{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:LGOLKZKODIZCG5N7NADGACNVSF","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":"7e5141c45ecb2987f0040552fd0cf46cdd7e3043320e3dc7a2e6f3c2dd00454d","cross_cats_sorted":["cs.AI","cs.CV","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-01-31T18:33:44Z","title_canon_sha256":"d4d9b4514e99ee1e4fe392670a01ad395132e0d349abfc914576c2e72f5b42fe"},"schema_version":"1.0","source":{"id":"2301.13823","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2301.13823","created_at":"2026-07-05T06:20:40Z"},{"alias_kind":"arxiv_version","alias_value":"2301.13823v4","created_at":"2026-07-05T06:20:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.13823","created_at":"2026-07-05T06:20:40Z"},{"alias_kind":"pith_short_12","alias_value":"LGOLKZKODIZC","created_at":"2026-07-05T06:20:40Z"},{"alias_kind":"pith_short_16","alias_value":"LGOLKZKODIZCG5N7","created_at":"2026-07-05T06:20:40Z"},{"alias_kind":"pith_short_8","alias_value":"LGOLKZKO","created_at":"2026-07-05T06:20:40Z"}],"graph_snapshots":[{"event_id":"sha256:05403b058e4945b0805b9763457bdcff502ca082d63bd4d46cd89be77244bb87","target":"graph","created_at":"2026-07-05T06:20:40Z","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/2301.13823/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose an efficient method to ground pretrained text-only language models to the visual domain, enabling them to process arbitrarily interleaved image-and-text data, and generate text interleaved with retrieved images. Our method leverages the abilities of language models learnt from large scale text-only pretraining, such as in-context learning and free-form text generation. We keep the language model frozen, and finetune input and output linear layers to enable cross-modality interactions. This allows our model to process arbitrarily interleaved image-and-text inputs, and generate free-f","authors_text":"Daniel Fried, Jing Yu Koh, Ruslan Salakhutdinov","cross_cats":["cs.AI","cs.CV","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-01-31T18:33:44Z","title":"Grounding Language Models to Images for Multimodal Inputs and Outputs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.13823","kind":"arxiv","version":4},"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:e129d7c481a73c96a40c0eee2f30baf1ee8c5fa7eceb23b541f309bb096ed430","target":"record","created_at":"2026-07-05T06:20:40Z","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":"7e5141c45ecb2987f0040552fd0cf46cdd7e3043320e3dc7a2e6f3c2dd00454d","cross_cats_sorted":["cs.AI","cs.CV","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-01-31T18:33:44Z","title_canon_sha256":"d4d9b4514e99ee1e4fe392670a01ad395132e0d349abfc914576c2e72f5b42fe"},"schema_version":"1.0","source":{"id":"2301.13823","kind":"arxiv","version":4}},"canonical_sha256":"599cb5654e1a322375bf68066009b5914d8e88df1185c12476b5c565640fa32c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"599cb5654e1a322375bf68066009b5914d8e88df1185c12476b5c565640fa32c","first_computed_at":"2026-07-05T06:20:40.321379Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:20:40.321379Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"eQBBZQq+NLIKtirMYJ87aCbqmDYMnBXIcSCIhteWZAGtRM4S0DrVa+jlysEMZ0PgIcfgkzlo5Bs3BtnB87zpDw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:20:40.321801Z","signed_message":"canonical_sha256_bytes"},"source_id":"2301.13823","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e129d7c481a73c96a40c0eee2f30baf1ee8c5fa7eceb23b541f309bb096ed430","sha256:05403b058e4945b0805b9763457bdcff502ca082d63bd4d46cd89be77244bb87"],"state_sha256":"e34cc2d46ba681a8f1dfa3039fcac225917a3e3985ae32e9be7f3e5cec1bedc5"}