{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:C757O2MRLHQBAEEYAMLEYHRIXC","short_pith_number":"pith:C757O2MR","canonical_record":{"source":{"id":"2303.11381","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-03-20T18:31:47Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"d8fc08a05575b94e41ebafb15d423ba6457301a1ecb6e571ce2d3f5d4f47bbb0","abstract_canon_sha256":"ad55e24432253d2a7fd679fd3f5d8e67b783e447d9f8098fe700f8965e46239c"},"schema_version":"1.0"},"canonical_sha256":"17fbf7699159e010109803164c1e28b8be7a9d986cdbd49dc4371790e0fd38f7","source":{"kind":"arxiv","id":"2303.11381","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.11381","created_at":"2026-05-18T03:00:13Z"},{"alias_kind":"arxiv_version","alias_value":"2303.11381v1","created_at":"2026-05-18T03:00:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.11381","created_at":"2026-05-18T03:00:13Z"},{"alias_kind":"pith_short_12","alias_value":"C757O2MRLHQB","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_16","alias_value":"C757O2MRLHQBAEEY","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_8","alias_value":"C757O2MR","created_at":"2026-05-18T12:33:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:C757O2MRLHQBAEEYAMLEYHRIXC","target":"record","payload":{"canonical_record":{"source":{"id":"2303.11381","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-03-20T18:31:47Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"d8fc08a05575b94e41ebafb15d423ba6457301a1ecb6e571ce2d3f5d4f47bbb0","abstract_canon_sha256":"ad55e24432253d2a7fd679fd3f5d8e67b783e447d9f8098fe700f8965e46239c"},"schema_version":"1.0"},"canonical_sha256":"17fbf7699159e010109803164c1e28b8be7a9d986cdbd49dc4371790e0fd38f7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:00:13.088103Z","signature_b64":"kMNFWkKgzOuQdXY3C7yoiTv2eBYTzSHtQUA2vkPYWFby03hLD0hPhnY/ANxKj8/i6TTsCgHoLbjK5nc8gV/uDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"17fbf7699159e010109803164c1e28b8be7a9d986cdbd49dc4371790e0fd38f7","last_reissued_at":"2026-05-18T03:00:13.087518Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:00:13.087518Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2303.11381","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T03:00:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Xsf8wNcQn2q3H7VFzhV2kwprx+suTVw0eJ5Ah72oDB38v95NAG+HUcF1XJd4lYf08EvVq1K/2HA5AjZHCo47CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T19:53:48.942643Z"},"content_sha256":"6be6ada2279a4422c5fd630b6d6a7af46aaa44ef6a2dd32dc0dbfb267d6bef07","schema_version":"1.0","event_id":"sha256:6be6ada2279a4422c5fd630b6d6a7af46aaa44ef6a2dd32dc0dbfb267d6bef07"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:C757O2MRLHQBAEEYAMLEYHRIXC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MM-REACT: Prompting ChatGPT for Multimodal Reasoning and Action","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"A textual prompt design lets ChatGPT collaborate with vision experts to handle advanced multimodal reasoning and action in zero-shot settings.","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Ce Liu, Ehsan Azarnasab, Faisal Ahmed, Jianfeng Wang, Kevin Lin, Lijuan Wang, Linjie Li, Michael Zeng, Zhengyuan Yang, Zicheng Liu","submitted_at":"2023-03-20T18:31:47Z","abstract_excerpt":"We propose MM-REACT, a system paradigm that integrates ChatGPT with a pool of vision experts to achieve multimodal reasoning and action. In this paper, we define and explore a comprehensive list of advanced vision tasks that are intriguing to solve, but may exceed the capabilities of existing vision and vision-language models. To achieve such advanced visual intelligence, MM-REACT introduces a textual prompt design that can represent text descriptions, textualized spatial coordinates, and aligned file names for dense visual signals such as images and videos. MM-REACT's prompt design allows lan"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Zero-shot experiments demonstrate MM-REACT's effectiveness in addressing the specified capabilities of interests and its wide application in different scenarios that require advanced visual understanding.