{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:VRRVUFNMRW2HTUN32OJZZOTEEP","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"e5a662addd2b83c39b6736acd34b246541a5c7ae372273ae2c4ffac63f8704c2","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-03-05T03:41:00Z","title_canon_sha256":"c19c6b384304ae7ff93e1ea56021374394f4ee6f6af093cec0b093bbf769ef0a"},"schema_version":"1.0","source":{"id":"2103.03454","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.03454","created_at":"2026-07-05T02:20:35Z"},{"alias_kind":"arxiv_version","alias_value":"2103.03454v1","created_at":"2026-07-05T02:20:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.03454","created_at":"2026-07-05T02:20:35Z"},{"alias_kind":"pith_short_12","alias_value":"VRRVUFNMRW2H","created_at":"2026-07-05T02:20:35Z"},{"alias_kind":"pith_short_16","alias_value":"VRRVUFNMRW2HTUN3","created_at":"2026-07-05T02:20:35Z"},{"alias_kind":"pith_short_8","alias_value":"VRRVUFNM","created_at":"2026-07-05T02:20:35Z"}],"graph_snapshots":[{"event_id":"sha256:f9db8984b9a7196b337ee95ddd5dec26d9a7910510c8e56d8e2af1daf910c1c5","target":"graph","created_at":"2026-07-05T02:20:35Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2103.03454/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Caiming Xiong, Hanqing Wang, Jianbing Shen, Wei Liang, Wenguan Wang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-03-05T03:41:00Z","title":"Structured Scene Memory for Vision-Language Navigation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.03454","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:173d0017d137923413a13aace78ed934f594273b8368f061b872faaff856004f","target":"record","created_at":"2026-07-05T02:20:35Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"e5a662addd2b83c39b6736acd34b246541a5c7ae372273ae2c4ffac63f8704c2","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-03-05T03:41:00Z","title_canon_sha256":"c19c6b384304ae7ff93e1ea56021374394f4ee6f6af093cec0b093bbf769ef0a"},"schema_version":"1.0","source":{"id":"2103.03454","kind":"arxiv","version":1}},"canonical_sha256":"ac635a15ac8db479d1bbd3939cba6423e2484a0bdde4a1ae94c54aaa417347ea","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ac635a15ac8db479d1bbd3939cba6423e2484a0bdde4a1ae94c54aaa417347ea","first_computed_at":"2026-07-05T02:20:35.502403Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:20:35.502403Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bJHodkCk3ZrKnzdqhn8xNlReD7jw+k3t6yhcFfsfKBX4IQKz9JUwJb3RxHYCEaIdilaky04sJT+JW90ZpZQeCA==","signature_status":"signed_v1","signed_at":"2026-07-05T02:20:35.502867Z","signed_message":"canonical_sha256_bytes"},"source_id":"2103.03454","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:173d0017d137923413a13aace78ed934f594273b8368f061b872faaff856004f","sha256:f9db8984b9a7196b337ee95ddd5dec26d9a7910510c8e56d8e2af1daf910c1c5"],"state_sha256":"e3fc311a9150b37432ec0f1356f2af7e6d25f9b089a8619365ff5686bb295be4"}