{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:6AKAYSTCGOHVIHRF6Z2XTVMP5N","short_pith_number":"pith:6AKAYSTC","schema_version":"1.0","canonical_sha256":"f0140c4a62338f541e25f67579d58feb58082cb7f472d5ff308ba8fb4d484919","source":{"kind":"arxiv","id":"1804.08454","version":2},"attestation_state":"computed","paper":{"title":"Attention Based Natural Language Grounding by Navigating Virtual Environment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.LG"],"primary_cat":"cs.CL","authors_text":"Abhishek Sinha, Akilesh B, Balaji Krishnamurthy, Mausoom Sarkar","submitted_at":"2018-04-23T14:11:17Z","abstract_excerpt":"In this work, we focus on the problem of grounding language by training an agent to follow a set of natural language instructions and navigate to a target object in an environment. The agent receives visual information through raw pixels and a natural language instruction telling what task needs to be achieved and is trained in an end-to-end way. We develop an attention mechanism for multi-modal fusion of visual and textual modalities that allows the agent to learn to complete the task and achieve language grounding. Our experimental results show that our attention mechanism outperforms the ex"},"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":"1804.08454","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-04-23T14:11:17Z","cross_cats_sorted":["cs.AI","cs.CV","cs.LG"],"title_canon_sha256":"cbb4e8d064a883e24bd61b93337cbd6cbc482e15fd2237e165b6b90dc4cf28ad","abstract_canon_sha256":"2844bd35c387060619264271ed49d8b33ecf9d31acd4d1b4398fd4228c446e17"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:57:32.006347Z","signature_b64":"Xs5g6+UDgWzjfqs343fNue95Soiv9H/DdkFV0cVOjc5GGelUEB+0mIdrH3jY5wbxl3rpdp0jwnA/6IJE+q17AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f0140c4a62338f541e25f67579d58feb58082cb7f472d5ff308ba8fb4d484919","last_reissued_at":"2026-05-17T23:57:32.005837Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:57:32.005837Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Attention Based Natural Language Grounding by Navigating Virtual Environment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.LG"],"primary_cat":"cs.CL","authors_text":"Abhishek Sinha, Akilesh B, Balaji Krishnamurthy, Mausoom Sarkar","submitted_at":"2018-04-23T14:11:17Z","abstract_excerpt":"In this work, we focus on the problem of grounding language by training an agent to follow a set of natural language instructions and navigate to a target object in an environment. The agent receives visual information through raw pixels and a natural language instruction telling what task needs to be achieved and is trained in an end-to-end way. We develop an attention mechanism for multi-modal fusion of visual and textual modalities that allows the agent to learn to complete the task and achieve language grounding. Our experimental results show that our attention mechanism outperforms the ex"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.08454","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":""},"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":"1804.08454","created_at":"2026-05-17T23:57:32.005915+00:00"},{"alias_kind":"arxiv_version","alias_value":"1804.08454v2","created_at":"2026-05-17T23:57:32.005915+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.08454","created_at":"2026-05-17T23:57:32.005915+00:00"},{"alias_kind":"pith_short_12","alias_value":"6AKAYSTCGOHV","created_at":"2026-05-18T12:32:08.215937+00:00"},{"alias_kind":"pith_short_16","alias_value":"6AKAYSTCGOHVIHRF","created_at":"2026-05-18T12:32:08.215937+00:00"},{"alias_kind":"pith_short_8","alias_value":"6AKAYSTC","created_at":"2026-05-18T12:32:08.215937+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/6AKAYSTCGOHVIHRF6Z2XTVMP5N","json":"https://pith.science/pith/6AKAYSTCGOHVIHRF6Z2XTVMP5N.json","graph_json":"https://pith.science/api/pith-number/6AKAYSTCGOHVIHRF6Z2XTVMP5N/graph.json","events_json":"https://pith.science/api/pith-number/6AKAYSTCGOHVIHRF6Z2XTVMP5N/events.json","paper":"https://pith.science/paper/6AKAYSTC"},"agent_actions":{"view_html":"https://pith.science/pith/6AKAYSTCGOHVIHRF6Z2XTVMP5N","download_json":"https://pith.science/pith/6AKAYSTCGOHVIHRF6Z2XTVMP5N.json","view_paper":"https://pith.science/paper/6AKAYSTC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1804.08454&json=true","fetch_graph":"https://pith.science/api/pith-number/6AKAYSTCGOHVIHRF6Z2XTVMP5N/graph.json","fetch_events":"https://pith.science/api/pith-number/6AKAYSTCGOHVIHRF6Z2XTVMP5N/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6AKAYSTCGOHVIHRF6Z2XTVMP5N/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6AKAYSTCGOHVIHRF6Z2XTVMP5N/action/storage_attestation","attest_author":"https://pith.science/pith/6AKAYSTCGOHVIHRF6Z2XTVMP5N/action/author_attestation","sign_citation":"https://pith.science/pith/6AKAYSTCGOHVIHRF6Z2XTVMP5N/action/citation_signature","submit_replication":"https://pith.science/pith/6AKAYSTCGOHVIHRF6Z2XTVMP5N/action/replication_record"}},"created_at":"2026-05-17T23:57:32.005915+00:00","updated_at":"2026-05-17T23:57:32.005915+00:00"}