{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:4LAAO7JWGDBRXIX744AKAYKASN","short_pith_number":"pith:4LAAO7JW","schema_version":"1.0","canonical_sha256":"e2c0077d3630c31ba2ffe700a061409343c9aee2965cb0336cb353512d9b2473","source":{"kind":"arxiv","id":"2411.00081","version":1},"attestation_state":"computed","paper":{"title":"PARTNR: A Benchmark for Planning and Reasoning in Embodied Multi-agent Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Akshara Rai, Alexander Clegg, Daniel Tran, Eric Undersander, Gunjan Chhablani, Ishita Prasad, Jacob Krantz, Joanne Truong, John M. Turner, Matthew Chang, Michal Hlavac, Mikael Dallaire Cote, Priyam Parashar, Ram Ramrakhya, Roozbeh Mottaghi, Ruta Desai, Siddharth Patki, Tsung-Yen Yang, Vladimir Karashchuk, Xavier Puig","submitted_at":"2024-10-31T17:53:12Z","abstract_excerpt":"We present a benchmark for Planning And Reasoning Tasks in humaN-Robot collaboration (PARTNR) designed to study human-robot coordination in household activities. PARTNR tasks exhibit characteristics of everyday tasks, such as spatial, temporal, and heterogeneous agent capability constraints. We employ a semi-automated task generation pipeline using Large Language Models (LLMs), incorporating simulation in the loop for grounding and verification. PARTNR stands as the largest benchmark of its kind, comprising 100,000 natural language tasks, spanning 60 houses and 5,819 unique objects. We analyze"},"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":"2411.00081","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-10-31T17:53:12Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7d1d369a01e8d9222a1e7135d5a2ba843fe3aa46697eaa9d6e94317536b7cd0d","abstract_canon_sha256":"abc5886bfc684b825be2759466dfa528568e620694736809251668698953b120"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:29:37.355979Z","signature_b64":"3X9rpptZ52w6cQRARqM0kAiDYEKFGsWbKhO894nsQer8lNh3qCmasWYQAEoieW+pdAaq82lL6FYxsnTfTDp/AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e2c0077d3630c31ba2ffe700a061409343c9aee2965cb0336cb353512d9b2473","last_reissued_at":"2026-07-05T09:29:37.355408Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:29:37.355408Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PARTNR: A Benchmark for Planning and Reasoning in Embodied Multi-agent Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Akshara Rai, Alexander Clegg, Daniel Tran, Eric Undersander, Gunjan Chhablani, Ishita Prasad, Jacob Krantz, Joanne Truong, John M. Turner, Matthew Chang, Michal Hlavac, Mikael Dallaire Cote, Priyam Parashar, Ram Ramrakhya, Roozbeh Mottaghi, Ruta Desai, Siddharth Patki, Tsung-Yen Yang, Vladimir Karashchuk, Xavier Puig","submitted_at":"2024-10-31T17:53:12Z","abstract_excerpt":"We present a benchmark for Planning And Reasoning Tasks in humaN-Robot collaboration (PARTNR) designed to study human-robot coordination in household activities. PARTNR tasks exhibit characteristics of everyday tasks, such as spatial, temporal, and heterogeneous agent capability constraints. We employ a semi-automated task generation pipeline using Large Language Models (LLMs), incorporating simulation in the loop for grounding and verification. PARTNR stands as the largest benchmark of its kind, comprising 100,000 natural language tasks, spanning 60 houses and 5,819 unique objects. We analyze"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.00081","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/2411.00081/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":"2411.00081","created_at":"2026-07-05T09:29:37.355464+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.00081v1","created_at":"2026-07-05T09:29:37.355464+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.00081","created_at":"2026-07-05T09:29:37.355464+00:00"},{"alias_kind":"pith_short_12","alias_value":"4LAAO7JWGDBR","created_at":"2026-07-05T09:29:37.355464+00:00"},{"alias_kind":"pith_short_16","alias_value":"4LAAO7JWGDBRXIX7","created_at":"2026-07-05T09:29:37.355464+00:00"},{"alias_kind":"pith_short_8","alias_value":"4LAAO7JW","created_at":"2026-07-05T09:29:37.355464+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.24350","citing_title":"PACT: Proactive Asking for Continual Task Assistance in Human-Robot Collaboration","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2606.28182","citing_title":"LLawCo: Learning Laws of Cooperation for Modeling Embodied Multi-Agent Behavior","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18109","citing_title":"TaskGround: Structured Executable Task Inference for Full-Scene Household Reasoning","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18431","citing_title":"Seeing Together: Multi-Robot Cooperative Egocentric Spatial Reasoning with Multimodal Large Language Models","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2510.05307","citing_title":"When Should Users Check? Modeling Confirmation Frequency inMulti-Step Agentic AI Tasks","ref_index":16,"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":20,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16813","citing_title":"PersonalHomeBench: Evaluating Agents in Personalized Smart Homes","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11174","citing_title":"EmbodiedGovBench: A Benchmark for Governance, Recovery, and Upgrade Safety in Embodied Agent Systems","ref_index":30,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4LAAO7JWGDBRXIX744AKAYKASN","json":"https://pith.science/pith/4LAAO7JWGDBRXIX744AKAYKASN.json","graph_json":"https://pith.science/api/pith-number/4LAAO7JWGDBRXIX744AKAYKASN/graph.json","events_json":"https://pith.science/api/pith-number/4LAAO7JWGDBRXIX744AKAYKASN/events.json","paper":"https://pith.science/paper/4LAAO7JW"},"agent_actions":{"view_html":"https://pith.science/pith/4LAAO7JWGDBRXIX744AKAYKASN","download_json":"https://pith.science/pith/4LAAO7JWGDBRXIX744AKAYKASN.json","view_paper":"https://pith.science/paper/4LAAO7JW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.00081&json=true","fetch_graph":"https://pith.science/api/pith-number/4LAAO7JWGDBRXIX744AKAYKASN/graph.json","fetch_events":"https://pith.science/api/pith-number/4LAAO7JWGDBRXIX744AKAYKASN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4LAAO7JWGDBRXIX744AKAYKASN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4LAAO7JWGDBRXIX744AKAYKASN/action/storage_attestation","attest_author":"https://pith.science/pith/4LAAO7JWGDBRXIX744AKAYKASN/action/author_attestation","sign_citation":"https://pith.science/pith/4LAAO7JWGDBRXIX744AKAYKASN/action/citation_signature","submit_replication":"https://pith.science/pith/4LAAO7JWGDBRXIX744AKAYKASN/action/replication_record"}},"created_at":"2026-07-05T09:29:37.355464+00:00","updated_at":"2026-07-05T09:29:37.355464+00:00"}