{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:AT6IIIBKMGQXJKXB23WLN6VKNG","short_pith_number":"pith:AT6IIIBK","canonical_record":{"source":{"id":"2304.14178","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-04-27T13:27:01Z","cross_cats_sorted":["cs.CV","cs.LG"],"title_canon_sha256":"3c5d275ad162ad38d5bf8cf676a8b0cfe0b40304c324518e72226a64d6c1fbc9","abstract_canon_sha256":"4d68b9992c87ab7c6a1e1216581044c9ca2c24d1b0c9f55e555a111729d8318e"},"schema_version":"1.0"},"canonical_sha256":"04fc84202a61a174aae1d6ecb6faaa69b77c7291d92966f229d694ee8862069a","source":{"kind":"arxiv","id":"2304.14178","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.14178","created_at":"2026-05-18T02:34:59Z"},{"alias_kind":"arxiv_version","alias_value":"2304.14178v3","created_at":"2026-05-18T02:34:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.14178","created_at":"2026-05-18T02:34:59Z"},{"alias_kind":"pith_short_12","alias_value":"AT6IIIBKMGQX","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_16","alias_value":"AT6IIIBKMGQXJKXB","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_8","alias_value":"AT6IIIBK","created_at":"2026-05-18T12:33:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:AT6IIIBKMGQXJKXB23WLN6VKNG","target":"record","payload":{"canonical_record":{"source":{"id":"2304.14178","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-04-27T13:27:01Z","cross_cats_sorted":["cs.CV","cs.LG"],"title_canon_sha256":"3c5d275ad162ad38d5bf8cf676a8b0cfe0b40304c324518e72226a64d6c1fbc9","abstract_canon_sha256":"4d68b9992c87ab7c6a1e1216581044c9ca2c24d1b0c9f55e555a111729d8318e"},"schema_version":"1.0"},"canonical_sha256":"04fc84202a61a174aae1d6ecb6faaa69b77c7291d92966f229d694ee8862069a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:34:59.992467Z","signature_b64":"HFnq1SM8xoGf9WwmoakxyIN90UdO1+7Z4IOniqgY+yM74SjQTGPTS9ciRPvXeO4zsPlKVwirk+mGG7lqvChjCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"04fc84202a61a174aae1d6ecb6faaa69b77c7291d92966f229d694ee8862069a","last_reissued_at":"2026-05-18T02:34:59.992030Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:34:59.992030Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2304.14178","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T02:34:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+DUJyUOpQuxPz6rkjDe8dpM5YDmyQAZQVFYas5Rpw5691on9XkZPUUPbhLr5jtV8k0flprexRN95gtSkNej0AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T18:45:45.781972Z"},"content_sha256":"c13872b5c569a227a936ce4a068be3616391dc9523db5a651555ff1e59a5a044","schema_version":"1.0","event_id":"sha256:c13872b5c569a227a936ce4a068be3616391dc9523db5a651555ff1e59a5a044"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:AT6IIIBKMGQXJKXB23WLN6VKNG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"mPLUG-Owl: Modularization Empowers Large Language Models with Multimodality","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"cs.CL","authors_text":"Anwen Hu, Chenliang Li, Fei Huang, Guohai Xu, Haiyang Xu, Hehong Chen, Jiabo Ye, Jingren Zhou, Ji Zhang, Junfeng Tian, Junyang Wang, Ming Yan, Pengcheng Shi, Qinghao Ye, Qi Qian, Yaya Shi, Yiyang Zhou, Yuanhong Xu","submitted_at":"2023-04-27T13:27:01Z","abstract_excerpt":"Large language models (LLMs) have demonstrated impressive zero-shot abilities on a variety of open-ended tasks, while recent research has also explored the use of LLMs for multi-modal generation. In this study, we introduce mPLUG-Owl, a novel training paradigm that equips LLMs with multi-modal abilities through modularized learning of foundation LLM, a visual knowledge module, and a visual abstractor module. This approach can support multiple modalities and facilitate diverse unimodal and multimodal abilities through modality collaboration. The training paradigm of mPLUG-Owl involves a two-sta"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.14178","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T02:34:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lpuaIKjJGkVsMHxPlKq2EK2ZAXK85TFaXUvrtttMphr5WAFyRI/X6fDXM8Ig1Uso2eeOJWo68xNInPfk/oa8DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T18:45:45.782690Z"},"content_sha256":"1149ccb686d6358ae38dd1a2049cc702e3d6a9f91ca00bf2ce0ec424331c8c30","schema_version":"1.0","event_id":"sha256:1149ccb686d6358ae38dd1a2049cc702e3d6a9f91ca00bf2ce0ec424331c8c30"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AT6IIIBKMGQXJKXB23WLN6VKNG/bundle.json","state_url":"https://pith.science/pith/AT6IIIBKMGQXJKXB23WLN6VKNG