{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:NAOKODBJFY4AER4DGT453O2JCS","short_pith_number":"pith:NAOKODBJ","schema_version":"1.0","canonical_sha256":"681ca70c292e3802478334f9ddbb4914889b7b561b664a3f5a8fc58ca151135c","source":{"kind":"arxiv","id":"2110.14143","version":1},"attestation_state":"computed","paper":{"title":"SOAT: A Scene- and Object-Aware Transformer for Vision-and-Language Navigation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Abhinav Moudgil, Arjun Majumdar, Dhruv Batra, Harsh Agrawal, Stefan Lee","submitted_at":"2021-10-27T03:29:34Z","abstract_excerpt":"Natural language instructions for visual navigation often use scene descriptions (e.g., \"bedroom\") and object references (e.g., \"green chairs\") to provide a breadcrumb trail to a goal location. This work presents a transformer-based vision-and-language navigation (VLN) agent that uses two different visual encoders -- a scene classification network and an object detector -- which produce features that match these two distinct types of visual cues. In our method, scene features contribute high-level contextual information that supports object-level processing. With this design, our model is able"},"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":"2110.14143","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-10-27T03:29:34Z","cross_cats_sorted":[],"title_canon_sha256":"8839ed5800742a2d903ed86c9dae9323109634c219cd34e600266e4b870603b0","abstract_canon_sha256":"15be88f00a7e68a10feeccbb6990c5ab5f3c8d9167ccfc02bfddda196f7928f8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:26:24.284979Z","signature_b64":"IkEqcRZF14NUbIsxsItDdqLjUno6PImOr5SlyS9GDbNXVLlz/wBU/bY3DJ7NEj71n6EXh2pz3msyVj1PXA5wCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"681ca70c292e3802478334f9ddbb4914889b7b561b664a3f5a8fc58ca151135c","last_reissued_at":"2026-07-05T03:26:24.284614Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:26:24.284614Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SOAT: A Scene- and Object-Aware Transformer for Vision-and-Language Navigation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Abhinav Moudgil, Arjun Majumdar, Dhruv Batra, Harsh Agrawal, Stefan Lee","submitted_at":"2021-10-27T03:29:34Z","abstract_excerpt":"Natural language instructions for visual navigation often use scene descriptions (e.g., \"bedroom\") and object references (e.g., \"green chairs\") to provide a breadcrumb trail to a goal location. This work presents a transformer-based vision-and-language navigation (VLN) agent that uses two different visual encoders -- a scene classification network and an object detector -- which produce features that match these two distinct types of visual cues. In our method, scene features contribute high-level contextual information that supports object-level processing. With this design, our model is able"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.14143","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/2110.14143/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":"2110.14143","created_at":"2026-07-05T03:26:24.284674+00:00"},{"alias_kind":"arxiv_version","alias_value":"2110.14143v1","created_at":"2026-07-05T03:26:24.284674+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.14143","created_at":"2026-07-05T03:26:24.284674+00:00"},{"alias_kind":"pith_short_12","alias_value":"NAOKODBJFY4A","created_at":"2026-07-05T03:26:24.284674+00:00"},{"alias_kind":"pith_short_16","alias_value":"NAOKODBJFY4AER4D","created_at":"2026-07-05T03:26:24.284674+00:00"},{"alias_kind":"pith_short_8","alias_value":"NAOKODBJ","created_at":"2026-07-05T03:26:24.284674+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2504.16516","citing_title":"Think Hierarchically, Act Dynamically: Hierarchical Multi-modal Fusion and Reasoning for Vision-and-Language Navigation","ref_index":37,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NAOKODBJFY4AER4DGT453O2JCS","json":"https://pith.science/pith/NAOKODBJFY4AER4DGT453O2JCS.json","graph_json":"https://pith.science/api/pith-number/NAOKODBJFY4AER4DGT453O2JCS/graph.json","events_json":"https://pith.science/api/pith-number/NAOKODBJFY4AER4DGT453O2JCS/events.json","paper":"https://pith.science/paper/NAOKODBJ"},"agent_actions":{"view_html":"https://pith.science/pith/NAOKODBJFY4AER4DGT453O2JCS","download_json":"https://pith.science/pith/NAOKODBJFY4AER4DGT453O2JCS.json","view_paper":"https://pith.science/paper/NAOKODBJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2110.14143&json=true","fetch_graph":"https://pith.science/api/pith-number/NAOKODBJFY4AER4DGT453O2JCS/graph.json","fetch_events":"https://pith.science/api/pith-number/NAOKODBJFY4AER4DGT453O2JCS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NAOKODBJFY4AER4DGT453O2JCS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NAOKODBJFY4AER4DGT453O2JCS/action/storage_attestation","attest_author":"https://pith.science/pith/NAOKODBJFY4AER4DGT453O2JCS/action/author_attestation","sign_citation":"https://pith.science/pith/NAOKODBJFY4AER4DGT453O2JCS/action/citation_signature","submit_replication":"https://pith.science/pith/NAOKODBJFY4AER4DGT453O2JCS/action/replication_record"}},"created_at":"2026-07-05T03:26:24.284674+00:00","updated_at":"2026-07-05T03:26:24.284674+00:00"}