{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:6Y3BUXWB5KIPOF2G7EKGWVIOGL","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":"5bf5074fb4cc9f5f6c5291acf32fa1d598b6076ff294857234462a78561bb5dd","cross_cats_sorted":["cs.AI","cs.CV","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-10-14T02:11:51Z","title_canon_sha256":"cc6151f94026a6b83cc56f7254207a988631fe562ec2b30a3826a1e1c666ab64"},"schema_version":"1.0","source":{"id":"2010.06775","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2010.06775","created_at":"2026-07-05T01:42:59Z"},{"alias_kind":"arxiv_version","alias_value":"2010.06775v1","created_at":"2026-07-05T01:42:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.06775","created_at":"2026-07-05T01:42:59Z"},{"alias_kind":"pith_short_12","alias_value":"6Y3BUXWB5KIP","created_at":"2026-07-05T01:42:59Z"},{"alias_kind":"pith_short_16","alias_value":"6Y3BUXWB5KIPOF2G","created_at":"2026-07-05T01:42:59Z"},{"alias_kind":"pith_short_8","alias_value":"6Y3BUXWB","created_at":"2026-07-05T01:42:59Z"}],"graph_snapshots":[{"event_id":"sha256:6bc935d7afbd2fb657fce006cef88840162b4dfe6be0c22b30828b6ea9ffcf45","target":"graph","created_at":"2026-07-05T01:42:59Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2010.06775/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Humans learn language by listening, speaking, writing, reading, and also, via interaction with the multimodal real world. Existing language pre-training frameworks show the effectiveness of text-only self-supervision while we explore the idea of a visually-supervised language model in this paper. We find that the main reason hindering this exploration is the large divergence in magnitude and distributions between the visually-grounded language datasets and pure-language corpora. Therefore, we develop a technique named \"vokenization\" that extrapolates multimodal alignments to language-only data","authors_text":"Hao Tan, Mohit Bansal","cross_cats":["cs.AI","cs.CV","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-10-14T02:11:51Z","title":"Vokenization: Improving Language Understanding with Contextualized, Visual-Grounded Supervision"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.06775","kind":"arxiv","version":1},"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:c626e648fdad3549609cf6ab44e81f9047894c5b587097ead39736be94999ee3","target":"record","created_at":"2026-07-05T01:42:59Z","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":"5bf5074fb4cc9f5f6c5291acf32fa1d598b6076ff294857234462a78561bb5dd","cross_cats_sorted":["cs.AI","cs.CV","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-10-14T02:11:51Z","title_canon_sha256":"cc6151f94026a6b83cc56f7254207a988631fe562ec2b30a3826a1e1c666ab64"},"schema_version":"1.0","source":{"id":"2010.06775","kind":"arxiv","version":1}},"canonical_sha256":"f6361a5ec1ea90f71746f9146b550e32d343742d96db229c8988641710fc7c17","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f6361a5ec1ea90f71746f9146b550e32d343742d96db229c8988641710fc7c17","first_computed_at":"2026-07-05T01:42:59.117447Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:42:59.117447Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/fsuX5CKhoFRKdOlNfWrsFjGQYBflM3zHaR1BHBTuCSmNvnt+M1M3j5+Sx6hur30ZglUbwC8mnj1pdHQVEiSAw==","signature_status":"signed_v1","signed_at":"2026-07-05T01:42:59.117850Z","signed_message":"canonical_sha256_bytes"},"source_id":"2010.06775","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c626e648fdad3549609cf6ab44e81f9047894c5b587097ead39736be94999ee3","sha256:6bc935d7afbd2fb657fce006cef88840162b4dfe6be0c22b30828b6ea9ffcf45"],"state_sha256":"0cfbb5efb5e4848ab9c8d211d250f4ac7a9bf92142831838726b8a783821411a"}