{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:OZVF2K7MUO3ITRMMQ5RQCEWHGJ","short_pith_number":"pith:OZVF2K7M","schema_version":"1.0","canonical_sha256":"766a5d2beca3b689c58c87630112c732726ab2ef5ae38145a1aff0f0695ec38d","source":{"kind":"arxiv","id":"2606.02113","version":1},"attestation_state":"computed","paper":{"title":"A Primer in Post-Training Reasoning Data: What We Know About How It Works","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Guangxiang Zhao, Lin Sun, Qilong Shi, Tong Yang, Xiangzheng Zhang, Yaoming Li","submitted_at":"2026-06-01T11:45:50Z","abstract_excerpt":"Post-training has become a primary driver of recent progress in large reasoning models, and reasoning data are often the key variable determining whether this stage succeeds. Work on post-training reasoning data has grown rapidly, yet this literature remains scattered across dataset papers, reinforcement-learning recipes, reward-model studies, benchmarks, and frontier system reports. This paper is the first primer to synthesize over 150 key public studies and system reports on post-training reasoning data. We organize the field around four questions: what data objects exist, what makes them us"},"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":"2606.02113","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-01T11:45:50Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"62f90d89cf50f824d5f1ad94eb1d4897d4f88d28446c48c8c2bd27fdaa6558f4","abstract_canon_sha256":"ea2eb580f1598f1f363c62f9b79d69b1db27481abdcea8c99587ebaa4829ab73"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T02:05:06.802271Z","signature_b64":"1nZou+4QgT9LgDS1vsxFyfCwHi0p8oywPL2/31zI6aHOb3rEEgUNM6Rab7O+R/1o3bxlFxFQ/9khTUoIVxkZBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"766a5d2beca3b689c58c87630112c732726ab2ef5ae38145a1aff0f0695ec38d","last_reissued_at":"2026-06-02T02:05:06.801846Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T02:05:06.801846Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Primer in Post-Training Reasoning Data: What We Know About How It Works","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Guangxiang Zhao, Lin Sun, Qilong Shi, Tong Yang, Xiangzheng Zhang, Yaoming Li","submitted_at":"2026-06-01T11:45:50Z","abstract_excerpt":"Post-training has become a primary driver of recent progress in large reasoning models, and reasoning data are often the key variable determining whether this stage succeeds. Work on post-training reasoning data has grown rapidly, yet this literature remains scattered across dataset papers, reinforcement-learning recipes, reward-model studies, benchmarks, and frontier system reports. This paper is the first primer to synthesize over 150 key public studies and system reports on post-training reasoning data. We organize the field around four questions: what data objects exist, what makes them us"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.02113","kind":"arxiv","version":1},"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/2606.02113/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":"2606.02113","created_at":"2026-06-02T02:05:06.801913+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.02113v1","created_at":"2026-06-02T02:05:06.801913+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.02113","created_at":"2026-06-02T02:05:06.801913+00:00"},{"alias_kind":"pith_short_12","alias_value":"OZVF2K7MUO3I","created_at":"2026-06-02T02:05:06.801913+00:00"},{"alias_kind":"pith_short_16","alias_value":"OZVF2K7MUO3ITRMM","created_at":"2026-06-02T02:05:06.801913+00:00"},{"alias_kind":"pith_short_8","alias_value":"OZVF2K7M","created_at":"2026-06-02T02:05:06.801913+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2606.03889","citing_title":"RealClawBench: Live OpenClaw Benchmarks from Real Developer-Agent Sessions","ref_index":35,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OZVF2K7MUO3ITRMMQ5RQCEWHGJ","json":"https://pith.science/pith/OZVF2K7MUO3ITRMMQ5RQCEWHGJ.json","graph_json":"https://pith.science/api/pith-number/OZVF2K7MUO3ITRMMQ5RQCEWHGJ/graph.json","events_json":"https://pith.science/api/pith-number/OZVF2K7MUO3ITRMMQ5RQCEWHGJ/events.json","paper":"https://pith.science/paper/OZVF2K7M"},"agent_actions":{"view_html":"https://pith.science/pith/OZVF2K7MUO3ITRMMQ5RQCEWHGJ","download_json":"https://pith.science/pith/OZVF2K7MUO3ITRMMQ5RQCEWHGJ.json","view_paper":"https://pith.science/paper/OZVF2K7M","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.02113&json=true","fetch_graph":"https://pith.science/api/pith-number/OZVF2K7MUO3ITRMMQ5RQCEWHGJ/graph.json","fetch_events":"https://pith.science/api/pith-number/OZVF2K7MUO3ITRMMQ5RQCEWHGJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OZVF2K7MUO3ITRMMQ5RQCEWHGJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OZVF2K7MUO3ITRMMQ5RQCEWHGJ/action/storage_attestation","attest_author":"https://pith.science/pith/OZVF2K7MUO3ITRMMQ5RQCEWHGJ/action/author_attestation","sign_citation":"https://pith.science/pith/OZVF2K7MUO3ITRMMQ5RQCEWHGJ/action/citation_signature","submit_replication":"https://pith.science/pith/OZVF2K7MUO3ITRMMQ5RQCEWHGJ/action/replication_record"}},"created_at":"2026-06-02T02:05:06.801913+00:00","updated_at":"2026-06-02T02:05:06.801913+00:00"}