{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:WZYJX3DEDTD2NX52MRKGZTYNMM","short_pith_number":"pith:WZYJX3DE","schema_version":"1.0","canonical_sha256":"b6709bec641cc7a6dfba64546ccf0d633dee267c1f07e9eb4abdddebe0e6dac5","source":{"kind":"arxiv","id":"2407.13771","version":1},"attestation_state":"computed","paper":{"title":"Training-Free Model Merging for Multi-target Domain Adaptation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Beiwen Tian, Hao Zhao, Huan-ang Gao, Mingju Gao, Rong Zhi, Wenyi Li","submitted_at":"2024-07-18T17:59:57Z","abstract_excerpt":"In this paper, we study multi-target domain adaptation of scene understanding models. While previous methods achieved commendable results through inter-domain consistency losses, they often assumed unrealistic simultaneous access to images from all target domains, overlooking constraints such as data transfer bandwidth limitations and data privacy concerns. Given these challenges, we pose the question: How to merge models adapted independently on distinct domains while bypassing the need for direct access to training data? Our solution to this problem involves two components, merging model par"},"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":"2407.13771","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-18T17:59:57Z","cross_cats_sorted":[],"title_canon_sha256":"5c1649b633c3eac6b1d3083934f98b255e53d38acee13f57f4d1aa8e0bc7794e","abstract_canon_sha256":"f6fe05a45296c8662a2f719b4f003160942db1811aaef2648ceda19c55903f54"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:45:43.960673Z","signature_b64":"2El6QvLZAPJHQrVJZRBI4ABFDhBcmi1e3Wn5qQZo0Ur/2gbExd0ViX6tQK1o3CBXWBBy5b7sUrZfKZ1+UA2cAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b6709bec641cc7a6dfba64546ccf0d633dee267c1f07e9eb4abdddebe0e6dac5","last_reissued_at":"2026-07-05T08:45:43.960243Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:45:43.960243Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Training-Free Model Merging for Multi-target Domain Adaptation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Beiwen Tian, Hao Zhao, Huan-ang Gao, Mingju Gao, Rong Zhi, Wenyi Li","submitted_at":"2024-07-18T17:59:57Z","abstract_excerpt":"In this paper, we study multi-target domain adaptation of scene understanding models. While previous methods achieved commendable results through inter-domain consistency losses, they often assumed unrealistic simultaneous access to images from all target domains, overlooking constraints such as data transfer bandwidth limitations and data privacy concerns. Given these challenges, we pose the question: How to merge models adapted independently on distinct domains while bypassing the need for direct access to training data? Our solution to this problem involves two components, merging model par"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.13771","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/2407.13771/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":"2407.13771","created_at":"2026-07-05T08:45:43.960298+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.13771v1","created_at":"2026-07-05T08:45:43.960298+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.13771","created_at":"2026-07-05T08:45:43.960298+00:00"},{"alias_kind":"pith_short_12","alias_value":"WZYJX3DEDTD2","created_at":"2026-07-05T08:45:43.960298+00:00"},{"alias_kind":"pith_short_16","alias_value":"WZYJX3DEDTD2NX52","created_at":"2026-07-05T08:45:43.960298+00:00"},{"alias_kind":"pith_short_8","alias_value":"WZYJX3DE","created_at":"2026-07-05T08:45:43.960298+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2408.07666","citing_title":"Model Merging in LLMs, MLLMs, and Beyond: Methods, Theories, Applications and Opportunities","ref_index":126,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WZYJX3DEDTD2NX52MRKGZTYNMM","json":"https://pith.science/pith/WZYJX3DEDTD2NX52MRKGZTYNMM.json","graph_json":"https://pith.science/api/pith-number/WZYJX3DEDTD2NX52MRKGZTYNMM/graph.json","events_json":"https://pith.science/api/pith-number/WZYJX3DEDTD2NX52MRKGZTYNMM/events.json","paper":"https://pith.science/paper/WZYJX3DE"},"agent_actions":{"view_html":"https://pith.science/pith/WZYJX3DEDTD2NX52MRKGZTYNMM","download_json":"https://pith.science/pith/WZYJX3DEDTD2NX52MRKGZTYNMM.json","view_paper":"https://pith.science/paper/WZYJX3DE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.13771&json=true","fetch_graph":"https://pith.science/api/pith-number/WZYJX3DEDTD2NX52MRKGZTYNMM/graph.json","fetch_events":"https://pith.science/api/pith-number/WZYJX3DEDTD2NX52MRKGZTYNMM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WZYJX3DEDTD2NX52MRKGZTYNMM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WZYJX3DEDTD2NX52MRKGZTYNMM/action/storage_attestation","attest_author":"https://pith.science/pith/WZYJX3DEDTD2NX52MRKGZTYNMM/action/author_attestation","sign_citation":"https://pith.science/pith/WZYJX3DEDTD2NX52MRKGZTYNMM/action/citation_signature","submit_replication":"https://pith.science/pith/WZYJX3DEDTD2NX52MRKGZTYNMM/action/replication_record"}},"created_at":"2026-07-05T08:45:43.960298+00:00","updated_at":"2026-07-05T08:45:43.960298+00:00"}