{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:Z7IS3I7SV55M3BB6SZB52NI3OR","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":"0e8382354aa93fdb4d05e1b5c30422151efcd34e6bbf650fbb0c236ebc69dd7d","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-06-04T03:54:29Z","title_canon_sha256":"7c1ce50475d74519a78f5e56b2146b639d1c866cf5329a2f4d4c0463a5910a50"},"schema_version":"1.0","source":{"id":"2006.02635","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.02635","created_at":"2026-07-05T02:28:16Z"},{"alias_kind":"arxiv_version","alias_value":"2006.02635v4","created_at":"2026-07-05T02:28:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.02635","created_at":"2026-07-05T02:28:16Z"},{"alias_kind":"pith_short_12","alias_value":"Z7IS3I7SV55M","created_at":"2026-07-05T02:28:16Z"},{"alias_kind":"pith_short_16","alias_value":"Z7IS3I7SV55M3BB6","created_at":"2026-07-05T02:28:16Z"},{"alias_kind":"pith_short_8","alias_value":"Z7IS3I7S","created_at":"2026-07-05T02:28:16Z"}],"graph_snapshots":[{"event_id":"sha256:23f409f7a73294ec3e92f068c861a13733f0494d7445ce1019f10aa5a162676a","target":"graph","created_at":"2026-07-05T02:28:16Z","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/2006.02635/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present M3P, a Multitask Multilingual Multimodal Pre-trained model that combines multilingual pre-training and multimodal pre-training into a unified framework via multitask pre-training. Our goal is to learn universal representations that can map objects occurred in different modalities or texts expressed in different languages into a common semantic space. In addition, to explicitly encourage fine-grained alignment between images and non-English languages, we also propose Multimodal Code-switched Training (MCT) to combine monolingual pre-training and multimodal pre-training via a code-swi","authors_text":"Dongdong Zhang, Edward Cui, Haoyang Huang, Jianfeng Gao, Lijuan Wang, Lin Su, Minheng Ni, Nan Duan, Taroon Bharti","cross_cats":["cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-06-04T03:54:29Z","title":"M3P: Learning Universal Representations via Multitask Multilingual Multimodal Pre-training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.02635","kind":"arxiv","version":4},"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:ade62867ae8cfabdc804d72eaa0b168ef32e3712fc293fd633215458d3f12fe5","target":"record","created_at":"2026-07-05T02:28:16Z","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":"0e8382354aa93fdb4d05e1b5c30422151efcd34e6bbf650fbb0c236ebc69dd7d","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-06-04T03:54:29Z","title_canon_sha256":"7c1ce50475d74519a78f5e56b2146b639d1c866cf5329a2f4d4c0463a5910a50"},"schema_version":"1.0","source":{"id":"2006.02635","kind":"arxiv","version":4}},"canonical_sha256":"cfd12da3f2af7acd843e9643dd351b7475771786ad2f2b223db6d225e3f7880e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cfd12da3f2af7acd843e9643dd351b7475771786ad2f2b223db6d225e3f7880e","first_computed_at":"2026-07-05T02:28:16.824971Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:28:16.824971Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"i2U/qxuxDUMGjUz7kvC99Mmx199pSjumJLR8Z4gWAs2i3Fl/etv+ojb0esS50pMLK9o1q34ronyBce0BUa0ICA==","signature_status":"signed_v1","signed_at":"2026-07-05T02:28:16.825368Z","signed_message":"canonical_sha256_bytes"},"source_id":"2006.02635","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ade62867ae8cfabdc804d72eaa0b168ef32e3712fc293fd633215458d3f12fe5","sha256:23f409f7a73294ec3e92f068c861a13733f0494d7445ce1019f10aa5a162676a"],"state_sha256":"e8329276cda644fab60a943870156d4a43fe67af1e94ca23f9a0593136fd827d"}