{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:2DOEWXMIAVC5WRIDDVK2MZYGRF","short_pith_number":"pith:2DOEWXMI","schema_version":"1.0","canonical_sha256":"d0dc4b5d880545db45031d55a6670689611764a61a64c3e3e7a9deae92972aba","source":{"kind":"arxiv","id":"2202.02312","version":3},"attestation_state":"computed","paper":{"title":"A Dataset for Interactive Vision-Language Navigation with Unknown Command Feasibility","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.HC"],"primary_cat":"cs.CL","authors_text":"Andrea Burns, Bryan A. Plummer, Deniz Arsan, Kate Saenko, Ranjitha Kumar, Sanjna Agrawal","submitted_at":"2022-02-04T18:51:50Z","abstract_excerpt":"Vision-language navigation (VLN), in which an agent follows language instruction in a visual environment, has been studied under the premise that the input command is fully feasible in the environment. Yet in practice, a request may not be possible due to language ambiguity or environment changes. To study VLN with unknown command feasibility, we introduce a new dataset Mobile app Tasks with Iterative Feedback (MoTIF), where the goal is to complete a natural language command in a mobile app. Mobile apps provide a scalable domain to study real downstream uses of VLN methods. Moreover, mobile ap"},"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":"2202.02312","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-02-04T18:51:50Z","cross_cats_sorted":["cs.CV","cs.HC"],"title_canon_sha256":"f276e760000a247753b2438ce079b51564a64eed63348c68a686622b104c18b3","abstract_canon_sha256":"3a55b92dc27e8b4a702eb79405e6a0fd9d0a7abbf3d2bb9ffa4c11725ad321e2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:48:10.403066Z","signature_b64":"h2LBD+YuE5ieGev7VqrBlkenv/Er8EFcs3EpaPOiJst69Z3z1Z/6S2tPosVBjDBwY/soM+9QHY8B7MME3lIdCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d0dc4b5d880545db45031d55a6670689611764a61a64c3e3e7a9deae92972aba","last_reissued_at":"2026-07-05T04:48:10.402571Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:48:10.402571Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Dataset for Interactive Vision-Language Navigation with Unknown Command Feasibility","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.HC"],"primary_cat":"cs.CL","authors_text":"Andrea Burns, Bryan A. Plummer, Deniz Arsan, Kate Saenko, Ranjitha Kumar, Sanjna Agrawal","submitted_at":"2022-02-04T18:51:50Z","abstract_excerpt":"Vision-language navigation (VLN), in which an agent follows language instruction in a visual environment, has been studied under the premise that the input command is fully feasible in the environment. Yet in practice, a request may not be possible due to language ambiguity or environment changes. To study VLN with unknown command feasibility, we introduce a new dataset Mobile app Tasks with Iterative Feedback (MoTIF), where the goal is to complete a natural language command in a mobile app. Mobile apps provide a scalable domain to study real downstream uses of VLN methods. Moreover, mobile ap"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.02312","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/2202.02312/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":"2202.02312","created_at":"2026-07-05T04:48:10.402632+00:00"},{"alias_kind":"arxiv_version","alias_value":"2202.02312v3","created_at":"2026-07-05T04:48:10.402632+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.02312","created_at":"2026-07-05T04:48:10.402632+00:00"},{"alias_kind":"pith_short_12","alias_value":"2DOEWXMIAVC5","created_at":"2026-07-05T04:48:10.402632+00:00"},{"alias_kind":"pith_short_16","alias_value":"2DOEWXMIAVC5WRID","created_at":"2026-07-05T04:48:10.402632+00:00"},{"alias_kind":"pith_short_8","alias_value":"2DOEWXMI","created_at":"2026-07-05T04:48:10.402632+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2401.10935","citing_title":"SeeClick: Harnessing GUI Grounding for Advanced Visual GUI Agents","ref_index":69,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2DOEWXMIAVC5WRIDDVK2MZYGRF","json":"https://pith.science/pith/2DOEWXMIAVC5WRIDDVK2MZYGRF.json","graph_json":"https://pith.science/api/pith-number/2DOEWXMIAVC5WRIDDVK2MZYGRF/graph.json","events_json":"https://pith.science/api/pith-number/2DOEWXMIAVC5WRIDDVK2MZYGRF/events.json","paper":"https://pith.science/paper/2DOEWXMI"},"agent_actions":{"view_html":"https://pith.science/pith/2DOEWXMIAVC5WRIDDVK2MZYGRF","download_json":"https://pith.science/pith/2DOEWXMIAVC5WRIDDVK2MZYGRF.json","view_paper":"https://pith.science/paper/2DOEWXMI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2202.02312&json=true","fetch_graph":"https://pith.science/api/pith-number/2DOEWXMIAVC5WRIDDVK2MZYGRF/graph.json","fetch_events":"https://pith.science/api/pith-number/2DOEWXMIAVC5WRIDDVK2MZYGRF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2DOEWXMIAVC5WRIDDVK2MZYGRF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2DOEWXMIAVC5WRIDDVK2MZYGRF/action/storage_attestation","attest_author":"https://pith.science/pith/2DOEWXMIAVC5WRIDDVK2MZYGRF/action/author_attestation","sign_citation":"https://pith.science/pith/2DOEWXMIAVC5WRIDDVK2MZYGRF/action/citation_signature","submit_replication":"https://pith.science/pith/2DOEWXMIAVC5WRIDDVK2MZYGRF/action/replication_record"}},"created_at":"2026-07-05T04:48:10.402632+00:00","updated_at":"2026-07-05T04:48:10.402632+00:00"}