{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:5BNUYIP7RKEFEUIIZE4CIASIVC","short_pith_number":"pith:5BNUYIP7","schema_version":"1.0","canonical_sha256":"e85b4c21ff8a88525108c938240248a89f2d3706a5b04a4a6afe6d520524ab13","source":{"kind":"arxiv","id":"2308.06262","version":1},"attestation_state":"computed","paper":{"title":"Foundation Model is Efficient Multimodal Multitask Model Selector","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Chonghe Jiang, Fanqing Meng, Kaipeng Zhang, Ping Luo, Wenqi Shao, Yu Qiao, Zhanglin Peng","submitted_at":"2023-08-11T17:54:44Z","abstract_excerpt":"This paper investigates an under-explored but important problem: given a collection of pre-trained neural networks, predicting their performance on each multi-modal task without fine-tuning them, such as image recognition, referring, captioning, visual question answering, and text question answering. A brute-force approach is to finetune all models on all target datasets, bringing high computational costs. Although recent-advanced approaches employed lightweight metrics to measure models' transferability,they often depend heavily on the prior knowledge of a single task, making them inapplicabl"},"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":"2308.06262","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-08-11T17:54:44Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c0362798fad5378682b8f439c1f1fd82eff213c73a042f39974026db2da7e98c","abstract_canon_sha256":"e516448c19eeb0d38180fdf045438ab00a02ed47518644b846349c1a1eb16e3a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:40:25.544373Z","signature_b64":"jXW6g3U48IjUneckt12yPyPAWdKSK5eSY/Jqm+qKs10VClR3pts9S+PURmZOhJPYHCM5OK5EQXKAoBZFqMX8AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e85b4c21ff8a88525108c938240248a89f2d3706a5b04a4a6afe6d520524ab13","last_reissued_at":"2026-07-05T06:40:25.543931Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:40:25.543931Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Foundation Model is Efficient Multimodal Multitask Model Selector","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Chonghe Jiang, Fanqing Meng, Kaipeng Zhang, Ping Luo, Wenqi Shao, Yu Qiao, Zhanglin Peng","submitted_at":"2023-08-11T17:54:44Z","abstract_excerpt":"This paper investigates an under-explored but important problem: given a collection of pre-trained neural networks, predicting their performance on each multi-modal task without fine-tuning them, such as image recognition, referring, captioning, visual question answering, and text question answering. A brute-force approach is to finetune all models on all target datasets, bringing high computational costs. Although recent-advanced approaches employed lightweight metrics to measure models' transferability,they often depend heavily on the prior knowledge of a single task, making them inapplicabl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.06262","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/2308.06262/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":"2308.06262","created_at":"2026-07-05T06:40:25.543991+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.06262v1","created_at":"2026-07-05T06:40:25.543991+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.06262","created_at":"2026-07-05T06:40:25.543991+00:00"},{"alias_kind":"pith_short_12","alias_value":"5BNUYIP7RKEF","created_at":"2026-07-05T06:40:25.543991+00:00"},{"alias_kind":"pith_short_16","alias_value":"5BNUYIP7RKEFEUII","created_at":"2026-07-05T06:40:25.543991+00:00"},{"alias_kind":"pith_short_8","alias_value":"5BNUYIP7","created_at":"2026-07-05T06:40:25.543991+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/5BNUYIP7RKEFEUIIZE4CIASIVC","json":"https://pith.science/pith/5BNUYIP7RKEFEUIIZE4CIASIVC.json","graph_json":"https://pith.science/api/pith-number/5BNUYIP7RKEFEUIIZE4CIASIVC/graph.json","events_json":"https://pith.science/api/pith-number/5BNUYIP7RKEFEUIIZE4CIASIVC/events.json","paper":"https://pith.science/paper/5BNUYIP7"},"agent_actions":{"view_html":"https://pith.science/pith/5BNUYIP7RKEFEUIIZE4CIASIVC","download_json":"https://pith.science/pith/5BNUYIP7RKEFEUIIZE4CIASIVC.json","view_paper":"https://pith.science/paper/5BNUYIP7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.06262&json=true","fetch_graph":"https://pith.science/api/pith-number/5BNUYIP7RKEFEUIIZE4CIASIVC/graph.json","fetch_events":"https://pith.science/api/pith-number/5BNUYIP7RKEFEUIIZE4CIASIVC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5BNUYIP7RKEFEUIIZE4CIASIVC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5BNUYIP7RKEFEUIIZE4CIASIVC/action/storage_attestation","attest_author":"https://pith.science/pith/5BNUYIP7RKEFEUIIZE4CIASIVC/action/author_attestation","sign_citation":"https://pith.science/pith/5BNUYIP7RKEFEUIIZE4CIASIVC/action/citation_signature","submit_replication":"https://pith.science/pith/5BNUYIP7RKEFEUIIZE4CIASIVC/action/replication_record"}},"created_at":"2026-07-05T06:40:25.543991+00:00","updated_at":"2026-07-05T06:40:25.543991+00:00"}