{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:EOGJQ6IPLWTUPCBUQG2T6LJVZG","short_pith_number":"pith:EOGJQ6IP","schema_version":"1.0","canonical_sha256":"238c98790f5da747883481b53f2d35c98c2161f85806282fdaffce44156ebdbd","source":{"kind":"arxiv","id":"2606.00609","version":1},"attestation_state":"computed","paper":{"title":"CARE-RL: Capability-Aware Reinforcement Learning for Mitigating Cross-Domain Conflicts","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Rui Zhang, Xinle Wu, Yao Lu","submitted_at":"2026-05-30T08:18:40Z","abstract_excerpt":"Reinforcement learning (RL) with verifiable rewards has achieved strong progress in reasoning-oriented LLMs, but extending it to multi-domain RL remains challenging due to reward unreliability in non-verifiable tasks and capability interference across domains. We propose CARE-RL to combine protocol-aware reward generation with capability-aware optimization for mitigating cross-domain conflicts. For non-verifiable tasks, the Protocol-Aware Generative Reward Model (PA-GRM) constructs prompt-level evaluation protocols and schemas before producing trace-conditioned rewards, enabling task-adaptive "},"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":"2606.00609","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-30T08:18:40Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3ef7031e4c1c471b2db3e28124e8995a170ba7fe2a7d6d00edd312e1a194765f","abstract_canon_sha256":"d14b5c825b55baee05e1c5399b01fd69991c31661f310aa0fb53cb2efb1c6652"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T01:03:59.563366Z","signature_b64":"H+QAf7hL1PVS/gyjVAB7VI5j+fC9dd6Ilu0rcCa3SJkxOo3ZSjJhwWs4lg9lUyyNCGymnQTqFmrDESOnL0bqDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"238c98790f5da747883481b53f2d35c98c2161f85806282fdaffce44156ebdbd","last_reissued_at":"2026-06-02T01:03:59.562844Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T01:03:59.562844Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CARE-RL: Capability-Aware Reinforcement Learning for Mitigating Cross-Domain Conflicts","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Rui Zhang, Xinle Wu, Yao Lu","submitted_at":"2026-05-30T08:18:40Z","abstract_excerpt":"Reinforcement learning (RL) with verifiable rewards has achieved strong progress in reasoning-oriented LLMs, but extending it to multi-domain RL remains challenging due to reward unreliability in non-verifiable tasks and capability interference across domains. We propose CARE-RL to combine protocol-aware reward generation with capability-aware optimization for mitigating cross-domain conflicts. For non-verifiable tasks, the Protocol-Aware Generative Reward Model (PA-GRM) constructs prompt-level evaluation protocols and schemas before producing trace-conditioned rewards, enabling task-adaptive "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.00609","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/2606.00609/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":"2606.00609","created_at":"2026-06-02T01:03:59.562902+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.00609v1","created_at":"2026-06-02T01:03:59.562902+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.00609","created_at":"2026-06-02T01:03:59.562902+00:00"},{"alias_kind":"pith_short_12","alias_value":"EOGJQ6IPLWTU","created_at":"2026-06-02T01:03:59.562902+00:00"},{"alias_kind":"pith_short_16","alias_value":"EOGJQ6IPLWTUPCBU","created_at":"2026-06-02T01:03:59.562902+00:00"},{"alias_kind":"pith_short_8","alias_value":"EOGJQ6IP","created_at":"2026-06-02T01:03:59.562902+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/EOGJQ6IPLWTUPCBUQG2T6LJVZG","json":"https://pith.science/pith/EOGJQ6IPLWTUPCBUQG2T6LJVZG.json","graph_json":"https://pith.science/api/pith-number/EOGJQ6IPLWTUPCBUQG2T6LJVZG/graph.json","events_json":"https://pith.science/api/pith-number/EOGJQ6IPLWTUPCBUQG2T6LJVZG/events.json","paper":"https://pith.science/paper/EOGJQ6IP"},"agent_actions":{"view_html":"https://pith.science/pith/EOGJQ6IPLWTUPCBUQG2T6LJVZG","download_json":"https://pith.science/pith/EOGJQ6IPLWTUPCBUQG2T6LJVZG.json","view_paper":"https://pith.science/paper/EOGJQ6IP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.00609&json=true","fetch_graph":"https://pith.science/api/pith-number/EOGJQ6IPLWTUPCBUQG2T6LJVZG/graph.json","fetch_events":"https://pith.science/api/pith-number/EOGJQ6IPLWTUPCBUQG2T6LJVZG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EOGJQ6IPLWTUPCBUQG2T6LJVZG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EOGJQ6IPLWTUPCBUQG2T6LJVZG/action/storage_attestation","attest_author":"https://pith.science/pith/EOGJQ6IPLWTUPCBUQG2T6LJVZG/action/author_attestation","sign_citation":"https://pith.science/pith/EOGJQ6IPLWTUPCBUQG2T6LJVZG/action/citation_signature","submit_replication":"https://pith.science/pith/EOGJQ6IPLWTUPCBUQG2T6LJVZG/action/replication_record"}},"created_at":"2026-06-02T01:03:59.562902+00:00","updated_at":"2026-06-02T01:03:59.562902+00:00"}