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The textual prompt design can faithfully represent and allow language models to process dense visual signals such as images and videos without loss of critical information.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"MM-REACT uses textual prompts to let ChatGPT collaborate with external vision experts for zero-shot multimodal reasoning and action on advanced visual tasks.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A textual prompt design lets ChatGPT collaborate with vision experts to handle advanced multimodal reasoning and action in zero-shot settings.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"9d7f11d0f7de4153634e5044445836d36d2ec36322404c5ff59d92a988d63b19"},"source":{"id":"2303.11381","kind":"arxiv","version":1},"verdict":{"id":"b74c6a6f-c277-4064-92f1-c74bac347ebb","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-14T01:12:43.672888Z","strongest_claim":"Zero-shot experiments demonstrate MM-REACT's effectiveness in addressing the specified capabilities of interests and its wide application in different scenarios that require advanced visual understanding.","one_line_summary":"MM-REACT uses textual prompts to let ChatGPT collaborate with external vision experts for zero-shot multimodal reasoning and action on advanced visual tasks.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The textual prompt design can faithfully represent and allow language models to process dense visual signals such as images and videos without loss of critical information.","pith_extraction_headline":"A textual prompt design lets ChatGPT collaborate with vision experts to handle advanced multimodal reasoning and action in zero-shot settings."},"references":{"count":60,"sample":[{"doi":"","year":2022,"title":"Do As I Can, Not As I Say: Grounding Language in Robotic Affordances","work_id":"037320f1-b0a9-4cbe-a639-bfb25409ce71","ref_index":1,"cited_arxiv_id":"2204.01691","is_internal_anchor":true},{"doi":"","year":2022,"title":"Flamingo: a Visual Language Model for Few-Shot Learning","work_id":"a110f764-38dc-41b2-a802-53744ecea1fc","ref_index":2,"cited_arxiv_id":"2204.14198","is_internal_anchor":true},{"doi":"","year":2020,"title":"Lan- guage models are few-shot learners","work_id":"9d80ea01-55d6-44ef-a69e-0ca87cabb940","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2020,"title":"End-to- end object detection with transformers","work_id":"8376a687-7c64-4343-88ee-9ab3141e93a7","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"Harrison Chase. Langchain. https://langchain. readthedocs.io/, 2023. 4 6 Figure 4. Case studies of MM-R EACT’s capabilities and application scenarios: visual math and text reasoning. 7","work_id":"28eb406b-9a34-43fa-94df-ca72fd959644","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":60,"snapshot_sha256":"0c88837ac336b5a608d05b739f13655b39808a38ed12b8adc144911be5f17fbb","internal_anchors":18},"formal_canon":{"evidence_count":2,"snapshot_sha256":"eaed9143d2045250ee98f9ffdd88129e7a4f5d96c1f76f99d18c8a3e7d5d81dd"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"b74c6a6f-c277-4064-92f1-c74bac347ebb"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T03:00:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lk334enxP0tvdE/mIRUQqebYk2DDFAo6QaIJNCRYxZj2ieF8n3JDJw70+JKb9vizXCV92z07eixREedHvzOZDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T19:53:48.943416Z"},"content_sha256":"ef9acd480b2a84e9f43996b523acef1678b9caa8e03c715a49a5ec3d6fc0588e","schema_version":"1.0","event_id":"sha256:ef9acd480b2a84e9f43996b523acef1678b9caa8e03c715a49a5ec3d6fc0588e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/C757O2MRLHQBAEEYAMLEYHRIXC/bundle.json","state_url":"https://pith.science/pith/C757O2MRLHQBAEEYAMLEYHRIXC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/C757O2MRLHQBAEEYAMLEYHRIXC/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":"2026-05-26T19:53:48Z","links":{"resolver":"https://pith.science/pith/C757O2MRLHQBAEEYAMLEYHRIXC","bundle":"https://pith.science/pith/C757O2MRLHQBAEEYAMLEYHRIXC/bundle.json","state":"https://pith.science/pith/C757O2MRLHQBAEEYAMLEYHRIXC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/C757O2MRLHQBAEEYAMLEYHRIXC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:C757O2MRLHQBAEEYAMLEYHRIXC","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":"ad55e24432253d2a7fd679fd3f5d8e67b783e447d9f8098fe700f8965e46239c","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-03-20T18:31:47Z","title_canon_sha256":"d8fc08a05575b94e41ebafb15d423ba6457301a1ecb6e571ce2d3f5d4f47bbb0"},"schema_version":"1.0","source":{"id":"2303.11381","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.11381","created_at":"2026-05-18T03:00:13Z"},{"alias_kind":"arxiv_version","alias_value":"2303.11381v1","created_at":"2026-05-18T03:00:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.11381","created_at":"2026-05-18T03:00:13Z"},{"alias_kind":"pith_short_12","alias_value":"C757O2MRLHQB","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_16","alias_value":"C757O2MRLHQBAEEY","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_8","alias_value":"C757O2MR","created_at":"2026-05-18T12:33:33Z"}],"graph_snapshots":[{"event_id":"sha256:ef9acd480b2a84e9f43996b523acef1678b9caa8e03c715a49a5ec3d6fc0588e","target":"graph","created_at":"2026-05-18T03:00:13Z","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":"Zero-shot experiments demonstrate MM-REACT's effectiveness in addressing the specified capabilities of interests and its wide application in different scenarios that require advanced visual understanding."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The textual prompt design can faithfully represent and allow language models to process dense visual signals such as images and videos without loss of critical information."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"MM-REACT uses textual prompts to let ChatGPT collaborate with external vision experts for zero-shot multimodal reasoning and action on advanced visual tasks."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"A textual prompt design lets ChatGPT collaborate with vision experts to handle advanced multimodal reasoning and action in zero-shot settings."}],"snapshot_sha256":"9d7f11d0f7de4153634e5044445836d36d2ec36322404c5ff59d92a988d63b19"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"eaed9143d2045250ee98f9ffdd88129e7a4f5d96c1f76f99d18c8a3e7d5d81dd"},"paper":{"abstract_excerpt":"We propose MM-REACT, a system paradigm that integrates ChatGPT with a pool of vision experts to achieve multimodal reasoning and action. In this paper, we define and explore a comprehensive list of advanced vision tasks that are intriguing to solve, but may exceed the capabilities of existing vision and vision-language models. To achieve such advanced visual intelligence, MM-REACT introduces a textual prompt design that can represent text descriptions, textualized spatial coordinates, and aligned file names for dense visual signals such as images and videos. MM-REACT's prompt design allows lan","authors_text":"Ce Liu, Ehsan Azarnasab, Faisal Ahmed, Jianfeng Wang, Kevin Lin, Lijuan Wang, Linjie Li, Michael Zeng, Zhengyuan Yang, Zicheng Liu","cross_cats":["cs.CL","cs.LG"],"headline":"A textual prompt design lets ChatGPT collaborate with vision experts to handle advanced multimodal reasoning and action in zero-shot settings.