{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:WGQKDO72K32SEV5SJN5XINFPKK","short_pith_number":"pith:WGQKDO72","schema_version":"1.0","canonical_sha256":"b1a0a1bbfa56f52257b24b7b7434af528a6aaf04624d59d089e589bf193c5ec4","source":{"kind":"arxiv","id":"2309.15698","version":1},"attestation_state":"computed","paper":{"title":"Deep Model Fusion: A Survey","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Han Hu, Liang Ding, Li Shen, Miao Zhang, Weishi Li, Yong Peng","submitted_at":"2023-09-27T14:40:12Z","abstract_excerpt":"Deep model fusion/merging is an emerging technique that merges the parameters or predictions of multiple deep learning models into a single one. It combines the abilities of different models to make up for the biases and errors of a single model to achieve better performance. However, deep model fusion on large-scale deep learning models (e.g., LLMs and foundation models) faces several challenges, including high computational cost, high-dimensional parameter space, interference between different heterogeneous models, etc. Although model fusion has attracted widespread attention due to its pote"},"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":"2309.15698","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-09-27T14:40:12Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d65104bbad79fba9e6f0e76d15c129260a8639a4cacd4fd71aec82157801175e","abstract_canon_sha256":"1afd3a1b66c31acdb0e2d7c424ab12e172efad6bf17c9178564de6a7e382f59e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:54:56.643350Z","signature_b64":"NaaOx2b2Kci59+tccdbymIJS9fGO7lrRKe+//XwmqpU/ZkiT1LU6cXMQwFS7/ZzJn3/42f+m/+Owj3xS1F2ODA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b1a0a1bbfa56f52257b24b7b7434af528a6aaf04624d59d089e589bf193c5ec4","last_reissued_at":"2026-07-05T06:54:56.642780Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:54:56.642780Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep Model Fusion: A Survey","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Han Hu, Liang Ding, Li Shen, Miao Zhang, Weishi Li, Yong Peng","submitted_at":"2023-09-27T14:40:12Z","abstract_excerpt":"Deep model fusion/merging is an emerging technique that merges the parameters or predictions of multiple deep learning models into a single one. It combines the abilities of different models to make up for the biases and errors of a single model to achieve better performance. However, deep model fusion on large-scale deep learning models (e.g., LLMs and foundation models) faces several challenges, including high computational cost, high-dimensional parameter space, interference between different heterogeneous models, etc. Although model fusion has attracted widespread attention due to its pote"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.15698","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/2309.15698/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":"2309.15698","created_at":"2026-07-05T06:54:56.642844+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.15698v1","created_at":"2026-07-05T06:54:56.642844+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.15698","created_at":"2026-07-05T06:54:56.642844+00:00"},{"alias_kind":"pith_short_12","alias_value":"WGQKDO72K32S","created_at":"2026-07-05T06:54:56.642844+00:00"},{"alias_kind":"pith_short_16","alias_value":"WGQKDO72K32SEV5S","created_at":"2026-07-05T06:54:56.642844+00:00"},{"alias_kind":"pith_short_8","alias_value":"WGQKDO72","created_at":"2026-07-05T06:54:56.642844+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":10,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.18627","citing_title":"PACT: Preserving Anchored Cores in Task-vectors for Model Merging","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2607.01689","citing_title":"Model Merging as Probabilistic Inference in Fine-Tuning Parameter Space","ref_index":58,"is_internal_anchor":false},{"citing_arxiv_id":"2606.04378","citing_title":"DLLG: Dynamic Logit-Level Gating of LLM Experts","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19409","citing_title":"Unlocking the Potential of Continual Model Merging: An ODE Perspective","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2604.01674","citing_title":"Can Heterogeneous Language Models Be Fused?","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19409","citing_title":"Unlocking the Potential of Continual Model Merging: An ODE Perspective","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19409","citing_title":"Unlocking the Potential of Continual Model Merging: An ODE Perspective","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2408.07666","citing_title":"Model Merging in LLMs, MLLMs, and Beyond: Methods, Theories, Applications and Opportunities","ref_index":127,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13839","citing_title":"Good Agentic Friends Do Not Just Give Verbal Advice: They Can Update Your Weights","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09442","citing_title":"UIPress: Bringing Optical Token Compression to UI-to-Code Generation","ref_index":22,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WGQKDO72K32SEV5SJN5XINFPKK","json":"https://pith.science/pith/WGQKDO72K32SEV5SJN5XINFPKK.json","graph_json":"https://pith.science/api/pith-number/WGQKDO72K32SEV5SJN5XINFPKK/graph.json","events_json":"https://pith.science/api/pith-number/WGQKDO72K32SEV5SJN5XINFPKK/events.json","paper":"https://pith.science/paper/WGQKDO72"},"agent_actions":{"view_html":"https://pith.science/pith/WGQKDO72K32SEV5SJN5XINFPKK","download_json":"https://pith.science/pith/WGQKDO72K32SEV5SJN5XINFPKK.json","view_paper":"https://pith.science/paper/WGQKDO72","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.15698&json=true","fetch_graph":"https://pith.science/api/pith-number/WGQKDO72K32SEV5SJN5XINFPKK/graph.json","fetch_events":"https://pith.science/api/pith-number/WGQKDO72K32SEV5SJN5XINFPKK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WGQKDO72K32SEV5SJN5XINFPKK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WGQKDO72K32SEV5SJN5XINFPKK/action/storage_attestation","attest_author":"https://pith.science/pith/WGQKDO72K32SEV5SJN5XINFPKK/action/author_attestation","sign_citation":"https://pith.science/pith/WGQKDO72K32SEV5SJN5XINFPKK/action/citation_signature","submit_replication":"https://pith.science/pith/WGQKDO72K32SEV5SJN5XINFPKK/action/replication_record"}},"created_at":"2026-07-05T06:54:56.642844+00:00","updated_at":"2026-07-05T06:54:56.642844+00:00"}