{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:NMDBPXUI22H2SH4DTEFY7JZVLW","short_pith_number":"pith:NMDBPXUI","schema_version":"1.0","canonical_sha256":"6b0617de88d68fa91f83990b8fa7355d87314a73e71cabe4394fd65fd4b80d33","source":{"kind":"arxiv","id":"2309.17421","version":2},"attestation_state":"computed","paper":{"title":"The Dawn of LMMs: Preliminary Explorations with GPT-4V(ision)","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"GPT-4V processes arbitrarily interleaved multimodal inputs to function as a multimodal generalist system","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Chung-Ching Lin, Jianfeng Wang, Kevin Lin, Lijuan Wang, Linjie Li, Zhengyuan Yang, Zicheng Liu","submitted_at":"2023-09-29T17:34:51Z","abstract_excerpt":"Large multimodal models (LMMs) extend large language models (LLMs) with multi-sensory skills, such as visual understanding, to achieve stronger generic intelligence. In this paper, we analyze the latest model, GPT-4V(ision), to deepen the understanding of LMMs. The analysis focuses on the intriguing tasks that GPT-4V can perform, containing test samples to probe the quality and genericity of GPT-4V's capabilities, its supported inputs and working modes, and the effective ways to prompt the model. In our approach to exploring GPT-4V, we curate and organize a collection of carefully designed qua"},"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":true,"formal_links_present":false},"canonical_record":{"source":{"id":"2309.17421","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-09-29T17:34:51Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"8b285fc2e758714f7dd2f834f9808704965ffb89cd3a77d831c7e465a14dc8c9","abstract_canon_sha256":"419c4dd291ec6081b8b8472e200380ff5ae1e9aaaf91a3194cd528ee0b111c54"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:38:49.790690Z","signature_b64":"/6ozsqY1ygdbm0r5HF4yHntNxliDToSl/tbhnAyXESTLN1MXrTyiGvYee1NDgNXxgfUzRZXZvSZ2/ZFnfFADDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6b0617de88d68fa91f83990b8fa7355d87314a73e71cabe4394fd65fd4b80d33","last_reissued_at":"2026-05-17T23:38:49.790175Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:38:49.790175Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Dawn of LMMs: Preliminary Explorations with GPT-4V(ision)","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"GPT-4V processes arbitrarily interleaved multimodal inputs to function as a multimodal generalist system","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Chung-Ching Lin, Jianfeng Wang, Kevin Lin, Lijuan Wang, Linjie Li, Zhengyuan Yang, Zicheng Liu","submitted_at":"2023-09-29T17:34:51Z","abstract_excerpt":"Large multimodal models (LMMs) extend large language models (LLMs) with multi-sensory skills, such as visual understanding, to achieve stronger generic intelligence. In this paper, we analyze the latest model, GPT-4V(ision), to deepen the understanding of LMMs. The analysis focuses on the intriguing tasks that GPT-4V can perform, containing test samples to probe the quality and genericity of GPT-4V's capabilities, its supported inputs and working modes, and the effective ways to prompt the model. In our approach to exploring GPT-4V, we curate and organize a collection of carefully designed qua"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Observations from these samples demonstrate that GPT-4V's unprecedented ability in processing arbitrarily interleaved multimodal inputs and the genericity of its capabilities together make GPT-4V a powerful multimodal generalist system.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the authors' hand-curated qualitative samples are representative enough to establish genericity and quality without quantitative benchmarks or controlled comparisons.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"GPT-4V processes interleaved image-text inputs generically and supports visual referring prompting for new human-AI interaction.