{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:DZ3QIOLHRHJYC36UDVRI4HHMXQ","short_pith_number":"pith:DZ3QIOLH","canonical_record":{"source":{"id":"2308.11971","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-08-23T07:36:30Z","cross_cats_sorted":["cs.CL","cs.LG","cs.MM"],"title_canon_sha256":"5284992c58f14e54997d8cb18487c4a5da428d1dc1830597f0ebc2436c0db4b4","abstract_canon_sha256":"f4d3d43a4df6b2ced213e639433de887121a9640965a936484e0d36be2697e3b"},"schema_version":"1.0"},"canonical_sha256":"1e7704396789d3816fd41d628e1cecbc155ae707e778c1f559ce1232a53c6b2f","source":{"kind":"arxiv","id":"2308.11971","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.11971","created_at":"2026-07-05T07:50:51Z"},{"alias_kind":"arxiv_version","alias_value":"2308.11971v2","created_at":"2026-07-05T07:50:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.11971","created_at":"2026-07-05T07:50:51Z"},{"alias_kind":"pith_short_12","alias_value":"DZ3QIOLHRHJY","created_at":"2026-07-05T07:50:51Z"},{"alias_kind":"pith_short_16","alias_value":"DZ3QIOLHRHJYC36U","created_at":"2026-07-05T07:50:51Z"},{"alias_kind":"pith_short_8","alias_value":"DZ3QIOLH","created_at":"2026-07-05T07:50:51Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:DZ3QIOLHRHJYC36UDVRI4HHMXQ","target":"record","payload":{"canonical_record":{"source":{"id":"2308.11971","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-08-23T07:36:30Z","cross_cats_sorted":["cs.CL","cs.LG","cs.MM"],"title_canon_sha256":"5284992c58f14e54997d8cb18487c4a5da428d1dc1830597f0ebc2436c0db4b4","abstract_canon_sha256":"f4d3d43a4df6b2ced213e639433de887121a9640965a936484e0d36be2697e3b"},"schema_version":"1.0"},"canonical_sha256":"1e7704396789d3816fd41d628e1cecbc155ae707e778c1f559ce1232a53c6b2f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:50:51.999178Z","signature_b64":"ziUo2p9VM7jX2+L4/BofrTl1ydeLW0iRejCvMzJqFpH80W/boJIjDvRmgIolh3zNrxsF3VZ17FSOVNEZlb+0DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1e7704396789d3816fd41d628e1cecbc155ae707e778c1f559ce1232a53c6b2f","last_reissued_at":"2026-07-05T07:50:51.998766Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:50:51.998766Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2308.11971","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:50:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rlpl9wByNn2Q6KqDcbnKWlzwL0qBgIiTWwMInbHOk9TMLu+tKnHAhvGvB/RTSnYgwImmXwCo+9J0pw51JFUECQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T18:25:28.210593Z"},"content_sha256":"84cbf0b6dc7289a64450eb0337e570f267d40944dd906c951375e6c9566cf381","schema_version":"1.0","event_id":"sha256:84cbf0b6dc7289a64450eb0337e570f267d40944dd906c951375e6c9566cf381"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:DZ3QIOLHRHJYC36UDVRI4HHMXQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"EVE: Efficient Vision-Language Pre-training with Masked Prediction and Modality-Aware MoE","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.LG","cs.MM"],"primary_cat":"cs.CV","authors_text":"Dongyu Zhang, Jia Sun, Junyi Chen, Liang Lin, Longteng Guo, Shuai Shao, Zehuan Yuan","submitted_at":"2023-08-23T07:36:30Z","abstract_excerpt":"Building scalable vision-language models to learn from diverse, multimodal data remains an open challenge. In this paper, we introduce an Efficient Vision-languagE foundation model, namely EVE, which is one unified multimodal Transformer pre-trained solely by one unified pre-training task. Specifically, EVE encodes both vision and language within a shared Transformer network integrated with modality-aware sparse Mixture-of-Experts (MoE) modules, which capture modality-specific information by selectively switching to different experts. To unify pre-training tasks of vision and language, EVE per"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.11971","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/2308.11971/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:50:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aXdiTVVgR7m2IsR+8snLzb4c6ozxw3DaBFaSpAi0n3YyaVckArbJl6hnM8ywkzD2ZbfQeVnvE8hMUqqhSQj+Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T18:25:28.211103Z"},"content_sha256":"d761cc19c3df1c7ae0321727863c8e9cf0ed8514335a8d5604fe96f22cc00da8","schema_version":"1.0","event_id":"sha256:d761cc19c3df1c7ae0321727863c8e9cf0ed8514335a8d5604fe96f22cc00da8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DZ3QIOLHRHJYC36UDVRI4HHMXQ/bundle.json","state_url":"https://pith.science/pith/DZ3QIOLHRHJYC36UDVRI4HHMXQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DZ3QIOLHRHJYC36UDVRI4HHMXQ/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":"2026-08-16T18:25:28Z","links":{"resolver":"https://pith.science/pith/DZ3QIOLHRHJYC36UDVRI4HHMXQ","bundle":"https://pith.science/pith/DZ3QIOLHRHJYC36UDVRI4HHMXQ/bundle.json","state":"https://pith.science/pith/DZ3QIOLHRHJYC36UDVRI4HHMXQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DZ3QIOLHRHJYC36UDVRI4HHMXQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:DZ3QIOLHRHJYC36UDVRI4HHMXQ","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":"f4d3d43a4df6b2ced213e639433de887121a9640965a936484e0d36be2697e3b","cross_cats_sorted":["cs.CL","cs.LG","cs.MM"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-08-23T07:36:30Z","title_canon_sha256":"5284992c58f14e54997d8cb18487c4a5da428d1dc1830597f0ebc2436c0db4b4"},"schema_version":"1.0","source":{"id":"2308.11971","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.11971","created_at":"2026-07-05T07:50:51Z"},{"alias_kind":"arxiv_version","alias_value":"2308.11971v2","created_at":"2026-07-05T07:50:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.11971","created_at":"2026-07-05T07:50:51Z"},{"alias_kind":"pith_short_12","alias_value":"DZ3QIOLHRHJY","created_at":"2026-07-05T07:50:51Z"},{"alias_kind":"pith_short_16","alias_value":"DZ3QIOLHRHJYC36U","created_at":"2026-07-05T07:50:51Z"},{"alias_kind":"pith_short_8","alias_value":"DZ3QIOLH","created_at":"2026-07-05T07:50:51Z"}],"graph_snapshots":[{"event_id":"sha256:d761cc19c3df1c7ae0321727863c8e9cf0ed8514335a8d5604fe96f22cc00da8","target":"graph","created_at":"2026-07-05T07:50:51Z","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/2308.11971/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Building scalable vision-language models to learn from diverse, multimodal data remains an open challenge. In this paper, we introduce an Efficient Vision-languagE foundation model, namely EVE, which is one unified multimodal Transformer pre-trained solely by one unified pre-training task. Specifically, EVE encodes both vision and language within a shared Transformer network integrated with modality-aware sparse Mixture-of-Experts (MoE) modules, which capture modality-specific information by selectively switching to different experts. To unify pre-training tasks of vision and language, EVE per","authors_text":"Dongyu Zhang, Jia Sun, Junyi Chen, Liang Lin, Longteng Guo, Shuai Shao, Zehuan Yuan","cross_cats":["cs.CL","cs.LG","cs.MM"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-08-23T07:36:30Z","title":"EVE: Efficient Vision-Language Pre-training with Masked Prediction and Modality-Aware MoE"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.11971","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":"sha256:84cbf0b6dc7289a64450eb0337e570f267d40944dd906c951375e6c9566cf381","target":"record","created_at":"2026-07-05T07:50:51Z","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":"f4d3d43a4df6b2ced213e639433de887121a9640965a936484e0d36be2697e3b","cross_cats_sorted":["cs.CL","cs.LG","cs.MM"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-08-23T07:36:30Z","title_canon_sha256":"5284992c58f14e54997d8cb18487c4a5da428d1dc1830597f0ebc2436c0db4b4"},"schema_version":"1.0","source":{"id":"2308.11971","kind":"arxiv","version":2}},"canonical_sha256":"1e7704396789d3816fd41d628e1cecbc155ae707e778c1f559ce1232a53c6b2f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1e7704396789d3816fd41d628e1cecbc155ae707e778c1f559ce1232a53c6b2f","first_computed_at":"2026-07-05T07:50:51.998766Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:50:51.998766Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ziUo2p9VM7jX2+L4/BofrTl1ydeLW0iRejCvMzJqFpH80W/boJIjDvRmgIolh3zNrxsF3VZ17FSOVNEZlb+0DQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:50:51.999178Z","signed_message":"canonical_sha256_bytes"},"source_id":"2308.11971","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:84cbf0b6dc7289a64450eb0337e570f267d40944dd906c951375e6c9566cf381","sha256:d761cc19c3df1c7ae0321727863c8e9cf0ed8514335a8d5604fe96f22cc00da8"],"state_sha256":"22f6176e5cf97f5fd99819d9ae68935378bcea6103659af848ff528f63a68d69"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jgeNCxxlIU8NM4oCrQVAp4n3nSFNlUKFN71p2+jzOxhjt+39oKZI6S1OMw2S2JFK7+VqDxMYQJwqdUTIhDCtAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-16T18:25:28.217360Z","bundle_sha256":"fda9f4f33505e6a92e9186ebad3fc53b1f030cb312d6dcd2020357202e100f34"}}