{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:V6Y3XUV3H7TUMGMWG7FDM4LBAW","short_pith_number":"pith:V6Y3XUV3","schema_version":"1.0","canonical_sha256":"afb1bbd2bb3fe746199637ca367161059c44638eff6cf5ab8e7e6aafb9a06f71","source":{"kind":"arxiv","id":"1905.13358","version":1},"attestation_state":"computed","paper":{"title":"Multi-modal Discriminative Model for Vision-and-Language Navigation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Eugene Ie, Haoshuo Huang, Harsh Mehta, Jason Baldridge, Vihan Jain","submitted_at":"2019-05-31T00:07:24Z","abstract_excerpt":"Vision-and-Language Navigation (VLN) is a natural language grounding task where agents have to interpret natural language instructions in the context of visual scenes in a dynamic environment to achieve prescribed navigation goals. Successful agents must have the ability to parse natural language of varying linguistic styles, ground them in potentially unfamiliar scenes, plan and react with ambiguous environmental feedback. Generalization ability is limited by the amount of human annotated data. In particular, \\emph{paired} vision-language sequence data is expensive to collect. We develop a di"},"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":"1905.13358","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2019-05-31T00:07:24Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"9dc84ffcae064a656739c56fbe03ae69968ccb2663fd6bf343598d9a0a754cc1","abstract_canon_sha256":"bfb39efed5d727e9e4a119106af59108e163a810374b4ecf5d81bed45bcbf6c3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:44:35.193559Z","signature_b64":"jyWm3cUR0e292qNugcMuqNrn8kQSR9JthxOuXLzv+Z0JUxHr2tKVPMvQLt4KzADAHcCf8iHdVPXAALHX4/BoDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"afb1bbd2bb3fe746199637ca367161059c44638eff6cf5ab8e7e6aafb9a06f71","last_reissued_at":"2026-05-17T23:44:35.193026Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:44:35.193026Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-modal Discriminative Model for Vision-and-Language Navigation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Eugene Ie, Haoshuo Huang, Harsh Mehta, Jason Baldridge, Vihan Jain","submitted_at":"2019-05-31T00:07:24Z","abstract_excerpt":"Vision-and-Language Navigation (VLN) is a natural language grounding task where agents have to interpret natural language instructions in the context of visual scenes in a dynamic environment to achieve prescribed navigation goals. Successful agents must have the ability to parse natural language of varying linguistic styles, ground them in potentially unfamiliar scenes, plan and react with ambiguous environmental feedback. Generalization ability is limited by the amount of human annotated data. In particular, \\emph{paired} vision-language sequence data is expensive to collect. We develop a di"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.13358","kind":"arxiv","version":1},"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":"1905.13358","created_at":"2026-05-17T23:44:35.193114+00:00"},{"alias_kind":"arxiv_version","alias_value":"1905.13358v1","created_at":"2026-05-17T23:44:35.193114+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.13358","created_at":"2026-05-17T23:44:35.193114+00:00"},{"alias_kind":"pith_short_12","alias_value":"V6Y3XUV3H7TU","created_at":"2026-05-18T12:33:30.264802+00:00"},{"alias_kind":"pith_short_16","alias_value":"V6Y3XUV3H7TUMGMW","created_at":"2026-05-18T12:33:30.264802+00:00"},{"alias_kind":"pith_short_8","alias_value":"V6Y3XUV3","created_at":"2026-05-18T12:33:30.264802+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/V6Y3XUV3H7TUMGMWG7FDM4LBAW","json":"https://pith.science/pith/V6Y3XUV3H7TUMGMWG7FDM4LBAW.json","graph_json":"https://pith.science/api/pith-number/V6Y3XUV3H7TUMGMWG7FDM4LBAW/graph.json","events_json":"https://pith.science/api/pith-number/V6Y3XUV3H7TUMGMWG7FDM4LBAW/events.json","paper":"https://pith.science/paper/V6Y3XUV3"},"agent_actions":{"view_html":"https://pith.science/pith/V6Y3XUV3H7TUMGMWG7FDM4LBAW","download_json":"https://pith.science/pith/V6Y3XUV3H7TUMGMWG7FDM4LBAW.json","view_paper":"https://pith.science/paper/V6Y3XUV3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1905.13358&json=true","fetch_graph":"https://pith.science/api/pith-number/V6Y3XUV3H7TUMGMWG7FDM4LBAW/graph.json","fetch_events":"https://pith.science/api/pith-number/V6Y3XUV3H7TUMGMWG7FDM4LBAW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/V6Y3XUV3H7TUMGMWG7FDM4LBAW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/V6Y3XUV3H7TUMGMWG7FDM4LBAW/action/storage_attestation","attest_author":"https://pith.science/pith/V6Y3XUV3H7TUMGMWG7FDM4LBAW/action/author_attestation","sign_citation":"https://pith.science/pith/V6Y3XUV3H7TUMGMWG7FDM4LBAW/action/citation_signature","submit_replication":"https://pith.science/pith/V6Y3XUV3H7TUMGMWG7FDM4LBAW/action/replication_record"}},"created_at":"2026-05-17T23:44:35.193114+00:00","updated_at":"2026-05-17T23:44:35.193114+00:00"}