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-03-20T18:31:47Z","title":"MM-REACT: Prompting ChatGPT for Multimodal Reasoning and Action"},"references":{"count":60,"internal_anchors":18,"resolved_work":60,"sample":[{"cited_arxiv_id":"2204.01691","doi":"","is_internal_anchor":true,"ref_index":1,"title":"Do As I Can, Not As I Say: Grounding Language in Robotic Affordances","work_id":"037320f1-b0a9-4cbe-a639-bfb25409ce71","year":2022},{"cited_arxiv_id":"2204.14198","doi":"","is_internal_anchor":true,"ref_index":2,"title":"Flamingo: a Visual Language Model for Few-Shot Learning","work_id":"a110f764-38dc-41b2-a802-53744ecea1fc","year":2022},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Lan- guage models are few-shot learners","work_id":"9d80ea01-55d6-44ef-a69e-0ca87cabb940","year":2020},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"End-to- end object detection with transformers","work_id":"8376a687-7c64-4343-88ee-9ab3141e93a7","year":2020},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Harrison Chase. Langchain. https://langchain. readthedocs.io/, 2023. 4 6 Figure 4. Case studies of MM-R EACT’s capabilities and application scenarios: visual math and text reasoning. 7","work_id":"28eb406b-9a34-43fa-94df-ca72fd959644","year":2023}],"snapshot_sha256":"0c88837ac336b5a608d05b739f13655b39808a38ed12b8adc144911be5f17fbb"},"source":{"id":"2303.11381","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-14T01:12:43.672888Z","id":"b74c6a6f-c277-4064-92f1-c74bac347ebb","model_set":{"reader":"grok-4.3"},"one_line_summary":"MM-REACT uses textual prompts to let ChatGPT collaborate with external vision experts for zero-shot multimodal reasoning and action on advanced visual tasks.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"A textual prompt design lets ChatGPT collaborate with vision experts to handle advanced multimodal reasoning and action in zero-shot settings.","strongest_claim":"Zero-shot experiments demonstrate MM-REACT's effectiveness in addressing the specified capabilities of interests and its wide application in different scenarios that require advanced visual understanding.","weakest_assumption":"The textual prompt design can faithfully represent and allow language models to process dense visual signals such as images and videos without loss of critical information."}},"verdict_id":"b74c6a6f-c277-4064-92f1-c74bac347ebb"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:6be6ada2279a4422c5fd630b6d6a7af46aaa44ef6a2dd32dc0dbfb267d6bef07","target":"record","created_at":"2026-05-18T03:00:13Z","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":"ad55e24432253d2a7fd679fd3f5d8e67b783e447d9f8098fe700f8965e46239c","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-03-20T18:31:47Z","title_canon_sha256":"d8fc08a05575b94e41ebafb15d423ba6457301a1ecb6e571ce2d3f5d4f47bbb0"},"schema_version":"1.0","source":{"id":"2303.11381","kind":"arxiv","version":1}},"canonical_sha256":"17fbf7699159e010109803164c1e28b8be7a9d986cdbd49dc4371790e0fd38f7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"17fbf7699159e010109803164c1e28b8be7a9d986cdbd49dc4371790e0fd38f7","first_computed_at":"2026-05-18T03:00:13.087518Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:00:13.087518Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kMNFWkKgzOuQdXY3C7yoiTv2eBYTzSHtQUA2vkPYWFby03hLD0hPhnY/ANxKj8/i6TTsCgHoLbjK5nc8gV/uDQ==","signature_status":"signed_v1","signed_at":"2026-05-18T03:00:13.088103Z","signed_message":"canonical_sha256_bytes"},"source_id":"2303.11381","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6be6ada2279a4422c5fd630b6d6a7af46aaa44ef6a2dd32dc0dbfb267d6bef07","sha256:ef9acd480b2a84e9f43996b523acef1678b9caa8e03c715a49a5ec3d6fc0588e"],"state_sha256":"16bdbeb32b98c6bae8eeb02316044e270d802896afa5e9c8f5cebd0d5f6b2519"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Opfm2dQbY9yS+0O+OtWSU8D3uafJJVTUXMflYXoT8x9izihLUeSG4eV3ifipOBNhpIp+jFmxsHe70aVxjLhICg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T19:53:48.947568Z","bundle_sha256":"6081ded526d64af7a0a184f4e88ab36b98ddbb42637f30bf00f50d43b451b9b1"}}