{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:XUOJBC4C6DUSXCH4KHD4RG22QB","short_pith_number":"pith:XUOJBC4C","schema_version":"1.0","canonical_sha256":"bd1c908b82f0e92b88fc51c7c89b5a8056bc26aa9dadce57f4f31d900b7f4cc6","source":{"kind":"arxiv","id":"2409.18073","version":1},"attestation_state":"computed","paper":{"title":"Infer Human's Intentions Before Following Natural Language Instructions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.AI","authors_text":"Jiayuan Mao, Natasha Jaques, Yanming Wan, Yiping Wang, Yue Wu","submitted_at":"2024-09-26T17:19:49Z","abstract_excerpt":"For AI agents to be helpful to humans, they should be able to follow natural language instructions to complete everyday cooperative tasks in human environments. However, real human instructions inherently possess ambiguity, because the human speakers assume sufficient prior knowledge about their hidden goals and intentions. Standard language grounding and planning methods fail to address such ambiguities because they do not model human internal goals as additional partially observable factors in the environment. We propose a new framework, Follow Instructions with Social and Embodied Reasoning"},"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":"2409.18073","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-09-26T17:19:49Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"62e5535777410ec6506d57b4933bdf62762897bb639180ca45efd726083fe277","abstract_canon_sha256":"83ec0d42a2ce690054c18066161a81a3172bf77fccbe994f09d9915bab4b71c5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:12:20.142016Z","signature_b64":"6Dzb8491Bo5X/rtILE1R+eeIgfLjhFw55r5LhbBtj+CbJwfqWiUml8gjT0nWd21WOw+0zSEPlwRdv70zpTZEDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bd1c908b82f0e92b88fc51c7c89b5a8056bc26aa9dadce57f4f31d900b7f4cc6","last_reissued_at":"2026-07-05T09:12:20.141523Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:12:20.141523Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Infer Human's Intentions Before Following Natural Language Instructions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.AI","authors_text":"Jiayuan Mao, Natasha Jaques, Yanming Wan, Yiping Wang, Yue Wu","submitted_at":"2024-09-26T17:19:49Z","abstract_excerpt":"For AI agents to be helpful to humans, they should be able to follow natural language instructions to complete everyday cooperative tasks in human environments. However, real human instructions inherently possess ambiguity, because the human speakers assume sufficient prior knowledge about their hidden goals and intentions. Standard language grounding and planning methods fail to address such ambiguities because they do not model human internal goals as additional partially observable factors in the environment. We propose a new framework, Follow Instructions with Social and Embodied Reasoning"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.18073","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/2409.18073/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":"2409.18073","created_at":"2026-07-05T09:12:20.141583+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.18073v1","created_at":"2026-07-05T09:12:20.141583+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.18073","created_at":"2026-07-05T09:12:20.141583+00:00"},{"alias_kind":"pith_short_12","alias_value":"XUOJBC4C6DUS","created_at":"2026-07-05T09:12:20.141583+00:00"},{"alias_kind":"pith_short_16","alias_value":"XUOJBC4C6DUSXCH4","created_at":"2026-07-05T09:12:20.141583+00:00"},{"alias_kind":"pith_short_8","alias_value":"XUOJBC4C","created_at":"2026-07-05T09:12:20.141583+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2504.17950","citing_title":"Collaborating Action by Action: A Multi-agent LLM Framework for Embodied Reasoning","ref_index":16,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XUOJBC4C6DUSXCH4KHD4RG22QB","json":"https://pith.science/pith/XUOJBC4C6DUSXCH4KHD4RG22QB.json","graph_json":"https://pith.science/api/pith-number/XUOJBC4C6DUSXCH4KHD4RG22QB/graph.json","events_json":"https://pith.science/api/pith-number/XUOJBC4C6DUSXCH4KHD4RG22QB/events.json","paper":"https://pith.science/paper/XUOJBC4C"},"agent_actions":{"view_html":"https://pith.science/pith/XUOJBC4C6DUSXCH4KHD4RG22QB","download_json":"https://pith.science/pith/XUOJBC4C6DUSXCH4KHD4RG22QB.json","view_paper":"https://pith.science/paper/XUOJBC4C","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.18073&json=true","fetch_graph":"https://pith.science/api/pith-number/XUOJBC4C6DUSXCH4KHD4RG22QB/graph.json","fetch_events":"https://pith.science/api/pith-number/XUOJBC4C6DUSXCH4KHD4RG22QB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XUOJBC4C6DUSXCH4KHD4RG22QB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XUOJBC4C6DUSXCH4KHD4RG22QB/action/storage_attestation","attest_author":"https://pith.science/pith/XUOJBC4C6DUSXCH4KHD4RG22QB/action/author_attestation","sign_citation":"https://pith.science/pith/XUOJBC4C6DUSXCH4KHD4RG22QB/action/citation_signature","submit_replication":"https://pith.science/pith/XUOJBC4C6DUSXCH4KHD4RG22QB/action/replication_record"}},"created_at":"2026-07-05T09:12:20.141583+00:00","updated_at":"2026-07-05T09:12:20.141583+00:00"}