{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:ZOORX4VPNBLDN3MCQWOXJQ5DG5","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":"92f16272ea4784a655c850f299c9f467371256663870772170927aadc58a5f33","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-20T15:50:02Z","title_canon_sha256":"dbfc0cda19fab32e2a48940a5b150f8373868eb40c8d82f6ae272509389e9720"},"schema_version":"1.0","source":{"id":"2607.18082","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.18082","created_at":"2026-07-21T02:22:15Z"},{"alias_kind":"arxiv_version","alias_value":"2607.18082v1","created_at":"2026-07-21T02:22:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.18082","created_at":"2026-07-21T02:22:15Z"},{"alias_kind":"pith_short_12","alias_value":"ZOORX4VPNBLD","created_at":"2026-07-21T02:22:15Z"},{"alias_kind":"pith_short_16","alias_value":"ZOORX4VPNBLDN3MC","created_at":"2026-07-21T02:22:15Z"},{"alias_kind":"pith_short_8","alias_value":"ZOORX4VP","created_at":"2026-07-21T02:22:15Z"}],"graph_snapshots":[{"event_id":"sha256:eaba7cc52517f29fd10e534735de8738741dbc2492abb9b209a47258f68513e1","target":"graph","created_at":"2026-07-21T02:22:15Z","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/2607.18082/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Rubric-based RL has recently shown promise in improving LLMs on open-ended tasks. A widely recognized limitation of rubric-based RL is limited exploration: criteria that no rollout manages to satisfy (Unexplored Criteria, UC) receive no optimization signal. Recent methods address this by incorporating rubric information as external guidance during rollout, yet they introduce a train-inference mismatch: the policy is optimized on rollouts produced under external guidance while this guidance is absent at inference time, causing error accumulation through autoregressive decoding. Moreover, these ","authors_text":"Chao Ye, Cheng Peng, Guangcheng Zhu, Haobo Wang, Mingxuan Xia, Shenzhi Yang, Shuai Zhu, Siqing Wang, Yuhang Yang, Yuhang Zhang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-20T15:50:02Z","title":"Enhancing Rubric-based RL via Self-Distillation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.18082","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:ae421dde14ea00fcd68de80e144b0951d3f18b110fbf6d61e5fa0bc8ca948c74","target":"record","created_at":"2026-07-21T02:22:15Z","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":"92f16272ea4784a655c850f299c9f467371256663870772170927aadc58a5f33","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-20T15:50:02Z","title_canon_sha256":"dbfc0cda19fab32e2a48940a5b150f8373868eb40c8d82f6ae272509389e9720"},"schema_version":"1.0","source":{"id":"2607.18082","kind":"arxiv","version":1}},"canonical_sha256":"cb9d1bf2af685636ed82859d74c3a3377424f3d8ac5ca3449074de25448b79b5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cb9d1bf2af685636ed82859d74c3a3377424f3d8ac5ca3449074de25448b79b5","first_computed_at":"2026-07-21T02:22:15.479992Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-21T02:22:15.479992Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"aNaV61jfnqVT0bHtyqD0WxbIX9iG5maX9tQ3AUUAIyfy/BAHBV7IBeZXy2T6kj5uFIdlE8iDewKI5nqpn6efDg==","signature_status":"signed_v1","signed_at":"2026-07-21T02:22:15.480826Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.18082","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ae421dde14ea00fcd68de80e144b0951d3f18b110fbf6d61e5fa0bc8ca948c74","sha256:eaba7cc52517f29fd10e534735de8738741dbc2492abb9b209a47258f68513e1"],"state_sha256":"ff1b57d27b5b34ecb3acf36c775700db5437897d49ad6bad469694b069a72e43"}