{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:FZA44P5LSMQDNSQUCC3HWE74JS","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":"16dd2ed4f91bb56e7799baa1f9be7fddbdc42c62a2c3395de7e9a19d18b1e4fd","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-07-31T10:19:41Z","title_canon_sha256":"1202b8708cc168c2bf51821767c6c3a28ed40901c8ec3e352d768eee19cdc98e"},"schema_version":"1.0","source":{"id":"2607.29246","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.29246","created_at":"2026-08-03T01:22:26Z"},{"alias_kind":"arxiv_version","alias_value":"2607.29246v1","created_at":"2026-08-03T01:22:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.29246","created_at":"2026-08-03T01:22:26Z"},{"alias_kind":"pith_short_12","alias_value":"FZA44P5LSMQD","created_at":"2026-08-03T01:22:26Z"},{"alias_kind":"pith_short_16","alias_value":"FZA44P5LSMQDNSQU","created_at":"2026-08-03T01:22:26Z"},{"alias_kind":"pith_short_8","alias_value":"FZA44P5L","created_at":"2026-08-03T01:22:26Z"}],"graph_snapshots":[{"event_id":"sha256:7de01083f9b6a37cdcf454600e644a929b71818bd229ff9bd0cee8a5f53d2453","target":"graph","created_at":"2026-08-03T01:22:26Z","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/2607.29246/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Modern large language models (LLMs) are expected not just to answer correctly, but to adapt their behavior to different human values and use cases. As a result, multi-reward reinforcement learning (RL) has become an increasingly important problem for LLMs, where each reward captures a different aspect of desired behavior. However, optimizing with multiple rewards suffers from a more severe alignment tax issue, where different optimization objectives can trade off or even conflict with each other, leading to unstable and inefficient post-training. In this work, we propose PRISM, a new multi-rew","authors_text":"Haiyun Guo, Jinqiao Wang, Ruiming Liang, Tianyi Tan, Tianyue Wang, Xianyuan Zhan, Yinan Zheng, Yizhen Yuan, Yi Zhong","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-07-31T10:19:41Z","title":"Don't Mix Rewards, Mix Policies: Policy Decomposition and Optimization for Multi-Reward RL"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.29246","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":"sha256:820ba9520ded5caf6e31322bc98e3bdba2ae4651a089afc680d93106a6805d91","target":"record","created_at":"2026-08-03T01:22:26Z","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":"16dd2ed4f91bb56e7799baa1f9be7fddbdc42c62a2c3395de7e9a19d18b1e4fd","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-07-31T10:19:41Z","title_canon_sha256":"1202b8708cc168c2bf51821767c6c3a28ed40901c8ec3e352d768eee19cdc98e"},"schema_version":"1.0","source":{"id":"2607.29246","kind":"arxiv","version":1}},"canonical_sha256":"2e41ce3fab932036ca1410b67b13fc4c82b4a0b530472d625f2489c8bca93c63","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2e41ce3fab932036ca1410b67b13fc4c82b4a0b530472d625f2489c8bca93c63","first_computed_at":"2026-08-03T01:22:26.660104Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-03T01:22:26.660104Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"l5SYwJhsSx25soeE7UrMJcmTOvER46tqrwjdRRBgxAu8sUeaiFpfcZvcv2A6vyj4TKrVbWma8uLlzh+t6mweBA==","signature_status":"signed_v1","signed_at":"2026-08-03T01:22:26.661538Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.29246","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:820ba9520ded5caf6e31322bc98e3bdba2ae4651a089afc680d93106a6805d91","sha256:7de01083f9b6a37cdcf454600e644a929b71818bd229ff9bd0cee8a5f53d2453"],"state_sha256":"b5605bf07e5e710dacbe0d83843b0e219b859e543a7cefb2bcaa24db9830f0e6"}