{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:FB5KP3RQ2UX22FVUOTZG2YM22F","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":"72f5add370b7d315bc42f69e8e26b65ceda0f227b28beb79a977308f7bd23a5a","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-09-25T20:02:54Z","title_canon_sha256":"547b713c219bbad9deee4a327bb7c409763c2db0e5ec86141e0813e01392bba6"},"schema_version":"1.0","source":{"id":"1909.11740","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1909.11740","created_at":"2026-07-05T01:20:12Z"},{"alias_kind":"arxiv_version","alias_value":"1909.11740v3","created_at":"2026-07-05T01:20:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.11740","created_at":"2026-07-05T01:20:12Z"},{"alias_kind":"pith_short_12","alias_value":"FB5KP3RQ2UX2","created_at":"2026-07-05T01:20:12Z"},{"alias_kind":"pith_short_16","alias_value":"FB5KP3RQ2UX22FVU","created_at":"2026-07-05T01:20:12Z"},{"alias_kind":"pith_short_8","alias_value":"FB5KP3RQ","created_at":"2026-07-05T01:20:12Z"}],"graph_snapshots":[{"event_id":"sha256:aa33e6e33a80f0d0490dac68892cd950fef7316dfd2fecbdde0e8de219addd0b","target":"graph","created_at":"2026-07-05T01:20:12Z","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/1909.11740/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Joint image-text embedding is the bedrock for most Vision-and-Language (V+L) tasks, where multimodality inputs are simultaneously processed for joint visual and textual understanding. In this paper, we introduce UNITER, a UNiversal Image-TExt Representation, learned through large-scale pre-training over four image-text datasets (COCO, Visual Genome, Conceptual Captions, and SBU Captions), which can power heterogeneous downstream V+L tasks with joint multimodal embeddings. We design four pre-training tasks: Masked Language Modeling (MLM), Masked Region Modeling (MRM, with three variants), Image","authors_text":"Ahmed El Kholy, Faisal Ahmed, Jingjing Liu, Licheng Yu, Linjie Li, Yen-Chun Chen, Yu Cheng, Zhe Gan","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-09-25T20:02:54Z","title":"UNITER: UNiversal Image-TExt Representation Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.11740","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":"sha256:55cc3aa947aebc679c3f3a9dbcfe986ff5d1c7324ba8b73eac993d5f0ca08421","target":"record","created_at":"2026-07-05T01:20:12Z","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":"72f5add370b7d315bc42f69e8e26b65ceda0f227b28beb79a977308f7bd23a5a","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-09-25T20:02:54Z","title_canon_sha256":"547b713c219bbad9deee4a327bb7c409763c2db0e5ec86141e0813e01392bba6"},"schema_version":"1.0","source":{"id":"1909.11740","kind":"arxiv","version":3}},"canonical_sha256":"287aa7ee30d52fad16b474f26d619ad156f04106ddaa25cf75783fccfccdc14f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"287aa7ee30d52fad16b474f26d619ad156f04106ddaa25cf75783fccfccdc14f","first_computed_at":"2026-07-05T01:20:12.219549Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:20:12.219549Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1PGRaWdw16Tl67CdndEM4oWKkGZtqbMIYUDOx7hkYALhd9SnOBdxso+m4FYo1Obx9H0JSuzcKCkK9ZTZ+AYDCw==","signature_status":"signed_v1","signed_at":"2026-07-05T01:20:12.220059Z","signed_message":"canonical_sha256_bytes"},"source_id":"1909.11740","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:55cc3aa947aebc679c3f3a9dbcfe986ff5d1c7324ba8b73eac993d5f0ca08421","sha256:aa33e6e33a80f0d0490dac68892cd950fef7316dfd2fecbdde0e8de219addd0b"],"state_sha256":"7803722d51ac3565a0a34849362c9cb2f3bba8918502c2606f835279717a323f"}