{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:UWDEXLHT25ELFEUF3U6VBRGDTY","short_pith_number":"pith:UWDEXLHT","schema_version":"1.0","canonical_sha256":"a5864bacf3d748b29285dd3d50c4c39e2d8312ae53bb1f72c12ceeac704bfa87","source":{"kind":"arxiv","id":"2009.14259","version":2},"attestation_state":"computed","paper":{"title":"Visually-Grounded Planning without Vision: Language Models Infer Detailed Plans from High-level Instructions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Peter A. Jansen","submitted_at":"2020-09-29T18:52:39Z","abstract_excerpt":"The recently proposed ALFRED challenge task aims for a virtual robotic agent to complete complex multi-step everyday tasks in a virtual home environment from high-level natural language directives, such as \"put a hot piece of bread on a plate\". Currently, the best-performing models are able to complete less than 5% of these tasks successfully. In this work we focus on modeling the translation problem of converting natural language directives into detailed multi-step sequences of actions that accomplish those goals in the virtual environment. We empirically demonstrate that it is possible to ge"},"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":"2009.14259","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2020-09-29T18:52:39Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"fcbd8e78823f67efb96e9d25b0c37d3e6b54f8b61c0e6443e759faa64fe631b6","abstract_canon_sha256":"c386d6f775fa27a98ebe18d7e03f8aff095f5ba5788ae87a39af13be25a33c32"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:46:26.642818Z","signature_b64":"jC6a7SgGchMoSmT168RPe/2bSh/J9BPnovvalWu+dxNnNWMxk+k2VsfHgdCk50QpMcVTmGouQVQo1HNzjSIRDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a5864bacf3d748b29285dd3d50c4c39e2d8312ae53bb1f72c12ceeac704bfa87","last_reissued_at":"2026-07-05T01:46:26.642395Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:46:26.642395Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Visually-Grounded Planning without Vision: Language Models Infer Detailed Plans from High-level Instructions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Peter A. Jansen","submitted_at":"2020-09-29T18:52:39Z","abstract_excerpt":"The recently proposed ALFRED challenge task aims for a virtual robotic agent to complete complex multi-step everyday tasks in a virtual home environment from high-level natural language directives, such as \"put a hot piece of bread on a plate\". Currently, the best-performing models are able to complete less than 5% of these tasks successfully. In this work we focus on modeling the translation problem of converting natural language directives into detailed multi-step sequences of actions that accomplish those goals in the virtual environment. We empirically demonstrate that it is possible to ge"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2009.14259","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/2009.14259/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":"2009.14259","created_at":"2026-07-05T01:46:26.642453+00:00"},{"alias_kind":"arxiv_version","alias_value":"2009.14259v2","created_at":"2026-07-05T01:46:26.642453+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2009.14259","created_at":"2026-07-05T01:46:26.642453+00:00"},{"alias_kind":"pith_short_12","alias_value":"UWDEXLHT25EL","created_at":"2026-07-05T01:46:26.642453+00:00"},{"alias_kind":"pith_short_16","alias_value":"UWDEXLHT25ELFEUF","created_at":"2026-07-05T01:46:26.642453+00:00"},{"alias_kind":"pith_short_8","alias_value":"UWDEXLHT","created_at":"2026-07-05T01:46:26.642453+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2307.05973","citing_title":"VoxPoser: Composable 3D Value Maps for Robotic Manipulation with Language Models","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2207.05608","citing_title":"Inner Monologue: Embodied Reasoning through Planning with Language Models","ref_index":51,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UWDEXLHT25ELFEUF3U6VBRGDTY","json":"https://pith.science/pith/UWDEXLHT25ELFEUF3U6VBRGDTY.json","graph_json":"https://pith.science/api/pith-number/UWDEXLHT25ELFEUF3U6VBRGDTY/graph.json","events_json":"https://pith.science/api/pith-number/UWDEXLHT25ELFEUF3U6VBRGDTY/events.json","paper":"https://pith.science/paper/UWDEXLHT"},"agent_actions":{"view_html":"https://pith.science/pith/UWDEXLHT25ELFEUF3U6VBRGDTY","download_json":"https://pith.science/pith/UWDEXLHT25ELFEUF3U6VBRGDTY.json","view_paper":"https://pith.science/paper/UWDEXLHT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2009.14259&json=true","fetch_graph":"https://pith.science/api/pith-number/UWDEXLHT25ELFEUF3U6VBRGDTY/graph.json","fetch_events":"https://pith.science/api/pith-number/UWDEXLHT25ELFEUF3U6VBRGDTY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UWDEXLHT25ELFEUF3U6VBRGDTY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UWDEXLHT25ELFEUF3U6VBRGDTY/action/storage_attestation","attest_author":"https://pith.science/pith/UWDEXLHT25ELFEUF3U6VBRGDTY/action/author_attestation","sign_citation":"https://pith.science/pith/UWDEXLHT25ELFEUF3U6VBRGDTY/action/citation_signature","submit_replication":"https://pith.science/pith/UWDEXLHT25ELFEUF3U6VBRGDTY/action/replication_record"}},"created_at":"2026-07-05T01:46:26.642453+00:00","updated_at":"2026-07-05T01:46:26.642453+00:00"}