{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:EYC7AMD4PVEIL5QB4AJMNVGJ4O","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":"8b75898ee178dcc32e8c0e4cd975c3bce15b501f126493bcedcdf5be7b6ad372","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-08-16T17:26:56Z","title_canon_sha256":"0232eaea9da9bc971f612f41d7693105b1ec4cb9bd4380c8deed0494e4b16c65"},"schema_version":"1.0","source":{"id":"1908.06066","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1908.06066","created_at":"2026-07-05T00:23:23Z"},{"alias_kind":"arxiv_version","alias_value":"1908.06066v3","created_at":"2026-07-05T00:23:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.06066","created_at":"2026-07-05T00:23:23Z"},{"alias_kind":"pith_short_12","alias_value":"EYC7AMD4PVEI","created_at":"2026-07-05T00:23:23Z"},{"alias_kind":"pith_short_16","alias_value":"EYC7AMD4PVEIL5QB","created_at":"2026-07-05T00:23:23Z"},{"alias_kind":"pith_short_8","alias_value":"EYC7AMD4","created_at":"2026-07-05T00:23:23Z"}],"graph_snapshots":[{"event_id":"sha256:24e01b9805bb95bc80d794b22cd047a5731a7803970f3b06f539e0925e48daab","target":"graph","created_at":"2026-07-05T00:23:23Z","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/1908.06066/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose Unicoder-VL, a universal encoder that aims to learn joint representations of vision and language in a pre-training manner. Borrow ideas from cross-lingual pre-trained models, such as XLM and Unicoder, both visual and linguistic contents are fed into a multi-layer Transformer for the cross-modal pre-training, where three pre-trained tasks are employed, including Masked Language Modeling (MLM), Masked Object Classification (MOC) and Visual-linguistic Matching (VLM). The first two tasks learn context-aware representations for input tokens based on linguistic and visual contents jointly","authors_text":"Daxin Jiang, Gen Li, Ming Gong, Ming Zhou, Nan Duan, Yuejian Fang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-08-16T17:26:56Z","title":"Unicoder-VL: A Universal Encoder for Vision and Language by Cross-modal Pre-training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.06066","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":"sha256:2d5d857f44b0b2ae28eb25f7c29a566bf48532b0b04a4d5bb911873f791b054c","target":"record","created_at":"2026-07-05T00:23:23Z","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":"8b75898ee178dcc32e8c0e4cd975c3bce15b501f126493bcedcdf5be7b6ad372","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-08-16T17:26:56Z","title_canon_sha256":"0232eaea9da9bc971f612f41d7693105b1ec4cb9bd4380c8deed0494e4b16c65"},"schema_version":"1.0","source":{"id":"1908.06066","kind":"arxiv","version":3}},"canonical_sha256":"2605f0307c7d4885f601e012c6d4c9e3981902e402c25584b0509f24a8992ad1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2605f0307c7d4885f601e012c6d4c9e3981902e402c25584b0509f24a8992ad1","first_computed_at":"2026-07-05T00:23:23.655665Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:23:23.655665Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DWSlAIKJMHudGE1D0ExmK4nzzKWubLfuhCG/vKtAzBFgUeqzm0ywsMO5zEPR55d+bUjGgWVkZkUN+ijSnkEZDw==","signature_status":"signed_v1","signed_at":"2026-07-05T00:23:23.656290Z","signed_message":"canonical_sha256_bytes"},"source_id":"1908.06066","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2d5d857f44b0b2ae28eb25f7c29a566bf48532b0b04a4d5bb911873f791b054c","sha256:24e01b9805bb95bc80d794b22cd047a5731a7803970f3b06f539e0925e48daab"],"state_sha256":"6403c52ad2a694704ce94755f1a7478fb9471dba8b6ed1d0a179a171dfb46874"}