{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:P2KLPH4TQLTXAOIIHF7PAXBXZ6","short_pith_number":"pith:P2KLPH4T","schema_version":"1.0","canonical_sha256":"7e94b79f9382e7703908397ef05c37cfa0ae1c771147ddecfb096cb519e96216","source":{"kind":"arxiv","id":"2210.09236","version":1},"attestation_state":"computed","paper":{"title":"ZooD: Exploiting Model Zoo for Out-of-Distribution Generalization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Awais Muhammad, Chuanlong Xie, Fengwei Zhou, Qishi Dong, Sung-Ho Bae, Tianyang Hu, Yongxin Yang, Zhenguo Li","submitted_at":"2022-10-17T16:31:57Z","abstract_excerpt":"Recent advances on large-scale pre-training have shown great potentials of leveraging a large set of Pre-Trained Models (PTMs) for improving Out-of-Distribution (OoD) generalization, for which the goal is to perform well on possible unseen domains after fine-tuning on multiple training domains. However, maximally exploiting a zoo of PTMs is challenging since fine-tuning all possible combinations of PTMs is computationally prohibitive while accurate selection of PTMs requires tackling the possible data distribution shift for OoD tasks. In this work, we propose ZooD, a paradigm for PTMs ranking "},"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":"2210.09236","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-10-17T16:31:57Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"69d65837b1d15878a8a8e7d14675f563e537d633263b7c8894b72504c6743de3","abstract_canon_sha256":"15a0f3fc5afc6dc00655c97f2ab87096ab5e97023d3a10d19363f724db152372"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:07:20.368241Z","signature_b64":"mQizoom+ilEaGIvqD1tfwI/NegR4rClxFzqz3omGW0THwwuXDXhtgkU07YgcqcDe6VZcuIahdtQklpSY1YHFAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7e94b79f9382e7703908397ef05c37cfa0ae1c771147ddecfb096cb519e96216","last_reissued_at":"2026-07-05T05:07:20.367875Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:07:20.367875Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ZooD: Exploiting Model Zoo for Out-of-Distribution Generalization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Awais Muhammad, Chuanlong Xie, Fengwei Zhou, Qishi Dong, Sung-Ho Bae, Tianyang Hu, Yongxin Yang, Zhenguo Li","submitted_at":"2022-10-17T16:31:57Z","abstract_excerpt":"Recent advances on large-scale pre-training have shown great potentials of leveraging a large set of Pre-Trained Models (PTMs) for improving Out-of-Distribution (OoD) generalization, for which the goal is to perform well on possible unseen domains after fine-tuning on multiple training domains. However, maximally exploiting a zoo of PTMs is challenging since fine-tuning all possible combinations of PTMs is computationally prohibitive while accurate selection of PTMs requires tackling the possible data distribution shift for OoD tasks. In this work, we propose ZooD, a paradigm for PTMs ranking "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.09236","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/2210.09236/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":"2210.09236","created_at":"2026-07-05T05:07:20.367930+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.09236v1","created_at":"2026-07-05T05:07:20.367930+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.09236","created_at":"2026-07-05T05:07:20.367930+00:00"},{"alias_kind":"pith_short_12","alias_value":"P2KLPH4TQLTX","created_at":"2026-07-05T05:07:20.367930+00:00"},{"alias_kind":"pith_short_16","alias_value":"P2KLPH4TQLTXAOII","created_at":"2026-07-05T05:07:20.367930+00:00"},{"alias_kind":"pith_short_8","alias_value":"P2KLPH4T","created_at":"2026-07-05T05:07:20.367930+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/P2KLPH4TQLTXAOIIHF7PAXBXZ6","json":"https://pith.science/pith/P2KLPH4TQLTXAOIIHF7PAXBXZ6.json","graph_json":"https://pith.science/api/pith-number/P2KLPH4TQLTXAOIIHF7PAXBXZ6/graph.json","events_json":"https://pith.science/api/pith-number/P2KLPH4TQLTXAOIIHF7PAXBXZ6/events.json","paper":"https://pith.science/paper/P2KLPH4T"},"agent_actions":{"view_html":"https://pith.science/pith/P2KLPH4TQLTXAOIIHF7PAXBXZ6","download_json":"https://pith.science/pith/P2KLPH4TQLTXAOIIHF7PAXBXZ6.json","view_paper":"https://pith.science/paper/P2KLPH4T","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.09236&json=true","fetch_graph":"https://pith.science/api/pith-number/P2KLPH4TQLTXAOIIHF7PAXBXZ6/graph.json","fetch_events":"https://pith.science/api/pith-number/P2KLPH4TQLTXAOIIHF7PAXBXZ6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/P2KLPH4TQLTXAOIIHF7PAXBXZ6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/P2KLPH4TQLTXAOIIHF7PAXBXZ6/action/storage_attestation","attest_author":"https://pith.science/pith/P2KLPH4TQLTXAOIIHF7PAXBXZ6/action/author_attestation","sign_citation":"https://pith.science/pith/P2KLPH4TQLTXAOIIHF7PAXBXZ6/action/citation_signature","submit_replication":"https://pith.science/pith/P2KLPH4TQLTXAOIIHF7PAXBXZ6/action/replication_record"}},"created_at":"2026-07-05T05:07:20.367930+00:00","updated_at":"2026-07-05T05:07:20.367930+00:00"}