{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:QDBDXW64DZO4MAOEAVLU6G24WC","short_pith_number":"pith:QDBDXW64","schema_version":"1.0","canonical_sha256":"80c23bdbdc1e5dc601c405574f1b5cb0882bbd26797c5e9922efe19cdf501588","source":{"kind":"arxiv","id":"1711.07280","version":3},"attestation_state":"computed","paper":{"title":"Vision-and-Language Navigation: Interpreting visually-grounded navigation instructions in real environments","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.RO"],"primary_cat":"cs.CV","authors_text":"Anton van den Hengel, Damien Teney, Ian Reid, Jake Bruce, Mark Johnson, Niko S\\\"underhauf, Peter Anderson, Qi Wu, Stephen Gould","submitted_at":"2017-11-20T12:17:47Z","abstract_excerpt":"A robot that can carry out a natural-language instruction has been a dream since before the Jetsons cartoon series imagined a life of leisure mediated by a fleet of attentive robot helpers. It is a dream that remains stubbornly distant. However, recent advances in vision and language methods have made incredible progress in closely related areas. This is significant because a robot interpreting a natural-language navigation instruction on the basis of what it sees is carrying out a vision and language process that is similar to Visual Question Answering. Both tasks can be interpreted as visual"},"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":"1711.07280","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-11-20T12:17:47Z","cross_cats_sorted":["cs.AI","cs.CL","cs.RO"],"title_canon_sha256":"c28ce10355a10be5dead8d3b0de729805fd44b22b2dc8c7a3f1044e77bfdac46","abstract_canon_sha256":"0bc5c5536a92315c442d4e48d19d1e00feb32c51a05fb5848306b9f36069a1a2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:19:08.570627Z","signature_b64":"EiYweLIg7xqNkqZ0lQ4y9yhOWuxhpq8dY4CjpR1MS99lT58kIPW1bCUxYZb2p/MWZI7ciyevcpuHyQQmhaSzCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"80c23bdbdc1e5dc601c405574f1b5cb0882bbd26797c5e9922efe19cdf501588","last_reissued_at":"2026-05-18T00:19:08.569855Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:19:08.569855Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Vision-and-Language Navigation: Interpreting visually-grounded navigation instructions in real environments","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.RO"],"primary_cat":"cs.CV","authors_text":"Anton van den Hengel, Damien Teney, Ian Reid, Jake Bruce, Mark Johnson, Niko S\\\"underhauf, Peter Anderson, Qi Wu, Stephen Gould","submitted_at":"2017-11-20T12:17:47Z","abstract_excerpt":"A robot that can carry out a natural-language instruction has been a dream since before the Jetsons cartoon series imagined a life of leisure mediated by a fleet of attentive robot helpers. It is a dream that remains stubbornly distant. However, recent advances in vision and language methods have made incredible progress in closely related areas. This is significant because a robot interpreting a natural-language navigation instruction on the basis of what it sees is carrying out a vision and language process that is similar to Visual Question Answering. Both tasks can be interpreted as visual"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.07280","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":""},"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":"1711.07280","created_at":"2026-05-18T00:19:08.570003+00:00"},{"alias_kind":"arxiv_version","alias_value":"1711.07280v3","created_at":"2026-05-18T00:19:08.570003+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.07280","created_at":"2026-05-18T00:19:08.570003+00:00"},{"alias_kind":"pith_short_12","alias_value":"QDBDXW64DZO4","created_at":"2026-05-18T12:31:37.085036+00:00"},{"alias_kind":"pith_short_16","alias_value":"QDBDXW64DZO4MAOE","created_at":"2026-05-18T12:31:37.085036+00:00"},{"alias_kind":"pith_short_8","alias_value":"QDBDXW64","created_at":"2026-05-18T12:31:37.085036+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":4,"sample":[{"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":9,"is_internal_anchor":true},{"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":9,"is_internal_anchor":true},{"citing_arxiv_id":"2605.18603","citing_title":"Starve to Perceive: Taming Lazy Perception in VLMs with Constrained Visual Bandwidth","ref_index":3,"is_internal_anchor":true},{"citing_arxiv_id":"2603.07080","citing_title":"VLN-Cache: Enabling Token Caching for VLN Models with Visual/Semantic Dynamics Awareness","ref_index":31,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QDBDXW64DZO4MAOEAVLU6G24WC","json":"https://pith.science/pith/QDBDXW64DZO4MAOEAVLU6G24WC.json","graph_json":"https://pith.science/api/pith-number/QDBDXW64DZO4MAOEAVLU6G24WC/graph.json","events_json":"https://pith.science/api/pith-number/QDBDXW64DZO4MAOEAVLU6G24WC/events.json","paper":"https://pith.science/paper/QDBDXW64"},"agent_actions":{"view_html":"https://pith.science/pith/QDBDXW64DZO4MAOEAVLU6G24WC","download_json":"https://pith.science/pith/QDBDXW64DZO4MAOEAVLU6G24WC.json","view_paper":"https://pith.science/paper/QDBDXW64","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1711.07280&json=true","fetch_graph":"https://pith.science/api/pith-number/QDBDXW64DZO4MAOEAVLU6G24WC/graph.json","fetch_events":"https://pith.science/api/pith-number/QDBDXW64DZO4MAOEAVLU6G24WC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QDBDXW64DZO4MAOEAVLU6G24WC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QDBDXW64DZO4MAOEAVLU6G24WC/action/storage_attestation","attest_author":"https://pith.science/pith/QDBDXW64DZO4MAOEAVLU6G24WC/action/author_attestation","sign_citation":"https://pith.science/pith/QDBDXW64DZO4MAOEAVLU6G24WC/action/citation_signature","submit_replication":"https://pith.science/pith/QDBDXW64DZO4MAOEAVLU6G24WC/action/replication_record"}},"created_at":"2026-05-18T00:19:08.570003+00:00","updated_at":"2026-05-18T00:19:08.570003+00:00"}