{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:LFRMKKPQBRP6IPUALV32KS4O5S","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":"37f11a86c8ca8a16cbf827cb99b982a7a98f6ec05b363f7dd44438b676a9adc1","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-05-26T12:49:19Z","title_canon_sha256":"33c2bb95ba8845494b877346b1c04f33f00efd8d27c864a0b0a3636530afe2e5"},"schema_version":"1.0","source":{"id":"2605.26958","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.26958","created_at":"2026-05-27T01:06:21Z"},{"alias_kind":"arxiv_version","alias_value":"2605.26958v1","created_at":"2026-05-27T01:06:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.26958","created_at":"2026-05-27T01:06:21Z"},{"alias_kind":"pith_short_12","alias_value":"LFRMKKPQBRP6","created_at":"2026-05-27T01:06:21Z"},{"alias_kind":"pith_short_16","alias_value":"LFRMKKPQBRP6IPUA","created_at":"2026-05-27T01:06:21Z"},{"alias_kind":"pith_short_8","alias_value":"LFRMKKPQ","created_at":"2026-05-27T01:06:21Z"}],"graph_snapshots":[{"event_id":"sha256:d56083023ac69db61963baa22283ebac7851e6a217195e8bce6d6b0f8654a3df","target":"graph","created_at":"2026-05-27T01:06:21Z","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/2605.26958/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning in open-ended long-form generation is challenging because reliable reference answers and automatic metrics are often unavailable. Existing rubric-based methods typically rely on pointwise LLM-as-a-judge scoring, but absolute scores are difficult to calibrate across complex responses, may provide weak discrimination among same-query rollouts, and can become saturated during optimization. We propose Tournament-GRPO, a group-wise reward framework that converts rubric-guided LLM judgments into relative rewards through repeated multi-round tournaments among same-query rollout","authors_text":"Erhan Zhang, Jiaxin Mao, Wei Yang, Xiaochi Wei, Yan Gao, Yao Hu, Yiqun Chen, Yi Wu, Zihan Shen, Zixuan Yang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-05-26T12:49:19Z","title":"Tournament-GRPO: Group-Wise Tournament Rewards for Reinforcement Learning in Open-Ended Long-Form Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.26958","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":"sha256:439f3b548577564916e3b7c2f7cbf8fec43b4fadc7c0b1438481d17a95cd2b3f","target":"record","created_at":"2026-05-27T01:06:21Z","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":"37f11a86c8ca8a16cbf827cb99b982a7a98f6ec05b363f7dd44438b676a9adc1","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-05-26T12:49:19Z","title_canon_sha256":"33c2bb95ba8845494b877346b1c04f33f00efd8d27c864a0b0a3636530afe2e5"},"schema_version":"1.0","source":{"id":"2605.26958","kind":"arxiv","version":1}},"canonical_sha256":"5962c529f00c5fe43e805d77a54b8eecbf0964220eb1111d96dc316d22da5467","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5962c529f00c5fe43e805d77a54b8eecbf0964220eb1111d96dc316d22da5467","first_computed_at":"2026-05-27T01:06:21.637077Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-27T01:06:21.637077Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"H0DCHLdT8lP3inw42HY3nfZePr3o+/cjaDBG5QQQFhISsvqxyQJzRsvsEDRX7pQDg1FBPBwGPR+XzX8X3FF0CQ==","signature_status":"signed_v1","signed_at":"2026-05-27T01:06:21.637866Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.26958","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:439f3b548577564916e3b7c2f7cbf8fec43b4fadc7c0b1438481d17a95cd2b3f","sha256:d56083023ac69db61963baa22283ebac7851e6a217195e8bce6d6b0f8654a3df"],"state_sha256":"c4fa5fc10ef7c7f50dbc9ab7a99f2de7d7d187573da3a68661267cf33a432bbe"}