{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:EXPRVP4POOZRZXCR56BWXTQVMT","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":"82fa06fc6be7456ae5d1298d36a59307d9879ef1813cd170b5e04fb576eb6bcd","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-14T17:59:58Z","title_canon_sha256":"37b83f43c5e6c0ec649261a3a260d6e9f8ed313fc19a6805a703a6acef117b0b"},"schema_version":"1.0","source":{"id":"2502.10339","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.10339","created_at":"2026-07-05T10:14:32Z"},{"alias_kind":"arxiv_version","alias_value":"2502.10339v1","created_at":"2026-07-05T10:14:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.10339","created_at":"2026-07-05T10:14:32Z"},{"alias_kind":"pith_short_12","alias_value":"EXPRVP4POOZR","created_at":"2026-07-05T10:14:32Z"},{"alias_kind":"pith_short_16","alias_value":"EXPRVP4POOZRZXCR","created_at":"2026-07-05T10:14:32Z"},{"alias_kind":"pith_short_8","alias_value":"EXPRVP4P","created_at":"2026-07-05T10:14:32Z"}],"graph_snapshots":[{"event_id":"sha256:06c5071ec608af750cbbfe8399de97e84176409302338f49fa795b727d4bfe3d","target":"graph","created_at":"2026-07-05T10:14:32Z","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/2502.10339/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Model merging is an efficient way of obtaining a multi-task model from several pretrained models without further fine-tuning, and it has gained attention in various domains, including natural language processing (NLP). Despite the efficiency, a key challenge in model merging is the seemingly inevitable decrease in task performance as the number of models increases. In this paper, we propose $\\mathbf{S}$pectral $\\mathbf{T}$runcation $\\mathbf{A}$nd $\\mathbf{R}$escale (STAR) that aims at mitigating ``merging conflicts'' by truncating small components in the respective spectral spaces, which is fo","authors_text":"Ching-Yun Ko, I-Hsin Chung, Mi-Yen Yeh, Pin-Yu Chen, Tejaswini Pedapati, Yu-Ang Lee","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-14T17:59:58Z","title":"STAR: Spectral Truncation and Rescale for Model Merging"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.10339","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:dc7b312d633648733be051c9750b74ce20ad4aee5a3866fef06a74b334eaff5b","target":"record","created_at":"2026-07-05T10:14:32Z","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":"82fa06fc6be7456ae5d1298d36a59307d9879ef1813cd170b5e04fb576eb6bcd","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-14T17:59:58Z","title_canon_sha256":"37b83f43c5e6c0ec649261a3a260d6e9f8ed313fc19a6805a703a6acef117b0b"},"schema_version":"1.0","source":{"id":"2502.10339","kind":"arxiv","version":1}},"canonical_sha256":"25df1abf8f73b31cdc51ef836bce1564e36478287612819978369a267fe00116","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"25df1abf8f73b31cdc51ef836bce1564e36478287612819978369a267fe00116","first_computed_at":"2026-07-05T10:14:32.643657Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:14:32.643657Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4MfbrXQMe+AeZ++/ziKP4KgH1Txwuf3wkLSErUjOuOHV5tMmngoJzJzY2YXTLTARs6xifzlKvoVxos6Vd90OAA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:14:32.644343Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.10339","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dc7b312d633648733be051c9750b74ce20ad4aee5a3866fef06a74b334eaff5b","sha256:06c5071ec608af750cbbfe8399de97e84176409302338f49fa795b727d4bfe3d"],"state_sha256":"ca5fcebd5a3d77f0d165eb9c609bb1fceaf3e27c6ae3565b79a9b6586dae6c4f"}