{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:MUR5YBFGGEJ263DKKODENKCC3T","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":"acad12f954e229c95d413ef978afc99e4c613370e367893e755d1e7c9cc59c3d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-29T15:28:26Z","title_canon_sha256":"620b969b1447af61908e2853a9ac579147c3a9ef84c8f77c1261cadbc21270fb"},"schema_version":"1.0","source":{"id":"2605.31433","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.31433","created_at":"2026-06-01T02:04:05Z"},{"alias_kind":"arxiv_version","alias_value":"2605.31433v1","created_at":"2026-06-01T02:04:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.31433","created_at":"2026-06-01T02:04:05Z"},{"alias_kind":"pith_short_12","alias_value":"MUR5YBFGGEJ2","created_at":"2026-06-01T02:04:05Z"},{"alias_kind":"pith_short_16","alias_value":"MUR5YBFGGEJ263DK","created_at":"2026-06-01T02:04:05Z"},{"alias_kind":"pith_short_8","alias_value":"MUR5YBFG","created_at":"2026-06-01T02:04:05Z"}],"graph_snapshots":[{"event_id":"sha256:0437da71cd97d5c0c053c8500b27c583fc709731546cbdbc1fa2b0c762a5417e","target":"graph","created_at":"2026-06-01T02:04:05Z","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/2605.31433/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Self-play can train language models without external supervision. However, existing methods require rule-checkable answers, leaving open-ended tasks dependent on curated prompts or frontier-model judges. We introduce SCOPE, a data-free self-play framework for open-ended tasks that co-evolves two policies: a Challenger that generates document-grounded tasks, and a Solver that answers them through multi-turn retrieval. A frozen copy of the initial model serves as the self-judge, which writes task-specific rubrics from the source document and grades Solver responses against them. Across three 7-8","authors_text":"Aryo Pradipta Gema, Joshua Ong Jun Leang, Pasquale Minervini, Wai-Chung Kwan","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-29T15:28:26Z","title":"SCOPE: Self-Play via Co-Evolving Policies for Open-Ended Tasks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.31433","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:da1bb72999b6b23de55aa07e781a72e5bda25c6f7498d93986fcb7e8cd708b61","target":"record","created_at":"2026-06-01T02:04:05Z","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":"acad12f954e229c95d413ef978afc99e4c613370e367893e755d1e7c9cc59c3d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-29T15:28:26Z","title_canon_sha256":"620b969b1447af61908e2853a9ac579147c3a9ef84c8f77c1261cadbc21270fb"},"schema_version":"1.0","source":{"id":"2605.31433","kind":"arxiv","version":1}},"canonical_sha256":"6523dc04a63113af6c6a538646a842dcf3dcf828042485ca66a80ebad436304b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6523dc04a63113af6c6a538646a842dcf3dcf828042485ca66a80ebad436304b","first_computed_at":"2026-06-01T02:04:05.506645Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-01T02:04:05.506645Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"I9EO9XurZNUZLQ/AoPkq6pP3FHDVWjOWUbDwcvQXyKQYtvkje/BscJgiWh4xOEPTkyoifRQzBP1BiRKXzWO9Bg==","signature_status":"signed_v1","signed_at":"2026-06-01T02:04:05.507590Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.31433","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:da1bb72999b6b23de55aa07e781a72e5bda25c6f7498d93986fcb7e8cd708b61","sha256:0437da71cd97d5c0c053c8500b27c583fc709731546cbdbc1fa2b0c762a5417e"],"state_sha256":"30e05a23129b8f5b1deaa48bba76e558e52a800f3baa62441170f5229aa68b38"}