{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:Z6V2NDYUTVQUDYOY5LFWZSDKEU","short_pith_number":"pith:Z6V2NDYU","schema_version":"1.0","canonical_sha256":"cfaba68f149d6141e1d8eacb6cc86a25301aeb1eeb2aeb789acec55ebe3bd84f","source":{"kind":"arxiv","id":"1902.01385","version":1},"attestation_state":"computed","paper":{"title":"Embodied Multimodal Multitask Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.RO","stat.ML"],"primary_cat":"cs.LG","authors_text":"Devendra Singh Chaplot, Devi Parikh, Dhruv Batra, Lisa Lee, Ruslan Salakhutdinov","submitted_at":"2019-02-04T18:53:14Z","abstract_excerpt":"Recent efforts on training visual navigation agents conditioned on language using deep reinforcement learning have been successful in learning policies for different multimodal tasks, such as semantic goal navigation and embodied question answering. In this paper, we propose a multitask model capable of jointly learning these multimodal tasks, and transferring knowledge of words and their grounding in visual objects across the tasks. The proposed model uses a novel Dual-Attention unit to disentangle the knowledge of words in the textual representations and visual concepts in the visual represe"},"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":"1902.01385","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-04T18:53:14Z","cross_cats_sorted":["cs.AI","cs.CL","cs.RO","stat.ML"],"title_canon_sha256":"3e0ff1c15bc63dac08a717a87a35a25f047a4e1b0a46bd03b43d84d6c4d208d0","abstract_canon_sha256":"0e5da668752edbbb6c03642cdb4233fe8d529e1be582458583ca3b56c40729fa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:54:49.003733Z","signature_b64":"8nViomtX6/Py7r/ABbRR/1Uh73LkjhFJZp6zK+SPcgczfJenS+H/FeYfYkud/D0+uIgBDPdBFeCacIMWCYUcCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cfaba68f149d6141e1d8eacb6cc86a25301aeb1eeb2aeb789acec55ebe3bd84f","last_reissued_at":"2026-05-17T23:54:49.003107Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:54:49.003107Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Embodied Multimodal Multitask Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.RO","stat.ML"],"primary_cat":"cs.LG","authors_text":"Devendra Singh Chaplot, Devi Parikh, Dhruv Batra, Lisa Lee, Ruslan Salakhutdinov","submitted_at":"2019-02-04T18:53:14Z","abstract_excerpt":"Recent efforts on training visual navigation agents conditioned on language using deep reinforcement learning have been successful in learning policies for different multimodal tasks, such as semantic goal navigation and embodied question answering. In this paper, we propose a multitask model capable of jointly learning these multimodal tasks, and transferring knowledge of words and their grounding in visual objects across the tasks. The proposed model uses a novel Dual-Attention unit to disentangle the knowledge of words in the textual representations and visual concepts in the visual represe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.01385","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":""},"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":"1902.01385","created_at":"2026-05-17T23:54:49.003204+00:00"},{"alias_kind":"arxiv_version","alias_value":"1902.01385v1","created_at":"2026-05-17T23:54:49.003204+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.01385","created_at":"2026-05-17T23:54:49.003204+00:00"},{"alias_kind":"pith_short_12","alias_value":"Z6V2NDYUTVQU","created_at":"2026-05-18T12:33:33.725879+00:00"},{"alias_kind":"pith_short_16","alias_value":"Z6V2NDYUTVQUDYOY","created_at":"2026-05-18T12:33:33.725879+00:00"},{"alias_kind":"pith_short_8","alias_value":"Z6V2NDYU","created_at":"2026-05-18T12:33:33.725879+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.22409","citing_title":"SpaMEM: Benchmarking Dynamic Spatial Reasoning via Perception-Memory Integration in Embodied Environments","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Z6V2NDYUTVQUDYOY5LFWZSDKEU","json":"https://pith.science/pith/Z6V2NDYUTVQUDYOY5LFWZSDKEU.json","graph_json":"https://pith.science/api/pith-number/Z6V2NDYUTVQUDYOY5LFWZSDKEU/graph.json","events_json":"https://pith.science/api/pith-number/Z6V2NDYUTVQUDYOY5LFWZSDKEU/events.json","paper":"https://pith.science/paper/Z6V2NDYU"},"agent_actions":{"view_html":"https://pith.science/pith/Z6V2NDYUTVQUDYOY5LFWZSDKEU","download_json":"https://pith.science/pith/Z6V2NDYUTVQUDYOY5LFWZSDKEU.json","view_paper":"https://pith.science/paper/Z6V2NDYU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1902.01385&json=true","fetch_graph":"https://pith.science/api/pith-number/Z6V2NDYUTVQUDYOY5LFWZSDKEU/graph.json","fetch_events":"https://pith.science/api/pith-number/Z6V2NDYUTVQUDYOY5LFWZSDKEU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Z6V2NDYUTVQUDYOY5LFWZSDKEU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Z6V2NDYUTVQUDYOY5LFWZSDKEU/action/storage_attestation","attest_author":"https://pith.science/pith/Z6V2NDYUTVQUDYOY5LFWZSDKEU/action/author_attestation","sign_citation":"https://pith.science/pith/Z6V2NDYUTVQUDYOY5LFWZSDKEU/action/citation_signature","submit_replication":"https://pith.science/pith/Z6V2NDYUTVQUDYOY5LFWZSDKEU/action/replication_record"}},"created_at":"2026-05-17T23:54:49.003204+00:00","updated_at":"2026-05-17T23:54:49.003204+00:00"}