{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:NVTPWGBN7HHQ6SDSLEPRSV5ZTQ","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":"91e6bd15d94ae44ee9d1fc3426176ec71028e2fc3d4a6ba6dc9e2caf53468ba2","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-04T10:15:12Z","title_canon_sha256":"31ffaed4c1d3114dbf27ab36ba4599c86b6c80446a781bc4e30aa3712293af63"},"schema_version":"1.0","source":{"id":"2412.03187","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.03187","created_at":"2026-07-05T10:20:17Z"},{"alias_kind":"arxiv_version","alias_value":"2412.03187v2","created_at":"2026-07-05T10:20:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.03187","created_at":"2026-07-05T10:20:17Z"},{"alias_kind":"pith_short_12","alias_value":"NVTPWGBN7HHQ","created_at":"2026-07-05T10:20:17Z"},{"alias_kind":"pith_short_16","alias_value":"NVTPWGBN7HHQ6SDS","created_at":"2026-07-05T10:20:17Z"},{"alias_kind":"pith_short_8","alias_value":"NVTPWGBN","created_at":"2026-07-05T10:20:17Z"}],"graph_snapshots":[{"event_id":"sha256:c2bcc3ab25cbe7ce25c4240639d27ab6cfc65659a104ab79bb74ce994c68806a","target":"graph","created_at":"2026-07-05T10:20:17Z","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/2412.03187/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While fusing heterogeneous open-source LLMs with varying architectures and sizes can potentially integrate the strengths of different models, existing fusion methods face significant challenges, such as vocabulary alignment and merging distribution matrices. These procedures are not only complex but also prone to introducing noise and errors. In this paper, we propose an implicit fusion method, Weighted-Reward Preference Optimization (WRPO), which leverages preference optimization between the source LLMs and the target LLM to transfer their capabilities effectively. WRPO eliminates the need fo","authors_text":"Fanqi Wan, 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":"2024-12-04T10:15:12Z","title":"Weighted-Reward Preference Optimization for Implicit Model Fusion"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.03187","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:a319ac8aea8c076f4f72744b90a79eac51bd43c59c2df45ff382e435b78486ed","target":"record","created_at":"2026-07-05T10:20:17Z","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":"91e6bd15d94ae44ee9d1fc3426176ec71028e2fc3d4a6ba6dc9e2caf53468ba2","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-04T10:15:12Z","title_canon_sha256":"31ffaed4c1d3114dbf27ab36ba4599c86b6c80446a781bc4e30aa3712293af63"},"schema_version":"1.0","source":{"id":"2412.03187","kind":"arxiv","version":2}},"canonical_sha256":"6d66fb182df9cf0f4872591f1957b99c0fb9f4e406536cc5a6bf3e1459d0b97b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6d66fb182df9cf0f4872591f1957b99c0fb9f4e406536cc5a6bf3e1459d0b97b","first_computed_at":"2026-07-05T10:20:17.936081Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:20:17.936081Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ICduAdsUbFKZTmrnIPjo8D3p35nJiibLqsDQ7eG/sCCYm24dk4w8hstK+i2q6JoA+M2Gv6M5MRhkwppiQsA/AQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:20:17.936621Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.03187","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a319ac8aea8c076f4f72744b90a79eac51bd43c59c2df45ff382e435b78486ed","sha256:c2bcc3ab25cbe7ce25c4240639d27ab6cfc65659a104ab79bb74ce994c68806a"],"state_sha256":"e94b010a4ac1deec2d5d23f1e5fb84226d8b57b99f4c68f18d496318dcb8497e"}