{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:EASDRUWRLY6GKBGB7TJLWW5UQY","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":"3c9918d0fcff430bbb3b79504070edb444b61f2befb3c1ceab18d51ce88a7d4b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-11-01T16:08:28Z","title_canon_sha256":"5c437a889838cbaa7b958bcd1e30e236ee944cccde6363c7aa88a8ff874eb04c"},"schema_version":"1.0","source":{"id":"2511.00602","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2511.00602","created_at":"2026-06-23T01:12:48Z"},{"alias_kind":"arxiv_version","alias_value":"2511.00602v3","created_at":"2026-06-23T01:12:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2511.00602","created_at":"2026-06-23T01:12:48Z"},{"alias_kind":"pith_short_12","alias_value":"EASDRUWRLY6G","created_at":"2026-06-23T01:12:48Z"},{"alias_kind":"pith_short_16","alias_value":"EASDRUWRLY6GKBGB","created_at":"2026-06-23T01:12:48Z"},{"alias_kind":"pith_short_8","alias_value":"EASDRUWR","created_at":"2026-06-23T01:12:48Z"}],"graph_snapshots":[{"event_id":"sha256:d33b2c48840f53ef1477d5db444a9a53faa1cb95ac859ced8b2b24c61e0d92ce","target":"graph","created_at":"2026-06-23T01:12:48Z","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/2511.00602/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advances in large language model (LLM) reasoning through reinforcement learning rely on annotated datasets for verifiable rewards, which may limit models' ability to surpass human-level performance. While self-play offers a promising alternative, prior methods yield only marginal or even negative gains on post-trained models because they generate problems that cluster around familiar concepts rather than discovering novel ones. We introduce Open-Ended Self-Improving Reasoner (OpenSIR), a self-play framework in which a single LLM alternates teacher and student roles to generate and solve","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":"2025-11-01T16:08:28Z","title":"OpenSIR: Open-Ended Self-Improving Reasoner"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2511.00602","kind":"arxiv","version":3},"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":"sha256:0a9cfd0fc55afa7922cae130478453c8037afff9dd574634887fec79c460383f","target":"record","created_at":"2026-06-23T01:12:48Z","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":"3c9918d0fcff430bbb3b79504070edb444b61f2befb3c1ceab18d51ce88a7d4b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-11-01T16:08:28Z","title_canon_sha256":"5c437a889838cbaa7b958bcd1e30e236ee944cccde6363c7aa88a8ff874eb04c"},"schema_version":"1.0","source":{"id":"2511.00602","kind":"arxiv","version":3}},"canonical_sha256":"202438d2d15e3c6504c1fcd2bb5bb4860e7cbd039d5d85ab3187bf3f73e39da7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"202438d2d15e3c6504c1fcd2bb5bb4860e7cbd039d5d85ab3187bf3f73e39da7","first_computed_at":"2026-06-23T01:12:48.046827Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-23T01:12:48.046827Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vGrFLcjmtcq3GC+itI04N6IazN2k724npwh5sejdJXlSMBXWHa/w59wM0QsEOLIufzOCz0B6Ut1K/5bwCsdCBA==","signature_status":"signed_v1","signed_at":"2026-06-23T01:12:48.047428Z","signed_message":"canonical_sha256_bytes"},"source_id":"2511.00602","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0a9cfd0fc55afa7922cae130478453c8037afff9dd574634887fec79c460383f","sha256:d33b2c48840f53ef1477d5db444a9a53faa1cb95ac859ced8b2b24c61e0d92ce"],"state_sha256":"71a7d5ec65f7293c25fa2dd6c6244ae0e0b81f1bdb11a833dc3d7837f9ce993d"}