{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:AK53QFNGCKVFZJMPRLYMP5PVUM","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":"5eae22ef2f6c1defbd29f76d73606ee9b8079cb6d42dcdc55c7d47bbca5c8fc7","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-05T10:00:19Z","title_canon_sha256":"d61a14e73fcca1dab14159bffbfc4fa0e20f3073d56eb82b7d1a548e7e8c65a9"},"schema_version":"1.0","source":{"id":"2606.07705","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.07705","created_at":"2026-06-09T01:04:49Z"},{"alias_kind":"arxiv_version","alias_value":"2606.07705v1","created_at":"2026-06-09T01:04:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.07705","created_at":"2026-06-09T01:04:49Z"},{"alias_kind":"pith_short_12","alias_value":"AK53QFNGCKVF","created_at":"2026-06-09T01:04:49Z"},{"alias_kind":"pith_short_16","alias_value":"AK53QFNGCKVFZJMP","created_at":"2026-06-09T01:04:49Z"},{"alias_kind":"pith_short_8","alias_value":"AK53QFNG","created_at":"2026-06-09T01:04:49Z"}],"graph_snapshots":[{"event_id":"sha256:a228138b2a4d64a5eb480b47a57d70244f38003863c742730a9785bfa127d50c","target":"graph","created_at":"2026-06-09T01:04:49Z","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/2606.07705/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Although multi-objective reinforcement learning (MORL) is central to aligning large language models with complex human preferences, the prevailing practice of static weighted summation overlooks a more fundamental phenomenon: reward learning is markedly asynchronous across objectives. Well-learned dimensions quickly produce homogeneous, low-variance signals whose residual noise contaminates the aggregated reward (in GRPO) or occupies a fixed share of the advantage budget (in GDPO), interfering with the scarce yet high-value signals carried by under-learned dimensions. To address this asynchron","authors_text":"Baolong Bi, Bolin Wan, Huaming Liao, Jiafeng Guo, Juan Chen, Shenghua Liu, Siqian Tong, Xueqi Cheng, Yuchen He, Yuyao Ge","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-05T10:00:19Z","title":"SAW: Stage-Aware Dynamic Weighting for Multi-Objective Reinforcement Learning in Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.07705","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":"sha256:87d9c72d41a0650a534458eee9683bcc74447b13f21d7967e449d2c6690f3556","target":"record","created_at":"2026-06-09T01:04:49Z","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":"5eae22ef2f6c1defbd29f76d73606ee9b8079cb6d42dcdc55c7d47bbca5c8fc7","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-05T10:00:19Z","title_canon_sha256":"d61a14e73fcca1dab14159bffbfc4fa0e20f3073d56eb82b7d1a548e7e8c65a9"},"schema_version":"1.0","source":{"id":"2606.07705","kind":"arxiv","version":1}},"canonical_sha256":"02bbb815a612aa5ca58f8af0c7f5f5a32f518c5b728cfdf61a2a711ae175ac53","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"02bbb815a612aa5ca58f8af0c7f5f5a32f518c5b728cfdf61a2a711ae175ac53","first_computed_at":"2026-06-09T01:04:49.798047Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-09T01:04:49.798047Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5baiTzm7CnqfahcENpL+2dMwvtpFeCT9ofMet2RLgPB3qCFTFIxhL0L7ZZRm7PKejW4Dj0f7jASAwUtkpEH5BA==","signature_status":"signed_v1","signed_at":"2026-06-09T01:04:49.798545Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.07705","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:87d9c72d41a0650a534458eee9683bcc74447b13f21d7967e449d2c6690f3556","sha256:a228138b2a4d64a5eb480b47a57d70244f38003863c742730a9785bfa127d50c"],"state_sha256":"2a6c96412ebe8f4bf1b1012e4e3b0a9e51a75f991b31d4aeaad7e9142e27c4b4"}