{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:LGOLKZKODIZCG5N7NADGACNVSF","short_pith_number":"pith:LGOLKZKO","schema_version":"1.0","canonical_sha256":"599cb5654e1a322375bf68066009b5914d8e88df1185c12476b5c565640fa32c","source":{"kind":"arxiv","id":"2301.13823","version":4},"attestation_state":"computed","paper":{"title":"Grounding Language Models to Images for Multimodal Inputs and Outputs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.LG"],"primary_cat":"cs.CL","authors_text":"Daniel Fried, Jing Yu Koh, Ruslan Salakhutdinov","submitted_at":"2023-01-31T18:33:44Z","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"},"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":"2301.13823","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-01-31T18:33:44Z","cross_cats_sorted":["cs.AI","cs.CV","cs.LG"],"title_canon_sha256":"d4d9b4514e99ee1e4fe392670a01ad395132e0d349abfc914576c2e72f5b42fe","abstract_canon_sha256":"7e5141c45ecb2987f0040552fd0cf46cdd7e3043320e3dc7a2e6f3c2dd00454d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:20:40.321801Z","signature_b64":"eQBBZQq+NLIKtirMYJ87aCbqmDYMnBXIcSCIhteWZAGtRM4S0DrVa+jlysEMZ0PgIcfgkzlo5Bs3BtnB87zpDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"599cb5654e1a322375bf68066009b5914d8e88df1185c12476b5c565640fa32c","last_reissued_at":"2026-07-05T06:20:40.321379Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:20:40.321379Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Grounding Language Models to Images for Multimodal Inputs and Outputs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.LG"],"primary_cat":"cs.CL","authors_text":"Daniel Fried, Jing Yu Koh, Ruslan Salakhutdinov","submitted_at":"2023-01-31T18:33:44Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.13823","kind":"arxiv","version":4},"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/2301.13823/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":"2301.13823","created_at":"2026-07-05T06:20:40.321428+00:00"},{"alias_kind":"arxiv_version","alias_value":"2301.13823v4","created_at":"2026-07-05T06:20:40.321428+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.13823","created_at":"2026-07-05T06:20:40.321428+00:00"},{"alias_kind":"pith_short_12","alias_value":"LGOLKZKODIZC","created_at":"2026-07-05T06:20:40.321428+00:00"},{"alias_kind":"pith_short_16","alias_value":"LGOLKZKODIZCG5N7","created_at":"2026-07-05T06:20:40.321428+00:00"},{"alias_kind":"pith_short_8","alias_value":"LGOLKZKO","created_at":"2026-07-05T06:20:40.321428+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.25325","citing_title":"Omni-Perception Policy Optimization for Multimodal Emotion Reasoning","ref_index":159,"is_internal_anchor":false},{"citing_arxiv_id":"2306.00978","citing_title":"AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2402.03766","citing_title":"MobileVLM V2: Faster and Stronger Baseline for Vision Language Model","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2401.15947","citing_title":"MoE-LLaVA: Mixture of Experts for Large Vision-Language Models","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2302.14045","citing_title":"Language Is Not All You Need: Aligning Perception with Language Models","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2308.01390","citing_title":"OpenFlamingo: An Open-Source Framework for Training Large Autoregressive Vision-Language Models","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2310.05737","citing_title":"Language Model Beats Diffusion -- Tokenizer is Key to Visual Generation","ref_index":107,"is_internal_anchor":false},{"citing_arxiv_id":"2304.08485","citing_title":"Visual Instruction Tuning","ref_index":24,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LGOLKZKODIZCG5N7NADGACNVSF","json":"https://pith.science/pith/LGOLKZKODIZCG5N7NADGACNVSF.json","graph_json":"https://pith.science/api/pith-number/LGOLKZKODIZCG5N7NADGACNVSF/graph.json","events_json":"https://pith.science/api/pith-number/LGOLKZKODIZCG5N7NADGACNVSF/events.json","paper":"https://pith.science/paper/LGOLKZKO"},"agent_actions":{"view_html":"https://pith.science/pith/LGOLKZKODIZCG5N7NADGACNVSF","download_json":"https://pith.science/pith/LGOLKZKODIZCG5N7NADGACNVSF.json","view_paper":"https://pith.science/paper/LGOLKZKO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2301.13823&json=true","fetch_graph":"https://pith.science/api/pith-number/LGOLKZKODIZCG5N7NADGACNVSF/graph.json","fetch_events":"https://pith.science/api/pith-number/LGOLKZKODIZCG5N7NADGACNVSF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LGOLKZKODIZCG5N7NADGACNVSF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LGOLKZKODIZCG5N7NADGACNVSF/action/storage_attestation","attest_author":"https://pith.science/pith/LGOLKZKODIZCG5N7NADGACNVSF/action/author_attestation","sign_citation":"https://pith.science/pith/LGOLKZKODIZCG5N7NADGACNVSF/action/citation_signature","submit_replication":"https://pith.science/pith/LGOLKZKODIZCG5N7NADGACNVSF/action/replication_record"}},"created_at":"2026-07-05T06:20:40.321428+00:00","updated_at":"2026-07-05T06:20:40.321428+00:00"}