{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:H4M7WT3WJKADRQIGFG3R4SH7A7","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":"e341ea0ca36fe33c88963fc62e4941e62344e2cc5a0b5678233f825cbb7c6c89","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-21T09:19:23Z","title_canon_sha256":"41fdbbacecf77e264af1e7a7a377763fa4c2aec3e8c17b83d17f77d172eb496c"},"schema_version":"1.0","source":{"id":"2605.22217","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.22217","created_at":"2026-05-22T01:04:32Z"},{"alias_kind":"arxiv_version","alias_value":"2605.22217v1","created_at":"2026-05-22T01:04:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.22217","created_at":"2026-05-22T01:04:32Z"},{"alias_kind":"pith_short_12","alias_value":"H4M7WT3WJKAD","created_at":"2026-05-22T01:04:32Z"},{"alias_kind":"pith_short_16","alias_value":"H4M7WT3WJKADRQIG","created_at":"2026-05-22T01:04:32Z"},{"alias_kind":"pith_short_8","alias_value":"H4M7WT3W","created_at":"2026-05-22T01:04:32Z"}],"graph_snapshots":[{"event_id":"sha256:a33e889b92d6ab2965eb7505b8c24f47acbbea908a4c2809e463dea1128c0bbd","target":"graph","created_at":"2026-05-22T01:04:32Z","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/2605.22217/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Self-play reinforcement learning trains language models on their own generated tasks, co-evolving a proposer and solver without human labels. Recent systems report strong reasoning gains, but collapse and instability are widely observed and poorly understood. The dominant response treats this as a reward-design problem. We argue instead that self-play stability is governed by two distinct levers: a data-level gate that decides which proposer-generated tasks enter the training pool, and the reward signal that updates the policy on tasks already admitted. Through controlled experiments on a Pyth","authors_text":"Chengzhi Liu, Gaowen Liu, Jayanth Srinivasa, Sophia Xiao Pu, William Yang Wang, Xin Eric Wang, Zhaotian Weng","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-21T09:19:23Z","title":"Survive or Collapse: The Asymmetric Roles of Data Gating and Reward Grounding in Self-Play RL"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.22217","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":"sha256:0ba0dc0aa88a85f50966cfc45a5ee4aba583534b451a42a85da4a0455159dea6","target":"record","created_at":"2026-05-22T01:04:32Z","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":"e341ea0ca36fe33c88963fc62e4941e62344e2cc5a0b5678233f825cbb7c6c89","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-21T09:19:23Z","title_canon_sha256":"41fdbbacecf77e264af1e7a7a377763fa4c2aec3e8c17b83d17f77d172eb496c"},"schema_version":"1.0","source":{"id":"2605.22217","kind":"arxiv","version":1}},"canonical_sha256":"3f19fb4f764a8038c10629b71e48ff07fba97f39cf9fadad9aaa01454263ed1a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3f19fb4f764a8038c10629b71e48ff07fba97f39cf9fadad9aaa01454263ed1a","first_computed_at":"2026-05-22T01:04:32.674978Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-22T01:04:32.674978Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zi6rRvQP1S9N2cPhxzoQ6ha+E2A7B4Ff8Q7v9rJSZ5OMl0kNEdDcgf3pNr5NoEn2kKjfF3lnCiGUSjQMHTDwBA==","signature_status":"signed_v1","signed_at":"2026-05-22T01:04:32.675826Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.22217","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0ba0dc0aa88a85f50966cfc45a5ee4aba583534b451a42a85da4a0455159dea6","sha256:a33e889b92d6ab2965eb7505b8c24f47acbbea908a4c2809e463dea1128c0bbd"],"state_sha256":"11507d0bff8cdbdcdc3b13d65afc31a871f3ee1c77119e35720d15bfe48db18b"}