{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:FNN2J2LG66LR5EBXOB4DSCZMXL","short_pith_number":"pith:FNN2J2LG","schema_version":"1.0","canonical_sha256":"2b5ba4e966f7971e90377078390b2cbac139b214134ae3ec4fc2447f1b759758","source":{"kind":"arxiv","id":"2103.01913","version":2},"attestation_state":"computed","paper":{"title":"WIT: Wikipedia-based Image Text Dataset for Multimodal Multilingual Machine Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.IR"],"primary_cat":"cs.CV","authors_text":"Jiecao Chen, Karthik Raman, Krishna Srinivasan, Marc Najork, Michael Bendersky","submitted_at":"2021-03-02T18:13:54Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2103.01913","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-03-02T18:13:54Z","cross_cats_sorted":["cs.CL","cs.IR"],"title_canon_sha256":"ae72b73986b4ec597efd79a96765a4696a42ee1b7b4a91c9ba34e5e3df5e8f8c","abstract_canon_sha256":"36b2c1d338a1fe158f0a8f368bd3a8e6b15c081a04826361b0c8693ce419a2da"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:43:07.206559Z","signature_b64":"VQgFIxJFJKn/+NpcqZdJaSfuEYITH4UIOBjhe7MXeOM5t2smUB7ldnlV+5be0dy/lO8obLaz5oUWOdH06xQPBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2b5ba4e966f7971e90377078390b2cbac139b214134ae3ec4fc2447f1b759758","last_reissued_at":"2026-07-05T05:43:07.206052Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:43:07.206052Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"WIT: Wikipedia-based Image Text Dataset for Multimodal Multilingual Machine Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.IR"],"primary_cat":"cs.CV","authors_text":"Jiecao Chen, Karthik Raman, Krishna Srinivasan, Marc Najork, Michael Bendersky","submitted_at":"2021-03-02T18:13:54Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.01913","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/2103.01913/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2103.01913","created_at":"2026-07-05T05:43:07.206112+00:00"},{"alias_kind":"arxiv_version","alias_value":"2103.01913v2","created_at":"2026-07-05T05:43:07.206112+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.01913","created_at":"2026-07-05T05:43:07.206112+00:00"},{"alias_kind":"pith_short_12","alias_value":"FNN2J2LG66LR","created_at":"2026-07-05T05:43:07.206112+00:00"},{"alias_kind":"pith_short_16","alias_value":"FNN2J2LG66LR5EBX","created_at":"2026-07-05T05:43:07.206112+00:00"},{"alias_kind":"pith_short_8","alias_value":"FNN2J2LG","created_at":"2026-07-05T05:43:07.206112+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.26794","citing_title":"ReasonCLIP-58M: Visually Grounded Commonsense Reasoning Supervision for CLIP","ref_index":77,"is_internal_anchor":false},{"citing_arxiv_id":"2303.15343","citing_title":"Sigmoid Loss for Language Image Pre-Training","ref_index":41,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FNN2J2LG66LR5EBXOB4DSCZMXL","json":"https://pith.science/pith/FNN2J2LG66LR5EBXOB4DSCZMXL.json","graph_json":"https://pith.science/api/pith-number/FNN2J2LG66LR5EBXOB4DSCZMXL/graph.json","events_json":"https://pith.science/api/pith-number/FNN2J2LG66LR5EBXOB4DSCZMXL/events.json","paper":"https://pith.science/paper/FNN2J2LG"},"agent_actions":{"view_html":"https://pith.science/pith/FNN2J2LG66LR5EBXOB4DSCZMXL","download_json":"https://pith.science/pith/FNN2J2LG66LR5EBXOB4DSCZMXL.json","view_paper":"https://pith.science/paper/FNN2J2LG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2103.01913&json=true","fetch_graph":"https://pith.science/api/pith-number/FNN2J2LG66LR5EBXOB4DSCZMXL/graph.json","fetch_events":"https://pith.science/api/pith-number/FNN2J2LG66LR5EBXOB4DSCZMXL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FNN2J2LG66LR5EBXOB4DSCZMXL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FNN2J2LG66LR5EBXOB4DSCZMXL/action/storage_attestation","attest_author":"https://pith.science/pith/FNN2J2LG66LR5EBXOB4DSCZMXL/action/author_attestation","sign_citation":"https://pith.science/pith/FNN2J2LG66LR5EBXOB4DSCZMXL/action/citation_signature","submit_replication":"https://pith.science/pith/FNN2J2LG66LR5EBXOB4DSCZMXL/action/replication_record"}},"created_at":"2026-07-05T05:43:07.206112+00:00","updated_at":"2026-07-05T05:43:07.206112+00:00"}