{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:TY37JXRPT62UALQKSWCGT73QF4","short_pith_number":"pith:TY37JXRP","schema_version":"1.0","canonical_sha256":"9e37f4de2f9fb5402e0a958469ff702f2818bcabb1700fc5022a4932647eaa26","source":{"kind":"arxiv","id":"2402.08178","version":1},"attestation_state":"computed","paper":{"title":"LoTa-Bench: Benchmarking Language-oriented Task Planners for Embodied Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Hyobin Ong, Jaehong Kim, Jae-Woo Choi, Minsu Jang, Youngwoo Yoon","submitted_at":"2024-02-13T02:28:57Z","abstract_excerpt":"Large language models (LLMs) have recently received considerable attention as alternative solutions for task planning. However, comparing the performance of language-oriented task planners becomes difficult, and there exists a dearth of detailed exploration regarding the effects of various factors such as pre-trained model selection and prompt construction. To address this, we propose a benchmark system for automatically quantifying performance of task planning for home-service embodied agents. Task planners are tested on two pairs of datasets and simulators: 1) ALFRED and AI2-THOR, 2) an exte"},"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":"2402.08178","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-02-13T02:28:57Z","cross_cats_sorted":[],"title_canon_sha256":"6315accc1ed6edee39d6fa856d1ec69ff15edf4b53a73ce2014651694f1ce900","abstract_canon_sha256":"f457de8436d8cc6a5a0b374e163fb99bb2d3af0d4c27abdd4fe96f46fa1dc717"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:44:28.228714Z","signature_b64":"010VlcqSEowa+0XRFZ8qlTOmyHrK8/uKYC+6HyQubPjH14WyPlwWUgpbwThCLEMPTEBkfEQYS3t7bxgRH11MBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9e37f4de2f9fb5402e0a958469ff702f2818bcabb1700fc5022a4932647eaa26","last_reissued_at":"2026-07-05T07:44:28.228258Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:44:28.228258Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LoTa-Bench: Benchmarking Language-oriented Task Planners for Embodied Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Hyobin Ong, Jaehong Kim, Jae-Woo Choi, Minsu Jang, Youngwoo Yoon","submitted_at":"2024-02-13T02:28:57Z","abstract_excerpt":"Large language models (LLMs) have recently received considerable attention as alternative solutions for task planning. However, comparing the performance of language-oriented task planners becomes difficult, and there exists a dearth of detailed exploration regarding the effects of various factors such as pre-trained model selection and prompt construction. To address this, we propose a benchmark system for automatically quantifying performance of task planning for home-service embodied agents. Task planners are tested on two pairs of datasets and simulators: 1) ALFRED and AI2-THOR, 2) an exte"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.08178","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/2402.08178/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":"2402.08178","created_at":"2026-07-05T07:44:28.228322+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.08178v1","created_at":"2026-07-05T07:44:28.228322+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.08178","created_at":"2026-07-05T07:44:28.228322+00:00"},{"alias_kind":"pith_short_12","alias_value":"TY37JXRPT62U","created_at":"2026-07-05T07:44:28.228322+00:00"},{"alias_kind":"pith_short_16","alias_value":"TY37JXRPT62UALQK","created_at":"2026-07-05T07:44:28.228322+00:00"},{"alias_kind":"pith_short_8","alias_value":"TY37JXRP","created_at":"2026-07-05T07:44:28.228322+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.29662","citing_title":"SAFE-Pruner: Semantic Attention-Guided Future-Aware Token Pruning for Efficient Vision-Language-Action Manipulation","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2405.14093","citing_title":"A Survey on Vision-Language-Action Models for Embodied AI","ref_index":203,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14504","citing_title":"When Robots Do the Chores: A Benchmark and Agent for Long-Horizon Household Task Execution","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18109","citing_title":"TaskGround: Structured Executable Task Inference for Full-Scene Household Reasoning","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2602.08392","citing_title":"ST-BiBench: Benchmarking Multi-Stream Multimodal Coordination in Bimanual Embodied Tasks for MLLMs","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14504","citing_title":"When Robots Do the Chores: A Benchmark and Agent for Long-Horizon Household Task Execution","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2507.21046","citing_title":"A Survey of Self-Evolving Agents: What, When, How, and Where to Evolve on the Path to Artificial Super Intelligence","ref_index":114,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TY37JXRPT62UALQKSWCGT73QF4","json":"https://pith.science/pith/TY37JXRPT62UALQKSWCGT73QF4.json","graph_json":"https://pith.science/api/pith-number/TY37JXRPT62UALQKSWCGT73QF4/graph.json","events_json":"https://pith.science/api/pith-number/TY37JXRPT62UALQKSWCGT73QF4/events.json","paper":"https://pith.science/paper/TY37JXRP"},"agent_actions":{"view_html":"https://pith.science/pith/TY37JXRPT62UALQKSWCGT73QF4","download_json":"https://pith.science/pith/TY37JXRPT62UALQKSWCGT73QF4.json","view_paper":"https://pith.science/paper/TY37JXRP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.08178&json=true","fetch_graph":"https://pith.science/api/pith-number/TY37JXRPT62UALQKSWCGT73QF4/graph.json","fetch_events":"https://pith.science/api/pith-number/TY37JXRPT62UALQKSWCGT73QF4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TY37JXRPT62UALQKSWCGT73QF4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TY37JXRPT62UALQKSWCGT73QF4/action/storage_attestation","attest_author":"https://pith.science/pith/TY37JXRPT62UALQKSWCGT73QF4/action/author_attestation","sign_citation":"https://pith.science/pith/TY37JXRPT62UALQKSWCGT73QF4/action/citation_signature","submit_replication":"https://pith.science/pith/TY37JXRPT62UALQKSWCGT73QF4/action/replication_record"}},"created_at":"2026-07-05T07:44:28.228322+00:00","updated_at":"2026-07-05T07:44:28.228322+00:00"}