{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:KSYOKW2VMRBY2EI2SVOXIFF2A6","short_pith_number":"pith:KSYOKW2V","schema_version":"1.0","canonical_sha256":"54b0e55b5564438d111a955d7414ba07ae2259deb453120e32d61905651f5aba","source":{"kind":"arxiv","id":"2205.12005","version":2},"attestation_state":"computed","paper":{"title":"mPLUG: Effective and Efficient Vision-Language Learning by Cross-modal Skip-connections","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Bin Bi, Chenliang Li, Fei Huang, Guohai Xu, Haiyang Xu, Hehong Chen, Jiabo Ye, Jingren Zhou, Ji Zhang, Junfeng Tian, Luo Si, Ming Yan, Songfang Huang, Wei Wang, Zheng Cao","submitted_at":"2022-05-24T11:52:06Z","abstract_excerpt":"Large-scale pretrained foundation models have been an emerging paradigm for building artificial intelligence (AI) systems, which can be quickly adapted to a wide range of downstream tasks. This paper presents mPLUG, a new vision-language foundation model for both cross-modal understanding and generation. Most existing pre-trained models suffer from the problems of low computational efficiency and information asymmetry brought by the long visual sequence in cross-modal alignment. To address these problems, mPLUG introduces an effective and efficient vision-language architecture with novel cross"},"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":"2205.12005","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-05-24T11:52:06Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"7b02890c0c32fac2d38ef4f92687567a2128df33add8122f41d3644be417fee3","abstract_canon_sha256":"305ce75c0d8fec3b1da7810c645aa079e8ecc92cf0f13d5dad98e52da2063bcb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:27:39.856376Z","signature_b64":"yOOa6STydXFpTxDKyAxBQgrHp7OZx82K5YQxULeFXDqwl3myIVlfU6JNJmLd4PDMWrUEx7/AFnF6r2QXLQgtCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"54b0e55b5564438d111a955d7414ba07ae2259deb453120e32d61905651f5aba","last_reissued_at":"2026-07-05T06:27:39.855959Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:27:39.855959Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"mPLUG: Effective and Efficient Vision-Language Learning by Cross-modal Skip-connections","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Bin Bi, Chenliang Li, Fei Huang, Guohai Xu, Haiyang Xu, Hehong Chen, Jiabo Ye, Jingren Zhou, Ji Zhang, Junfeng Tian, Luo Si, Ming Yan, Songfang Huang, Wei Wang, Zheng Cao","submitted_at":"2022-05-24T11:52:06Z","abstract_excerpt":"Large-scale pretrained foundation models have been an emerging paradigm for building artificial intelligence (AI) systems, which can be quickly adapted to a wide range of downstream tasks. This paper presents mPLUG, a new vision-language foundation model for both cross-modal understanding and generation. Most existing pre-trained models suffer from the problems of low computational efficiency and information asymmetry brought by the long visual sequence in cross-modal alignment. To address these problems, mPLUG introduces an effective and efficient vision-language architecture with novel cross"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.12005","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/2205.12005/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":"2205.12005","created_at":"2026-07-05T06:27:39.856015+00:00"},{"alias_kind":"arxiv_version","alias_value":"2205.12005v2","created_at":"2026-07-05T06:27:39.856015+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.12005","created_at":"2026-07-05T06:27:39.856015+00:00"},{"alias_kind":"pith_short_12","alias_value":"KSYOKW2VMRBY","created_at":"2026-07-05T06:27:39.856015+00:00"},{"alias_kind":"pith_short_16","alias_value":"KSYOKW2VMRBY2EI2","created_at":"2026-07-05T06:27:39.856015+00:00"},{"alias_kind":"pith_short_8","alias_value":"KSYOKW2V","created_at":"2026-07-05T06:27:39.856015+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.24058","citing_title":"VisChronos: Revolutionizing Image Captioning Through Real-Life Events","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2412.08110","citing_title":"The ART of Composition: Attention-Regularized Training for Compositional Visual Grounding","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2505.12217","citing_title":"HyperCap: Hyperspectral Land Cover Captioning Dataset for Vision Language Models","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2510.20093","citing_title":"StableSketcher: Enhancing Diffusion Model for Pixel-based Sketch Generation via Visual Question Answering Feedback","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2205.14100","citing_title":"GIT: A Generative Image-to-text Transformer for Vision and Language","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2308.01390","citing_title":"OpenFlamingo: An Open-Source Framework for Training Large Autoregressive Vision-Language Models","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2403.05135","citing_title":"ELLA: Equip Diffusion Models with LLM for Enhanced Semantic Alignment","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17889","citing_title":"AeroRAG: Structured Multimodal Retrieval-Augmented LLM for Fine-Grained Aerial Visual Reasoning","ref_index":43,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KSYOKW2VMRBY2EI2SVOXIFF2A6","json":"https://pith.science/pith/KSYOKW2VMRBY2EI2SVOXIFF2A6.json","graph_json":"https://pith.science/api/pith-number/KSYOKW2VMRBY2EI2SVOXIFF2A6/graph.json","events_json":"https://pith.science/api/pith-number/KSYOKW2VMRBY2EI2SVOXIFF2A6/events.json","paper":"https://pith.science/paper/KSYOKW2V"},"agent_actions":{"view_html":"https://pith.science/pith/KSYOKW2VMRBY2EI2SVOXIFF2A6","download_json":"https://pith.science/pith/KSYOKW2VMRBY2EI2SVOXIFF2A6.json","view_paper":"https://pith.science/paper/KSYOKW2V","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2205.12005&json=true","fetch_graph":"https://pith.science/api/pith-number/KSYOKW2VMRBY2EI2SVOXIFF2A6/graph.json","fetch_events":"https://pith.science/api/pith-number/KSYOKW2VMRBY2EI2SVOXIFF2A6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KSYOKW2VMRBY2EI2SVOXIFF2A6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KSYOKW2VMRBY2EI2SVOXIFF2A6/action/storage_attestation","attest_author":"https://pith.science/pith/KSYOKW2VMRBY2EI2SVOXIFF2A6/action/author_attestation","sign_citation":"https://pith.science/pith/KSYOKW2VMRBY2EI2SVOXIFF2A6/action/citation_signature","submit_replication":"https://pith.science/pith/KSYOKW2VMRBY2EI2SVOXIFF2A6/action/replication_record"}},"created_at":"2026-07-05T06:27:39.856015+00:00","updated_at":"2026-07-05T06:27:39.856015+00:00"}