{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:R5NJ5PH45IHS7GKEXRJIQ7BTLJ","short_pith_number":"pith:R5NJ5PH4","schema_version":"1.0","canonical_sha256":"8f5a9ebcfcea0f2f9944bc52887c335a797eb56359b1abf04c00d6c7e20359f4","source":{"kind":"arxiv","id":"2302.00402","version":1},"attestation_state":"computed","paper":{"title":"mPLUG-2: A Modularized Multi-modal Foundation Model Across Text, Image and Video","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.MM"],"primary_cat":"cs.CV","authors_text":"Bin Bi, Chenliang Li, Fei Huang, Guohai Xu, Haiyang Xu, Jiabo Ye, Jingren Zhou, Ji Zhang, Ming Yan, Qinghao Ye, Qi Qian, Songfang Huang, Wei Wang, Yaya Shi, Yuanhong Xu","submitted_at":"2023-02-01T12:40:03Z","abstract_excerpt":"Recent years have witnessed a big convergence of language, vision, and multi-modal pretraining. In this work, we present mPLUG-2, a new unified paradigm with modularized design for multi-modal pretraining, which can benefit from modality collaboration while addressing the problem of modality entanglement. In contrast to predominant paradigms of solely relying on sequence-to-sequence generation or encoder-based instance discrimination, mPLUG-2 introduces a multi-module composition network by sharing common universal modules for modality collaboration and disentangling different modality modules"},"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":"2302.00402","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-02-01T12:40:03Z","cross_cats_sorted":["cs.CL","cs.MM"],"title_canon_sha256":"ac4cdeb542fe5d0087d00e5c2bc370bfd8608b7743a2a09181501014f33934af","abstract_canon_sha256":"c5243f27f97aea35087242b394f9b08b0ffba4d5e18dda23d78fb3318fc34c57"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:09:08.112297Z","signature_b64":"TueJjNBxiruHlb2QKMMK/QH7WLHzdVpmsB2AOySSgwTtcGOC5OXdv8cBOpbuV8NdUvRBKgZIxTXQPbePc90DAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8f5a9ebcfcea0f2f9944bc52887c335a797eb56359b1abf04c00d6c7e20359f4","last_reissued_at":"2026-07-05T06:09:08.111853Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:09:08.111853Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"mPLUG-2: A Modularized Multi-modal Foundation Model Across Text, Image and Video","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.MM"],"primary_cat":"cs.CV","authors_text":"Bin Bi, Chenliang Li, Fei Huang, Guohai Xu, Haiyang Xu, Jiabo Ye, Jingren Zhou, Ji Zhang, Ming Yan, Qinghao Ye, Qi Qian, Songfang Huang, Wei Wang, Yaya Shi, Yuanhong Xu","submitted_at":"2023-02-01T12:40:03Z","abstract_excerpt":"Recent years have witnessed a big convergence of language, vision, and multi-modal pretraining. In this work, we present mPLUG-2, a new unified paradigm with modularized design for multi-modal pretraining, which can benefit from modality collaboration while addressing the problem of modality entanglement. In contrast to predominant paradigms of solely relying on sequence-to-sequence generation or encoder-based instance discrimination, mPLUG-2 introduces a multi-module composition network by sharing common universal modules for modality collaboration and disentangling different modality modules"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.00402","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/2302.00402/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":"2302.00402","created_at":"2026-07-05T06:09:08.111910+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.00402v1","created_at":"2026-07-05T06:09:08.111910+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.00402","created_at":"2026-07-05T06:09:08.111910+00:00"},{"alias_kind":"pith_short_12","alias_value":"R5NJ5PH45IHS","created_at":"2026-07-05T06:09:08.111910+00:00"},{"alias_kind":"pith_short_16","alias_value":"R5NJ5PH45IHS7GKE","created_at":"2026-07-05T06:09:08.111910+00:00"},{"alias_kind":"pith_short_8","alias_value":"R5NJ5PH4","created_at":"2026-07-05T06:09:08.111910+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2304.14178","citing_title":"mPLUG-Owl: Modularization Empowers Large Language Models with Multimodality","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2307.06942","citing_title":"InternVid: A Large-scale Video-Text Dataset for Multimodal Understanding and Generation","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2402.17177","citing_title":"Sora: A Review on Background, Technology, Limitations, and Opportunities of Large Vision Models","ref_index":81,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/R5NJ5PH45IHS7GKEXRJIQ7BTLJ","json":"https://pith.science/pith/R5NJ5PH45IHS7GKEXRJIQ7BTLJ.json","graph_json":"https://pith.science/api/pith-number/R5NJ5PH45IHS7GKEXRJIQ7BTLJ/graph.json","events_json":"https://pith.science/api/pith-number/R5NJ5PH45IHS7GKEXRJIQ7BTLJ/events.json","paper":"https://pith.science/paper/R5NJ5PH4"},"agent_actions":{"view_html":"https://pith.science/pith/R5NJ5PH45IHS7GKEXRJIQ7BTLJ","download_json":"https://pith.science/pith/R5NJ5PH45IHS7GKEXRJIQ7BTLJ.json","view_paper":"https://pith.science/paper/R5NJ5PH4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.00402&json=true","fetch_graph":"https://pith.science/api/pith-number/R5NJ5PH45IHS7GKEXRJIQ7BTLJ/graph.json","fetch_events":"https://pith.science/api/pith-number/R5NJ5PH45IHS7GKEXRJIQ7BTLJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/R5NJ5PH45IHS7GKEXRJIQ7BTLJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/R5NJ5PH45IHS7GKEXRJIQ7BTLJ/action/storage_attestation","attest_author":"https://pith.science/pith/R5NJ5PH45IHS7GKEXRJIQ7BTLJ/action/author_attestation","sign_citation":"https://pith.science/pith/R5NJ5PH45IHS7GKEXRJIQ7BTLJ/action/citation_signature","submit_replication":"https://pith.science/pith/R5NJ5PH45IHS7GKEXRJIQ7BTLJ/action/replication_record"}},"created_at":"2026-07-05T06:09:08.111910+00:00","updated_at":"2026-07-05T06:09:08.111910+00:00"}