{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:PEF6GYZSXEFOVCQBD24G3XKJFJ","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":"bc86dd252dc8ed241dea637e6d294b77731074e7e266cf6859635f46344754c4","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-09-24T17:17:26Z","title_canon_sha256":"40f262b6130f4bd7b652b9b0d04cdfa8b85fff68364a2e0c39c53ea73ece774d"},"schema_version":"1.0","source":{"id":"1909.11059","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1909.11059","created_at":"2026-07-05T00:23:51Z"},{"alias_kind":"arxiv_version","alias_value":"1909.11059v3","created_at":"2026-07-05T00:23:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.11059","created_at":"2026-07-05T00:23:51Z"},{"alias_kind":"pith_short_12","alias_value":"PEF6GYZSXEFO","created_at":"2026-07-05T00:23:51Z"},{"alias_kind":"pith_short_16","alias_value":"PEF6GYZSXEFOVCQB","created_at":"2026-07-05T00:23:51Z"},{"alias_kind":"pith_short_8","alias_value":"PEF6GYZS","created_at":"2026-07-05T00:23:51Z"}],"graph_snapshots":[{"event_id":"sha256:bd6624515e12aa5b23f47f5b082860428b498eaca52a8cce1307b3d0bfb04a76","target":"graph","created_at":"2026-07-05T00:23:51Z","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/1909.11059/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper presents a unified Vision-Language Pre-training (VLP) model. The model is unified in that (1) it can be fine-tuned for either vision-language generation (e.g., image captioning) or understanding (e.g., visual question answering) tasks, and (2) it uses a shared multi-layer transformer network for both encoding and decoding, which differs from many existing methods where the encoder and decoder are implemented using separate models. The unified VLP model is pre-trained on a large amount of image-text pairs using the unsupervised learning objectives of two tasks: bidirectional and sequ","authors_text":"Hamid Palangi, Houdong Hu, Jason J. Corso, Jianfeng Gao, Lei Zhang, Luowei Zhou","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-09-24T17:17:26Z","title":"Unified Vision-Language Pre-Training for Image Captioning and VQA"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.11059","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:af6d9387eee58b6ccfc418015d6586caeb046d29a67abfc1cddea89b483387f4","target":"record","created_at":"2026-07-05T00:23:51Z","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":"bc86dd252dc8ed241dea637e6d294b77731074e7e266cf6859635f46344754c4","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-09-24T17:17:26Z","title_canon_sha256":"40f262b6130f4bd7b652b9b0d04cdfa8b85fff68364a2e0c39c53ea73ece774d"},"schema_version":"1.0","source":{"id":"1909.11059","kind":"arxiv","version":3}},"canonical_sha256":"790be36332b90aea8a011eb86ddd492a549cbd25d00bea6265605ce0846240f2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"790be36332b90aea8a011eb86ddd492a549cbd25d00bea6265605ce0846240f2","first_computed_at":"2026-07-05T00:23:51.326420Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:23:51.326420Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fJkFZNVQYUvM08afr9wEBu/XAEtKAWaN9vZHlOKtShnfqPb4gXhKQ0jjU9rD4M/4ygkeV0HszRY7H6SnpZbLDg==","signature_status":"signed_v1","signed_at":"2026-07-05T00:23:51.326924Z","signed_message":"canonical_sha256_bytes"},"source_id":"1909.11059","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:af6d9387eee58b6ccfc418015d6586caeb046d29a67abfc1cddea89b483387f4","sha256:bd6624515e12aa5b23f47f5b082860428b498eaca52a8cce1307b3d0bfb04a76"],"state_sha256":"1f60f6f36f24e71ca474fe154e6bf6227347e9f1a740d9f547f807759a406d0b"}