{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:E6UMKSZDA5YPIWHU2JTNM5YXNV","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":"63d69b025ff8d903daf4876a3e1ae68f8e0555933fa1ad6ec2404616d5373b87","cross_cats_sorted":["cs.AI","cs.CL","cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2020-12-09T20:02:03Z","title_canon_sha256":"bef87249070a0353850ae1cfde6f45394ba25a99fdd9b3808bbb5a0d7be3a381"},"schema_version":"1.0","source":{"id":"2012.05292","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2012.05292","created_at":"2026-07-05T01:58:21Z"},{"alias_kind":"arxiv_version","alias_value":"2012.05292v1","created_at":"2026-07-05T01:58:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.05292","created_at":"2026-07-05T01:58:21Z"},{"alias_kind":"pith_short_12","alias_value":"E6UMKSZDA5YP","created_at":"2026-07-05T01:58:21Z"},{"alias_kind":"pith_short_16","alias_value":"E6UMKSZDA5YPIWHU","created_at":"2026-07-05T01:58:21Z"},{"alias_kind":"pith_short_8","alias_value":"E6UMKSZD","created_at":"2026-07-05T01:58:21Z"}],"graph_snapshots":[{"event_id":"sha256:d668cf2183ee74993e3ad0cb3600729436ce4f29ec1ff732c3aae36f33362206","target":"graph","created_at":"2026-07-05T01:58:21Z","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/2012.05292/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Conventional approaches to vision-and-language navigation (VLN) are trained end-to-end but struggle to perform well in freely traversable environments. Inspired by the robotics community, we propose a modular approach to VLN using topological maps. Given a natural language instruction and topological map, our approach leverages attention mechanisms to predict a navigation plan in the map. The plan is then executed with low-level actions (e.g. forward, rotate) using a robust controller. Experiments show that our method outperforms previous end-to-end approaches, generates interpretable navigati","authors_text":"Jo Chuang, Junshen K. Chen, Kevin Chen, Marynel V\\'azquez, Silvio Savarese","cross_cats":["cs.AI","cs.CL","cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2020-12-09T20:02:03Z","title":"Topological Planning with Transformers for Vision-and-Language Navigation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.05292","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:b9d6ea0f5c18f57331259b8e55dfc2f5c81fe6bf2545f18a156a3b90b98d8049","target":"record","created_at":"2026-07-05T01:58:21Z","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":"63d69b025ff8d903daf4876a3e1ae68f8e0555933fa1ad6ec2404616d5373b87","cross_cats_sorted":["cs.AI","cs.CL","cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2020-12-09T20:02:03Z","title_canon_sha256":"bef87249070a0353850ae1cfde6f45394ba25a99fdd9b3808bbb5a0d7be3a381"},"schema_version":"1.0","source":{"id":"2012.05292","kind":"arxiv","version":1}},"canonical_sha256":"27a8c54b230770f458f4d266d677176d4e09cdf2797ab4a6d3f4d5c9230361c1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"27a8c54b230770f458f4d266d677176d4e09cdf2797ab4a6d3f4d5c9230361c1","first_computed_at":"2026-07-05T01:58:21.980709Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:58:21.980709Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GZtsF9XSWfwH8ZLOaxFF2h0zbz/7/43hSeqSrqv1P3eJ9BhCXkQ8VchU2f8xKfY6XQNX4PvxeiDjpGNB5fssCw==","signature_status":"signed_v1","signed_at":"2026-07-05T01:58:21.981113Z","signed_message":"canonical_sha256_bytes"},"source_id":"2012.05292","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b9d6ea0f5c18f57331259b8e55dfc2f5c81fe6bf2545f18a156a3b90b98d8049","sha256:d668cf2183ee74993e3ad0cb3600729436ce4f29ec1ff732c3aae36f33362206"],"state_sha256":"32956241090b1b1ac41f4b78fff32ae3ee110a94a6e01d3f7a1cc9a7220ccb57"}