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"GPT-4V processes arbitrarily interleaved multimodal inputs to function as a multimodal generalist system","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"2edf31b0bc266fe59db181c18996c7d14a2d29c1d0e200067180a07d22e88480"},"source":{"id":"2309.17421","kind":"arxiv","version":2},"verdict":{"id":"f2725e2c-7377-4b1e-b5b2-bc56b54ce40e","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T23:22:38.619369Z","strongest_claim":"Observations from these samples demonstrate that GPT-4V's unprecedented ability in processing arbitrarily interleaved multimodal inputs and the genericity of its capabilities together make GPT-4V a powerful multimodal generalist system.","one_line_summary":"GPT-4V processes interleaved image-text inputs generically and supports visual referring prompting for new human-AI interaction.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the authors' hand-curated qualitative samples are representative enough to establish genericity and quality without quantitative benchmarks or controlled comparisons.","pith_extraction_headline":"GPT-4V processes arbitrarily interleaved multimodal inputs to function as a multimodal generalist system"},"references":{"count":160,"sample":[{"doi":"","year":2023,"title":"https://openai.com/blog/ chatgpt-can-now-see-hear-and-speak , 2023","work_id":"35ab23ac-eb48-4ba1-aed5-48df69df9ff0","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"Deepfloyd if. https://github.com/deep-floyd/IF, 2023","work_id":"2d3a7b46-a054-458f-8990-ac38d4c99efd","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"Guidance. https://github.com/microsoft/guidance/, 2023","work_id":"98a2d882-61bf-4897-88b5-c13ba133dedc","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"Midjourney. https://www.midjourney.com/, 2023","work_id":"862286be-a5ac-41c3-9be2-5bcc00f44797","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2011,"title":"Building rome in a day","work_id":"e957ed10-08b0-4b1d-a9fd-2d84342d4e2c","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":160,"snapshot_sha256":"eecd12b7c90b7da3920833d6dc1b5ea6731b7ec3b61fc942968ade52ba2bdbb9","internal_anchors":35},"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":"2309.17421","created_at":"2026-05-17T23:38:49.790267+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.17421v2","created_at":"2026-05-17T23:38:49.790267+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.17421","created_at":"2026-05-17T23:38:49.790267+00:00"},{"alias_kind":"pith_short_12","alias_value":"NMDBPXUI22H2","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"NMDBPXUI22H2SH4D","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"NMDBPXUI","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":40,"internal_anchor_count":40,"sample":[{"citing_arxiv_id":"2511.17171","citing_title":"FireScope: Wildfire Risk Raster Prediction with a Chain-of-Thought Oracle","ref_index":61,"is_internal_anchor":true},{"citing_arxiv_id":"2412.18158","citing_title":"Semantics Disentanglement and Composition for Universal Image Coding with Efficiently LLM Reasoning and Generative Diffusion","ref_index":44,"is_internal_anchor":true},{"citing_arxiv_id":"2603.11689","citing_title":"Explicit Logic Channel for Validation and Enhancement of MLLMs on Zero-Shot Tasks","ref_index":68,"is_internal_anchor":true},{"citing_arxiv_id":"2605.20469","citing_title":"HalluCXR: Benchmarking and Mitigating Hallucinations in Medical Vision-Language Models for Chest Radiograph Interpretation","ref_index":8,"is_internal_anchor":true},{"citing_arxiv_id":"2605.20892","citing_title":"FruitEnsemble: MLLM-Guided Arbitration for Heterogeneous ensemble in Fine-Grained Fruit Recognition","ref_index":41,"is_internal_anchor":true},{"citing_arxiv_id":"2605.20682","citing_title":"IndusAgent: Reinforcing Open-Vocabulary Industrial Anomaly Detection with Agentic Tools","ref_index":60,"is_internal_anchor":true},{"citing_arxiv_id":"2605.19634","citing_title":"P2DNav: Panorama-to-Downview Reasoning for Zero-shot Vision-and-Language Navigation","ref_index":7,"is_internal_anchor":true},{"citing_arxiv_id":"2408.04840","citing_title":"mPLUG-Owl3: Towards Long Image-Sequence Understanding in Multi-Modal Large Language Models","ref_index":116,"is_internal_anchor":true},{"citing_arxiv_id":"2605.19663","citing_title":"Pseudocode-Guided Structured Reasoning for