{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:4GMVRD56KIGAOZBNP7BYUZXOWC","short_pith_number":"pith:4GMVRD56","schema_version":"1.0","canonical_sha256":"e199588fbe520c07642d7fc38a66eeb09a6ef22663b841c52531f352dd63cad3","source":{"kind":"arxiv","id":"2312.06722","version":3},"attestation_state":"computed","paper":{"title":"EgoPlan-Bench: Benchmarking Multimodal Large Language Models for Human-Level Planning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.RO"],"primary_cat":"cs.CV","authors_text":"Bohao Li, Mingyu Ding, Ruifeng Xu, Rui Wang, Xihui Liu, Yi Chen, Ying Shan, Yixiao Ge, Yuying Ge","submitted_at":"2023-12-11T03:35:58Z","abstract_excerpt":"The pursuit of artificial general intelligence (AGI) has been accelerated by Multimodal Large Language Models (MLLMs), which exhibit superior reasoning, generalization capabilities, and proficiency in processing multimodal inputs. A crucial milestone in the evolution of AGI is the attainment of human-level planning, a fundamental ability for making informed decisions in complex environments, and solving a wide range of real-world problems. Despite the impressive advancements in MLLMs, a question remains: How far are current MLLMs from achieving human-level planning? To shed light on this quest"},"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":"2312.06722","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-11T03:35:58Z","cross_cats_sorted":["cs.CL","cs.RO"],"title_canon_sha256":"5dea9ce68c2b956ad2646af06958a1022945efbeb29ca0164faf00e039b68127","abstract_canon_sha256":"c1cc48872b8ee596830a07bd3dfcc59701aa186396c04c66b16ca83dbd3b6e7b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:30:06.762219Z","signature_b64":"wG9Kduu7aaXN/akMEgFY4RWa+DKpXmmj3IJ/bZHwXK57rXVwIz1Po9Vk63CcPdQsk3jwchLr2LBd70RV4WKgCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e199588fbe520c07642d7fc38a66eeb09a6ef22663b841c52531f352dd63cad3","last_reissued_at":"2026-07-05T08:30:06.761748Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:30:06.761748Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EgoPlan-Bench: Benchmarking Multimodal Large Language Models for Human-Level Planning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.RO"],"primary_cat":"cs.CV","authors_text":"Bohao Li, Mingyu Ding, Ruifeng Xu, Rui Wang, Xihui Liu, Yi Chen, Ying Shan, Yixiao Ge, Yuying Ge","submitted_at":"2023-12-11T03:35:58Z","abstract_excerpt":"The pursuit of artificial general intelligence (AGI) has been accelerated by Multimodal Large Language Models (MLLMs), which exhibit superior reasoning, generalization capabilities, and proficiency in processing multimodal inputs. A crucial milestone in the evolution of AGI is the attainment of human-level planning, a fundamental ability for making informed decisions in complex environments, and solving a wide range of real-world problems. Despite the impressive advancements in MLLMs, a question remains: How far are current MLLMs from achieving human-level planning? To shed light on this quest"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.06722","kind":"arxiv","version":3},"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/2312.06722/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":"2312.06722","created_at":"2026-07-05T08:30:06.761801+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.06722v3","created_at":"2026-07-05T08:30:06.761801+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.06722","created_at":"2026-07-05T08:30:06.761801+00:00"},{"alias_kind":"pith_short_12","alias_value":"4GMVRD56KIGA","created_at":"2026-07-05T08:30:06.761801+00:00"},{"alias_kind":"pith_short_16","alias_value":"4GMVRD56KIGAOZBN","created_at":"2026-07-05T08:30:06.761801+00:00"},{"alias_kind":"pith_short_8","alias_value":"4GMVRD56","created_at":"2026-07-05T08:30:06.761801+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":11,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.24338","citing_title":"RoBoSR: Structured Scene Representations for Embodied Robotic Reasoning","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2606.24422","citing_title":"EgoSAT: A Comprehensive Benchmark of Egocentric Streaming Interaction Understanding","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.31529","citing_title":"SVI-Bench: A Dynamic Microworld for Strategic Video Intelligence","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2605.31529","citing_title":"SVI-Bench: A Dynamic Microworld for Strategic Video Intelligence","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2405.14093","citing_title":"A Survey on Vision-Language-Action Models for Embodied AI","ref_index":200,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19559","citing_title":"EgoCoT-Bench: Benchmarking Grounded and Verifiable Operation-Centric Chain of Thought Reasoning for MLLMs","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2507.16815","citing_title":"ThinkAct: Vision-Language-Action Reasoning via Reinforced Visual Latent Planning","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2511.16518","citing_title":"MiMo-Embodied: X-Embodied Foundation Model Technical Report","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2508.13073","citing_title":"Large VLM-based Vision-Language-Action Models for Robotic Manipulation: A Survey","ref_index":227,"is_internal_anchor":false},{"citing_arxiv_id":"2604.27472","citing_title":"PRTS: A Primitive Reasoning and Tasking System via Contrastive Representations","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16022","citing_title":"SocialGrid: A Benchmark for Planning and Social Reasoning in Embodied Multi-Agent Systems","ref_index":5,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4GMVRD56KIGAOZBNP7BYUZXOWC","json":"https://pith.science/pith/4GMVRD56KIGAOZBNP7BYUZXOWC.json","graph_json":"https://pith.science/api/pith-number/4GMVRD56KIGAOZBNP7BYUZXOWC/graph.json","events_json":"https://pith.science/api/pith-number/4GMVRD56KIGAOZBNP7BYUZXOWC/events.json","paper":"https://pith.science/paper/4GMVRD56"},"agent_actions":{"view_html":"https://pith.science/pith/4GMVRD56KIGAOZBNP7BYUZXOWC","download_json":"https://pith.science/pith/4GMVRD56KIGAOZBNP7BYUZXOWC.json","view_paper":"https://pith.science/paper/4GMVRD56","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.06722&json=true","fetch_graph":"https://pith.science/api/pith-number/4GMVRD56KIGAOZBNP7BYUZXOWC/graph.json","fetch_events":"https://pith.science/api/pith-number/4GMVRD56KIGAOZBNP7BYUZXOWC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4GMVRD56KIGAOZBNP7BYUZXOWC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4GMVRD56KIGAOZBNP7BYUZXOWC/action/storage_attestation","attest_author":"https://pith.science/pith/4GMVRD56KIGAOZBNP7BYUZXOWC/action/author_attestation","sign_citation":"https://pith.science/pith/4GMVRD56KIGAOZBNP7BYUZXOWC/action/citation_signature","submit_replication":"https://pith.science/pith/4GMVRD56KIGAOZBNP7BYUZXOWC/action/replication_record"}},"created_at":"2026-07-05T08:30:06.761801+00:00","updated_at":"2026-07-05T08:30:06.761801+00:00"}