{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:HZWEPZSKC7LTSXVBV24CKEOSDX","short_pith_number":"pith:HZWEPZSK","schema_version":"1.0","canonical_sha256":"3e6c47e64a17d7395ea1aeb82511d21df0a8f948409eaca1d94ad2b8937d3fd5","source":{"kind":"arxiv","id":"2410.02396","version":1},"attestation_state":"computed","paper":{"title":"Parameter Competition Balancing for Model Merging","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Daojing He, Guodong Du, Hanting Liu, Ho-Kin Tang, Jing Li, Junlin Lee, Min Zhang, Runhua Jiang, Shuyang Yu, Sim Kuan Goh, Yifei Guo","submitted_at":"2024-10-03T11:17:58Z","abstract_excerpt":"While fine-tuning pretrained models has become common practice, these models often underperform outside their specific domains. Recently developed model merging techniques enable the direct integration of multiple models, each fine-tuned for distinct tasks, into a single model. This strategy promotes multitasking capabilities without requiring retraining on the original datasets. However, existing methods fall short in addressing potential conflicts and complex correlations between tasks, especially in parameter-level adjustments, posing a challenge in effectively balancing parameter competiti"},"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":"2410.02396","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-03T11:17:58Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"8f0497be16a7411d20d979e6b1f9665c69f31a6f727c285518ad56a861a497bb","abstract_canon_sha256":"11cbe8b51e4492128358ac550d98b0009949104e4d2b12edcaaeecf6f40fac34"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:15:20.166390Z","signature_b64":"e92qYTgJSNRuNbC0wrj5Y1y8T2//Ac0OWqnqC19MHh+dG16RRhNcsGq5wVupYdliv/iyn67G3ohLZFEvXGlzCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3e6c47e64a17d7395ea1aeb82511d21df0a8f948409eaca1d94ad2b8937d3fd5","last_reissued_at":"2026-07-05T09:15:20.165883Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:15:20.165883Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Parameter Competition Balancing for Model Merging","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Daojing He, Guodong Du, Hanting Liu, Ho-Kin Tang, Jing Li, Junlin Lee, Min Zhang, Runhua Jiang, Shuyang Yu, Sim Kuan Goh, Yifei Guo","submitted_at":"2024-10-03T11:17:58Z","abstract_excerpt":"While fine-tuning pretrained models has become common practice, these models often underperform outside their specific domains. Recently developed model merging techniques enable the direct integration of multiple models, each fine-tuned for distinct tasks, into a single model. This strategy promotes multitasking capabilities without requiring retraining on the original datasets. However, existing methods fall short in addressing potential conflicts and complex correlations between tasks, especially in parameter-level adjustments, posing a challenge in effectively balancing parameter competiti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.02396","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/2410.02396/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":"2410.02396","created_at":"2026-07-05T09:15:20.165943+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.02396v1","created_at":"2026-07-05T09:15:20.165943+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.02396","created_at":"2026-07-05T09:15:20.165943+00:00"},{"alias_kind":"pith_short_12","alias_value":"HZWEPZSKC7LT","created_at":"2026-07-05T09:15:20.165943+00:00"},{"alias_kind":"pith_short_16","alias_value":"HZWEPZSKC7LTSXVB","created_at":"2026-07-05T09:15:20.165943+00:00"},{"alias_kind":"pith_short_8","alias_value":"HZWEPZSK","created_at":"2026-07-05T09:15:20.165943+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.01674","citing_title":"Can Heterogeneous Language Models Be Fused?","ref_index":35,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HZWEPZSKC7LTSXVBV24CKEOSDX","json":"https://pith.science/pith/HZWEPZSKC7LTSXVBV24CKEOSDX.json","graph_json":"https://pith.science/api/pith-number/HZWEPZSKC7LTSXVBV24CKEOSDX/graph.json","events_json":"https://pith.science/api/pith-number/HZWEPZSKC7LTSXVBV24CKEOSDX/events.json","paper":"https://pith.science/paper/HZWEPZSK"},"agent_actions":{"view_html":"https://pith.science/pith/HZWEPZSKC7LTSXVBV24CKEOSDX","download_json":"https://pith.science/pith/HZWEPZSKC7LTSXVBV24CKEOSDX.json","view_paper":"https://pith.science/paper/HZWEPZSK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.02396&json=true","fetch_graph":"https://pith.science/api/pith-number/HZWEPZSKC7LTSXVBV24CKEOSDX/graph.json","fetch_events":"https://pith.science/api/pith-number/HZWEPZSKC7LTSXVBV24CKEOSDX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HZWEPZSKC7LTSXVBV24CKEOSDX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HZWEPZSKC7LTSXVBV24CKEOSDX/action/storage_attestation","attest_author":"https://pith.science/pith/HZWEPZSKC7LTSXVBV24CKEOSDX/action/author_attestation","sign_citation":"https://pith.science/pith/HZWEPZSKC7LTSXVBV24CKEOSDX/action/citation_signature","submit_replication":"https://pith.science/pith/HZWEPZSKC7LTSXVBV24CKEOSDX/action/replication_record"}},"created_at":"2026-07-05T09:15:20.165943+00:00","updated_at":"2026-07-05T09:15:20.165943+00:00"}