{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:ZI7DRNYQ6XNQ5RDA2CRQR45ERJ","short_pith_number":"pith:ZI7DRNYQ","canonical_record":{"source":{"id":"2310.02071","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-10-03T14:13:36Z","cross_cats_sorted":["cs.CL","cs.CV","cs.RO"],"title_canon_sha256":"ea1166250e7a8fc41c559b9b306116cf21a9e344fc33acc6bc0ffb352b79dcc4","abstract_canon_sha256":"bd17e2a1d8ee6aaf4e9253d62f09af416935579bb03a46f38066dd2a0c8ed02b"},"schema_version":"1.0"},"canonical_sha256":"ca3e38b710f5db0ec460d0a308f3a48a7e6eee47efe45d70b367c946ccd66553","source":{"kind":"arxiv","id":"2310.02071","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.02071","created_at":"2026-07-05T07:17:32Z"},{"alias_kind":"arxiv_version","alias_value":"2310.02071v4","created_at":"2026-07-05T07:17:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.02071","created_at":"2026-07-05T07:17:32Z"},{"alias_kind":"pith_short_12","alias_value":"ZI7DRNYQ6XNQ","created_at":"2026-07-05T07:17:32Z"},{"alias_kind":"pith_short_16","alias_value":"ZI7DRNYQ6XNQ5RDA","created_at":"2026-07-05T07:17:32Z"},{"alias_kind":"pith_short_8","alias_value":"ZI7DRNYQ","created_at":"2026-07-05T07:17:32Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:ZI7DRNYQ6XNQ5RDA2CRQR45ERJ","target":"record","payload":{"canonical_record":{"source":{"id":"2310.02071","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-10-03T14:13:36Z","cross_cats_sorted":["cs.CL","cs.CV","cs.RO"],"title_canon_sha256":"ea1166250e7a8fc41c559b9b306116cf21a9e344fc33acc6bc0ffb352b79dcc4","abstract_canon_sha256":"bd17e2a1d8ee6aaf4e9253d62f09af416935579bb03a46f38066dd2a0c8ed02b"},"schema_version":"1.0"},"canonical_sha256":"ca3e38b710f5db0ec460d0a308f3a48a7e6eee47efe45d70b367c946ccd66553","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:17:32.254585Z","signature_b64":"lYUB74+ksXj1R6zWfRKVYXMdMvwaxsjztoQFJr/aUxc/yRdSLTAqBdxjL3FwLLMHJ3r5cq88HWgulvT8ZavXDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ca3e38b710f5db0ec460d0a308f3a48a7e6eee47efe45d70b367c946ccd66553","last_reissued_at":"2026-07-05T07:17:32.254128Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:17:32.254128Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.02071","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:17:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YAnc/VsnrXukhwyoD6lgadcgFxmsNSYqeFq7XKwsBoE/2vFyMURJL9DLn1AKSv2FDbuuxSTftlULwi+V7F/wAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T17:36:30.529368Z"},"content_sha256":"411347d01b37f34b765baa78af33ea4aea642d57c7f5cc3c56106dd3f563f4dd","schema_version":"1.0","event_id":"sha256:411347d01b37f34b765baa78af33ea4aea642d57c7f5cc3c56106dd3f563f4dd"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:ZI7DRNYQ6XNQ5RDA2CRQR45ERJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Towards End-to-End Embodied Decision Making via Multi-modal Large Language Model: Explorations with GPT4-Vision and Beyond","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.CV","cs.RO"],"primary_cat":"cs.AI","authors_text":"Baobao Chang, Haozhe Zhao, Liang Chen, Peiyi Wang, Shuhuai Ren, Tianyu Liu, Yichi Zhang, Yuchi Wang, Zefan Cai","submitted_at":"2023-10-03T14:13:36Z","abstract_excerpt":"In this study, we explore the potential of Multimodal Large Language Models (MLLMs) in improving embodied decision-making processes for agents. While Large Language Models (LLMs) have been widely used due to their advanced reasoning skills and vast world knowledge, MLLMs like GPT4-Vision offer enhanced visual understanding and reasoning capabilities. We investigate whether state-of-the-art MLLMs can handle embodied decision-making in an end-to-end manner and whether collaborations between LLMs and MLLMs can enhance decision-making. To address these questions, we introduce a new benchmark calle"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.02071","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/2310.02071/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:17:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9I8mNd6MlXj9JoAurI2te5vrJ5fXSBYwn1NhzY7VyjRZDVxzW00vPdsVGZT4CNfmmoEg180EzWxqvzA53/QfBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T17:36:30.529878Z"},"content_sha256":"98fb29b6ee15598767a700ee409eff4da2cd82dd1ed54138390eb02b317d2a97","schema_version":"1.0","event_id":"sha256:98fb29b6ee15598767a700ee409eff4da2cd82dd1ed54138390eb02b317d2a97"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZI7DRNYQ6XNQ5RDA2CRQR45ERJ/bundle.json","state_url":"https://pith.science/pith/ZI7DRNYQ6XNQ5RDA2CRQR45ERJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZI7DRNYQ6XNQ5RDA2CRQR45ERJ/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":"2026-08-21T17:36:30Z","links":{"resolver":"https://pith.science/pith/ZI7DRNYQ6XNQ5RDA2CRQR45ERJ","bundle":"https://pith.science/pith/ZI7DRNYQ6XNQ5RDA2CRQR45ERJ/bundle.json","state":"https://pith.science/pith/ZI7DRNYQ6XNQ5RDA2CRQR45ERJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZI7DRNYQ6XNQ5RDA2CRQR45ERJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:ZI7DRNYQ6XNQ5RDA2CRQR45ERJ","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":"bd17e2a1d8ee6aaf4e9253d62f09af416935579bb03a46f38066dd2a0c8ed02b","cross_cats_sorted":["cs.CL","cs.CV","cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-10-03T14:13:36Z","title_canon_sha256":"ea1166250e7a8fc41c559b9b306116cf21a9e344fc33acc6bc0ffb352b79dcc4"},"schema_version":"1.0","source":{"id":"2310.02071","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.02071","created_at":"2026-07-05T07:17:32Z"},{"alias_kind":"arxiv_version","alias_value":"2310.02071v4","created_at":"2026-07-05T07:17:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.02071","created_at":"2026-07-05T07:17:32Z"},{"alias_kind":"pith_short_12","alias_value":"ZI7DRNYQ6XNQ","created_at":"2026-07-05T07:17:32Z"},{"alias_kind":"pith_short_16","alias_value":"ZI7DRNYQ6XNQ5RDA","created_at":"2026-07-05T07:17:32Z"},{"alias_kind":"pith_short_8","alias_value":"ZI7DRNYQ","created_at":"2026-07-05T07:17:32Z"}],"graph_snapshots":[{"event_id":"sha256:98fb29b6ee15598767a700ee409eff4da2cd82dd1ed54138390eb02b317d2a97","target":"graph","created_at":"2026-07-05T07:17:32Z","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/2310.02071/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this study, we explore the potential of Multimodal Large Language Models (MLLMs) in improving embodied decision-making processes for agents. While Large Language Models (LLMs) have been widely used due to their advanced reasoning skills and vast world knowledge, MLLMs like GPT4-Vision offer enhanced visual understanding and reasoning capabilities. We investigate whether state-of-the-art MLLMs can handle embodied decision-making in an end-to-end manner and whether collaborations between LLMs and MLLMs can enhance decision-making. To address these questions, we introduce a new benchmark calle","authors_text":"Baobao Chang, Haozhe Zhao, Liang Chen, Peiyi Wang, Shuhuai Ren, Tianyu Liu, Yichi Zhang, Yuchi Wang, Zefan Cai","cross_cats":["cs.CL","cs.CV","cs.RO"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-10-03T14:13:36Z","title":"Towards End-to-End Embodied Decision Making via Multi-modal Large Language Model: Explorations with GPT4-Vision and Beyond"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.02071","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":"sha256:411347d01b37f34b765baa78af33ea4aea642d57c7f5cc3c56106dd3f563f4dd","target":"record","created_at":"2026-07-05T07:17:32Z","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":"bd17e2a1d8ee6aaf4e9253d62f09af416935579bb03a46f38066dd2a0c8ed02b","cross_cats_sorted":["cs.CL","cs.CV","cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-10-03T14:13:36Z","title_canon_sha256":"ea1166250e7a8fc41c559b9b306116cf21a9e344fc33acc6bc0ffb352b79dcc4"},"schema_version":"1.0","source":{"id":"2310.02071","kind":"arxiv","version":4}},"canonical_sha256":"ca3e38b710f5db0ec460d0a308f3a48a7e6eee47efe45d70b367c946ccd66553","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ca3e38b710f5db0ec460d0a308f3a48a7e6eee47efe45d70b367c946ccd66553","first_computed_at":"2026-07-05T07:17:32.254128Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:17:32.254128Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lYUB74+ksXj1R6zWfRKVYXMdMvwaxsjztoQFJr/aUxc/yRdSLTAqBdxjL3FwLLMHJ3r5cq88HWgulvT8ZavXDA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:17:32.254585Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.02071","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:411347d01b37f34b765baa78af33ea4aea642d57c7f5cc3c56106dd3f563f4dd","sha256:98fb29b6ee15598767a700ee409eff4da2cd82dd1ed54138390eb02b317d2a97"],"state_sha256":"f087f9cde1bde2bf796c864460cfcee2f4c08cff23d1e543c7da4c8431650d4f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VdQLmjEe0IIFcW6u33OUWFXvUdv8YSohWyMrxmIyORFReDml345WCDk0RqnFo0CRw/6aJ4aTh/mHiB5U38XnDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-21T17:36:30.533693Z","bundle_sha256":"cc1a0a20369359ff01abb789fed549bffbe53fdc32d2500e1afe4fc38e60fc46"}}