{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:3QS5BWJMNJCQ4FEDBHXHA3K7U2","short_pith_number":"pith:3QS5BWJM","schema_version":"1.0","canonical_sha256":"dc25d0d92c6a450e148309ee706d5fa6a2083743431ce7b7f1c96233fa486d3e","source":{"kind":"arxiv","id":"2409.15813","version":1},"attestation_state":"computed","paper":{"title":"Layer-wise Model Merging for Unsupervised Domain Adaptation in Segmentation Tasks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.MM"],"primary_cat":"cs.CV","authors_text":"Jose M Mart\\'inez, Juan C. SanMiguel, Marcos Escudero-Vi\\~nolo, Roberto Alcover-Couso","submitted_at":"2024-09-24T07:19:30Z","abstract_excerpt":"Merging parameters of multiple models has resurfaced as an effective strategy to enhance task performance and robustness, but prior work is limited by the high costs of ensemble creation and inference. In this paper, we leverage the abundance of freely accessible trained models to introduce a cost-free approach to model merging. It focuses on a layer-wise integration of merged models, aiming to maintain the distinctiveness of the task-specific final layers while unifying the initial layers, which are primarily associated with feature extraction. This approach ensures parameter consistency acro"},"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":"2409.15813","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-24T07:19:30Z","cross_cats_sorted":["cs.AI","cs.MM"],"title_canon_sha256":"3ceee191996a8c7057f28403683967662f136dc48ab65a57962740083af2333b","abstract_canon_sha256":"d8460010af438a18f2c1dd94c523dd56e98c26c51862e2132475710fae158d54"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:11:00.740300Z","signature_b64":"eyKSGLkSLsaMfOLyq72+SldOXNCq7BriU2SnUC++nWrzfFPM1ZXuU870EqMU9Bwsmpjm9Rn+EQ4QsyddCkWLBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dc25d0d92c6a450e148309ee706d5fa6a2083743431ce7b7f1c96233fa486d3e","last_reissued_at":"2026-07-05T09:11:00.739790Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:11:00.739790Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Layer-wise Model Merging for Unsupervised Domain Adaptation in Segmentation Tasks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.MM"],"primary_cat":"cs.CV","authors_text":"Jose M Mart\\'inez, Juan C. SanMiguel, Marcos Escudero-Vi\\~nolo, Roberto Alcover-Couso","submitted_at":"2024-09-24T07:19:30Z","abstract_excerpt":"Merging parameters of multiple models has resurfaced as an effective strategy to enhance task performance and robustness, but prior work is limited by the high costs of ensemble creation and inference. In this paper, we leverage the abundance of freely accessible trained models to introduce a cost-free approach to model merging. It focuses on a layer-wise integration of merged models, aiming to maintain the distinctiveness of the task-specific final layers while unifying the initial layers, which are primarily associated with feature extraction. This approach ensures parameter consistency acro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.15813","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/2409.15813/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":"2409.15813","created_at":"2026-07-05T09:11:00.739858+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.15813v1","created_at":"2026-07-05T09:11:00.739858+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.15813","created_at":"2026-07-05T09:11:00.739858+00:00"},{"alias_kind":"pith_short_12","alias_value":"3QS5BWJMNJCQ","created_at":"2026-07-05T09:11:00.739858+00:00"},{"alias_kind":"pith_short_16","alias_value":"3QS5BWJMNJCQ4FED","created_at":"2026-07-05T09:11:00.739858+00:00"},{"alias_kind":"pith_short_8","alias_value":"3QS5BWJM","created_at":"2026-07-05T09:11:00.739858+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.16592","citing_title":"Leveraging Contrastive Learning for Semantic Segmentation with Consistent Labels Across Varying Appearances","ref_index":6,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3QS5BWJMNJCQ4FEDBHXHA3K7U2","json":"https://pith.science/pith/3QS5BWJMNJCQ4FEDBHXHA3K7U2.json","graph_json":"https://pith.science/api/pith-number/3QS5BWJMNJCQ4FEDBHXHA3K7U2/graph.json","events_json":"https://pith.science/api/pith-number/3QS5BWJMNJCQ4FEDBHXHA3K7U2/events.json","paper":"https://pith.science/paper/3QS5BWJM"},"agent_actions":{"view_html":"https://pith.science/pith/3QS5BWJMNJCQ4FEDBHXHA3K7U2","download_json":"https://pith.science/pith/3QS5BWJMNJCQ4FEDBHXHA3K7U2.json","view_paper":"https://pith.science/paper/3QS5BWJM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.15813&json=true","fetch_graph":"https://pith.science/api/pith-number/3QS5BWJMNJCQ4FEDBHXHA3K7U2/graph.json","fetch_events":"https://pith.science/api/pith-number/3QS5BWJMNJCQ4FEDBHXHA3K7U2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3QS5BWJMNJCQ4FEDBHXHA3K7U2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3QS5BWJMNJCQ4FEDBHXHA3K7U2/action/storage_attestation","attest_author":"https://pith.science/pith/3QS5BWJMNJCQ4FEDBHXHA3K7U2/action/author_attestation","sign_citation":"https://pith.science/pith/3QS5BWJMNJCQ4FEDBHXHA3K7U2/action/citation_signature","submit_replication":"https://pith.science/pith/3QS5BWJMNJCQ4FEDBHXHA3K7U2/action/replication_record"}},"created_at":"2026-07-05T09:11:00.739858+00:00","updated_at":"2026-07-05T09:11:00.739858+00:00"}