{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:F7S7P3DFDBDSA4YYSX7ZFMYCFM","short_pith_number":"pith:F7S7P3DF","schema_version":"1.0","canonical_sha256":"2fe5f7ec65184720731895ff92b3022b34b1f511da78ab2531a739ef15f51f16","source":{"kind":"arxiv","id":"2012.05446","version":3},"attestation_state":"computed","paper":{"title":"Visual Perception Generalization for Vision-and-Language Navigation via Meta-Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Donglin Wang, Ting Wang, Zongkai Wu","submitted_at":"2020-12-10T04:10:04Z","abstract_excerpt":"Vision-and-language navigation (VLN) is a challenging task that requires an agent to navigate in real-world environments by understanding natural language instructions and visual information received in real-time. Prior works have implemented VLN tasks on continuous environments or physical robots, all of which use a fixed camera configuration due to the limitations of datasets, such as 1.5 meters height, 90 degrees horizontal field of view (HFOV), etc. However, real-life robots with different purposes have multiple camera configurations, and the huge gap in visual information makes it difficu"},"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":"2012.05446","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2020-12-10T04:10:04Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3aa48e92963240c26eb4793f2c950548a1d21c9bfcda6938ec58681f6170e8ea","abstract_canon_sha256":"4d1a272b6acb7c889f2932f794595bd76a8a45d2cbf4728c0d8dc21700f2bf36"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:07:53.213307Z","signature_b64":"1jvWdGTh8ZwKGLePDILhjefLtPimHEjcPcJ0sI8f+QWvtErWZ326uwDiX7uY4p+LeaoBmSyi1Shf+DIIYYzZCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2fe5f7ec65184720731895ff92b3022b34b1f511da78ab2531a739ef15f51f16","last_reissued_at":"2026-07-05T02:07:53.212925Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:07:53.212925Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Visual Perception Generalization for Vision-and-Language Navigation via Meta-Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Donglin Wang, Ting Wang, Zongkai Wu","submitted_at":"2020-12-10T04:10:04Z","abstract_excerpt":"Vision-and-language navigation (VLN) is a challenging task that requires an agent to navigate in real-world environments by understanding natural language instructions and visual information received in real-time. Prior works have implemented VLN tasks on continuous environments or physical robots, all of which use a fixed camera configuration due to the limitations of datasets, such as 1.5 meters height, 90 degrees horizontal field of view (HFOV), etc. However, real-life robots with different purposes have multiple camera configurations, and the huge gap in visual information makes it difficu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.05446","kind":"arxiv","version":3},"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/2012.05446/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":"2012.05446","created_at":"2026-07-05T02:07:53.212978+00:00"},{"alias_kind":"arxiv_version","alias_value":"2012.05446v3","created_at":"2026-07-05T02:07:53.212978+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.05446","created_at":"2026-07-05T02:07:53.212978+00:00"},{"alias_kind":"pith_short_12","alias_value":"F7S7P3DFDBDS","created_at":"2026-07-05T02:07:53.212978+00:00"},{"alias_kind":"pith_short_16","alias_value":"F7S7P3DFDBDSA4YY","created_at":"2026-07-05T02:07:53.212978+00:00"},{"alias_kind":"pith_short_8","alias_value":"F7S7P3DF","created_at":"2026-07-05T02:07:53.212978+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/F7S7P3DFDBDSA4YYSX7ZFMYCFM","json":"https://pith.science/pith/F7S7P3DFDBDSA4YYSX7ZFMYCFM.json","graph_json":"https://pith.science/api/pith-number/F7S7P3DFDBDSA4YYSX7ZFMYCFM/graph.json","events_json":"https://pith.science/api/pith-number/F7S7P3DFDBDSA4YYSX7ZFMYCFM/events.json","paper":"https://pith.science/paper/F7S7P3DF"},"agent_actions":{"view_html":"https://pith.science/pith/F7S7P3DFDBDSA4YYSX7ZFMYCFM","download_json":"https://pith.science/pith/F7S7P3DFDBDSA4YYSX7ZFMYCFM.json","view_paper":"https://pith.science/paper/F7S7P3DF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2012.05446&json=true","fetch_graph":"https://pith.science/api/pith-number/F7S7P3DFDBDSA4YYSX7ZFMYCFM/graph.json","fetch_events":"https://pith.science/api/pith-number/F7S7P3DFDBDSA4YYSX7ZFMYCFM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/F7S7P3DFDBDSA4YYSX7ZFMYCFM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/F7S7P3DFDBDSA4YYSX7ZFMYCFM/action/storage_attestation","attest_author":"https://pith.science/pith/F7S7P3DFDBDSA4YYSX7ZFMYCFM/action/author_attestation","sign_citation":"https://pith.science/pith/F7S7P3DFDBDSA4YYSX7ZFMYCFM/action/citation_signature","submit_replication":"https://pith.science/pith/F7S7P3DFDBDSA4YYSX7ZFMYCFM/action/replication_record"}},"created_at":"2026-07-05T02:07:53.212978+00:00","updated_at":"2026-07-05T02:07:53.212978+00:00"}