{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:MQKWIOUNAUVHHNX6ICPTNOAPC7","short_pith_number":"pith:MQKWIOUN","schema_version":"1.0","canonical_sha256":"6415643a8d052a73b6fe409f36b80f17db18667f849c7e118e7dfacfd4392c5f","source":{"kind":"arxiv","id":"2306.03900","version":1},"attestation_state":"computed","paper":{"title":"Model Spider: Learning to Rank Pre-Trained Models Efficiently","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"De-Chuan Zhan, Han-Jia Ye, Ting-Ji Huang, Yao-Xiang Ding, Yi-Kai Zhang","submitted_at":"2023-06-06T17:58:12Z","abstract_excerpt":"Figuring out which Pre-Trained Model (PTM) from a model zoo fits the target task is essential to take advantage of plentiful model resources. With the availability of numerous heterogeneous PTMs from diverse fields, efficiently selecting the most suitable PTM is challenging due to the time-consuming costs of carrying out forward or backward passes over all PTMs. In this paper, we propose Model Spider, which tokenizes both PTMs and tasks by summarizing their characteristics into vectors to enable efficient PTM selection. By leveraging the approximated performance of PTMs on a separate set of tr"},"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":"2306.03900","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-06-06T17:58:12Z","cross_cats_sorted":[],"title_canon_sha256":"ccd71932b516550b502744342c10a68ecacf63f6de40bc06397420d43aa37a17","abstract_canon_sha256":"e403fdaf900c7c92c22f810f2007223c8fd0402bd12a0002a03a63b696ff6696"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:18:03.430231Z","signature_b64":"6vcNBl61jQ7pS2QSNN9OjQwA6W5oJ/CKLyedOB8L/6DKVqDS14ZV8PSegcm+8cZQaCh5yXAUgytMFtcz01J6BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6415643a8d052a73b6fe409f36b80f17db18667f849c7e118e7dfacfd4392c5f","last_reissued_at":"2026-07-05T06:18:03.429786Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:18:03.429786Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Model Spider: Learning to Rank Pre-Trained Models Efficiently","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"De-Chuan Zhan, Han-Jia Ye, Ting-Ji Huang, Yao-Xiang Ding, Yi-Kai Zhang","submitted_at":"2023-06-06T17:58:12Z","abstract_excerpt":"Figuring out which Pre-Trained Model (PTM) from a model zoo fits the target task is essential to take advantage of plentiful model resources. With the availability of numerous heterogeneous PTMs from diverse fields, efficiently selecting the most suitable PTM is challenging due to the time-consuming costs of carrying out forward or backward passes over all PTMs. In this paper, we propose Model Spider, which tokenizes both PTMs and tasks by summarizing their characteristics into vectors to enable efficient PTM selection. By leveraging the approximated performance of PTMs on a separate set of tr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.03900","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/2306.03900/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":"2306.03900","created_at":"2026-07-05T06:18:03.429843+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.03900v1","created_at":"2026-07-05T06:18:03.429843+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.03900","created_at":"2026-07-05T06:18:03.429843+00:00"},{"alias_kind":"pith_short_12","alias_value":"MQKWIOUNAUVH","created_at":"2026-07-05T06:18:03.429843+00:00"},{"alias_kind":"pith_short_16","alias_value":"MQKWIOUNAUVHHNX6","created_at":"2026-07-05T06:18:03.429843+00:00"},{"alias_kind":"pith_short_8","alias_value":"MQKWIOUN","created_at":"2026-07-05T06:18:03.429843+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.07587","citing_title":"The Routing Plateau: Understanding and Breaking the Accuracy Limits of LLM Routers","ref_index":74,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MQKWIOUNAUVHHNX6ICPTNOAPC7","json":"https://pith.science/pith/MQKWIOUNAUVHHNX6ICPTNOAPC7.json","graph_json":"https://pith.science/api/pith-number/MQKWIOUNAUVHHNX6ICPTNOAPC7/graph.json","events_json":"https://pith.science/api/pith-number/MQKWIOUNAUVHHNX6ICPTNOAPC7/events.json","paper":"https://pith.science/paper/MQKWIOUN"},"agent_actions":{"view_html":"https://pith.science/pith/MQKWIOUNAUVHHNX6ICPTNOAPC7","download_json":"https://pith.science/pith/MQKWIOUNAUVHHNX6ICPTNOAPC7.json","view_paper":"https://pith.science/paper/MQKWIOUN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.03900&json=true","fetch_graph":"https://pith.science/api/pith-number/MQKWIOUNAUVHHNX6ICPTNOAPC7/graph.json","fetch_events":"https://pith.science/api/pith-number/MQKWIOUNAUVHHNX6ICPTNOAPC7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MQKWIOUNAUVHHNX6ICPTNOAPC7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MQKWIOUNAUVHHNX6ICPTNOAPC7/action/storage_attestation","attest_author":"https://pith.science/pith/MQKWIOUNAUVHHNX6ICPTNOAPC7/action/author_attestation","sign_citation":"https://pith.science/pith/MQKWIOUNAUVHHNX6ICPTNOAPC7/action/citation_signature","submit_replication":"https://pith.science/pith/MQKWIOUNAUVHHNX6ICPTNOAPC7/action/replication_record"}},"created_at":"2026-07-05T06:18:03.429843+00:00","updated_at":"2026-07-05T06:18:03.429843+00:00"}