{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:LEJLBWEN2DVHGXYDGSDTUVUIBV","short_pith_number":"pith:LEJLBWEN","schema_version":"1.0","canonical_sha256":"5912b0d88dd0ea735f0334873a56880d46fa43b4dfff6cb58d37661a36683322","source":{"kind":"arxiv","id":"2205.15237","version":1},"attestation_state":"computed","paper":{"title":"VLUE: A Multi-Task Benchmark for Evaluating Vision-Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Shizhe Diao, Wangchunshu Zhou, Xinsong Zhang, Yan Zeng","submitted_at":"2022-05-30T16:52:30Z","abstract_excerpt":"Recent advances in vision-language pre-training (VLP) have demonstrated impressive performance in a range of vision-language (VL) tasks. However, there exist several challenges for measuring the community's progress in building general multi-modal intelligence. First, most of the downstream VL datasets are annotated using raw images that are already seen during pre-training, which may result in an overestimation of current VLP models' generalization ability. Second, recent VLP work mainly focuses on absolute performance but overlooks the efficiency-performance trade-off, which is also an impor"},"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":"2205.15237","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-05-30T16:52:30Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"6406987ec8f85f208bbf00212684fc8b7571dec7e1eb9de9260973e14d9539a6","abstract_canon_sha256":"cc5ea8dfda16a330252507431628951162e15b396dc356155dcb8bf528c6aa06"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:27:25.957106Z","signature_b64":"H9ZtGUH63gQ3JCeuazkhe5rMhs1gA8FqpIr2wEjbfU3hA35krI79Pg2HfCj5ZYmdobE1eq7L1H46X2S7mOxiBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5912b0d88dd0ea735f0334873a56880d46fa43b4dfff6cb58d37661a36683322","last_reissued_at":"2026-07-05T04:27:25.956658Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:27:25.956658Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VLUE: A Multi-Task Benchmark for Evaluating Vision-Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Shizhe Diao, Wangchunshu Zhou, Xinsong Zhang, Yan Zeng","submitted_at":"2022-05-30T16:52:30Z","abstract_excerpt":"Recent advances in vision-language pre-training (VLP) have demonstrated impressive performance in a range of vision-language (VL) tasks. However, there exist several challenges for measuring the community's progress in building general multi-modal intelligence. First, most of the downstream VL datasets are annotated using raw images that are already seen during pre-training, which may result in an overestimation of current VLP models' generalization ability. Second, recent VLP work mainly focuses on absolute performance but overlooks the efficiency-performance trade-off, which is also an impor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.15237","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/2205.15237/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":"2205.15237","created_at":"2026-07-05T04:27:25.956728+00:00"},{"alias_kind":"arxiv_version","alias_value":"2205.15237v1","created_at":"2026-07-05T04:27:25.956728+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.15237","created_at":"2026-07-05T04:27:25.956728+00:00"},{"alias_kind":"pith_short_12","alias_value":"LEJLBWEN2DVH","created_at":"2026-07-05T04:27:25.956728+00:00"},{"alias_kind":"pith_short_16","alias_value":"LEJLBWEN2DVHGXYD","created_at":"2026-07-05T04:27:25.956728+00:00"},{"alias_kind":"pith_short_8","alias_value":"LEJLBWEN","created_at":"2026-07-05T04:27:25.956728+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/LEJLBWEN2DVHGXYDGSDTUVUIBV","json":"https://pith.science/pith/LEJLBWEN2DVHGXYDGSDTUVUIBV.json","graph_json":"https://pith.science/api/pith-number/LEJLBWEN2DVHGXYDGSDTUVUIBV/graph.json","events_json":"https://pith.science/api/pith-number/LEJLBWEN2DVHGXYDGSDTUVUIBV/events.json","paper":"https://pith.science/paper/LEJLBWEN"},"agent_actions":{"view_html":"https://pith.science/pith/LEJLBWEN2DVHGXYDGSDTUVUIBV","download_json":"https://pith.science/pith/LEJLBWEN2DVHGXYDGSDTUVUIBV.json","view_paper":"https://pith.science/paper/LEJLBWEN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2205.15237&json=true","fetch_graph":"https://pith.science/api/pith-number/LEJLBWEN2DVHGXYDGSDTUVUIBV/graph.json","fetch_events":"https://pith.science/api/pith-number/LEJLBWEN2DVHGXYDGSDTUVUIBV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LEJLBWEN2DVHGXYDGSDTUVUIBV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LEJLBWEN2DVHGXYDGSDTUVUIBV/action/storage_attestation","attest_author":"https://pith.science/pith/LEJLBWEN2DVHGXYDGSDTUVUIBV/action/author_attestation","sign_citation":"https://pith.science/pith/LEJLBWEN2DVHGXYDGSDTUVUIBV/action/citation_signature","submit_replication":"https://pith.science/pith/LEJLBWEN2DVHGXYDGSDTUVUIBV/action/replication_record"}},"created_at":"2026-07-05T04:27:25.956728+00:00","updated_at":"2026-07-05T04:27:25.956728+00:00"}