{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:UH46VEJOFTNTVBZUXA4JDZANQD","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":"8a1f6ad74ad4384fd6a62f613cb2f536f30b9fb43e4ce6ca4a5e7bbffec67f03","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-08-10T05:02:28Z","title_canon_sha256":"1906b2de80679a03b117b6b22a7810b27dcc2c9f1f6746a35ca720a17bb0b1da"},"schema_version":"1.0","source":{"id":"2608.09123","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.09123","created_at":"2026-08-11T02:21:51Z"},{"alias_kind":"arxiv_version","alias_value":"2608.09123v1","created_at":"2026-08-11T02:21:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.09123","created_at":"2026-08-11T02:21:51Z"},{"alias_kind":"pith_short_12","alias_value":"UH46VEJOFTNT","created_at":"2026-08-11T02:21:51Z"},{"alias_kind":"pith_short_16","alias_value":"UH46VEJOFTNTVBZU","created_at":"2026-08-11T02:21:51Z"},{"alias_kind":"pith_short_8","alias_value":"UH46VEJO","created_at":"2026-08-11T02:21:51Z"}],"graph_snapshots":[{"event_id":"sha256:1beb5cf050e5e15ec5e3948ee2580391f2c029154109b17e9bfc99ead8cf785d","target":"graph","created_at":"2026-08-11T02:21:51Z","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/2608.09123/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Aligning Large Language Models (LLMs) for open-ended tasks is challenging because responses must satisfy multidimensional criteria without following a single correct generation trajectory. Existing rubric-based reinforcement learning (RL) methods compress fine-grained criterion-level feedback into scalar rewards, making persistent capability gaps difficult to target under limited on-policy exploration. We propose $\\textbf{RISE-RL}$ (Rubric-Informed Selective Exploration), which uses repeatedly missed rubric criteria to elicit privileged trajectories that are difficult to discover through ungui","authors_text":"Hongsheng Xin, Huimin Ren, Jinkun Hou, Kun Zhan, Pan Zhou, Zhuo Liu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-08-10T05:02:28Z","title":"RISE-RL: Rubric-Informed Selective Exploration for Open-Ended Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.09123","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":"sha256:1683f3a375759a90b521fe263d54aae53b0ec89722453a82870e4c7774d13c1b","target":"record","created_at":"2026-08-11T02:21:51Z","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":"8a1f6ad74ad4384fd6a62f613cb2f536f30b9fb43e4ce6ca4a5e7bbffec67f03","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-08-10T05:02:28Z","title_canon_sha256":"1906b2de80679a03b117b6b22a7810b27dcc2c9f1f6746a35ca720a17bb0b1da"},"schema_version":"1.0","source":{"id":"2608.09123","kind":"arxiv","version":1}},"canonical_sha256":"a1f9ea912e2cdb3a8734b83891e40d80fc81d84177ab7b76ce728cb8574587ae","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a1f9ea912e2cdb3a8734b83891e40d80fc81d84177ab7b76ce728cb8574587ae","first_computed_at":"2026-08-11T02:21:51.384659Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-11T02:21:51.384659Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"56C8cbLtDrr2LAZMoC/RGoy7831MyYHOMyn5cfEAdnD8s07Hav2SD4Vyo9QDlPZAKG687+zgKFUX5c6LwMLyDw==","signature_status":"signed_v1","signed_at":"2026-08-11T02:21:51.386402Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.09123","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1683f3a375759a90b521fe263d54aae53b0ec89722453a82870e4c7774d13c1b","sha256:1beb5cf050e5e15ec5e3948ee2580391f2c029154109b17e9bfc99ead8cf785d"],"state_sha256":"34594e8dc43c01e62d8c0632b2efa24d3a550d54d90f8f75b58b4964f4934cd2"}