{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:RIJWQIQWH4DNXMWQLWAUINSQTO","short_pith_number":"pith:RIJWQIQW","schema_version":"1.0","canonical_sha256":"8a136822163f06dbb2d05d814436509b864dcc07f253480fe030a85ade2b0724","source":{"kind":"arxiv","id":"2306.08400","version":1},"attestation_state":"computed","paper":{"title":"Simple Embodied Language Learning as a Byproduct of Meta-Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Allan Zhou, Chelsea Finn, Evan Zheran Liu, Sahaana Suri, Tong Mu","submitted_at":"2023-06-14T09:48:48Z","abstract_excerpt":"Whereas machine learning models typically learn language by directly training on language tasks (e.g., next-word prediction), language emerges in human children as a byproduct of solving non-language tasks (e.g., acquiring food). Motivated by this observation, we ask: can embodied reinforcement learning (RL) agents also indirectly learn language from non-language tasks? Learning to associate language with its meaning requires a dynamic environment with varied language. Therefore, we investigate this question in a multi-task environment with language that varies across the different tasks. Spec"},"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":"2306.08400","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-14T09:48:48Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"0c30b2b1e9760a34e4c61fc0e689e6a0bd8774de641549f3f9a7fdab74f4b1c9","abstract_canon_sha256":"048841c5b33273a8e18e9dba0ee97747649aaab85a79865fb529ee8f260d9bdc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:20:52.098982Z","signature_b64":"u8to95IHopR8wxR3SrrZCVEf4sMJdJe+0oRdIlPatgAuv9VfWMPm7IENfe9W4feDZjOnfisXoE2uJwP0Cv8yCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8a136822163f06dbb2d05d814436509b864dcc07f253480fe030a85ade2b0724","last_reissued_at":"2026-07-05T06:20:52.098568Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:20:52.098568Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Simple Embodied Language Learning as a Byproduct of Meta-Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Allan Zhou, Chelsea Finn, Evan Zheran Liu, Sahaana Suri, Tong Mu","submitted_at":"2023-06-14T09:48:48Z","abstract_excerpt":"Whereas machine learning models typically learn language by directly training on language tasks (e.g., next-word prediction), language emerges in human children as a byproduct of solving non-language tasks (e.g., acquiring food). Motivated by this observation, we ask: can embodied reinforcement learning (RL) agents also indirectly learn language from non-language tasks? Learning to associate language with its meaning requires a dynamic environment with varied language. Therefore, we investigate this question in a multi-task environment with language that varies across the different tasks. Spec"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.08400","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/2306.08400/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":"2306.08400","created_at":"2026-07-05T06:20:52.098631+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.08400v1","created_at":"2026-07-05T06:20:52.098631+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.08400","created_at":"2026-07-05T06:20:52.098631+00:00"},{"alias_kind":"pith_short_12","alias_value":"RIJWQIQWH4DN","created_at":"2026-07-05T06:20:52.098631+00:00"},{"alias_kind":"pith_short_16","alias_value":"RIJWQIQWH4DNXMWQ","created_at":"2026-07-05T06:20:52.098631+00:00"},{"alias_kind":"pith_short_8","alias_value":"RIJWQIQW","created_at":"2026-07-05T06:20:52.098631+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RIJWQIQWH4DNXMWQLWAUINSQTO","json":"https://pith.science/pith/RIJWQIQWH4DNXMWQLWAUINSQTO.json","graph_json":"https://pith.science/api/pith-number/RIJWQIQWH4DNXMWQLWAUINSQTO/graph.json","events_json":"https://pith.science/api/pith-number/RIJWQIQWH4DNXMWQLWAUINSQTO/events.json","paper":"https://pith.science/paper/RIJWQIQW"},"agent_actions":{"view_html":"https://pith.science/pith/RIJWQIQWH4DNXMWQLWAUINSQTO","download_json":"https://pith.science/pith/RIJWQIQWH4DNXMWQLWAUINSQTO.json","view_paper":"https://pith.science/paper/RIJWQIQW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.08400&json=true","fetch_graph":"https://pith.science/api/pith-number/RIJWQIQWH4DNXMWQLWAUINSQTO/graph.json","fetch_events":"https://pith.science/api/pith-number/RIJWQIQWH4DNXMWQLWAUINSQTO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RIJWQIQWH4DNXMWQLWAUINSQTO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RIJWQIQWH4DNXMWQLWAUINSQTO/action/storage_attestation","attest_author":"https://pith.science/pith/RIJWQIQWH4DNXMWQLWAUINSQTO/action/author_attestation","sign_citation":"https://pith.science/pith/RIJWQIQWH4DNXMWQLWAUINSQTO/action/citation_signature","submit_replication":"https://pith.science/pith/RIJWQIQWH4DNXMWQLWAUINSQTO/action/replication_record"}},"created_at":"2026-07-05T06:20:52.098631+00:00","updated_at":"2026-07-05T06:20:52.098631+00:00"}