{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:NMDBPXUI22H2SH4DTEFY7JZVLW","short_pith_number":"pith:NMDBPXUI","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"},"canonical_sha256":"6b0617de88d68fa91f83990b8fa7355d87314a73e71cabe4394fd65fd4b80d33","source":{"kind":"arxiv","id":"2309.17421","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.17421","created_at":"2026-05-17T23:38:49Z"},{"alias_kind":"arxiv_version","alias_value":"2309.17421v2","created_at":"2026-05-17T23:38:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.17421","created_at":"2026-05-17T23:38:49Z"},{"alias_kind":"pith_short_12","alias_value":"NMDBPXUI22H2","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"NMDBPXUI22H2SH4D","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"NMDBPXUI","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:NMDBPXUI22H2SH4DTEFY7JZVLW","target":"record","payload":{"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"},"canonical_sha256":"6b0617de88d68fa91f83990b8fa7355d87314a73e71cabe4394fd65fd4b80d33","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"},"source_kind":"arxiv","source_id":"2309.17421","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:38:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SyrvnuxJ5SToBpLExaWgSBBGUXJGXv0/cBuf24/MwnUb/BJu1E69HnwTlhn6D74Mj7n1dt8UbSzhsIBrpI4nAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T05:51:14.359677Z"},"content_sha256":"22246402ab80d3779308ce96d66896992472b6bc158e349ea9e8f9508f215a0a","schema_version":"1.0","event_id":"sha256:22246402ab80d3779308ce96d66896992472b6bc158e349ea9e8f9508f215a0a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:NMDBPXUI22H2SH4DTEFY7JZVLW","target":"graph","payload":{"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"},"verdict_id":"f2725e2c-7377-4b1e-b5b2-bc56b54ce40e"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:38:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"t5mLcE+j+4F+hXtM4z8cpnX0KggTXqd8nXUBt6qwCOcW/LG9+iiy8RCnV5yGjRLVBpsbVCfdTu8SPhQqbqV8Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T05:51:14.360728Z"},"content_sha256":"8b7f4543c9b0ceb13325798ea371600c9caa571fc1376d5b433332cc93d8b9ef","schema_version":"1.0","event_id":"sha256:8b7f4543c9b0ceb13325798ea371600c9caa571fc1376d5b433332cc93d8b9ef"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NMDBPXUI22H2SH4DTEFY7JZVLW/bundle.json","state_url":"https://pith.science/pith/NMDBPXUI22H2SH4DTEFY7JZVLW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NMDBPXUI22H2SH4DTEFY7JZVLW/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-25T05:51:14Z","links":{"resolver":"https://pith.science/pith/NMDBPXUI22H2SH4DTEFY7JZVLW","bundle":"https://pith.science/pith/NMDBPXUI22H2SH4DTEFY7JZVLW/bundle.json","state":"https://pith.science/pith/NMDBPXUI22H2SH4DTEFY7JZVLW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NMDBPXUI22H2SH4DTEFY7JZVLW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:NMDBPXUI22H2SH4DTEFY7JZVLW","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":"419c4dd291ec6081b8b8472e200380ff5ae1e9aaaf91a3194cd528ee0b111c54","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-09-29T17:34:51Z","title_canon_sha256":"8b285fc2e758714f7dd2f834f9808704965ffb89cd3a77d831c7e465a14dc8c9"},"schema_version":"1.0","source":{"id":"2309.17421","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.17421","created_at":"2026-05-17T23:38:49Z"},{"alias_kind":"arxiv_version","alias_value":"2309.17421v2","created_at":"2026-05-17T23:38:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.17421","created_at":"2026-05-17T23:38:49Z"},{"alias_kind":"pith_short_12","alias_value":"NMDBPXUI22H2","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"NMDBPXUI22H2SH4D","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"NMDBPXUI","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:8b7f4543c9b0ceb13325798ea371600c9caa571fc1376d5b433332cc93d8b9ef","target":"graph","created_at":"2026-05-17T23:38:49Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That the authors' hand-curated qualitative samples are representative enough to establish genericity and quality without quantitative benchmarks or controlled comparisons."