{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:4R3OIYEJZJMIXAMSPYOLXTYRE6","short_pith_number":"pith:4R3OIYEJ","schema_version":"1.0","canonical_sha256":"e476e46089ca588b81927e1cbbcf112797d5237769a953bccb19838363c1166a","source":{"kind":"arxiv","id":"2010.09890","version":2},"attestation_state":"computed","paper":{"title":"Watch-And-Help: A Challenge for Social Perception and Human-AI Collaboration","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG","cs.MA"],"primary_cat":"cs.AI","authors_text":"Antonio Torralba, Joshua B. Tenenbaum, Sanja Fidler, Shuang Li, Tianmin Shu, Xavier Puig, Yuan-Hong Liao, Zilin Wang","submitted_at":"2020-10-19T21:48:31Z","abstract_excerpt":"In this paper, we introduce Watch-And-Help (WAH), a challenge for testing social intelligence in agents. In WAH, an AI agent needs to help a human-like agent perform a complex household task efficiently. To succeed, the AI agent needs to i) understand the underlying goal of the task by watching a single demonstration of the human-like agent performing the same task (social perception), and ii) coordinate with the human-like agent to solve the task in an unseen environment as fast as possible (human-AI collaboration). For this challenge, we build VirtualHome-Social, a multi-agent household envi"},"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":"2010.09890","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2020-10-19T21:48:31Z","cross_cats_sorted":["cs.LG","cs.MA"],"title_canon_sha256":"d01320266fe5d85a9eb5ebe09da73cfa59cf3edced9f716c50ee419ab3fdc537","abstract_canon_sha256":"24184fea5dd06d519b75c4e6b437cd7f1153c67cd45a175cc5f5e70234126cfb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:36:45.993629Z","signature_b64":"s1kGRR+/hU14ZDcn8sHfQb7gkczgQCdpgNzyIXd+VQydwUnTIflNBY6CP/zUPW+EZzKu8mz52FISMq0TcMhOCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e476e46089ca588b81927e1cbbcf112797d5237769a953bccb19838363c1166a","last_reissued_at":"2026-07-05T02:36:45.993086Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:36:45.993086Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Watch-And-Help: A Challenge for Social Perception and Human-AI Collaboration","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG","cs.MA"],"primary_cat":"cs.AI","authors_text":"Antonio Torralba, Joshua B. Tenenbaum, Sanja Fidler, Shuang Li, Tianmin Shu, Xavier Puig, Yuan-Hong Liao, Zilin Wang","submitted_at":"2020-10-19T21:48:31Z","abstract_excerpt":"In this paper, we introduce Watch-And-Help (WAH), a challenge for testing social intelligence in agents. In WAH, an AI agent needs to help a human-like agent perform a complex household task efficiently. To succeed, the AI agent needs to i) understand the underlying goal of the task by watching a single demonstration of the human-like agent performing the same task (social perception), and ii) coordinate with the human-like agent to solve the task in an unseen environment as fast as possible (human-AI collaboration). For this challenge, we build VirtualHome-Social, a multi-agent household envi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.09890","kind":"arxiv","version":2},"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/2010.09890/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":"2010.09890","created_at":"2026-07-05T02:36:45.993151+00:00"},{"alias_kind":"arxiv_version","alias_value":"2010.09890v2","created_at":"2026-07-05T02:36:45.993151+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.09890","created_at":"2026-07-05T02:36:45.993151+00:00"},{"alias_kind":"pith_short_12","alias_value":"4R3OIYEJZJMI","created_at":"2026-07-05T02:36:45.993151+00:00"},{"alias_kind":"pith_short_16","alias_value":"4R3OIYEJZJMIXAMS","created_at":"2026-07-05T02:36:45.993151+00:00"},{"alias_kind":"pith_short_8","alias_value":"4R3OIYEJ","created_at":"2026-07-05T02:36:45.993151+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":11,"internal_anchor_count":3,"sample":[{"citing_arxiv_id":"2607.06691","citing_title":"CoMind: Understanding Collaborative Human Activity from Multiple Minds and Views","ref_index":62,"is_internal_anchor":true},{"citing_arxiv_id":"2607.06534","citing_title":"CAIRN: Cross-Room 3D Scene Understanding with Topology-Aware Large Multimodal Models","ref_index":41,"is_internal_anchor":true},{"citing_arxiv_id":"2605.27394","citing_title":"Human-AI Collaboration for Estimating Scientific Replicability","ref_index":49,"is_internal_anchor":true},{"citing_arxiv_id":"2606.28182","citing_title":"LLawCo: Learning Laws of Cooperation for Modeling Embodied Multi-Agent Behavior","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22995","citing_title":"Whose Good, Whose Place? The Moral Geography of Agentic AI for Social Good","ref_index":82,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12920","citing_title":"Embodied Multi-Agent Coordination by Aligning World Models Through Dialogue","ref_index":37,"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":24,"is_internal_anchor":false},{"citing_arxiv_id":"2401.03568","citing_title":"Agent AI: Surveying the Horizons of Multimodal Interaction","ref_index":206,"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":24,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11688","citing_title":"Shaping Zero-Shot Coordination via State Blocking","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17019","citing_title":"Mini-BEHAVIOR-Gran: Revealing U-Shaped Effects of Instruction Granularity on Language-Guided Embodied Agents","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4R3OIYEJZJMIXAMSPYOLXTYRE6","json":"https://pith.science/pith/4R3OIYEJZJMIXAMSPYOLXTYRE6.json","graph_json":"https://pith.science/api/pith-number/4R3OIYEJZJMIXAMSPYOLXTYRE6/graph.json","events_json":"https://pith.science/api/pith-number/4R3OIYEJZJMIXAMSPYOLXTYRE6/events.json","paper":"https://pith.science/paper/4R3OIYEJ"},"agent_actions":{"view_html":"https://pith.science/pith/4R3OIYEJZJMIXAMSPYOLXTYRE6","download_json":"https://pith.science/pith/4R3OIYEJZJMIXAMSPYOLXTYRE6.json","view_paper":"https://pith.science/paper/4R3OIYEJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2010.09890&json=true","fetch_graph":"https://pith.science/api/pith-number/4R3OIYEJZJMIXAMSPYOLXTYRE6/graph.json","fetch_events":"https://pith.science/api/pith-number/4R3OIYEJZJMIXAMSPYOLXTYRE6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4R3OIYEJZJMIXAMSPYOLXTYRE6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4R3OIYEJZJMIXAMSPYOLXTYRE6/action/storage_attestation","attest_author":"https://pith.science/pith/4R3OIYEJZJMIXAMSPYOLXTYRE6/action/author_attestation","sign_citation":"https://pith.science/pith/4R3OIYEJZJMIXAMSPYOLXTYRE6/action/citation_signature","submit_replication":"https://pith.science/pith/4R3OIYEJZJMIXAMSPYOLXTYRE6/action/replication_record"}},"created_at":"2026-07-05T02:36:45.993151+00:00","updated_at":"2026-07-05T02:36:45.993151+00:00"}