Automating Reliable Inference in Vision-Language Models","ref_index":2,"is_internal_anchor":true},{"citing_arxiv_id":"2605.16953","citing_title":"How do Humans Process AI-generated Hallucination Contents: a Neuroimaging Study","ref_index":13,"is_internal_anchor":true},{"citing_arxiv_id":"2605.15203","citing_title":"Agent4POI: Agentic Context-Conditioned Affordance Reasoning for Multimodal Point-of-Interest Recommendation","ref_index":36,"is_internal_anchor":true},{"citing_arxiv_id":"2509.09794","citing_title":"Synthetic Homes: A Multimodal Generative AI Pipeline for Residential Building Data Generation under Data Scarcity","ref_index":37,"is_internal_anchor":true},{"citing_arxiv_id":"2510.22102","citing_title":"Mitigating Coordinate Prediction Bias from Positional Encoding Failures","ref_index":23,"is_internal_anchor":true},{"citing_arxiv_id":"2402.15852","citing_title":"NaVid: Video-based VLM Plans the Next Step for Vision-and-Language Navigation","ref_index":109,"is_internal_anchor":true},{"citing_arxiv_id":"2412.14058","citing_title":"What Matters in Building Vision-Language-Action Models for Generalist Robots","ref_index":47,"is_internal_anchor":true},{"citing_arxiv_id":"2511.17171","citing_title":"FireScope: Wildfire Risk Raster Prediction with a Chain-of-Thought Oracle","ref_index":61,"is_internal_anchor":true},{"citing_arxiv_id":"2312.13771","citing_title":"AppAgent: Multimodal Agents as Smartphone Users","ref_index":53,"is_internal_anchor":true},{"citing_arxiv_id":"2401.10935","citing_title":"SeeClick: Harnessing GUI Grounding for Advanced Visual GUI Agents","ref_index":104,"is_internal_anchor":true},{"citing_arxiv_id":"2407.01284","citing_title":"We-Math: Does Your Large Multimodal Model Achieve Human-like Mathematical Reasoning?","ref_index":28,"is_internal_anchor":true},{"citing_arxiv_id":"2512.21815","citing_title":"High-Entropy Tokens as Multimodal Failure Points in Vision-Language Models","ref_index":49,"is_internal_anchor":true},{"citing_arxiv_id":"2403.09611","citing_title":"MM1: Methods, Analysis & Insights from Multimodal LLM Pre-training","ref_index":122,"is_internal_anchor":true},{"citing_arxiv_id":"2306.13549","citing_title":"A Survey on Multimodal Large Language Models","ref_index":137,"is_internal_anchor":true},{"citing_arxiv_id":"2404.12390","citing_title":"BLINK: Multimodal Large Language Models Can See but Not Perceive","ref_index":85,"is_internal_anchor":true},{"citing_arxiv_id":"2412.10345","citing_title":"TraceVLA: Visual Trace Prompting Enhances Spatial-Temporal Awareness for Generalist Robotic Policies","ref_index":101,"is_internal_anchor":true},{"citing_arxiv_id":"2603.02972","citing_title":"TagaVLM: Topology-Aware Global Action Reasoning for Vision-Language Navigation","ref_index":9,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NMDBPXUI22H2SH4DTEFY7JZVLW","json":"https://pith.science/pith/NMDBPXUI22H2SH4DTEFY7JZVLW.json","graph_json":"https://pith.science/api/pith-number/NMDBPXUI22H2SH4DTEFY7JZVLW/graph.json","events_json":"https://pith.science/api/pith-number/NMDBPXUI22H2SH4DTEFY7JZVLW/events.json","paper":"https://pith.science/paper/NMDBPXUI"},"agent_actions":{"view_html":"https://pith.science/pith/NMDBPXUI22H2SH4DTEFY7JZVLW","download_json":"https://pith.science/pith/NMDBPXUI22H2SH4DTEFY7JZVLW.json","view_paper":"https://pith.science/paper/NMDBPXUI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.17421&json=true","fetch_graph":"https://pith.science/api/pith-number/NMDBPXUI22H2SH4DTEFY7JZVLW/graph.json","fetch_events":"https://pith.science/api/pith-number/NMDBPXUI22H2SH4DTEFY7JZVLW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NMDBPXUI22H2SH4DTEFY7JZVLW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NMDBPXUI22H2SH4DTEFY7JZVLW/action/storage_attestation","attest_author":"https://pith.science/pith/NMDBPXUI22H2SH4DTEFY7JZVLW/action/author_attestation","sign_citation":"https://pith.science/pith/NMDBPXUI22H2SH4DTEFY7JZVLW/action/citation_signature","submit_replication":"https://pith.science/pith/NMDBPXUI22H2SH4DTEFY7JZVLW/action/replication_record"}},"created_at":"2026-05-17T23:38:49.790267+00:00","updated_at":"2026-05-17T23:38:49.790267+00:00"}