{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:7ZMX4MQX43AU6MXCRS273HP72A","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":"a45f8bd32ebc4991e7e063dd4ba7d0411721356c43185d291921cfe62d927af3","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-11-22T20:26:44Z","title_canon_sha256":"2db65baa3f5058b9bcb69cfb0cc36148a4a9c9417be9e02f9f798828a7fc0bd4"},"schema_version":"1.0","source":{"id":"2211.12561","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.12561","created_at":"2026-07-05T06:17:42Z"},{"alias_kind":"arxiv_version","alias_value":"2211.12561v2","created_at":"2026-07-05T06:17:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.12561","created_at":"2026-07-05T06:17:42Z"},{"alias_kind":"pith_short_12","alias_value":"7ZMX4MQX43AU","created_at":"2026-07-05T06:17:42Z"},{"alias_kind":"pith_short_16","alias_value":"7ZMX4MQX43AU6MXC","created_at":"2026-07-05T06:17:42Z"},{"alias_kind":"pith_short_8","alias_value":"7ZMX4MQX","created_at":"2026-07-05T06:17:42Z"}],"graph_snapshots":[{"event_id":"sha256:5c19000cd1c75e59e747675e9670d624742aff526f486e768e104b5a63eee323","target":"graph","created_at":"2026-07-05T06:17:42Z","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/2211.12561/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent multimodal models such as DALL-E and CM3 have achieved remarkable progress in text-to-image and image-to-text generation. However, these models store all learned knowledge (e.g., the appearance of the Eiffel Tower) in the model parameters, requiring increasingly larger models and training data to capture more knowledge. To integrate knowledge in a more scalable and modular way, we propose a retrieval-augmented multimodal model, which enables a base multimodal model (generator) to refer to relevant text and images fetched by a retriever from external memory (e.g., documents on the web). ","authors_text":"Armen Aghajanyan, Jure Leskovec, Luke Zettlemoyer, Michihiro Yasunaga, Mike Lewis, Percy Liang, Rich James, Weijia Shi, Wen-tau Yih","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-11-22T20:26:44Z","title":"Retrieval-Augmented Multimodal Language Modeling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.12561","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":"sha256:70bea6975fd56f03217bbc3c06e5c9aa6c91cc3ba04ae8cfe8a087e4eb8107a4","target":"record","created_at":"2026-07-05T06:17:42Z","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":"a45f8bd32ebc4991e7e063dd4ba7d0411721356c43185d291921cfe62d927af3","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-11-22T20:26:44Z","title_canon_sha256":"2db65baa3f5058b9bcb69cfb0cc36148a4a9c9417be9e02f9f798828a7fc0bd4"},"schema_version":"1.0","source":{"id":"2211.12561","kind":"arxiv","version":2}},"canonical_sha256":"fe597e3217e6c14f32e28cb5fd9dffd02eea2bd22b2806d04aa219574220b1ef","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fe597e3217e6c14f32e28cb5fd9dffd02eea2bd22b2806d04aa219574220b1ef","first_computed_at":"2026-07-05T06:17:42.690444Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:17:42.690444Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vzb9Jv19fves1tQ4zDtWhfv2JGfP2/OvmVvsdSsNrtsB7OzxyTScHbARusJ2qp14oV6uqg0YnYwDaeIAgJsyAw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:17:42.690885Z","signed_message":"canonical_sha256_bytes"},"source_id":"2211.12561","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:70bea6975fd56f03217bbc3c06e5c9aa6c91cc3ba04ae8cfe8a087e4eb8107a4","sha256:5c19000cd1c75e59e747675e9670d624742aff526f486e768e104b5a63eee323"],"state_sha256":"302d9f9be3baa0dce73e32d6024458297f849685186aa2c347de47dcea8998eb"}