{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:O5TNFI5A3MB5DGINSUCW37SKGW","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":"2bd89e9e51a5bf34349b83d54e5e7ca972fe56cc6f51115e68aed42b7e9eeaaf","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-08-19T14:39:18Z","title_canon_sha256":"8842cf62e15670106f625b8f28ed542565289a051e6027f5ce0d1d6bd213ef7a"},"schema_version":"1.0","source":{"id":"2208.09374","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2208.09374","created_at":"2026-07-05T04:49:59Z"},{"alias_kind":"arxiv_version","alias_value":"2208.09374v1","created_at":"2026-07-05T04:49:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.09374","created_at":"2026-07-05T04:49:59Z"},{"alias_kind":"pith_short_12","alias_value":"O5TNFI5A3MB5","created_at":"2026-07-05T04:49:59Z"},{"alias_kind":"pith_short_16","alias_value":"O5TNFI5A3MB5DGIN","created_at":"2026-07-05T04:49:59Z"},{"alias_kind":"pith_short_8","alias_value":"O5TNFI5A","created_at":"2026-07-05T04:49:59Z"}],"graph_snapshots":[{"event_id":"sha256:abb58329b315a3cc98e36c8782152cc956582170881c867709b22cdc5e61f33d","target":"graph","created_at":"2026-07-05T04:49:59Z","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/2208.09374/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Image and language modeling is of crucial importance for vision-language pre-training (VLP), which aims to learn multi-modal representations from large-scale paired image-text data. However, we observe that most existing VLP methods focus on modeling the interactions between image and text features while neglecting the information disparity between image and text, thus suffering from focal bias. To address this problem, we propose a vision-language masked autoencoder framework (VLMAE). VLMAE employs visual generative learning, facilitating the model to acquire fine-grained and unbiased feature","authors_text":"Bo Ren, Chen Wu, Ruizhi Qiao, Sunan He, Taian Guo, Tao Dai, Xiujun Shu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-08-19T14:39:18Z","title":"VLMAE: Vision-Language Masked Autoencoder"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.09374","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":"sha256:24c00678ee1135a283c90649f55e572381d0b5817ee260f2a01408036af01f13","target":"record","created_at":"2026-07-05T04:49:59Z","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":"2bd89e9e51a5bf34349b83d54e5e7ca972fe56cc6f51115e68aed42b7e9eeaaf","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-08-19T14:39:18Z","title_canon_sha256":"8842cf62e15670106f625b8f28ed542565289a051e6027f5ce0d1d6bd213ef7a"},"schema_version":"1.0","source":{"id":"2208.09374","kind":"arxiv","version":1}},"canonical_sha256":"7766d2a3a0db03d1990d95056dfe4a3594ff630e1cd6e6daf2ea28aa44203c1b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7766d2a3a0db03d1990d95056dfe4a3594ff630e1cd6e6daf2ea28aa44203c1b","first_computed_at":"2026-07-05T04:49:59.280729Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:49:59.280729Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"O+zbJylU26YiwkvlFMQjOUsHQFE8NhoS7/1RuM9GgEb06qo/CfKOqmLOi4klBCI2GMg49Mw4RI2SYd1OEKIpDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:49:59.281075Z","signed_message":"canonical_sha256_bytes"},"source_id":"2208.09374","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:24c00678ee1135a283c90649f55e572381d0b5817ee260f2a01408036af01f13","sha256:abb58329b315a3cc98e36c8782152cc956582170881c867709b22cdc5e61f33d"],"state_sha256":"569d0c164db8991ced699cf35cf1cec2d2fb6d0e3744f63d4b6e395a2fcd74de"}