{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:VRRVUFNMRW2HTUN32OJZZOTEEP","short_pith_number":"pith:VRRVUFNM","schema_version":"1.0","canonical_sha256":"ac635a15ac8db479d1bbd3939cba6423e2484a0bdde4a1ae94c54aaa417347ea","source":{"kind":"arxiv","id":"2103.03454","version":1},"attestation_state":"computed","paper":{"title":"Structured Scene Memory for Vision-Language Navigation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Caiming Xiong, Hanqing Wang, Jianbing Shen, Wei Liang, Wenguan Wang","submitted_at":"2021-03-05T03:41:00Z","abstract_excerpt":"Recently, numerous algorithms have been developed to tackle the problem of vision-language navigation (VLN), i.e., entailing an agent to navigate 3D environments through following linguistic instructions. However, current VLN agents simply store their past experiences/observations as latent states in recurrent networks, failing to capture environment layouts and make long-term planning. To address these limitations, we propose a crucial architecture, called Structured Scene Memory (SSM). It is compartmentalized enough to accurately memorize the percepts during navigation. It also serves as a s"},"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":"2103.03454","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-03-05T03:41:00Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c19c6b384304ae7ff93e1ea56021374394f4ee6f6af093cec0b093bbf769ef0a","abstract_canon_sha256":"e5a662addd2b83c39b6736acd34b246541a5c7ae372273ae2c4ffac63f8704c2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:20:35.502867Z","signature_b64":"bJHodkCk3ZrKnzdqhn8xNlReD7jw+k3t6yhcFfsfKBX4IQKz9JUwJb3RxHYCEaIdilaky04sJT+JW90ZpZQeCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ac635a15ac8db479d1bbd3939cba6423e2484a0bdde4a1ae94c54aaa417347ea","last_reissued_at":"2026-07-05T02:20:35.502403Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:20:35.502403Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Structured Scene Memory for Vision-Language Navigation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Caiming Xiong, Hanqing Wang, Jianbing Shen, Wei Liang, Wenguan Wang","submitted_at":"2021-03-05T03:41:00Z","abstract_excerpt":"Recently, numerous algorithms have been developed to tackle the problem of vision-language navigation (VLN), i.e., entailing an agent to navigate 3D environments through following linguistic instructions. However, current VLN agents simply store their past experiences/observations as latent states in recurrent networks, failing to capture environment layouts and make long-term planning. To address these limitations, we propose a crucial architecture, called Structured Scene Memory (SSM). It is compartmentalized enough to accurately memorize the percepts during navigation. It also serves as a s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.03454","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/2103.03454/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":"2103.03454","created_at":"2026-07-05T02:20:35.502466+00:00"},{"alias_kind":"arxiv_version","alias_value":"2103.03454v1","created_at":"2026-07-05T02:20:35.502466+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.03454","created_at":"2026-07-05T02:20:35.502466+00:00"},{"alias_kind":"pith_short_12","alias_value":"VRRVUFNMRW2H","created_at":"2026-07-05T02:20:35.502466+00:00"},{"alias_kind":"pith_short_16","alias_value":"VRRVUFNMRW2HTUN3","created_at":"2026-07-05T02:20:35.502466+00:00"},{"alias_kind":"pith_short_8","alias_value":"VRRVUFNM","created_at":"2026-07-05T02:20:35.502466+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":50,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VRRVUFNMRW2HTUN32OJZZOTEEP","json":"https://pith.science/pith/VRRVUFNMRW2HTUN32OJZZOTEEP.json","graph_json":"https://pith.science/api/pith-number/VRRVUFNMRW2HTUN32OJZZOTEEP/graph.json","events_json":"https://pith.science/api/pith-number/VRRVUFNMRW2HTUN32OJZZOTEEP/events.json","paper":"https://pith.science/paper/VRRVUFNM"},"agent_actions":{"view_html":"https://pith.science/pith/VRRVUFNMRW2HTUN32OJZZOTEEP","download_json":"https://pith.science/pith/VRRVUFNMRW2HTUN32OJZZOTEEP.json","view_paper":"https://pith.science/paper/VRRVUFNM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2103.03454&json=true","fetch_graph":"https://pith.science/api/pith-number/VRRVUFNMRW2HTUN32OJZZOTEEP/graph.json","fetch_events":"https://pith.science/api/pith-number/VRRVUFNMRW2HTUN32OJZZOTEEP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VRRVUFNMRW2HTUN32OJZZOTEEP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VRRVUFNMRW2HTUN32OJZZOTEEP/action/storage_attestation","attest_author":"https://pith.science/pith/VRRVUFNMRW2HTUN32OJZZOTEEP/action/author_attestation","sign_citation":"https://pith.science/pith/VRRVUFNMRW2HTUN32OJZZOTEEP/action/citation_signature","submit_replication":"https://pith.science/pith/VRRVUFNMRW2HTUN32OJZZOTEEP/action/replication_record"}},"created_at":"2026-07-05T02:20:35.502466+00:00","updated_at":"2026-07-05T02:20:35.502466+00:00"}