{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:FNN2J2LG66LR5EBXOB4DSCZMXL","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":"36b2c1d338a1fe158f0a8f368bd3a8e6b15c081a04826361b0c8693ce419a2da","cross_cats_sorted":["cs.CL","cs.IR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-03-02T18:13:54Z","title_canon_sha256":"ae72b73986b4ec597efd79a96765a4696a42ee1b7b4a91c9ba34e5e3df5e8f8c"},"schema_version":"1.0","source":{"id":"2103.01913","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.01913","created_at":"2026-07-05T05:43:07Z"},{"alias_kind":"arxiv_version","alias_value":"2103.01913v2","created_at":"2026-07-05T05:43:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.01913","created_at":"2026-07-05T05:43:07Z"},{"alias_kind":"pith_short_12","alias_value":"FNN2J2LG66LR","created_at":"2026-07-05T05:43:07Z"},{"alias_kind":"pith_short_16","alias_value":"FNN2J2LG66LR5EBX","created_at":"2026-07-05T05:43:07Z"},{"alias_kind":"pith_short_8","alias_value":"FNN2J2LG","created_at":"2026-07-05T05:43:07Z"}],"graph_snapshots":[{"event_id":"sha256:482e58f8d28b0e494b9f70a14acdbdd52a31ca05194d748b02e08dfb140a4e7a","target":"graph","created_at":"2026-07-05T05:43:07Z","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/2103.01913/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The milestone improvements brought about by deep representation learning and pre-training techniques have led to large performance gains across downstream NLP, IR and Vision tasks. Multimodal modeling techniques aim to leverage large high-quality visio-linguistic datasets for learning complementary information (across image and text modalities). In this paper, we introduce the Wikipedia-based Image Text (WIT) Dataset (https://github.com/google-research-datasets/wit) to better facilitate multimodal, multilingual learning. WIT is composed of a curated set of 37.6 million entity rich image-text e","authors_text":"Jiecao Chen, Karthik Raman, Krishna Srinivasan, Marc Najork, Michael Bendersky","cross_cats":["cs.CL","cs.IR"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-03-02T18:13:54Z","title":"WIT: Wikipedia-based Image Text Dataset for Multimodal Multilingual Machine Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.01913","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":"sha256:0c976f077a553d83370a9ce395de88cb2060b8d4a1373d0e8d58c231ac77e0ef","target":"record","created_at":"2026-07-05T05:43:07Z","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":"36b2c1d338a1fe158f0a8f368bd3a8e6b15c081a04826361b0c8693ce419a2da","cross_cats_sorted":["cs.CL","cs.IR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-03-02T18:13:54Z","title_canon_sha256":"ae72b73986b4ec597efd79a96765a4696a42ee1b7b4a91c9ba34e5e3df5e8f8c"},"schema_version":"1.0","source":{"id":"2103.01913","kind":"arxiv","version":2}},"canonical_sha256":"2b5ba4e966f7971e90377078390b2cbac139b214134ae3ec4fc2447f1b759758","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2b5ba4e966f7971e90377078390b2cbac139b214134ae3ec4fc2447f1b759758","first_computed_at":"2026-07-05T05:43:07.206052Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:43:07.206052Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VQgFIxJFJKn/+NpcqZdJaSfuEYITH4UIOBjhe7MXeOM5t2smUB7ldnlV+5be0dy/lO8obLaz5oUWOdH06xQPBA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:43:07.206559Z","signed_message":"canonical_sha256_bytes"},"source_id":"2103.01913","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0c976f077a553d83370a9ce395de88cb2060b8d4a1373d0e8d58c231ac77e0ef","sha256:482e58f8d28b0e494b9f70a14acdbdd52a31ca05194d748b02e08dfb140a4e7a"],"state_sha256":"12293f691b25792110a847708a732acce482fb8619065a23c8c9b9fa790f030d"}