{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:ZKQ7OI7QRCZSDCOGMATIJX7TE5","short_pith_number":"pith:ZKQ7OI7Q","schema_version":"1.0","canonical_sha256":"caa1f723f088b32189c6602684dff32740cf1c4a6bbde7c8268e61872a9731d5","source":{"kind":"arxiv","id":"2302.00763","version":1},"attestation_state":"computed","paper":{"title":"Collaborating with language models for embodied reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Arun Ahuja, Christine Kaeser-Chen, Felix Hill, Ishita Dasgupta, Kenneth Marino, Rob Fergus, Sheila Babayan","submitted_at":"2023-02-01T21:26:32Z","abstract_excerpt":"Reasoning in a complex and ambiguous environment is a key goal for Reinforcement Learning (RL) agents. While some sophisticated RL agents can successfully solve difficult tasks, they require a large amount of training data and often struggle to generalize to new unseen environments and new tasks. On the other hand, Large Scale Language Models (LSLMs) have exhibited strong reasoning ability and the ability to to adapt to new tasks through in-context learning. However, LSLMs do not inherently have the ability to interrogate or intervene on the environment. In this work, we investigate how to com"},"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":"2302.00763","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-02-01T21:26:32Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"3e981023e7e9c42b272f8280424371d6d74a612077f10301e1dcafe9e14ab10e","abstract_canon_sha256":"cdd4fa1dec7b5ae7c5697897d8474907162db61cb71e0111985a0b0b6109ba14"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:38:11.957531Z","signature_b64":"6vw3lqyXeVHLiOykfHh2Zq1M2a5O4LAcYy/z4cz3eHFqV0Z2ShFXgmQqfO0XJSOwaOFUBCJVzCrku+b9/tPZBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"caa1f723f088b32189c6602684dff32740cf1c4a6bbde7c8268e61872a9731d5","last_reissued_at":"2026-07-05T05:38:11.957092Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:38:11.957092Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Collaborating with language models for embodied reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Arun Ahuja, Christine Kaeser-Chen, Felix Hill, Ishita Dasgupta, Kenneth Marino, Rob Fergus, Sheila Babayan","submitted_at":"2023-02-01T21:26:32Z","abstract_excerpt":"Reasoning in a complex and ambiguous environment is a key goal for Reinforcement Learning (RL) agents. While some sophisticated RL agents can successfully solve difficult tasks, they require a large amount of training data and often struggle to generalize to new unseen environments and new tasks. On the other hand, Large Scale Language Models (LSLMs) have exhibited strong reasoning ability and the ability to to adapt to new tasks through in-context learning. However, LSLMs do not inherently have the ability to interrogate or intervene on the environment. In this work, we investigate how to com"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.00763","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/2302.00763/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":"2302.00763","created_at":"2026-07-05T05:38:11.957148+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.00763v1","created_at":"2026-07-05T05:38:11.957148+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.00763","created_at":"2026-07-05T05:38:11.957148+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZKQ7OI7QRCZS","created_at":"2026-07-05T05:38:11.957148+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZKQ7OI7QRCZSDCOG","created_at":"2026-07-05T05:38:11.957148+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZKQ7OI7Q","created_at":"2026-07-05T05:38:11.957148+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2308.11432","citing_title":"A Survey on Large Language Model based Autonomous Agents","ref_index":138,"is_internal_anchor":false},{"citing_arxiv_id":"2402.01680","citing_title":"Large Language Model based Multi-Agents: A Survey of Progress and Challenges","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07462","citing_title":"The Moltbook Files: A Harmless Slopocalypse or Humanity's Last Experiment","ref_index":47,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZKQ7OI7QRCZSDCOGMATIJX7TE5","json":"https://pith.science/pith/ZKQ7OI7QRCZSDCOGMATIJX7TE5.json","graph_json":"https://pith.science/api/pith-number/ZKQ7OI7QRCZSDCOGMATIJX7TE5/graph.json","events_json":"https://pith.science/api/pith-number/ZKQ7OI7QRCZSDCOGMATIJX7TE5/events.json","paper":"https://pith.science/paper/ZKQ7OI7Q"},"agent_actions":{"view_html":"https://pith.science/pith/ZKQ7OI7QRCZSDCOGMATIJX7TE5","download_json":"https://pith.science/pith/ZKQ7OI7QRCZSDCOGMATIJX7TE5.json","view_paper":"https://pith.science/paper/ZKQ7OI7Q","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.00763&json=true","fetch_graph":"https://pith.science/api/pith-number/ZKQ7OI7QRCZSDCOGMATIJX7TE5/graph.json","fetch_events":"https://pith.science/api/pith-number/ZKQ7OI7QRCZSDCOGMATIJX7TE5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZKQ7OI7QRCZSDCOGMATIJX7TE5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZKQ7OI7QRCZSDCOGMATIJX7TE5/action/storage_attestation","attest_author":"https://pith.science/pith/ZKQ7OI7QRCZSDCOGMATIJX7TE5/action/author_attestation","sign_citation":"https://pith.science/pith/ZKQ7OI7QRCZSDCOGMATIJX7TE5/action/citation_signature","submit_replication":"https://pith.science/pith/ZKQ7OI7QRCZSDCOGMATIJX7TE5/action/replication_record"}},"created_at":"2026-07-05T05:38:11.957148+00:00","updated_at":"2026-07-05T05:38:11.957148+00:00"}