{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:P4THYW2GJKOKMIVT346FTAT2KS","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":"ac5986bf22892dff5c126bcd08501da2ad5a06e712f138814e83888643533c03","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-05-20T13:41:12Z","title_canon_sha256":"8f3cf0239170085bbf780baef02193a6757155e44639a46360d7a01172ed974a"},"schema_version":"1.0","source":{"id":"2205.10178","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.10178","created_at":"2026-07-05T05:45:28Z"},{"alias_kind":"arxiv_version","alias_value":"2205.10178v2","created_at":"2026-07-05T05:45:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.10178","created_at":"2026-07-05T05:45:28Z"},{"alias_kind":"pith_short_12","alias_value":"P4THYW2GJKOK","created_at":"2026-07-05T05:45:28Z"},{"alias_kind":"pith_short_16","alias_value":"P4THYW2GJKOKMIVT","created_at":"2026-07-05T05:45:28Z"},{"alias_kind":"pith_short_8","alias_value":"P4THYW2G","created_at":"2026-07-05T05:45:28Z"}],"graph_snapshots":[{"event_id":"sha256:4f3ba292dbc3b39aa8536e6d90d741ba3b8c2fedfdaf7193631919a2d1a6bee5","target":"graph","created_at":"2026-07-05T05:45:28Z","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/2205.10178/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Human language is grounded on multimodal knowledge including visual knowledge like colors, sizes, and shapes. However, current large-scale pre-trained language models rely on text-only self-supervised training with massive text data, which precludes them from utilizing relevant visual information when necessary. To address this, we propose a novel pre-training framework, named VaLM, to Visually-augment text tokens with retrieved relevant images for Language Modeling. Specifically, VaLM builds on a novel latent text-image alignment method via an image retrieval module to fetch corresponding ima","authors_text":"Furu Wei, Hao Cheng, Haoyu Song, Jianfeng Gao, Li Dong, Weizhi Wang, XiaoDong Liu, Xifeng Yan","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-05-20T13:41:12Z","title":"Visually-Augmented Language Modeling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.10178","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":"sha256:9874fb96d414180479aa0bc7b6a8c8169c9eb33ab9d5891adebe0fc698f98fe6","target":"record","created_at":"2026-07-05T05:45:28Z","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":"ac5986bf22892dff5c126bcd08501da2ad5a06e712f138814e83888643533c03","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-05-20T13:41:12Z","title_canon_sha256":"8f3cf0239170085bbf780baef02193a6757155e44639a46360d7a01172ed974a"},"schema_version":"1.0","source":{"id":"2205.10178","kind":"arxiv","version":2}},"canonical_sha256":"7f267c5b464a9ca622b3df3c59827a54aedc9b05d8ad07bc1bef65c1b5b2d802","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7f267c5b464a9ca622b3df3c59827a54aedc9b05d8ad07bc1bef65c1b5b2d802","first_computed_at":"2026-07-05T05:45:28.542915Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:45:28.542915Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"T7tLZhQPAL3dc4TLR+KW8mH86T8/NDQTMsfEky2tWmBJPbGbd2pGEq21niWachhwrCAMv7/MVN80/BeaSiJhBw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:45:28.543362Z","signed_message":"canonical_sha256_bytes"},"source_id":"2205.10178","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9874fb96d414180479aa0bc7b6a8c8169c9eb33ab9d5891adebe0fc698f98fe6","sha256:4f3ba292dbc3b39aa8536e6d90d741ba3b8c2fedfdaf7193631919a2d1a6bee5"],"state_sha256":"712a54762f98851e9eb3e82ad75ac859c4008dd95727f3dd81b84f88c6dfa215"}