{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:AK53QFNGCKVFZJMPRLYMP5PVUM","short_pith_number":"pith:AK53QFNG","canonical_record":{"source":{"id":"2606.07705","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-05T10:00:19Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d61a14e73fcca1dab14159bffbfc4fa0e20f3073d56eb82b7d1a548e7e8c65a9","abstract_canon_sha256":"5eae22ef2f6c1defbd29f76d73606ee9b8079cb6d42dcdc55c7d47bbca5c8fc7"},"schema_version":"1.0"},"canonical_sha256":"02bbb815a612aa5ca58f8af0c7f5f5a32f518c5b728cfdf61a2a711ae175ac53","source":{"kind":"arxiv","id":"2606.07705","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:AK53QFNGCKVFZJMPRLYMP5PVUM","target":"record","payload":{"canonical_record":{"source":{"id":"2606.07705","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-05T10:00:19Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d61a14e73fcca1dab14159bffbfc4fa0e20f3073d56eb82b7d1a548e7e8c65a9","abstract_canon_sha256":"5eae22ef2f6c1defbd29f76d73606ee9b8079cb6d42dcdc55c7d47bbca5c8fc7"},"schema_version":"1.0"},"canonical_sha256":"02bbb815a612aa5ca58f8af0c7f5f5a32f518c5b728cfdf61a2a711ae175ac53","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-09T01:04:49.798545Z","signature_b64":"5baiTzm7CnqfahcENpL+2dMwvtpFeCT9ofMet2RLgPB3qCFTFIxhL0L7ZZRm7PKejW4Dj0f7jASAwUtkpEH5BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"02bbb815a612aa5ca58f8af0c7f5f5a32f518c5b728cfdf61a2a711ae175ac53","last_reissued_at":"2026-06-09T01:04:49.798047Z","signature_status":"signed_v1","first_computed_at":"2026-06-09T01:04:49.798047Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.07705","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-09T01:04:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fTnr0kK7SvmHh/gcQSsn/AUcDGEbtAF6IS+qQzLsrH1wJ2sf48wf3lyvqxFiRKWk/cNb+479Z7V+wczA9ZsKBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-24T09:22:13.470261Z"},"content_sha256":"87d9c72d41a0650a534458eee9683bcc74447b13f21d7967e449d2c6690f3556","schema_version":"1.0","event_id":"sha256:87d9c72d41a0650a534458eee9683bcc74447b13f21d7967e449d2c6690f3556"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:AK53QFNGCKVFZJMPRLYMP5PVUM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SAW: Stage-Aware Dynamic Weighting for Multi-Objective Reinforcement Learning in Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Baolong Bi, Bolin Wan, Huaming Liao, Jiafeng Guo, Juan Chen, Shenghua Liu, Siqian Tong, Xueqi Cheng, Yuchen He, Yuyao Ge","submitted_at":"2026-06-05T10:00:19Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.07705","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/2606.07705/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-09T01:04:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LDLmS4AqReGQKyp7sBiPUdD/Jo6MmBgTF5IynuOTAzVFsWGPc0lqZw/cca3WAeocqgAX6XOnjd0VQWb4lixiBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-24T09:22:13.470673Z"},"content_sha256":"a228138b2a4d64a5eb480b47a57d70244f38003863c742730a9785bfa127d50c","schema_version":"1.0","event_id":"sha256:a228138b2a4d64a5eb480b47a57d70244f38003863c742730a9785bfa127d50c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AK53QFNGCKVFZJMPRLYMP5PVUM/bundle.json","state_url":"https://pith.science/pith/AK53QFNGCKVFZJMPRLYMP5PVUM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AK53QFNGCKVFZJMPRLYMP5PVUM/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-24T09:22:13Z","links":{"resolver":"https://pith.science/pith/AK53QFNGCKVFZJMPRLYMP5PVUM","bundle":"https://pith.science/pith/AK53QFNGCKVFZJMPRLYMP5PVUM/bundle.json","state":"https://pith.science/pith/AK53QFNGCKVFZJMPRLYMP5PVUM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AK53QFNGCKVFZJMPRLYMP5PVUM/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"F3v2B0TC2j2geJ5nzpwHCqYUD20b41ATQbfU9qDI8qiZHNMgv6YBcfwIBMnzvT6/wMFGLDRI2em9PdCrqcUcAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-24T09:22:13.472744Z","bundle_sha256":"343581c0ceb4ad6f7ee419faed22575f86125d3b4ea1cf5934d08490c80e88ed"}}