{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:H4M7WT3WJKADRQIGFG3R4SH7A7","short_pith_number":"pith:H4M7WT3W","canonical_record":{"source":{"id":"2605.22217","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-21T09:19:23Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"41fdbbacecf77e264af1e7a7a377763fa4c2aec3e8c17b83d17f77d172eb496c","abstract_canon_sha256":"e341ea0ca36fe33c88963fc62e4941e62344e2cc5a0b5678233f825cbb7c6c89"},"schema_version":"1.0"},"canonical_sha256":"3f19fb4f764a8038c10629b71e48ff07fba97f39cf9fadad9aaa01454263ed1a","source":{"kind":"arxiv","id":"2605.22217","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:H4M7WT3WJKADRQIGFG3R4SH7A7","target":"record","payload":{"canonical_record":{"source":{"id":"2605.22217","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-21T09:19:23Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"41fdbbacecf77e264af1e7a7a377763fa4c2aec3e8c17b83d17f77d172eb496c","abstract_canon_sha256":"e341ea0ca36fe33c88963fc62e4941e62344e2cc5a0b5678233f825cbb7c6c89"},"schema_version":"1.0"},"canonical_sha256":"3f19fb4f764a8038c10629b71e48ff07fba97f39cf9fadad9aaa01454263ed1a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-22T01:04:32.675826Z","signature_b64":"zi6rRvQP1S9N2cPhxzoQ6ha+E2A7B4Ff8Q7v9rJSZ5OMl0kNEdDcgf3pNr5NoEn2kKjfF3lnCiGUSjQMHTDwBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3f19fb4f764a8038c10629b71e48ff07fba97f39cf9fadad9aaa01454263ed1a","last_reissued_at":"2026-05-22T01:04:32.674978Z","signature_status":"signed_v1","first_computed_at":"2026-05-22T01:04:32.674978Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.22217","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-22T01:04:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sqp0ZDT/fn9VYznsMMW+VG7+MbHZUvScLHOilzDMFlMvafUywBeAf43PVWuvw+uwe1/yZ3Z6S0GMVDCc9+9jBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-23T08:31:05.416755Z"},"content_sha256":"0ba0dc0aa88a85f50966cfc45a5ee4aba583534b451a42a85da4a0455159dea6","schema_version":"1.0","event_id":"sha256:0ba0dc0aa88a85f50966cfc45a5ee4aba583534b451a42a85da4a0455159dea6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:H4M7WT3WJKADRQIGFG3R4SH7A7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Survive or Collapse: The Asymmetric Roles of Data Gating and Reward Grounding in Self-Play RL","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Chengzhi Liu, Gaowen Liu, Jayanth Srinivasa, Sophia Xiao Pu, William Yang Wang, Xin Eric Wang, Zhaotian Weng","submitted_at":"2026-05-21T09:19:23Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.22217","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/2605.22217/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-22T01:04:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2xo4b+9MfEkZZJJSheJeSSuy+OPVwUIxGVXODW4mUVaaJgn0TysLzyEFaqsdFsXWSYcUTnE+Ecl+nGdLbfT+AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-23T08:31:05.417479Z"},"content_sha256":"a33e889b92d6ab2965eb7505b8c24f47acbbea908a4c2809e463dea1128c0bbd","schema_version":"1.0","event_id":"sha256:a33e889b92d6ab2965eb7505b8c24f47acbbea908a4c2809e463dea1128c0bbd"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/H4M7WT3WJKADRQIGFG3R4SH7A7/bundle.json","state_url":"https://pith.science/pith/H4M7WT3WJKADRQIGFG3R4SH7A7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/H4M7WT3WJKADRQIGFG3R4SH7A7/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-23T08:31:05Z","links":{"resolver":"https://pith.science/pith/H4M7WT3WJKADRQIGFG3R4SH7A7","bundle":"https://pith.science/pith/H4M7WT3WJKADRQIGFG3R4SH7A7/bundle.json","state":"https://pith.science/pith/H4M7WT3WJKADRQIGFG3R4SH7A7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/H4M7WT3WJKADRQIGFG3R4SH7A7/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8TjRiAN7TRBfH9fy02fHU07UCRlJBWqGQkWCKskzslWd+r4MfVOR8AGMsWxSxq5JQHDcgzmIPPyvujXdMvSfDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-23T08:31:05.420932Z","bundle_sha256":"ab6f7ce5e89088ac68bb0190bc0aafa59f718c6f3c8ba23759b01d5414d836df"}}