{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:ZGPSCEC3RWXYBX7OLHLIWT7VZC","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":"aca53f0423ad7aff21f4c4a364682209af3e34e3a63353175536ea15ee61fe32","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-01-22T11:35:58Z","title_canon_sha256":"a152f616807c13d042585eb17b788330bab60effec8dd1fe115266108b9ff3da"},"schema_version":"1.0","source":{"id":"2001.07966","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2001.07966","created_at":"2026-07-05T00:35:11Z"},{"alias_kind":"arxiv_version","alias_value":"2001.07966v2","created_at":"2026-07-05T00:35:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2001.07966","created_at":"2026-07-05T00:35:11Z"},{"alias_kind":"pith_short_12","alias_value":"ZGPSCEC3RWXY","created_at":"2026-07-05T00:35:11Z"},{"alias_kind":"pith_short_16","alias_value":"ZGPSCEC3RWXYBX7O","created_at":"2026-07-05T00:35:11Z"},{"alias_kind":"pith_short_8","alias_value":"ZGPSCEC3","created_at":"2026-07-05T00:35:11Z"}],"graph_snapshots":[{"event_id":"sha256:5a8ae17ce730d65bb3c85c11fe98275c54a60ded8346a972e43a1f0796b67816","target":"graph","created_at":"2026-07-05T00:35:11Z","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/2001.07966/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Arun Sacheti, Di Qi, Edward Cui, Jia Song, Lin Su, Taroon Bharti","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-01-22T11:35:58Z","title":"ImageBERT: Cross-modal Pre-training with Large-scale Weak-supervised Image-Text Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2001.07966","kind":"arxiv","version":2},"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:aba9058c2756cb99519b2bca10ab0f150f6c66bd4c52bcdda806fde18c0d6efd","target":"record","created_at":"2026-07-05T00:35:11Z","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":"aca53f0423ad7aff21f4c4a364682209af3e34e3a63353175536ea15ee61fe32","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-01-22T11:35:58Z","title_canon_sha256":"a152f616807c13d042585eb17b788330bab60effec8dd1fe115266108b9ff3da"},"schema_version":"1.0","source":{"id":"2001.07966","kind":"arxiv","version":2}},"canonical_sha256":"c99f21105b8daf80dfee59d68b4ff5c8a751e25e3f0d7fe3d4ba37ceaeb69dd1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c99f21105b8daf80dfee59d68b4ff5c8a751e25e3f0d7fe3d4ba37ceaeb69dd1","first_computed_at":"2026-07-05T00:35:11.094671Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:35:11.094671Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3tEb1Z+Jhj7IFv9o2UvlHtySLk1gtLHqNwpaatHx1f1v7+a5Zpg+OfWGQeudB13kX8nauN9rpuS0w8d1Of+TAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T00:35:11.095155Z","signed_message":"canonical_sha256_bytes"},"source_id":"2001.07966","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:aba9058c2756cb99519b2bca10ab0f150f6c66bd4c52bcdda806fde18c0d6efd","sha256:5a8ae17ce730d65bb3c85c11fe98275c54a60ded8346a972e43a1f0796b67816"],"state_sha256":"3047ec913fa1ff5a05bd0b7d80606260d961a51edf31053b7847ef57941b37e5"}