{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:NAOKODBJFY4AER4DGT453O2JCS","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":"15be88f00a7e68a10feeccbb6990c5ab5f3c8d9167ccfc02bfddda196f7928f8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-10-27T03:29:34Z","title_canon_sha256":"8839ed5800742a2d903ed86c9dae9323109634c219cd34e600266e4b870603b0"},"schema_version":"1.0","source":{"id":"2110.14143","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.14143","created_at":"2026-07-05T03:26:24Z"},{"alias_kind":"arxiv_version","alias_value":"2110.14143v1","created_at":"2026-07-05T03:26:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.14143","created_at":"2026-07-05T03:26:24Z"},{"alias_kind":"pith_short_12","alias_value":"NAOKODBJFY4A","created_at":"2026-07-05T03:26:24Z"},{"alias_kind":"pith_short_16","alias_value":"NAOKODBJFY4AER4D","created_at":"2026-07-05T03:26:24Z"},{"alias_kind":"pith_short_8","alias_value":"NAOKODBJ","created_at":"2026-07-05T03:26:24Z"}],"graph_snapshots":[{"event_id":"sha256:7c8e62651e7d8a10dfbca85ec541633c1d020012d6d3d7cc35ebf3ad66d82517","target":"graph","created_at":"2026-07-05T03:26:24Z","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/2110.14143/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Abhinav Moudgil, Arjun Majumdar, Dhruv Batra, Harsh Agrawal, Stefan Lee","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-10-27T03:29:34Z","title":"SOAT: A Scene- and Object-Aware Transformer for Vision-and-Language Navigation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.14143","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:e870af92060237d053206e867ba7c80636181a35c007a21e0a464a8b40b822e4","target":"record","created_at":"2026-07-05T03:26:24Z","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":"15be88f00a7e68a10feeccbb6990c5ab5f3c8d9167ccfc02bfddda196f7928f8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-10-27T03:29:34Z","title_canon_sha256":"8839ed5800742a2d903ed86c9dae9323109634c219cd34e600266e4b870603b0"},"schema_version":"1.0","source":{"id":"2110.14143","kind":"arxiv","version":1}},"canonical_sha256":"681ca70c292e3802478334f9ddbb4914889b7b561b664a3f5a8fc58ca151135c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"681ca70c292e3802478334f9ddbb4914889b7b561b664a3f5a8fc58ca151135c","first_computed_at":"2026-07-05T03:26:24.284614Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:26:24.284614Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"IkEqcRZF14NUbIsxsItDdqLjUno6PImOr5SlyS9GDbNXVLlz/wBU/bY3DJ7NEj71n6EXh2pz3msyVj1PXA5wCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T03:26:24.284979Z","signed_message":"canonical_sha256_bytes"},"source_id":"2110.14143","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e870af92060237d053206e867ba7c80636181a35c007a21e0a464a8b40b822e4","sha256:7c8e62651e7d8a10dfbca85ec541633c1d020012d6d3d7cc35ebf3ad66d82517"],"state_sha256":"21b367f5051343190f37715190a3652897c443f53e31f72c7a416a14095880d7"}