{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:GVXXTUZZCN2CPD24T7XZRWNRAD","short_pith_number":"pith:GVXXTUZZ","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"},"canonical_sha256":"356f79d3391374278f5c9fef98d9b100e892c563e93cbfdaa246b4685e6bde98","source":{"kind":"arxiv","id":"2112.04482","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:GVXXTUZZCN2CPD24T7XZRWNRAD","target":"record","payload":{"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"},"canonical_sha256":"356f79d3391374278f5c9fef98d9b100e892c563e93cbfdaa246b4685e6bde98","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"},"source_kind":"arxiv","source_id":"2112.04482","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:09:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"T5QVC0qRcWQqFbuy19ECiaxC9yLJEG7VbdXcCSV3lmMOlBAQB9XBqolu/ckdRn04oTy47SSXZ3tY8sb5tAjQDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T04:53:19.234191Z"},"content_sha256":"9b4f47504ed434eaaa7406053faf51d2109d60553172c2b014c7ea17c2fcac1f","schema_version":"1.0","event_id":"sha256:9b4f47504ed434eaaa7406053faf51d2109d60553172c2b014c7ea17c2fcac1f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:GVXXTUZZCN2CPD24T7XZRWNRAD","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:09:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rn8nZLMsw7NrISb+vX2O7RJSRQp/GMmDy1tRqsavxx/g8ojcSDZU/z9/LhQPAOOEcfaNNA5x6JMjeifdWOa1BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T04:53:19.234699Z"},"content_sha256":"4609fb729ec4495bffec7a021c9c235a81b7ae6042e4e42fe86df86184aafd9c","schema_version":"1.0","event_id":"sha256:4609fb729ec4495bffec7a021c9c235a81b7ae6042e4e42fe86df86184aafd9c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GVXXTUZZCN2CPD24T7XZRWNRAD/bundle.json","state_url":"https://pith.science/pith/GVXXTUZZCN2CPD24T7XZRWNRAD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GVXXTUZZCN2CPD24T7XZRWNRAD/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-11T04:53:19Z","links":{"resolver":"https://pith.science/pith/GVXXTUZZCN2CPD24T7XZRWNRAD","bundle":"https://pith.science/pith/GVXXTUZZCN2CPD24T7XZRWNRAD/bundle.json","state":"https://pith.science/pith/GVXXTUZZCN2CPD24T7XZRWNRAD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GVXXTUZZCN2CPD24T7XZRWNRAD/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sq+JNtkiUGKnzcgBcUkQJicD2mUZi2nuSHR1eXXjuPyJF2knHgGgXotdb7Y+XLnaHrvCt9ml9Xwd9nBPBsr3AQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T04:53:19.238711Z","bundle_sha256":"17ab98e8fac643e088985277334d7288fe6500f96cb459e1ebe5f65fc66b6870"}}