{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:23XRBAGGAG7VC57CRFJHYQB53F","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":"de603d0ac8f614a537039a60c52ec4bd8d40cd9e8a11b3d4931cba4333da4818","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-09-09T16:11:11Z","title_canon_sha256":"fc04e464879ce4f4a2dc3095e76bec4fefa87ed3bc9f04f86d677291a74b6d89"},"schema_version":"1.0","source":{"id":"2209.04372","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2209.04372","created_at":"2026-07-05T04:55:58Z"},{"alias_kind":"arxiv_version","alias_value":"2209.04372v1","created_at":"2026-07-05T04:55:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.04372","created_at":"2026-07-05T04:55:58Z"},{"alias_kind":"pith_short_12","alias_value":"23XRBAGGAG7V","created_at":"2026-07-05T04:55:58Z"},{"alias_kind":"pith_short_16","alias_value":"23XRBAGGAG7VC57C","created_at":"2026-07-05T04:55:58Z"},{"alias_kind":"pith_short_8","alias_value":"23XRBAGG","created_at":"2026-07-05T04:55:58Z"}],"graph_snapshots":[{"event_id":"sha256:98ee586eea9cc9df1438fe73d8da20313e5401da7b37d091b52d4fe5859c8c73","target":"graph","created_at":"2026-07-05T04:55:58Z","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/2209.04372/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present a pre-training approach for vision and language transformer models, which is based on a mixture of diverse tasks. We explore both the use of image-text captioning data in pre-training, which does not need additional supervision, as well as object-aware strategies to pre-train the model. We evaluate the method on a number of textgenerative vision+language tasks, such as Visual Question Answering, visual entailment and captioning, and demonstrate large gains over standard pre-training methods.","authors_text":"AJ Piergiovanni, Anelia Angelova, Weicheng Kuo","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-09-09T16:11:11Z","title":"Pre-training image-language transformers for open-vocabulary tasks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.04372","kind":"arxiv","version":1},"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":"sha256:27412ee94fd4a4b2d0058e9438dabfbb0d73fbe0d50fe9e7471591094785dd02","target":"record","created_at":"2026-07-05T04:55:58Z","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":"de603d0ac8f614a537039a60c52ec4bd8d40cd9e8a11b3d4931cba4333da4818","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-09-09T16:11:11Z","title_canon_sha256":"fc04e464879ce4f4a2dc3095e76bec4fefa87ed3bc9f04f86d677291a74b6d89"},"schema_version":"1.0","source":{"id":"2209.04372","kind":"arxiv","version":1}},"canonical_sha256":"d6ef1080c601bf5177e289527c403dd95f2ef9f63c6bae58dc011aa7865b137d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d6ef1080c601bf5177e289527c403dd95f2ef9f63c6bae58dc011aa7865b137d","first_computed_at":"2026-07-05T04:55:58.879711Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:55:58.879711Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"iEkcaRxeSH4X4otl5jnkaijbuAMkPhS7ViQ/KmNKkAMyNrhVGK81yDggpHEA2XWF442EP3TjWYAOGUsFPUvTDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:55:58.880115Z","signed_message":"canonical_sha256_bytes"},"source_id":"2209.04372","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:27412ee94fd4a4b2d0058e9438dabfbb0d73fbe0d50fe9e7471591094785dd02","sha256:98ee586eea9cc9df1438fe73d8da20313e5401da7b37d091b52d4fe5859c8c73"],"state_sha256":"46ae7773ac3ec71118f917457479d4d432921aa51b170ea7686e55936f45d442"}