{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:2ACTI7WIN35LY2WUGWSCWKP4ND","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":"808907210a5ca8ee2e9f2301d317452c223913818ff22934d449de1690a5463a","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-03-03T12:17:36Z","title_canon_sha256":"ee6dc51cc20c2c00dbe34523f13e6f0e52e9ef042995d7cc27ac5f085b31f525"},"schema_version":"1.0","source":{"id":"2503.01461","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.01461","created_at":"2026-07-05T11:13:21Z"},{"alias_kind":"arxiv_version","alias_value":"2503.01461v2","created_at":"2026-07-05T11:13:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.01461","created_at":"2026-07-05T11:13:21Z"},{"alias_kind":"pith_short_12","alias_value":"2ACTI7WIN35L","created_at":"2026-07-05T11:13:21Z"},{"alias_kind":"pith_short_16","alias_value":"2ACTI7WIN35LY2WU","created_at":"2026-07-05T11:13:21Z"},{"alias_kind":"pith_short_8","alias_value":"2ACTI7WI","created_at":"2026-07-05T11:13:21Z"}],"graph_snapshots":[{"event_id":"sha256:23eb4d8c66816bb251c1ffa478ba86c84d7be0a4e84618582632c98a6e836dc7","target":"graph","created_at":"2026-07-05T11:13:21Z","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/2503.01461/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Reasoning Models(LRMs) such as OpenAI o1 and DeepSeek-R1 have shown remarkable reasoning capabilities by scaling test-time compute and generating long Chain-of-Thought(CoT). Distillation--post-training on LRMs-generated data--is a straightforward yet effective method to enhance the reasoning abilities of smaller models, but faces a critical bottleneck: we found that distilled long CoT data poses learning difficulty for small models and leads to the inheritance of biases (i.e. over-thinking) when using Supervised Fine-tuning (SFT) and Reinforcement Learning (RL) methods. To alleviate this","authors_text":"Bo Zeng, Chenyang Lyu, Hao Wang, Huifeng Yin, Kaifu Zhang, Liangying Shao, Longyue Wang, Minghao Wu, Tianqi Shi, Weihua Luo, Xuanfan Ni, Yu Zhao","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-03-03T12:17:36Z","title":"Marco-o1 v2: Towards Widening The Distillation Bottleneck for Reasoning Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.01461","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":"sha256:0cbd762a590feaa6d0ef51088410c86354c04fd99188f654acac35c5a93b511c","target":"record","created_at":"2026-07-05T11:13:21Z","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":"808907210a5ca8ee2e9f2301d317452c223913818ff22934d449de1690a5463a","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-03-03T12:17:36Z","title_canon_sha256":"ee6dc51cc20c2c00dbe34523f13e6f0e52e9ef042995d7cc27ac5f085b31f525"},"schema_version":"1.0","source":{"id":"2503.01461","kind":"arxiv","version":2}},"canonical_sha256":"d005347ec86efabc6ad435a42b29fc68f0974c16244f24cf36219d7f6a3b4a65","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d005347ec86efabc6ad435a42b29fc68f0974c16244f24cf36219d7f6a3b4a65","first_computed_at":"2026-07-05T11:13:21.817530Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:13:21.817530Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FqXtgUiTeXnTNGb69SQkMCZDYc4tc8ORF8116heLoWuAcEm4J5s1X0ZE6EOmUF+6DT1NkQ6CNVTTkz0MiEgUBg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:13:21.817970Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.01461","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0cbd762a590feaa6d0ef51088410c86354c04fd99188f654acac35c5a93b511c","sha256:23eb4d8c66816bb251c1ffa478ba86c84d7be0a4e84618582632c98a6e836dc7"],"state_sha256":"a6abda059e65d0ec532531053fca8529641038cb466e6a917b3f4c14b541aa52"}