+cvN/TUK1vCWjFjx6vzr/NABf3l5S7QUNk0zCZYP3p8fJribwrLEXB9CV+SWKltIk4i3BA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:16:09.798252Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.03295","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d88d6bc280139d4e2bf1a885ae772efbc14cf66185442ac83ab71a1d7b4ac594","sha256:07050783a47ac646c3baa3f6e949f36ef47e171dc4fc379aef92c00f1f3a2a72"],"state_sha256":"be93fce7fa3f2587ba871af6ec1a0c5bad40b5cf83ddef41dd529a9b1567ef03"}