{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:7QYJMUUVKAQBFOVTGDN7SQIUNW","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":"6acb278fe32398550e963c11ed5fc316f55fa49d2c6ca4d9980ae16ebafad382","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-07-02T17:30:24Z","title_canon_sha256":"ab7b67767a668414949a08463e78fbf7ab20bd04cc5a51a8a256519d759053ad"},"schema_version":"1.0","source":{"id":"2507.01921","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.01921","created_at":"2026-07-05T11:30:58Z"},{"alias_kind":"arxiv_version","alias_value":"2507.01921v1","created_at":"2026-07-05T11:30:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.01921","created_at":"2026-07-05T11:30:58Z"},{"alias_kind":"pith_short_12","alias_value":"7QYJMUUVKAQB","created_at":"2026-07-05T11:30:58Z"},{"alias_kind":"pith_short_16","alias_value":"7QYJMUUVKAQBFOVT","created_at":"2026-07-05T11:30:58Z"},{"alias_kind":"pith_short_8","alias_value":"7QYJMUUV","created_at":"2026-07-05T11:30:58Z"}],"graph_snapshots":[{"event_id":"sha256:1869a2dc09b3c9fc32bb943b96aeb4b179dc1eb2673bc370dfd39d81e8608440","target":"graph","created_at":"2026-07-05T11:30:58Z","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/2507.01921/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent work has shown that distilling reasoning traces from a larger teacher model via supervised finetuning outperforms reinforcement learning with the smaller student model alone (Guo et al. 2025). However, there has not been a systematic study of what kind of reasoning demonstrations from the teacher are most effective in improving the student model's reasoning capabilities. In this work we curate high-quality \"NaturalThoughts\" by selecting reasoning traces from a strong teacher model based on a large pool of questions from NaturalReasoning (Yuan et al. 2025). We first conduct a systematic ","authors_text":"Dong Wang, Ilia Kulikov, Jack Lanchantin, Jason Weston, Karthik Padthe, Shang-Wen Li, Thao Nguyen, Weizhe Yuan, Xian Li, Yang Li, Youssef Emad","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-07-02T17:30:24Z","title":"NaturalThoughts: Selecting and Distilling Reasoning Traces for General Reasoning Tasks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.01921","kind":"arxiv","version":1},"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:c35f48a1a7fb252dd997943e6f87f4ed25e17a20896cb77321530584d5b17ad7","target":"record","created_at":"2026-07-05T11:30:58Z","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":"6acb278fe32398550e963c11ed5fc316f55fa49d2c6ca4d9980ae16ebafad382","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-07-02T17:30:24Z","title_canon_sha256":"ab7b67767a668414949a08463e78fbf7ab20bd04cc5a51a8a256519d759053ad"},"schema_version":"1.0","source":{"id":"2507.01921","kind":"arxiv","version":1}},"canonical_sha256":"fc30965295502012bab330dbf941146da79f1ce56227fd76765b249ada15a70f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fc30965295502012bab330dbf941146da79f1ce56227fd76765b249ada15a70f","first_computed_at":"2026-07-05T11:30:58.271210Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:30:58.271210Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SjVHj7T+VL5ZpOCKUSGRAWar799nUQGDv2hs+638OJubZb2wMTNBLhRJVD5R3B9tzl7uoef0mk6mgSrA2HXdAw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:30:58.271724Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.01921","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c35f48a1a7fb252dd997943e6f87f4ed25e17a20896cb77321530584d5b17ad7","sha256:1869a2dc09b3c9fc32bb943b96aeb4b179dc1eb2673bc370dfd39d81e8608440"],"state_sha256":"e234c9f765e459f166e9cc2171565fb6c0b3840f24ef2f02f07cee079df15fef"}