{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:ZGPSCEC3RWXYBX7OLHLIWT7VZC","short_pith_number":"pith:ZGPSCEC3","schema_version":"1.0","canonical_sha256":"c99f21105b8daf80dfee59d68b4ff5c8a751e25e3f0d7fe3d4ba37ceaeb69dd1","source":{"kind":"arxiv","id":"2001.07966","version":2},"attestation_state":"computed","paper":{"title":"ImageBERT: Cross-modal Pre-training with Large-scale Weak-supervised Image-Text Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Arun Sacheti, Di Qi, Edward Cui, Jia Song, Lin Su, Taroon Bharti","submitted_at":"2020-01-22T11:35:58Z","abstract_excerpt":"In this paper, we introduce a new vision-language pre-trained model -- ImageBERT -- for image-text joint embedding. Our model is a Transformer-based model, which takes different modalities as input and models the relationship between them. The model is pre-trained on four tasks simultaneously: Masked Language Modeling (MLM), Masked Object Classification (MOC), Masked Region Feature Regression (MRFR), and Image Text Matching (ITM). To further enhance the pre-training quality, we have collected a Large-scale weAk-supervised Image-Text (LAIT) dataset from Web. We first pre-train the model on this"},"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":"2001.07966","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-01-22T11:35:58Z","cross_cats_sorted":[],"title_canon_sha256":"a152f616807c13d042585eb17b788330bab60effec8dd1fe115266108b9ff3da","abstract_canon_sha256":"aca53f0423ad7aff21f4c4a364682209af3e34e3a63353175536ea15ee61fe32"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:35:11.095155Z","signature_b64":"3tEb1Z+Jhj7IFv9o2UvlHtySLk1gtLHqNwpaatHx1f1v7+a5Zpg+OfWGQeudB13kX8nauN9rpuS0w8d1Of+TAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c99f21105b8daf80dfee59d68b4ff5c8a751e25e3f0d7fe3d4ba37ceaeb69dd1","last_reissued_at":"2026-07-05T00:35:11.094671Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:35:11.094671Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ImageBERT: Cross-modal Pre-training with Large-scale Weak-supervised Image-Text Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Arun Sacheti, Di Qi, Edward Cui, Jia Song, Lin Su, Taroon Bharti","submitted_at":"2020-01-22T11:35:58Z","abstract_excerpt":"In this paper, we introduce a new vision-language pre-trained model -- ImageBERT -- for image-text joint embedding. Our model is a Transformer-based model, which takes different modalities as input and models the relationship between them. The model is pre-trained on four tasks simultaneously: Masked Language Modeling (MLM), Masked Object Classification (MOC), Masked Region Feature Regression (MRFR), and Image Text Matching (ITM). To further enhance the pre-training quality, we have collected a Large-scale weAk-supervised Image-Text (LAIT) dataset from Web. We first pre-train the model on this"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2001.07966","kind":"arxiv","version":2},"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/2001.07966/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":"2001.07966","created_at":"2026-07-05T00:35:11.094730+00:00"},{"alias_kind":"arxiv_version","alias_value":"2001.07966v2","created_at":"2026-07-05T00:35:11.094730+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2001.07966","created_at":"2026-07-05T00:35:11.094730+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZGPSCEC3RWXY","created_at":"2026-07-05T00:35:11.094730+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZGPSCEC3RWXYBX7O","created_at":"2026-07-05T00:35:11.094730+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZGPSCEC3","created_at":"2026-07-05T00:35:11.094730+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2111.11432","citing_title":"Florence: A New Foundation Model for Computer Vision","ref_index":16,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZGPSCEC3RWXYBX7OLHLIWT7VZC","json":"https://pith.science/pith/ZGPSCEC3RWXYBX7OLHLIWT7VZC.json","graph_json":"https://pith.science/api/pith-number/ZGPSCEC3RWXYBX7OLHLIWT7VZC/graph.json","events_json":"https://pith.science/api/pith-number/ZGPSCEC3RWXYBX7OLHLIWT7VZC/events.json","paper":"https://pith.science/paper/ZGPSCEC3"},"agent_actions":{"view_html":"https://pith.science/pith/ZGPSCEC3RWXYBX7OLHLIWT7VZC","download_json":"https://pith.science/pith/ZGPSCEC3RWXYBX7OLHLIWT7VZC.json","view_paper":"https://pith.science/paper/ZGPSCEC3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2001.07966&json=true","fetch_graph":"https://pith.science/api/pith-number/ZGPSCEC3RWXYBX7OLHLIWT7VZC/graph.json","fetch_events":"https://pith.science/api/pith-number/ZGPSCEC3RWXYBX7OLHLIWT7VZC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZGPSCEC3RWXYBX7OLHLIWT7VZC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZGPSCEC3RWXYBX7OLHLIWT7VZC/action/storage_attestation","attest_author":"https://pith.science/pith/ZGPSCEC3RWXYBX7OLHLIWT7VZC/action/author_attestation","sign_citation":"https://pith.science/pith/ZGPSCEC3RWXYBX7OLHLIWT7VZC/action/citation_signature","submit_replication":"https://pith.science/pith/ZGPSCEC3RWXYBX7OLHLIWT7VZC/action/replication_record"}},"created_at":"2026-07-05T00:35:11.094730+00:00","updated_at":"2026-07-05T00:35:11.094730+00:00"}