{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:GVXXTUZZCN2CPD24T7XZRWNRAD","short_pith_number":"pith:GVXXTUZZ","schema_version":"1.0","canonical_sha256":"356f79d3391374278f5c9fef98d9b100e892c563e93cbfdaa246b4685e6bde98","source":{"kind":"arxiv","id":"2112.04482","version":3},"attestation_state":"computed","paper":{"title":"FLAVA: A Foundational Language And Vision Alignment Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Amanpreet Singh, Douwe Kiela, Guillaume Couairon, Marcus Rohrbach, Ronghang Hu, Vedanuj Goswami, Wojciech Galuba","submitted_at":"2021-12-08T18:59:16Z","abstract_excerpt":"State-of-the-art vision and vision-and-language models rely on large-scale visio-linguistic pretraining for obtaining good performance on a variety of downstream tasks. Generally, such models are often either cross-modal (contrastive) or multi-modal (with earlier fusion) but not both; and they often only target specific modalities or tasks. A promising direction would be to use a single holistic universal model, as a \"foundation\", that targets all modalities at once -- a true vision and language foundation model should be good at vision tasks, language tasks, and cross- and multi-modal vision "},"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":"2112.04482","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-12-08T18:59:16Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"32e3a35817aed573b8337517ffa3a38e77ff59edcce6d5088f142c921db92584","abstract_canon_sha256":"f7fb7355c4a7d805eccf7afc245a7762aa158a8a96557fe8331ed96191a0e30e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:09:59.962023Z","signature_b64":"FXzhR+wAtmKFfaXqS/Ip8l/gvj64xyjRprV5SGddOaMYpv9FMozPCwpilTy/j8C3zIBfeHdRKRwv6pIIISzWCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"356f79d3391374278f5c9fef98d9b100e892c563e93cbfdaa246b4685e6bde98","last_reissued_at":"2026-07-05T04:09:59.961580Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:09:59.961580Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FLAVA: A Foundational Language And Vision Alignment Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Amanpreet Singh, Douwe Kiela, Guillaume Couairon, Marcus Rohrbach, Ronghang Hu, Vedanuj Goswami, Wojciech Galuba","submitted_at":"2021-12-08T18:59:16Z","abstract_excerpt":"State-of-the-art vision and vision-and-language models rely on large-scale visio-linguistic pretraining for obtaining good performance on a variety of downstream tasks. Generally, such models are often either cross-modal (contrastive) or multi-modal (with earlier fusion) but not both; and they often only target specific modalities or tasks. A promising direction would be to use a single holistic universal model, as a \"foundation\", that targets all modalities at once -- a true vision and language foundation model should be good at vision tasks, language tasks, and cross- and multi-modal vision "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.04482","kind":"arxiv","version":3},"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/2112.04482/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":"2112.04482","created_at":"2026-07-05T04:09:59.961637+00:00"},{"alias_kind":"arxiv_version","alias_value":"2112.04482v3","created_at":"2026-07-05T04:09:59.961637+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.04482","created_at":"2026-07-05T04:09:59.961637+00:00"},{"alias_kind":"pith_short_12","alias_value":"GVXXTUZZCN2C","created_at":"2026-07-05T04:09:59.961637+00:00"},{"alias_kind":"pith_short_16","alias_value":"GVXXTUZZCN2CPD24","created_at":"2026-07-05T04:09:59.961637+00:00"},{"alias_kind":"pith_short_8","alias_value":"GVXXTUZZ","created_at":"2026-07-05T04:09:59.961637+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2309.16671","citing_title":"Demystifying CLIP Data","ref_index":81,"is_internal_anchor":false},{"citing_arxiv_id":"2205.01917","citing_title":"CoCa: Contrastive Captioners are Image-Text Foundation Models","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2204.14198","citing_title":"Flamingo: a Visual Language Model for Few-Shot Learning","ref_index":102,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GVXXTUZZCN2CPD24T7XZRWNRAD","json":"https://pith.science/pith/GVXXTUZZCN2CPD24T7XZRWNRAD.json","graph_json":"https://pith.science/api/pith-number/GVXXTUZZCN2CPD24T7XZRWNRAD/graph.json","events_json":"https://pith.science/api/pith-number/GVXXTUZZCN2CPD24T7XZRWNRAD/events.json","paper":"https://pith.science/paper/GVXXTUZZ"},"agent_actions":{"view_html":"https://pith.science/pith/GVXXTUZZCN2CPD24T7XZRWNRAD","download_json":"https://pith.science/pith/GVXXTUZZCN2CPD24T7XZRWNRAD.json","view_paper":"https://pith.science/paper/GVXXTUZZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2112.04482&json=true","fetch_graph":"https://pith.science/api/pith-number/GVXXTUZZCN2CPD24T7XZRWNRAD/graph.json","fetch_events":"https://pith.science/api/pith-number/GVXXTUZZCN2CPD24T7XZRWNRAD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GVXXTUZZCN2CPD24T7XZRWNRAD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GVXXTUZZCN2CPD24T7XZRWNRAD/action/storage_attestation","attest_author":"https://pith.science/pith/GVXXTUZZCN2CPD24T7XZRWNRAD/action/author_attestation","sign_citation":"https://pith.science/pith/GVXXTUZZCN2CPD24T7XZRWNRAD/action/citation_signature","submit_replication":"https://pith.science/pith/GVXXTUZZCN2CPD24T7XZRWNRAD/action/replication_record"}},"created_at":"2026-07-05T04:09:59.961637+00:00","updated_at":"2026-07-05T04:09:59.961637+00:00"}