{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:UPWYUI3QWAAIJTYNCH7ZZBEUKJ","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":"5de436cec54f60b81a4b2734bebe99260da460a7edee19bb501b28a8b99cd28c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-04-09T03:51:53Z","title_canon_sha256":"ad316090d7113ffc7a56f59e44717aa997e894578386a147789d8eceb4f730ec"},"schema_version":"1.0","source":{"id":"2504.06562","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.06562","created_at":"2026-07-05T10:50:12Z"},{"alias_kind":"arxiv_version","alias_value":"2504.06562v2","created_at":"2026-07-05T10:50:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.06562","created_at":"2026-07-05T10:50:12Z"},{"alias_kind":"pith_short_12","alias_value":"UPWYUI3QWAAI","created_at":"2026-07-05T10:50:12Z"},{"alias_kind":"pith_short_16","alias_value":"UPWYUI3QWAAIJTYN","created_at":"2026-07-05T10:50:12Z"},{"alias_kind":"pith_short_8","alias_value":"UPWYUI3Q","created_at":"2026-07-05T10:50:12Z"}],"graph_snapshots":[{"event_id":"sha256:7119809910765f67fdc9feda723843383afefc949af639712d4a76acd023eb73","target":"graph","created_at":"2026-07-05T10:50:12Z","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/2504.06562/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Heterogeneous model fusion enhances the performance of LLMs by integrating the knowledge and capabilities of multiple structurally diverse models. However, existing approaches often rely solely on selecting the best output for each prompt from source models, which underutilizes their full potential due to limited source knowledge and results in sparse optimization signals. To address this limitation, we propose FuseRL, a novel two-stage framework comprising FuseSFT and FusePO to maximize the utilization of source LLMs. FuseSFT establishes a robust initialization by integrating the strengths of","authors_text":"Fanqi Wan, Guosheng Liang, Longguang Zhong, Tianyuan Shi, Xiaojun Quan, Ziyi Yang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-04-09T03:51:53Z","title":"FuseRL: Dense Preference Optimization for Heterogeneous Model Fusion"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.06562","kind":"arxiv","version":2},"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:b7a63dd892f5f0ca4a0307e9d9b9af357bc1150b51e95899a5317dce6d218c4f","target":"record","created_at":"2026-07-05T10:50:12Z","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":"5de436cec54f60b81a4b2734bebe99260da460a7edee19bb501b28a8b99cd28c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-04-09T03:51:53Z","title_canon_sha256":"ad316090d7113ffc7a56f59e44717aa997e894578386a147789d8eceb4f730ec"},"schema_version":"1.0","source":{"id":"2504.06562","kind":"arxiv","version":2}},"canonical_sha256":"a3ed8a2370b00084cf0d11ff9c84945262a6c81eb264d4e322772ecd68345ba2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a3ed8a2370b00084cf0d11ff9c84945262a6c81eb264d4e322772ecd68345ba2","first_computed_at":"2026-07-05T10:50:12.649647Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:50:12.649647Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Je37VynOvY+uM4kB6X2lI0kvzrdVxlzIU3QCnMaujsfHUcNNyntDKWl4Q80qYSDEWTlfv5w7MKv7K3dUdpRvAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:50:12.650145Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.06562","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b7a63dd892f5f0ca4a0307e9d9b9af357bc1150b51e95899a5317dce6d218c4f","sha256:7119809910765f67fdc9feda723843383afefc949af639712d4a76acd023eb73"],"state_sha256":"d29e0fb54cf498e5928621ea7c5ca022cc27aebe32b6e6c7a56fd4067aa8fa64"}