{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:GVXXTUZZCN2CPD24T7XZRWNRAD","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"f7fb7355c4a7d805eccf7afc245a7762aa158a8a96557fe8331ed96191a0e30e","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-12-08T18:59:16Z","title_canon_sha256":"32e3a35817aed573b8337517ffa3a38e77ff59edcce6d5088f142c921db92584"},"schema_version":"1.0","source":{"id":"2112.04482","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.04482","created_at":"2026-07-05T04:09:59Z"},{"alias_kind":"arxiv_version","alias_value":"2112.04482v3","created_at":"2026-07-05T04:09:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.04482","created_at":"2026-07-05T04:09:59Z"},{"alias_kind":"pith_short_12","alias_value":"GVXXTUZZCN2C","created_at":"2026-07-05T04:09:59Z"},{"alias_kind":"pith_short_16","alias_value":"GVXXTUZZCN2CPD24","created_at":"2026-07-05T04:09:59Z"},{"alias_kind":"pith_short_8","alias_value":"GVXXTUZZ","created_at":"2026-07-05T04:09:59Z"}],"graph_snapshots":[{"event_id":"sha256:4609fb729ec4495bffec7a021c9c235a81b7ae6042e4e42fe86df86184aafd9c","target":"graph","created_at":"2026-07-05T04:09:59Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2112.04482/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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 ","authors_text":"Amanpreet Singh, Douwe Kiela, Guillaume Couairon, Marcus Rohrbach, Ronghang Hu, Vedanuj Goswami, Wojciech Galuba","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-12-08T18:59:16Z","title":"FLAVA: A Foundational Language And Vision Alignment Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.04482","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:9b4f47504ed434eaaa7406053faf51d2109d60553172c2b014c7ea17c2fcac1f","target":"record","created_at":"2026-07-05T04:09:59Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"f7fb7355c4a7d805eccf7afc245a7762aa158a8a96557fe8331ed96191a0e30e","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-12-08T18:59:16Z","title_canon_sha256":"32e3a35817aed573b8337517ffa3a38e77ff59edcce6d5088f142c921db92584"},"schema_version":"1.0","source":{"id":"2112.04482","kind":"arxiv","version":3}},"canonical_sha256":"356f79d3391374278f5c9fef98d9b100e892c563e93cbfdaa246b4685e6bde98","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"356f79d3391374278f5c9fef98d9b100e892c563e93cbfdaa246b4685e6bde98","first_computed_at":"2026-07-05T04:09:59.961580Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:09:59.961580Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FXzhR+wAtmKFfaXqS/Ip8l/gvj64xyjRprV5SGddOaMYpv9FMozPCwpilTy/j8C3zIBfeHdRKRwv6pIIISzWCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:09:59.962023Z","signed_message":"canonical_sha256_bytes"},"source_id":"2112.04482","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9b4f47504ed434eaaa7406053faf51d2109d60553172c2b014c7ea17c2fcac1f","sha256:4609fb729ec4495bffec7a021c9c235a81b7ae6042e4e42fe86df86184aafd9c"],"state_sha256":"613c084cbd437bd56282ede2a6667c3dcc364b495ffe17869551bb8095af9009"}