{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:YB6POMZEMWOUNXL3DT32NEC5FA","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":"4fe447dcbc23b0b7fa50c4372275a835f1b243c5ae9f700c11060ecbb6d735db","cross_cats_sorted":["cs.CL","cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2021-08-26T17:57:02Z","title_canon_sha256":"3de699df08c26ed7447bfdbe44b5f3c200344445f825198880a3294898333781"},"schema_version":"1.0","source":{"id":"2108.11945","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2108.11945","created_at":"2026-07-05T03:09:11Z"},{"alias_kind":"arxiv_version","alias_value":"2108.11945v1","created_at":"2026-07-05T03:09:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.11945","created_at":"2026-07-05T03:09:11Z"},{"alias_kind":"pith_short_12","alias_value":"YB6POMZEMWOU","created_at":"2026-07-05T03:09:11Z"},{"alias_kind":"pith_short_16","alias_value":"YB6POMZEMWOUNXL3","created_at":"2026-07-05T03:09:11Z"},{"alias_kind":"pith_short_8","alias_value":"YB6POMZE","created_at":"2026-07-05T03:09:11Z"}],"graph_snapshots":[{"event_id":"sha256:ddffd77a59d7c11e7d90fb4db8e31dbc2f581661d4d3c53d8c6ab4fb28243fd9","target":"graph","created_at":"2026-07-05T03:09:11Z","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/2108.11945/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper presents a novel approach for the Vision-and-Language Navigation (VLN) task in continuous 3D environments, which requires an autonomous agent to follow natural language instructions in unseen environments. Existing end-to-end learning-based VLN methods struggle at this task as they focus mostly on utilizing raw visual observations and lack the semantic spatio-temporal reasoning capabilities which is crucial in generalizing to new environments. In this regard, we present a hybrid transformer-recurrence model which focuses on combining classical semantic mapping techniques with a lear","authors_text":"Han-Pang Chiu, Muhammad Zubair Irshad, Niluthpol Chowdhury Mithun, Rakesh Kumar, Supun Samarasekera, Zachary Seymour","cross_cats":["cs.CL","cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2021-08-26T17:57:02Z","title":"SASRA: Semantically-aware Spatio-temporal Reasoning Agent for Vision-and-Language Navigation in Continuous Environments"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.11945","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":"sha256:78baf89ec21bd002fd5706162e6313c24dec82093ad0f4ddf0e37a3178b47d62","target":"record","created_at":"2026-07-05T03:09:11Z","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":"4fe447dcbc23b0b7fa50c4372275a835f1b243c5ae9f700c11060ecbb6d735db","cross_cats_sorted":["cs.CL","cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2021-08-26T17:57:02Z","title_canon_sha256":"3de699df08c26ed7447bfdbe44b5f3c200344445f825198880a3294898333781"},"schema_version":"1.0","source":{"id":"2108.11945","kind":"arxiv","version":1}},"canonical_sha256":"c07cf73324659d46dd7b1cf7a6905d2831e33ac83b7f6afdebf82213e7ff24a0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c07cf73324659d46dd7b1cf7a6905d2831e33ac83b7f6afdebf82213e7ff24a0","first_computed_at":"2026-07-05T03:09:11.210956Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:09:11.210956Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Ld2WPvA/1cPmYWF+Q2/8rNZwVwxEDwL7GRzttIU2NwUEFltQulbSm6mGWdxpSfuexINPpBHewr1Xur11yA03Dg==","signature_status":"signed_v1","signed_at":"2026-07-05T03:09:11.211390Z","signed_message":"canonical_sha256_bytes"},"source_id":"2108.11945","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:78baf89ec21bd002fd5706162e6313c24dec82093ad0f4ddf0e37a3178b47d62","sha256:ddffd77a59d7c11e7d90fb4db8e31dbc2f581661d4d3c53d8c6ab4fb28243fd9"],"state_sha256":"c4e70451825ebc1c9bef56c7df716e7250bc94318d59eee166d9b4a14a46bf70"}