{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:FKWGND5KCH7RGXREQC7K7T7ZJD","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":"20501789dd30a5eb1103b0b944b2c8e1986b57a8c1e2fff1271712a6b7863c1b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-05-25T05:42:57Z","title_canon_sha256":"d2203f1e07d1fabdf405df502e84a224f4af4070be5b00a3a41ddf3589555dcc"},"schema_version":"1.0","source":{"id":"2605.25443","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.25443","created_at":"2026-05-26T02:04:35Z"},{"alias_kind":"arxiv_version","alias_value":"2605.25443v1","created_at":"2026-05-26T02:04:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.25443","created_at":"2026-05-26T02:04:35Z"},{"alias_kind":"pith_short_12","alias_value":"FKWGND5KCH7R","created_at":"2026-05-26T02:04:35Z"},{"alias_kind":"pith_short_16","alias_value":"FKWGND5KCH7RGXRE","created_at":"2026-05-26T02:04:35Z"},{"alias_kind":"pith_short_8","alias_value":"FKWGND5K","created_at":"2026-05-26T02:04:35Z"}],"graph_snapshots":[{"event_id":"sha256:8fdc0ad75975641e261050c5f7cd7642ee921314219685df0cbd10103493de65","target":"graph","created_at":"2026-05-26T02:04:35Z","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/2605.25443/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Post-training has significantly enhanced the reasoning capability of Large Reasoning Models (LRMs), especially with Reinforcement Learning (RL) like Group Relative Policy Optimization (GRPO). However, GRPO-style RL methods in multi-domain settings often fail to achieve consistent improvements across all domains due to inherent interference in policy optimization. Prior studies on multi-domain RL primarily focus on alleviating cross-domain interference, while often neglecting the pivotal role of knowledge sharing, which we argue is the key to transforming cross-domain interactions from harmful ","authors_text":"Chaochao Lu, Chen Gong, Hao Fang, Runmin Cong, Wenshui Luo, Yiliu Sun, Zongji Yu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-05-25T05:42:57Z","title":"Harmony in Diversity: Multi-domain Contrastive Policy Optimization for Large Reasoning Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.25443","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":"sha256:238b2a20385ba6bc0a0f0300865704f7391b54941dd1346b67cbd2740b2ae76f","target":"record","created_at":"2026-05-26T02:04:35Z","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":"20501789dd30a5eb1103b0b944b2c8e1986b57a8c1e2fff1271712a6b7863c1b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-05-25T05:42:57Z","title_canon_sha256":"d2203f1e07d1fabdf405df502e84a224f4af4070be5b00a3a41ddf3589555dcc"},"schema_version":"1.0","source":{"id":"2605.25443","kind":"arxiv","version":1}},"canonical_sha256":"2aac668faa11ff135e2480beafcff948eec58c832dcaa1044becdcd513d56690","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2aac668faa11ff135e2480beafcff948eec58c832dcaa1044becdcd513d56690","first_computed_at":"2026-05-26T02:04:35.595329Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-26T02:04:35.595329Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vaav1dqhDro77vuOXKuz7Y3/Tgr4wXWTWkipJ5cAoxOVKVusvujiMDorIq/6gJccfdJMIAMhQae0va3laT5KCw==","signature_status":"signed_v1","signed_at":"2026-05-26T02:04:35.596123Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.25443","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:238b2a20385ba6bc0a0f0300865704f7391b54941dd1346b67cbd2740b2ae76f","sha256:8fdc0ad75975641e261050c5f7cd7642ee921314219685df0cbd10103493de65"],"state_sha256":"e9149871a61d89df0287cfe1b0728cc991381b44bca7344d4dc30e239a772425"}