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AT6IIIBKMGQXJKXB23WLN6VKNG/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-25T18:45:45Z","links":{"resolver":"https://pith.science/pith/AT6IIIBKMGQXJKXB23WLN6VKNG","bundle":"https://pith.science/pith/AT6IIIBKMGQXJKXB23WLN6VKNG/bundle.json","state":"https://pith.science/pith/AT6IIIBKMGQXJKXB23WLN6VKNG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AT6IIIBKMGQXJKXB23WLN6VKNG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:AT6IIIBKMGQXJKXB23WLN6VKNG","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":"4d68b9992c87ab7c6a1e1216581044c9ca2c24d1b0c9f55e555a111729d8318e","cross_cats_sorted":["cs.CV","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-04-27T13:27:01Z","title_canon_sha256":"3c5d275ad162ad38d5bf8cf676a8b0cfe0b40304c324518e72226a64d6c1fbc9"},"schema_version":"1.0","source":{"id":"2304.14178","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.14178","created_at":"2026-05-18T02:34:59Z"},{"alias_kind":"arxiv_version","alias_value":"2304.14178v3","created_at":"2026-05-18T02:34:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.14178","created_at":"2026-05-18T02:34:59Z"},{"alias_kind":"pith_short_12","alias_value":"AT6IIIBKMGQX","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_16","alias_value":"AT6IIIBKMGQXJKXB","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_8","alias_value":"AT6IIIBK","created_at":"2026-05-18T12:33:33Z"}],"graph_snapshots":[{"event_id":"sha256:1149ccb686d6358ae38dd1a2049cc702e3d6a9f91ca00bf2ce0ec424331c8c30","target":"graph","created_at":"2026-05-18T02:34:59Z","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"},"paper":{"abstract_excerpt":"Large language models (LLMs) have demonstrated impressive zero-shot abilities on a variety of open-ended tasks, while recent research has also explored the use of LLMs for multi-modal generation. In this study, we introduce mPLUG-Owl, a novel training paradigm that equips LLMs with multi-modal abilities through modularized learning of foundation LLM, a visual knowledge module, and a visual abstractor module. This approach can support multiple modalities and facilitate diverse unimodal and multimodal abilities through modality collaboration. The training paradigm of mPLUG-Owl involves a two-sta","authors_text":"Anwen Hu, Chenliang Li, Fei Huang, Guohai Xu, Haiyang Xu, Hehong Chen, Jiabo Ye, Jingren Zhou, Ji Zhang, Junfeng Tian, Junyang Wang, Ming Yan, Pengcheng Shi, Qinghao Ye, Qi Qian, Yaya Shi, Yiyang Zhou, Yuanhong Xu","cross_cats":["cs.CV","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-04-27T13:27:01Z","title":"mPLUG-Owl: Modularization Empowers Large Language Models with Multimodality"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.14178","kind":"arxiv","version":3},"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:c13872b5c569a227a936ce4a068be3616391dc9523db5a651555ff1e59a5a044","target":"record","created_at":"2026-05-18T02:34:59Z","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":"4d68b9992c87ab7c6a1e1216581044c9ca2c24d1b0c9f55e555a111729d8318e","cross_cats_sorted":["cs.CV","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-04-27T13:27:01Z","title_canon_sha256":"3c5d275ad162ad38d5bf8cf676a8b0cfe0b40304c324518e72226a64d6c1fbc9"},"schema_version":"1.0","source":{"id":"2304.14178","kind":"arxiv","version":3}},"canonical_sha256":"04fc84202a61a174aae1d6ecb6faaa69b77c7291d92966f229d694ee8862069a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"04fc84202a61a174aae1d6ecb6faaa69b77c7291d92966f229d694ee8862069a","first_computed_at":"2026-05-18T02:34:59.992030Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T02:34:59.992030Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HFnq1SM8xoGf9WwmoakxyIN90UdO1+7Z4IOniqgY+yM74SjQTGPTS9ciRPvXeO4zsPlKVwirk+mGG7lqvChjCQ==","signature_status":"signed_v1","signed_at":"2026-05-18T02:34:59.992467Z","signed_message":"canonical_sha256_bytes"},"source_id":"2304.14178","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c13872b5c569a227a936ce4a068be3616391dc9523db5a651555ff1e59a5a044","sha256:1149ccb686d6358ae38dd1a2049cc702e3d6a9f91ca00bf2ce0ec424331c8c30"],"state_sha256":"f0b3f90eff6211e91e2d37e38c1324c31567ef9afd3410b39571dfbca5764133"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"d01ZD8K1b00BKyOb5dJGUvoYo7Pz3XVQfdOODLQjCa8dq8VRNI7V6TVjcldb8Pp+bZUTFJuLRegb5+QhbYPBAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T18:45:45.787635Z","bundle_sha256":"7a2396dad8c4e769cb15b5e08278b6e15403e0e8a56cbbc7964c5a2a1cb13b65"}}