{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:HERP3XJWGKBLXFCKH43YA2DIKA","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":"c0232b05a38c377f789c7f1c4a9ac10c96960fb073be7058042932814cd3634f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-03-06T15:34:27Z","title_canon_sha256":"e5c2b9604850faeb9c42285cd0ab880eed757c3357e4a688f26cf7d11e89edb7"},"schema_version":"1.0","source":{"id":"2503.04548","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.04548","created_at":"2026-07-05T10:25:41Z"},{"alias_kind":"arxiv_version","alias_value":"2503.04548v1","created_at":"2026-07-05T10:25:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.04548","created_at":"2026-07-05T10:25:41Z"},{"alias_kind":"pith_short_12","alias_value":"HERP3XJWGKBL","created_at":"2026-07-05T10:25:41Z"},{"alias_kind":"pith_short_16","alias_value":"HERP3XJWGKBLXFCK","created_at":"2026-07-05T10:25:41Z"},{"alias_kind":"pith_short_8","alias_value":"HERP3XJW","created_at":"2026-07-05T10:25:41Z"}],"graph_snapshots":[{"event_id":"sha256:72082e7f917a389733c6639880573f2ad1c44d29b7d73b017b3666328fdbba83","target":"graph","created_at":"2026-07-05T10:25:41Z","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/2503.04548/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this report, we present the third technical report on the development of slow-thinking models as part of the STILL project. As the technical pathway becomes clearer, scaling RL training has become a central technique for implementing such reasoning models. We systematically experiment with and document the effects of various factors influencing RL training, conducting experiments on both base models and fine-tuned models. Specifically, we demonstrate that our RL training approach consistently improves the Qwen2.5-32B base models, enhancing both response length and test accuracy. Furthermore","authors_text":"Beichen Zhang, Daixuan Cheng, Jie Chen, Jinhao Jiang, Ji-Rong Wen, Lei Fang, Wayne Xin Zhao, Xu Miao, Yang Lu, Yingqian Min, Zheng Liu, Zhipeng Chen, Zhongyuan Wang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-03-06T15:34:27Z","title":"An Empirical Study on Eliciting and Improving R1-like Reasoning Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.04548","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:cd445b0bf4dca015748536cde2c23fc51f4a4329c9f247a9a3dc91eb442f93be","target":"record","created_at":"2026-07-05T10:25:41Z","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":"c0232b05a38c377f789c7f1c4a9ac10c96960fb073be7058042932814cd3634f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-03-06T15:34:27Z","title_canon_sha256":"e5c2b9604850faeb9c42285cd0ab880eed757c3357e4a688f26cf7d11e89edb7"},"schema_version":"1.0","source":{"id":"2503.04548","kind":"arxiv","version":1}},"canonical_sha256":"3922fddd363282bb944a3f378068685024fd0176a9695a7d7ce33906d4179aa9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3922fddd363282bb944a3f378068685024fd0176a9695a7d7ce33906d4179aa9","first_computed_at":"2026-07-05T10:25:41.806921Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:25:41.806921Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gpxCYJpoTVYdN7BkZ48rrRRWVtXpycPFaX4SgZZRz+jnLZVUjaezlHMGpzlnU0jioE3YDNT1rlQt29/pksQgBw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:25:41.807476Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.04548","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cd445b0bf4dca015748536cde2c23fc51f4a4329c9f247a9a3dc91eb442f93be","sha256:72082e7f917a389733c6639880573f2ad1c44d29b7d73b017b3666328fdbba83"],"state_sha256":"ca215b832d094cf59ca42e13dec669fb3ab23aeb5a2e20e3f551534bdf469055"}