{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:DSPLC4SNDLFHHV3AEYZU4LPGKD","short_pith_number":"pith:DSPLC4SN","schema_version":"1.0","canonical_sha256":"1c9eb1724d1aca73d76026334e2de650c74270c5e96dd683725e1b9e21ace1f2","source":{"kind":"arxiv","id":"2605.25381","version":1},"attestation_state":"computed","paper":{"title":"Not only where, But when: Temporal Scheduling for RLVR","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Feng Zhao, Jiaqi Wang, Jinghao Zhang, Ruilin Li","submitted_at":"2026-05-25T03:10:51Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2605.25381","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-25T03:10:51Z","cross_cats_sorted":[],"title_canon_sha256":"79096bff842813431d0fe82af60c03679f5503b02a2b274026e417676cb8a915","abstract_canon_sha256":"ddc36fc17eac2f1dfd588c1b4506114a1933d895593a379e0e177fd3d4fbc61a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T02:04:31.826083Z","signature_b64":"T3JbXVIlZ+11/MU+/Y+3GfyDjVtmOUP6oouHfHM8Fy51J5WdBtQYTGvhK9kflQAQhzs9SXiNnE75kQqfWHhPBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1c9eb1724d1aca73d76026334e2de650c74270c5e96dd683725e1b9e21ace1f2","last_reissued_at":"2026-05-26T02:04:31.825305Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T02:04:31.825305Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Not only where, But when: Temporal Scheduling for RLVR","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Feng Zhao, Jiaqi Wang, Jinghao Zhang, Ruilin Li","submitted_at":"2026-05-25T03:10:51Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.25381","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.25381/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2605.25381","created_at":"2026-05-26T02:04:31.825440+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.25381v1","created_at":"2026-05-26T02:04:31.825440+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.25381","created_at":"2026-05-26T02:04:31.825440+00:00"},{"alias_kind":"pith_short_12","alias_value":"DSPLC4SNDLFH","created_at":"2026-05-26T02:04:31.825440+00:00"},{"alias_kind":"pith_short_16","alias_value":"DSPLC4SNDLFHHV3A","created_at":"2026-05-26T02:04:31.825440+00:00"},{"alias_kind":"pith_short_8","alias_value":"DSPLC4SN","created_at":"2026-05-26T02:04:31.825440+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DSPLC4SNDLFHHV3AEYZU4LPGKD","json":"https://pith.science/pith/DSPLC4SNDLFHHV3AEYZU4LPGKD.json","graph_json":"https://pith.science/api/pith-number/DSPLC4SNDLFHHV3AEYZU4LPGKD/graph.json","events_json":"https://pith.science/api/pith-number/DSPLC4SNDLFHHV3AEYZU4LPGKD/events.json","paper":"https://pith.science/paper/DSPLC4SN"},"agent_actions":{"view_html":"https://pith.science/pith/DSPLC4SNDLFHHV3AEYZU4LPGKD","download_json":"https://pith.science/pith/DSPLC4SNDLFHHV3AEYZU4LPGKD.json","view_paper":"https://pith.science/paper/DSPLC4SN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.25381&json=true","fetch_graph":"https://pith.science/api/pith-number/DSPLC4SNDLFHHV3AEYZU4LPGKD/graph.json","fetch_events":"https://pith.science/api/pith-number/DSPLC4SNDLFHHV3AEYZU4LPGKD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DSPLC4SNDLFHHV3AEYZU4LPGKD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DSPLC4SNDLFHHV3AEYZU4LPGKD/action/storage_attestation","attest_author":"https://pith.science/pith/DSPLC4SNDLFHHV3AEYZU4LPGKD/action/author_attestation","sign_citation":"https://pith.science/pith/DSPLC4SNDLFHHV3AEYZU4LPGKD/action/citation_signature","submit_replication":"https://pith.science/pith/DSPLC4SNDLFHHV3AEYZU4LPGKD/action/replication_record"}},"created_at":"2026-05-26T02:04:31.825440+00:00","updated_at":"2026-05-26T02:04:31.825440+00:00"}