{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:KSYOKW2VMRBY2EI2SVOXIFF2A6","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":"305ce75c0d8fec3b1da7810c645aa079e8ecc92cf0f13d5dad98e52da2063bcb","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-05-24T11:52:06Z","title_canon_sha256":"7b02890c0c32fac2d38ef4f92687567a2128df33add8122f41d3644be417fee3"},"schema_version":"1.0","source":{"id":"2205.12005","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.12005","created_at":"2026-07-05T06:27:39Z"},{"alias_kind":"arxiv_version","alias_value":"2205.12005v2","created_at":"2026-07-05T06:27:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.12005","created_at":"2026-07-05T06:27:39Z"},{"alias_kind":"pith_short_12","alias_value":"KSYOKW2VMRBY","created_at":"2026-07-05T06:27:39Z"},{"alias_kind":"pith_short_16","alias_value":"KSYOKW2VMRBY2EI2","created_at":"2026-07-05T06:27:39Z"},{"alias_kind":"pith_short_8","alias_value":"KSYOKW2V","created_at":"2026-07-05T06:27:39Z"}],"graph_snapshots":[{"event_id":"sha256:52d8de5a0be49a1cbcd86e631d62d55b7162136a6581cfd56f739e60a67b15f9","target":"graph","created_at":"2026-07-05T06:27:39Z","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/2205.12005/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","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","cross_cats":["cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-05-24T11:52:06Z","title":"mPLUG: Effective and Efficient Vision-Language Learning by Cross-modal Skip-connections"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.12005","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":"sha256:05e7ee151a41cba6a56cbbb1f875ec3d7740c90df27f16d81624099e066a55f2","target":"record","created_at":"2026-07-05T06:27:39Z","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":"305ce75c0d8fec3b1da7810c645aa079e8ecc92cf0f13d5dad98e52da2063bcb","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-05-24T11:52:06Z","title_canon_sha256":"7b02890c0c32fac2d38ef4f92687567a2128df33add8122f41d3644be417fee3"},"schema_version":"1.0","source":{"id":"2205.12005","kind":"arxiv","version":2}},"canonical_sha256":"54b0e55b5564438d111a955d7414ba07ae2259deb453120e32d61905651f5aba","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"54b0e55b5564438d111a955d7414ba07ae2259deb453120e32d61905651f5aba","first_computed_at":"2026-07-05T06:27:39.855959Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:27:39.855959Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yOOa6STydXFpTxDKyAxBQgrHp7OZx82K5YQxULeFXDqwl3myIVlfU6JNJmLd4PDMWrUEx7/AFnF6r2QXLQgtCg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:27:39.856376Z","signed_message":"canonical_sha256_bytes"},"source_id":"2205.12005","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:05e7ee151a41cba6a56cbbb1f875ec3d7740c90df27f16d81624099e066a55f2","sha256:52d8de5a0be49a1cbcd86e631d62d55b7162136a6581cfd56f739e60a67b15f9"],"state_sha256":"73c6ca0e3a344ec37591e3e2159c12bfe02f3e189709e6c95585336c4718945a"}