{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:ANEXRLB7PDEZ6NW45CAWU3LLWW","short_pith_number":"pith:ANEXRLB7","schema_version":"1.0","canonical_sha256":"034978ac3f78c99f36dce8816a6d6bb59714300a3cd1396405d09dc2b6c94385","source":{"kind":"arxiv","id":"2103.14025","version":1},"attestation_state":"computed","paper":{"title":"The ThreeDWorld Transport Challenge: A Visually Guided Task-and-Motion Planning Benchmark for Physically Realistic Embodied AI","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.RO"],"primary_cat":"cs.CV","authors_text":"Abhishek Bhandwaldar, Antonio Torralba, Chuang Gan, Dan Gutfreund, Daniel L.K. Yamins, James J DiCarlo, Jeremy Schwartz, Josh McDermott, Joshua B. Tenenbaum, Seth Alter, Siyuan Zhou","submitted_at":"2021-03-25T17:59:08Z","abstract_excerpt":"We introduce a visually-guided and physics-driven task-and-motion planning benchmark, which we call the ThreeDWorld Transport Challenge. In this challenge, an embodied agent equipped with two 9-DOF articulated arms is spawned randomly in a simulated physical home environment. The agent is required to find a small set of objects scattered around the house, pick them up, and transport them to a desired final location. We also position containers around the house that can be used as tools to assist with transporting objects efficiently. To complete the task, an embodied agent must plan a sequence"},"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":"2103.14025","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-03-25T17:59:08Z","cross_cats_sorted":["cs.AI","cs.LG","cs.RO"],"title_canon_sha256":"d983b620afe89deeb230fc210320f7050b2c31d9dd1c1d66b76dff5957076975","abstract_canon_sha256":"79e6399602262d8c2308f0c7461b3eb31ac873788b914b2c3da26c064b0d44c6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:26:24.752154Z","signature_b64":"vTJ7Ornqe09RFaG6BW1ysttes+dYmDZ+/piCrUBMa+jFh5nPNHf9XLfijXvvAb9t5967D5iLL1sa6kBIzDFmAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"034978ac3f78c99f36dce8816a6d6bb59714300a3cd1396405d09dc2b6c94385","last_reissued_at":"2026-07-05T02:26:24.751674Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:26:24.751674Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The ThreeDWorld Transport Challenge: A Visually Guided Task-and-Motion Planning Benchmark for Physically Realistic Embodied AI","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.RO"],"primary_cat":"cs.CV","authors_text":"Abhishek Bhandwaldar, Antonio Torralba, Chuang Gan, Dan Gutfreund, Daniel L.K. Yamins, James J DiCarlo, Jeremy Schwartz, Josh McDermott, Joshua B. Tenenbaum, Seth Alter, Siyuan Zhou","submitted_at":"2021-03-25T17:59:08Z","abstract_excerpt":"We introduce a visually-guided and physics-driven task-and-motion planning benchmark, which we call the ThreeDWorld Transport Challenge. In this challenge, an embodied agent equipped with two 9-DOF articulated arms is spawned randomly in a simulated physical home environment. The agent is required to find a small set of objects scattered around the house, pick them up, and transport them to a desired final location. We also position containers around the house that can be used as tools to assist with transporting objects efficiently. To complete the task, an embodied agent must plan a sequence"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.14025","kind":"arxiv","version":1},"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/2103.14025/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":"2103.14025","created_at":"2026-07-05T02:26:24.751752+00:00"},{"alias_kind":"arxiv_version","alias_value":"2103.14025v1","created_at":"2026-07-05T02:26:24.751752+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.14025","created_at":"2026-07-05T02:26:24.751752+00:00"},{"alias_kind":"pith_short_12","alias_value":"ANEXRLB7PDEZ","created_at":"2026-07-05T02:26:24.751752+00:00"},{"alias_kind":"pith_short_16","alias_value":"ANEXRLB7PDEZ6NW4","created_at":"2026-07-05T02:26:24.751752+00:00"},{"alias_kind":"pith_short_8","alias_value":"ANEXRLB7","created_at":"2026-07-05T02:26:24.751752+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.17511","citing_title":"MagicSim: A Unified Infrastructure for Executable Embodied Interaction","ref_index":107,"is_internal_anchor":false},{"citing_arxiv_id":"2505.20122","citing_title":"MEBench: A Novel Benchmark for Understanding Mutual Exclusivity Bias in Vision-Language Models","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2403.09227","citing_title":"BEHAVIOR-1K: A Human-Centered, Embodied AI Benchmark with 1,000 Everyday Activities and Realistic Simulation","ref_index":19,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ANEXRLB7PDEZ6NW45CAWU3LLWW","json":"https://pith.science/pith/ANEXRLB7PDEZ6NW45CAWU3LLWW.json","graph_json":"https://pith.science/api/pith-number/ANEXRLB7PDEZ6NW45CAWU3LLWW/graph.json","events_json":"https://pith.science/api/pith-number/ANEXRLB7PDEZ6NW45CAWU3LLWW/events.json","paper":"https://pith.science/paper/ANEXRLB7"},"agent_actions":{"view_html":"https://pith.science/pith/ANEXRLB7PDEZ6NW45CAWU3LLWW","download_json":"https://pith.science/pith/ANEXRLB7PDEZ6NW45CAWU3LLWW.json","view_paper":"https://pith.science/paper/ANEXRLB7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2103.14025&json=true","fetch_graph":"https://pith.science/api/pith-number/ANEXRLB7PDEZ6NW45CAWU3LLWW/graph.json","fetch_events":"https://pith.science/api/pith-number/ANEXRLB7PDEZ6NW45CAWU3LLWW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ANEXRLB7PDEZ6NW45CAWU3LLWW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ANEXRLB7PDEZ6NW45CAWU3LLWW/action/storage_attestation","attest_author":"https://pith.science/pith/ANEXRLB7PDEZ6NW45CAWU3LLWW/action/author_attestation","sign_citation":"https://pith.science/pith/ANEXRLB7PDEZ6NW45CAWU3LLWW/action/citation_signature","submit_replication":"https://pith.science/pith/ANEXRLB7PDEZ6NW45CAWU3LLWW/action/replication_record"}},"created_at":"2026-07-05T02:26:24.751752+00:00","updated_at":"2026-07-05T02:26:24.751752+00:00"}