{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:63YW7VJG2BIWWKIHBOSSWAZ5TN","short_pith_number":"pith:63YW7VJG","schema_version":"1.0","canonical_sha256":"f6f16fd526d0516b29070ba52b033d9b5bdb99c6a5d083321fa9a61bea877a58","source":{"kind":"arxiv","id":"2004.02857","version":2},"attestation_state":"computed","paper":{"title":"Beyond the Nav-Graph: Vision-and-Language Navigation in Continuous Environments","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.RO"],"primary_cat":"cs.CV","authors_text":"Arjun Majumdar, Dhruv Batra, Erik Wijmans, Jacob Krantz, Stefan Lee","submitted_at":"2020-04-06T17:49:12Z","abstract_excerpt":"We develop a language-guided navigation task set in a continuous 3D environment where agents must execute low-level actions to follow natural language navigation directions. By being situated in continuous environments, this setting lifts a number of assumptions implicit in prior work that represents environments as a sparse graph of panoramas with edges corresponding to navigability. Specifically, our setting drops the presumptions of known environment topologies, short-range oracle navigation, and perfect agent localization. To contextualize this new task, we develop models that mirror many "},"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":"2004.02857","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-04-06T17:49:12Z","cross_cats_sorted":["cs.CL","cs.RO"],"title_canon_sha256":"67fdf5b07b7a5ae9ccd18149f323dc826c135114eac3d58746ba2320dd973263","abstract_canon_sha256":"5d6d055d0317387bdef8b63d28aa77323cb62ebfe2c7a88b64cde08998283adc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:59:43.557120Z","signature_b64":"gB1nWIpLUlKi4JnTzcJRcilWvecFLeHK4knSdmyd6piyEoR73tcnLpnNKE2FNQTZjnrDyAqwajz2foi4VF1oDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f6f16fd526d0516b29070ba52b033d9b5bdb99c6a5d083321fa9a61bea877a58","last_reissued_at":"2026-07-05T00:59:43.556684Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:59:43.556684Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Beyond the Nav-Graph: Vision-and-Language Navigation in Continuous Environments","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.RO"],"primary_cat":"cs.CV","authors_text":"Arjun Majumdar, Dhruv Batra, Erik Wijmans, Jacob Krantz, Stefan Lee","submitted_at":"2020-04-06T17:49:12Z","abstract_excerpt":"We develop a language-guided navigation task set in a continuous 3D environment where agents must execute low-level actions to follow natural language navigation directions. By being situated in continuous environments, this setting lifts a number of assumptions implicit in prior work that represents environments as a sparse graph of panoramas with edges corresponding to navigability. Specifically, our setting drops the presumptions of known environment topologies, short-range oracle navigation, and perfect agent localization. To contextualize this new task, we develop models that mirror many "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.02857","kind":"arxiv","version":2},"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/2004.02857/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":"2004.02857","created_at":"2026-07-05T00:59:43.556743+00:00"},{"alias_kind":"arxiv_version","alias_value":"2004.02857v2","created_at":"2026-07-05T00:59:43.556743+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.02857","created_at":"2026-07-05T00:59:43.556743+00:00"},{"alias_kind":"pith_short_12","alias_value":"63YW7VJG2BIW","created_at":"2026-07-05T00:59:43.556743+00:00"},{"alias_kind":"pith_short_16","alias_value":"63YW7VJG2BIWWKIH","created_at":"2026-07-05T00:59:43.556743+00:00"},{"alias_kind":"pith_short_8","alias_value":"63YW7VJG","created_at":"2026-07-05T00:59:43.556743+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.02417","citing_title":"LIME: Learning Intent-aware Camera Motion from Egocentric Video","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2606.30151","citing_title":"AERIS: Aerial-Edge Role-Driven Intelligence at Runtime via Orchestrated Language-Model Swarm","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17776","citing_title":"CosFly-Track: A Large-Scale Multi-Modal Dataset for UAV Visual Tracking via Multi-Constraint Trajectory Optimization","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17776","citing_title":"CosFly-Track: A Large-Scale Multi-Modal Dataset for UAV Visual Tracking via Multi-Constraint Trajectory Optimization","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2603.07080","citing_title":"VLN-Cache: Enabling Token Caching for VLN Models with Visual/Semantic Dynamics Awareness","ref_index":33,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/63YW7VJG2BIWWKIHBOSSWAZ5TN","json":"https://pith.science/pith/63YW7VJG2BIWWKIHBOSSWAZ5TN.json","graph_json":"https://pith.science/api/pith-number/63YW7VJG2BIWWKIHBOSSWAZ5TN/graph.json","events_json":"https://pith.science/api/pith-number/63YW7VJG2BIWWKIHBOSSWAZ5TN/events.json","paper":"https://pith.science/paper/63YW7VJG"},"agent_actions":{"view_html":"https://pith.science/pith/63YW7VJG2BIWWKIHBOSSWAZ5TN","download_json":"https://pith.science/pith/63YW7VJG2BIWWKIHBOSSWAZ5TN.json","view_paper":"https://pith.science/paper/63YW7VJG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2004.02857&json=true","fetch_graph":"https://pith.science/api/pith-number/63YW7VJG2BIWWKIHBOSSWAZ5TN/graph.json","fetch_events":"https://pith.science/api/pith-number/63YW7VJG2BIWWKIHBOSSWAZ5TN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/63YW7VJG2BIWWKIHBOSSWAZ5TN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/63YW7VJG2BIWWKIHBOSSWAZ5TN/action/storage_attestation","attest_author":"https://pith.science/pith/63YW7VJG2BIWWKIHBOSSWAZ5TN/action/author_attestation","sign_citation":"https://pith.science/pith/63YW7VJG2BIWWKIHBOSSWAZ5TN/action/citation_signature","submit_replication":"https://pith.science/pith/63YW7VJG2BIWWKIHBOSSWAZ5TN/action/replication_record"}},"created_at":"2026-07-05T00:59:43.556743+00:00","updated_at":"2026-07-05T00:59:43.556743+00:00"}