{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ZBYMGZDCMGWWOHUNZLSHNKJBAR","short_pith_number":"pith:ZBYMGZDC","schema_version":"1.0","canonical_sha256":"c870c3646261ad671e8dcae476a9210460e0a138d69a42a0a7a87fdb0dca733b","source":{"kind":"arxiv","id":"2410.10112","version":2},"attestation_state":"computed","paper":{"title":"Can We Predict Performance of Large Models across Vision-Language Tasks?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Akshay Asthana, Kartik Gupta, Liang Zheng, Ming Xu, Qinyu Zhao, Stephen Gould","submitted_at":"2024-10-14T03:00:12Z","abstract_excerpt":"Evaluating large vision-language models (LVLMs) is very expensive, due to high computational cost and the wide variety of tasks. The good news is that if we already have some observed performance scores, we may be able to infer unknown ones. In this study, we propose a new framework for predicting unknown performance scores based on observed ones from other LVLMs or tasks. We first formulate the performance prediction as a matrix completion task. Specifically, we construct a sparse performance matrix $\\boldsymbol{R}$, where each entry $R_{mn}$ represents the performance score of the $m$-th mod"},"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":"2410.10112","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-14T03:00:12Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"835e7e8cdb11f5f9d0b0501757930ad008c64168df109db5992cd9b2cec5a792","abstract_canon_sha256":"05d6ecc597f54ed649575b8ad57873d948d566c13cb0e79e9c0c839c4f215f30"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:11:35.896805Z","signature_b64":"5SSYNQOGI7kxiFxt9Cx9YrAY4Fnl/z/9RKh5aG4BbqQjWsTBN114Os6IGqcCUfndXd59H6dCmz3T0H/8uKVaCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c870c3646261ad671e8dcae476a9210460e0a138d69a42a0a7a87fdb0dca733b","last_reissued_at":"2026-07-05T11:11:35.896262Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:11:35.896262Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Can We Predict Performance of Large Models across Vision-Language Tasks?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Akshay Asthana, Kartik Gupta, Liang Zheng, Ming Xu, Qinyu Zhao, Stephen Gould","submitted_at":"2024-10-14T03:00:12Z","abstract_excerpt":"Evaluating large vision-language models (LVLMs) is very expensive, due to high computational cost and the wide variety of tasks. The good news is that if we already have some observed performance scores, we may be able to infer unknown ones. In this study, we propose a new framework for predicting unknown performance scores based on observed ones from other LVLMs or tasks. We first formulate the performance prediction as a matrix completion task. Specifically, we construct a sparse performance matrix $\\boldsymbol{R}$, where each entry $R_{mn}$ represents the performance score of the $m$-th mod"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.10112","kind":"arxiv","version":2},"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/2410.10112/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":"2410.10112","created_at":"2026-07-05T11:11:35.896325+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.10112v2","created_at":"2026-07-05T11:11:35.896325+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.10112","created_at":"2026-07-05T11:11:35.896325+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZBYMGZDCMGWW","created_at":"2026-07-05T11:11:35.896325+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZBYMGZDCMGWWOHUN","created_at":"2026-07-05T11:11:35.896325+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZBYMGZDC","created_at":"2026-07-05T11:11:35.896325+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/ZBYMGZDCMGWWOHUNZLSHNKJBAR","json":"https://pith.science/pith/ZBYMGZDCMGWWOHUNZLSHNKJBAR.json","graph_json":"https://pith.science/api/pith-number/ZBYMGZDCMGWWOHUNZLSHNKJBAR/graph.json","events_json":"https://pith.science/api/pith-number/ZBYMGZDCMGWWOHUNZLSHNKJBAR/events.json","paper":"https://pith.science/paper/ZBYMGZDC"},"agent_actions":{"view_html":"https://pith.science/pith/ZBYMGZDCMGWWOHUNZLSHNKJBAR","download_json":"https://pith.science/pith/ZBYMGZDCMGWWOHUNZLSHNKJBAR.json","view_paper":"https://pith.science/paper/ZBYMGZDC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.10112&json=true","fetch_graph":"https://pith.science/api/pith-number/ZBYMGZDCMGWWOHUNZLSHNKJBAR/graph.json","fetch_events":"https://pith.science/api/pith-number/ZBYMGZDCMGWWOHUNZLSHNKJBAR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZBYMGZDCMGWWOHUNZLSHNKJBAR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZBYMGZDCMGWWOHUNZLSHNKJBAR/action/storage_attestation","attest_author":"https://pith.science/pith/ZBYMGZDCMGWWOHUNZLSHNKJBAR/action/author_attestation","sign_citation":"https://pith.science/pith/ZBYMGZDCMGWWOHUNZLSHNKJBAR/action/citation_signature","submit_replication":"https://pith.science/pith/ZBYMGZDCMGWWOHUNZLSHNKJBAR/action/replication_record"}},"created_at":"2026-07-05T11:11:35.896325+00:00","updated_at":"2026-07-05T11:11:35.896325+00:00"}