{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:23XRBAGGAG7VC57CRFJHYQB53F","short_pith_number":"pith:23XRBAGG","schema_version":"1.0","canonical_sha256":"d6ef1080c601bf5177e289527c403dd95f2ef9f63c6bae58dc011aa7865b137d","source":{"kind":"arxiv","id":"2209.04372","version":1},"attestation_state":"computed","paper":{"title":"Pre-training image-language transformers for open-vocabulary tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"AJ Piergiovanni, Anelia Angelova, Weicheng Kuo","submitted_at":"2022-09-09T16:11:11Z","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."},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2209.04372","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-09-09T16:11:11Z","cross_cats_sorted":[],"title_canon_sha256":"fc04e464879ce4f4a2dc3095e76bec4fefa87ed3bc9f04f86d677291a74b6d89","abstract_canon_sha256":"de603d0ac8f614a537039a60c52ec4bd8d40cd9e8a11b3d4931cba4333da4818"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:55:58.880115Z","signature_b64":"iEkcaRxeSH4X4otl5jnkaijbuAMkPhS7ViQ/KmNKkAMyNrhVGK81yDggpHEA2XWF442EP3TjWYAOGUsFPUvTDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d6ef1080c601bf5177e289527c403dd95f2ef9f63c6bae58dc011aa7865b137d","last_reissued_at":"2026-07-05T04:55:58.879711Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:55:58.879711Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Pre-training image-language transformers for open-vocabulary tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"AJ Piergiovanni, Anelia Angelova, Weicheng Kuo","submitted_at":"2022-09-09T16:11:11Z","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."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.04372","kind":"arxiv","version":1},"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/2209.04372/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2209.04372","created_at":"2026-07-05T04:55:58.879767+00:00"},{"alias_kind":"arxiv_version","alias_value":"2209.04372v1","created_at":"2026-07-05T04:55:58.879767+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.04372","created_at":"2026-07-05T04:55:58.879767+00:00"},{"alias_kind":"pith_short_12","alias_value":"23XRBAGGAG7V","created_at":"2026-07-05T04:55:58.879767+00:00"},{"alias_kind":"pith_short_16","alias_value":"23XRBAGGAG7VC57C","created_at":"2026-07-05T04:55:58.879767+00:00"},{"alias_kind":"pith_short_8","alias_value":"23XRBAGG","created_at":"2026-07-05T04:55:58.879767+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.19584","citing_title":"Language-Instructed Vision Embeddings for Controllable and Generalizable Perception","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2412.03555","citing_title":"PaliGemma 2: A Family of Versatile VLMs for Transfer","ref_index":76,"is_internal_anchor":false},{"citing_arxiv_id":"2407.07726","citing_title":"PaliGemma: A versatile 3B VLM for transfer","ref_index":109,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/23XRBAGGAG7VC57CRFJHYQB53F","json":"https://pith.science/pith/23XRBAGGAG7VC57CRFJHYQB53F.json","graph_json":"https://pith.science/api/pith-number/23XRBAGGAG7VC57CRFJHYQB53F/graph.json","events_json":"https://pith.science/api/pith-number/23XRBAGGAG7VC57CRFJHYQB53F/events.json","paper":"https://pith.science/paper/23XRBAGG"},"agent_actions":{"view_html":"https://pith.science/pith/23XRBAGGAG7VC57CRFJHYQB53F","download_json":"https://pith.science/pith/23XRBAGGAG7VC57CRFJHYQB53F.json","view_paper":"https://pith.science/paper/23XRBAGG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2209.04372&json=true","fetch_graph":"https://pith.science/api/pith-number/23XRBAGGAG7VC57CRFJHYQB53F/graph.json","fetch_events":"https://pith.science/api/pith-number/23XRBAGGAG7VC57CRFJHYQB53F/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/23XRBAGGAG7VC57CRFJHYQB53F/action/timestamp_anchor","attest_storage":"https://pith.science/pith/23XRBAGGAG7VC57CRFJHYQB53F/action/storage_attestation","attest_author":"https://pith.science/pith/23XRBAGGAG7VC57CRFJHYQB53F/action/author_attestation","sign_citation":"https://pith.science/pith/23XRBAGGAG7VC57CRFJHYQB53F/action/citation_signature","submit_replication":"https://pith.science/pith/23XRBAGGAG7VC57CRFJHYQB53F/action/replication_record"}},"created_at":"2026-07-05T04:55:58.879767+00:00","updated_at":"2026-07-05T04:55:58.879767+00:00"}