{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ZJSFBEXQ2V2CNLTLIM3EE2WYOT","short_pith_number":"pith:ZJSFBEXQ","schema_version":"1.0","canonical_sha256":"ca645092f0d57426ae6b4336426ad874f507271ad7c9b60bce6f360fd3588f95","source":{"kind":"arxiv","id":"2508.03232","version":1},"attestation_state":"computed","paper":{"title":"CookBench: A Long-Horizon Embodied Planning Benchmark for Complex Cooking Scenarios","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Jiaxin Zhang, Muzhen Cai, Ting Liu, Wang Xu, Weinan Zhang, Xiubo Chen, Xuesong Wang, Yining An","submitted_at":"2025-08-05T09:01:47Z","abstract_excerpt":"Embodied Planning is dedicated to the goal of creating agents capable of executing long-horizon tasks in complex physical worlds. However, existing embodied planning benchmarks frequently feature short-horizon tasks and coarse-grained action primitives. To address this challenge, we introduce CookBench, a benchmark for long-horizon planning in complex cooking scenarios. By leveraging a high-fidelity simulation environment built upon the powerful Unity game engine, we define frontier AI challenges in a complex, realistic environment. The core task in CookBench is designed as a two-stage process"},"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":"2508.03232","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-08-05T09:01:47Z","cross_cats_sorted":[],"title_canon_sha256":"077cd891d4845531fb5989c0d924f831fb78c58b57bc062b870b48c4d5d82bcf","abstract_canon_sha256":"69e14050ea1582ffc41a1e6c29afdbf6ea08b254cc0bfcb6d99c0fa8e209a519"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:48:39.442509Z","signature_b64":"ztTTsPtU41H+Ivczq4iEUVUi3hAhEyUMhWglVpewVEurAvJo2tCeFevslcj/HMkYV1h/SqWIByhwxYy4iNsfCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ca645092f0d57426ae6b4336426ad874f507271ad7c9b60bce6f360fd3588f95","last_reissued_at":"2026-07-05T11:48:39.441977Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:48:39.441977Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CookBench: A Long-Horizon Embodied Planning Benchmark for Complex Cooking Scenarios","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Jiaxin Zhang, Muzhen Cai, Ting Liu, Wang Xu, Weinan Zhang, Xiubo Chen, Xuesong Wang, Yining An","submitted_at":"2025-08-05T09:01:47Z","abstract_excerpt":"Embodied Planning is dedicated to the goal of creating agents capable of executing long-horizon tasks in complex physical worlds. However, existing embodied planning benchmarks frequently feature short-horizon tasks and coarse-grained action primitives. To address this challenge, we introduce CookBench, a benchmark for long-horizon planning in complex cooking scenarios. By leveraging a high-fidelity simulation environment built upon the powerful Unity game engine, we define frontier AI challenges in a complex, realistic environment. The core task in CookBench is designed as a two-stage process"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.03232","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/2508.03232/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":"2508.03232","created_at":"2026-07-05T11:48:39.442037+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.03232v1","created_at":"2026-07-05T11:48:39.442037+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.03232","created_at":"2026-07-05T11:48:39.442037+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZJSFBEXQ2V2C","created_at":"2026-07-05T11:48:39.442037+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZJSFBEXQ2V2CNLTL","created_at":"2026-07-05T11:48:39.442037+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZJSFBEXQ","created_at":"2026-07-05T11:48:39.442037+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.25788","citing_title":"KinDER: A Physical Reasoning Benchmark for Robot Learning and Planning","ref_index":82,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07774","citing_title":"RoboAgent: Chaining Basic Capabilities for Embodied Task Planning","ref_index":10,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZJSFBEXQ2V2CNLTLIM3EE2WYOT","json":"https://pith.science/pith/ZJSFBEXQ2V2CNLTLIM3EE2WYOT.json","graph_json":"https://pith.science/api/pith-number/ZJSFBEXQ2V2CNLTLIM3EE2WYOT/graph.json","events_json":"https://pith.science/api/pith-number/ZJSFBEXQ2V2CNLTLIM3EE2WYOT/events.json","paper":"https://pith.science/paper/ZJSFBEXQ"},"agent_actions":{"view_html":"https://pith.science/pith/ZJSFBEXQ2V2CNLTLIM3EE2WYOT","download_json":"https://pith.science/pith/ZJSFBEXQ2V2CNLTLIM3EE2WYOT.json","view_paper":"https://pith.science/paper/ZJSFBEXQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.03232&json=true","fetch_graph":"https://pith.science/api/pith-number/ZJSFBEXQ2V2CNLTLIM3EE2WYOT/graph.json","fetch_events":"https://pith.science/api/pith-number/ZJSFBEXQ2V2CNLTLIM3EE2WYOT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZJSFBEXQ2V2CNLTLIM3EE2WYOT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZJSFBEXQ2V2CNLTLIM3EE2WYOT/action/storage_attestation","attest_author":"https://pith.science/pith/ZJSFBEXQ2V2CNLTLIM3EE2WYOT/action/author_attestation","sign_citation":"https://pith.science/pith/ZJSFBEXQ2V2CNLTLIM3EE2WYOT/action/citation_signature","submit_replication":"https://pith.science/pith/ZJSFBEXQ2V2CNLTLIM3EE2WYOT/action/replication_record"}},"created_at":"2026-07-05T11:48:39.442037+00:00","updated_at":"2026-07-05T11:48:39.442037+00:00"}