{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:MOAOUI5ZPJVSKWATO7LND7YOG4","short_pith_number":"pith:MOAOUI5Z","schema_version":"1.0","canonical_sha256":"6380ea23b97a6b25581377d6d1ff0e3710315593014971535a85b7ae556c53e6","source":{"kind":"arxiv","id":"2109.02161","version":1},"attestation_state":"computed","paper":{"title":"Modular Framework for Visuomotor Language Grounding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Charless C. Fowlkes, Daeyun Shin, Kolby Nottingham, Litian Liang, Roy Fox, Sameer Singh","submitted_at":"2021-09-05T20:11:53Z","abstract_excerpt":"Natural language instruction following tasks serve as a valuable test-bed for grounded language and robotics research. However, data collection for these tasks is expensive and end-to-end approaches suffer from data inefficiency. We propose the structuring of language, acting, and visual tasks into separate modules that can be trained independently. Using a Language, Action, and Vision (LAV) framework removes the dependence of action and vision modules on instruction following datasets, making them more efficient to train. We also present a preliminary evaluation of LAV on the ALFRED task for "},"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":"2109.02161","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2021-09-05T20:11:53Z","cross_cats_sorted":[],"title_canon_sha256":"c42e1d1e86cd8507ab6b0e89bf57c9066ea3d838bf61cbb6a69f288e31e3dbc1","abstract_canon_sha256":"ba6ccdaaf268d1c68a2653e769068eae3eba58083297b609d9c5d34fd7b5678f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:11:39.461286Z","signature_b64":"5qlRCuk0r02TIytzDIvxeCQBZImtghaAtdS7sB8d8R7RarS8bkakzPc/ApylTcM4pwWCcE/6qiQjFMnm2sTdAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6380ea23b97a6b25581377d6d1ff0e3710315593014971535a85b7ae556c53e6","last_reissued_at":"2026-07-05T03:11:39.460897Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:11:39.460897Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Modular Framework for Visuomotor Language Grounding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Charless C. Fowlkes, Daeyun Shin, Kolby Nottingham, Litian Liang, Roy Fox, Sameer Singh","submitted_at":"2021-09-05T20:11:53Z","abstract_excerpt":"Natural language instruction following tasks serve as a valuable test-bed for grounded language and robotics research. However, data collection for these tasks is expensive and end-to-end approaches suffer from data inefficiency. We propose the structuring of language, acting, and visual tasks into separate modules that can be trained independently. Using a Language, Action, and Vision (LAV) framework removes the dependence of action and vision modules on instruction following datasets, making them more efficient to train. We also present a preliminary evaluation of LAV on the ALFRED task for "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.02161","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/2109.02161/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":"2109.02161","created_at":"2026-07-05T03:11:39.460960+00:00"},{"alias_kind":"arxiv_version","alias_value":"2109.02161v1","created_at":"2026-07-05T03:11:39.460960+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.02161","created_at":"2026-07-05T03:11:39.460960+00:00"},{"alias_kind":"pith_short_12","alias_value":"MOAOUI5ZPJVS","created_at":"2026-07-05T03:11:39.460960+00:00"},{"alias_kind":"pith_short_16","alias_value":"MOAOUI5ZPJVSKWAT","created_at":"2026-07-05T03:11:39.460960+00:00"},{"alias_kind":"pith_short_8","alias_value":"MOAOUI5Z","created_at":"2026-07-05T03:11:39.460960+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/MOAOUI5ZPJVSKWATO7LND7YOG4","json":"https://pith.science/pith/MOAOUI5ZPJVSKWATO7LND7YOG4.json","graph_json":"https://pith.science/api/pith-number/MOAOUI5ZPJVSKWATO7LND7YOG4/graph.json","events_json":"https://pith.science/api/pith-number/MOAOUI5ZPJVSKWATO7LND7YOG4/events.json","paper":"https://pith.science/paper/MOAOUI5Z"},"agent_actions":{"view_html":"https://pith.science/pith/MOAOUI5ZPJVSKWATO7LND7YOG4","download_json":"https://pith.science/pith/MOAOUI5ZPJVSKWATO7LND7YOG4.json","view_paper":"https://pith.science/paper/MOAOUI5Z","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2109.02161&json=true","fetch_graph":"https://pith.science/api/pith-number/MOAOUI5ZPJVSKWATO7LND7YOG4/graph.json","fetch_events":"https://pith.science/api/pith-number/MOAOUI5ZPJVSKWATO7LND7YOG4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MOAOUI5ZPJVSKWATO7LND7YOG4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MOAOUI5ZPJVSKWATO7LND7YOG4/action/storage_attestation","attest_author":"https://pith.science/pith/MOAOUI5ZPJVSKWATO7LND7YOG4/action/author_attestation","sign_citation":"https://pith.science/pith/MOAOUI5ZPJVSKWATO7LND7YOG4/action/citation_signature","submit_replication":"https://pith.science/pith/MOAOUI5ZPJVSKWATO7LND7YOG4/action/replication_record"}},"created_at":"2026-07-05T03:11:39.460960+00:00","updated_at":"2026-07-05T03:11:39.460960+00:00"}