{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:DSPLC4SNDLFHHV3AEYZU4LPGKD","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":"ddc36fc17eac2f1dfd588c1b4506114a1933d895593a379e0e177fd3d4fbc61a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-25T03:10:51Z","title_canon_sha256":"79096bff842813431d0fe82af60c03679f5503b02a2b274026e417676cb8a915"},"schema_version":"1.0","source":{"id":"2605.25381","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.25381","created_at":"2026-05-26T02:04:31Z"},{"alias_kind":"arxiv_version","alias_value":"2605.25381v1","created_at":"2026-05-26T02:04:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.25381","created_at":"2026-05-26T02:04:31Z"},{"alias_kind":"pith_short_12","alias_value":"DSPLC4SNDLFH","created_at":"2026-05-26T02:04:31Z"},{"alias_kind":"pith_short_16","alias_value":"DSPLC4SNDLFHHV3A","created_at":"2026-05-26T02:04:31Z"},{"alias_kind":"pith_short_8","alias_value":"DSPLC4SN","created_at":"2026-05-26T02:04:31Z"}],"graph_snapshots":[{"event_id":"sha256:ef9fedb734b77e2d8ebcc202b4232a1c3cada8c4dde216024204e225b1948d42","target":"graph","created_at":"2026-05-26T02:04:31Z","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/2605.25381/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning with verifiable rewards (RLVR) has become a core technique for post-training of Large Language Models (LLMs). While policy optimization is driven by all sampled tokens under a globally broadcast scalar reward, the heterogeneous policy behaviors exhibited along trajectories are largely overlooked without differentiation. Existing works address this by credit allocation, including token-level advantage reweighting, and selective token optimization, however, the allocation criterion are principally stagnant throughout training, limiting resilient policy evolution. In this w","authors_text":"Feng Zhao, Jiaqi Wang, Jinghao Zhang, Ruilin Li","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-25T03:10:51Z","title":"Not only where, But when: Temporal Scheduling for RLVR"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.25381","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":"sha256:08da776d217034764665b36bae593d92806416619557ed6add4cbe10025b5904","target":"record","created_at":"2026-05-26T02:04:31Z","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":"ddc36fc17eac2f1dfd588c1b4506114a1933d895593a379e0e177fd3d4fbc61a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-25T03:10:51Z","title_canon_sha256":"79096bff842813431d0fe82af60c03679f5503b02a2b274026e417676cb8a915"},"schema_version":"1.0","source":{"id":"2605.25381","kind":"arxiv","version":1}},"canonical_sha256":"1c9eb1724d1aca73d76026334e2de650c74270c5e96dd683725e1b9e21ace1f2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1c9eb1724d1aca73d76026334e2de650c74270c5e96dd683725e1b9e21ace1f2","first_computed_at":"2026-05-26T02:04:31.825305Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-26T02:04:31.825305Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"T3JbXVIlZ+11/MU+/Y+3GfyDjVtmOUP6oouHfHM8Fy51J5WdBtQYTGvhK9kflQAQhzs9SXiNnE75kQqfWHhPBA==","signature_status":"signed_v1","signed_at":"2026-05-26T02:04:31.826083Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.25381","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:08da776d217034764665b36bae593d92806416619557ed6add4cbe10025b5904","sha256:ef9fedb734b77e2d8ebcc202b4232a1c3cada8c4dde216024204e225b1948d42"],"state_sha256":"67ea72fe0b228fb3b563424da507f3f1efcf1ddccd5c257b241141a7440e959c"}