{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:KJGZE7Y26TT4EWPANHULIVS6FU","short_pith_number":"pith:KJGZE7Y2","schema_version":"1.0","canonical_sha256":"524d927f1af4e7c259e069e8b4565e2d3bf422b827fe8830e8e9f8566be616d3","source":{"kind":"arxiv","id":"2204.08790","version":6},"attestation_state":"computed","paper":{"title":"ELEVATER: A Benchmark and Toolkit for Evaluating Language-Augmented Visual Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Chunyuan Li, Haotian Liu, Houdong Hu, Jianfeng Gao, Jianwei Yang, Jyoti Aneja, Liunian Harold Li, Pengchuan Zhang, Ping Jin, Yong Jae Lee, Zicheng Liu","submitted_at":"2022-04-19T10:23:42Z","abstract_excerpt":"Learning visual representations from natural language supervision has recently shown great promise in a number of pioneering works. In general, these language-augmented visual models demonstrate strong transferability to a variety of datasets and tasks. However, it remains challenging to evaluate the transferablity of these models due to the lack of easy-to-use evaluation toolkits and public benchmarks. To tackle this, we build ELEVATER (Evaluation of Language-augmented Visual Task-level Transfer), the first benchmark and toolkit for evaluating(pre-trained) language-augmented visual models. EL"},"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":"2204.08790","kind":"arxiv","version":6},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-04-19T10:23:42Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"91145ccfda3644bf43a957b190e05c5707bf24aa6ea6426ede6e027e39697254","abstract_canon_sha256":"9bf66a1a91c37d07dd7afb6d87291e51b890434f9915f2d1268722436b1a0f62"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:06:11.000700Z","signature_b64":"CtvY/RNtcGrSoJgraANjhxzgHHI+j5ttbg8EskDEBQB/vFr4KPzCCBWmLKJa9a+XF7ixi2hIlkbKi3T/vZIYCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"524d927f1af4e7c259e069e8b4565e2d3bf422b827fe8830e8e9f8566be616d3","last_reissued_at":"2026-07-05T05:06:11.000274Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:06:11.000274Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ELEVATER: A Benchmark and Toolkit for Evaluating Language-Augmented Visual Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Chunyuan Li, Haotian Liu, Houdong Hu, Jianfeng Gao, Jianwei Yang, Jyoti Aneja, Liunian Harold Li, Pengchuan Zhang, Ping Jin, Yong Jae Lee, Zicheng Liu","submitted_at":"2022-04-19T10:23:42Z","abstract_excerpt":"Learning visual representations from natural language supervision has recently shown great promise in a number of pioneering works. In general, these language-augmented visual models demonstrate strong transferability to a variety of datasets and tasks. However, it remains challenging to evaluate the transferablity of these models due to the lack of easy-to-use evaluation toolkits and public benchmarks. To tackle this, we build ELEVATER (Evaluation of Language-augmented Visual Task-level Transfer), the first benchmark and toolkit for evaluating(pre-trained) language-augmented visual models. EL"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.08790","kind":"arxiv","version":6},"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/2204.08790/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":"2204.08790","created_at":"2026-07-05T05:06:11.000336+00:00"},{"alias_kind":"arxiv_version","alias_value":"2204.08790v6","created_at":"2026-07-05T05:06:11.000336+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.08790","created_at":"2026-07-05T05:06:11.000336+00:00"},{"alias_kind":"pith_short_12","alias_value":"KJGZE7Y26TT4","created_at":"2026-07-05T05:06:11.000336+00:00"},{"alias_kind":"pith_short_16","alias_value":"KJGZE7Y26TT4EWPA","created_at":"2026-07-05T05:06:11.000336+00:00"},{"alias_kind":"pith_short_8","alias_value":"KJGZE7Y2","created_at":"2026-07-05T05:06:11.000336+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.16749","citing_title":"AnySynth: Harnessing the Power of Image Synthetic Data Generation for Generalized Vision-Language Tasks","ref_index":25,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KJGZE7Y26TT4EWPANHULIVS6FU","json":"https://pith.science/pith/KJGZE7Y26TT4EWPANHULIVS6FU.json","graph_json":"https://pith.science/api/pith-number/KJGZE7Y26TT4EWPANHULIVS6FU/graph.json","events_json":"https://pith.science/api/pith-number/KJGZE7Y26TT4EWPANHULIVS6FU/events.json","paper":"https://pith.science/paper/KJGZE7Y2"},"agent_actions":{"view_html":"https://pith.science/pith/KJGZE7Y26TT4EWPANHULIVS6FU","download_json":"https://pith.science/pith/KJGZE7Y26TT4EWPANHULIVS6FU.json","view_paper":"https://pith.science/paper/KJGZE7Y2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2204.08790&json=true","fetch_graph":"https://pith.science/api/pith-number/KJGZE7Y26TT4EWPANHULIVS6FU/graph.json","fetch_events":"https://pith.science/api/pith-number/KJGZE7Y26TT4EWPANHULIVS6FU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KJGZE7Y26TT4EWPANHULIVS6FU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KJGZE7Y26TT4EWPANHULIVS6FU/action/storage_attestation","attest_author":"https://pith.science/pith/KJGZE7Y26TT4EWPANHULIVS6FU/action/author_attestation","sign_citation":"https://pith.science/pith/KJGZE7Y26TT4EWPANHULIVS6FU/action/citation_signature","submit_replication":"https://pith.science/pith/KJGZE7Y26TT4EWPANHULIVS6FU/action/replication_record"}},"created_at":"2026-07-05T05:06:11.000336+00:00","updated_at":"2026-07-05T05:06:11.000336+00:00"}