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"GPT-4V processes interleaved image-text inputs generically and supports visual referring prompting for new human-AI interaction."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"GPT-4V processes arbitrarily interleaved multimodal inputs to function as a multimodal generalist system"}],"snapshot_sha256":"2edf31b0bc266fe59db181c18996c7d14a2d29c1d0e200067180a07d22e88480"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"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","authors_text":"Chung-Ching Lin, Jianfeng Wang, Kevin Lin, Lijuan Wang, Linjie Li, Zhengyuan Yang, Zicheng Liu","cross_cats":["cs.CL"],"headline":"GPT-4V processes arbitrarily interleaved multimodal inputs to function as a multimodal generalist system","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-09-29T17:34:51Z","title":"The Dawn of LMMs: Preliminary Explorations with GPT-4V(ision)"},"references":{"count":160,"internal_anchors":35,"resolved_work":160,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"https://openai.com/blog/ chatgpt-can-now-see-hear-and-speak , 2023","work_id":"35ab23ac-eb48-4ba1-aed5-48df69df9ff0","year":2023},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Deepfloyd if. https://github.com/deep-floyd/IF, 2023","work_id":"2d3a7b46-a054-458f-8990-ac38d4c99efd","year":2023},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Guidance. https://github.com/microsoft/guidance/, 2023","work_id":"98a2d882-61bf-4897-88b5-c13ba133dedc","year":2023},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Midjourney. https://www.midjourney.com/, 2023","work_id":"862286be-a5ac-41c3-9be2-5bcc00f44797","year":2023},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Building rome in a day","work_id":"e957ed10-08b0-4b1d-a9fd-2d84342d4e2c","year":2011}],"snapshot_sha256":"eecd12b7c90b7da3920833d6dc1b5ea6731b7ec3b61fc942968ade52ba2bdbb9"},"source":{"id":"2309.17421","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-15T23:22:38.619369Z","id":"f2725e2c-7377-4b1e-b5b2-bc56b54ce40e","model_set":{"reader":"grok-4.3"},"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","pith_extraction_headline":"GPT-4V processes arbitrarily interleaved multimodal inputs to function as a multimodal generalist system","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.","weakest_assumption":"That the authors' hand-curated qualitative samples are representative enough to establish genericity and quality without quantitative benchmarks or controlled comparisons."}},"verdict_id":"f2725e2c-7377-4b1e-b5b2-bc56b54ce40e"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:22246402ab80d3779308ce96d66896992472b6bc158e349ea9e8f9508f215a0a","target":"record","created_at":"2026-05-17T23:38:49Z","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":"419c4dd291ec6081b8b8472e200380ff5ae1e9aaaf91a3194cd528ee0b111c54","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-09-29T17:34:51Z","title_canon_sha256":"8b285fc2e758714f7dd2f834f9808704965ffb89cd3a77d831c7e465a14dc8c9"},"schema_version":"1.0","source":{"id":"2309.17421","kind":"arxiv","version":2}},"canonical_sha256":"6b0617de88d68fa91f83990b8fa7355d87314a73e71cabe4394fd65fd4b80d33","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6b0617de88d68fa91f83990b8fa7355d87314a73e71cabe4394fd65fd4b80d33","first_computed_at":"2026-05-17T23:38:49.790175Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:38:49.790175Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/6ozsqY1ygdbm0r5HF4yHntNxliDToSl/tbhnAyXESTLN1MXrTyiGvYee1NDgNXxgfUzRZXZvSZ2/ZFnfFADDg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:38:49.790690Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.17421","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:22246402ab80d3779308ce96d66896992472b6bc158e349ea9e8f9508f215a0a","sha256:8b7f4543c9b0ceb13325798ea371600c9caa571fc1376d5b433332cc93d8b9ef"],"state_sha256":"dce09f8839073e1d41420f9f8edd31698e58231abe25a34e277f665f6a238c4d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TtQSAOtQsUeU/bKUsWG2JAW+QVdwc7B7t1/wKqtRtT5QixRbGfShok/0XZTwpC/9FOsVdAm4KQRiMmnEjZ/7Aw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T05:51:14.365567Z","bundle_sha256":"06998cc8ea074e77fe42df3f73a5581a5d5cdb738fc8cce3906a791ccfb31dae"}}