{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:LRJNCYY2XPMNDL3JVFFS3YQL3C","short_pith_number":"pith:LRJNCYY2","schema_version":"1.0","canonical_sha256":"5c52d1631abbd8d1af69a94b2de20bd8a17bea43e5d7dba4f3563664b83019a1","source":{"kind":"arxiv","id":"1806.02724","version":2},"attestation_state":"computed","paper":{"title":"Speaker-Follower Models for Vision-and-Language Navigation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Anna Rohrbach, Daniel Fried, Dan Klein, Jacob Andreas, Kate Saenko, Louis-Philippe Morency, Ronghang Hu, Taylor Berg-Kirkpatrick, Trevor Darrell, Volkan Cirik","submitted_at":"2018-06-07T15:15:35Z","abstract_excerpt":"Navigation guided by natural language instructions presents a challenging reasoning problem for instruction followers. Natural language instructions typically identify only a few high-level decisions and landmarks rather than complete low-level motor behaviors; much of the missing information must be inferred based on perceptual context. In machine learning settings, this is doubly challenging: it is difficult to collect enough annotated data to enable learning of this reasoning process from scratch, and also difficult to implement the reasoning process using generic sequence models. Here we d"},"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":"1806.02724","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-06-07T15:15:35Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"873e418f566ae575127d82084b6aa5282dcadef12cd845a38f18375476e276f9","abstract_canon_sha256":"258b1cc4136da9927a61711a5e2334b09f3d5c0ddf373b52a1c84e59cf3cbcdd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:02:09.799960Z","signature_b64":"7C5T85f7CQQdvEy3Yb+yWTR7UL+xcoWBQodrFz4deA7Gz7dpNPqlhT6LEVYHa6OBqQSLHxhvayWyVC7Ma/YxAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5c52d1631abbd8d1af69a94b2de20bd8a17bea43e5d7dba4f3563664b83019a1","last_reissued_at":"2026-05-18T00:02:09.799347Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:02:09.799347Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Speaker-Follower Models for Vision-and-Language Navigation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Anna Rohrbach, Daniel Fried, Dan Klein, Jacob Andreas, Kate Saenko, Louis-Philippe Morency, Ronghang Hu, Taylor Berg-Kirkpatrick, Trevor Darrell, Volkan Cirik","submitted_at":"2018-06-07T15:15:35Z","abstract_excerpt":"Navigation guided by natural language instructions presents a challenging reasoning problem for instruction followers. Natural language instructions typically identify only a few high-level decisions and landmarks rather than complete low-level motor behaviors; much of the missing information must be inferred based on perceptual context. In machine learning settings, this is doubly challenging: it is difficult to collect enough annotated data to enable learning of this reasoning process from scratch, and also difficult to implement the reasoning process using generic sequence models. Here we d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.02724","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":""},"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":"1806.02724","created_at":"2026-05-18T00:02:09.799470+00:00"},{"alias_kind":"arxiv_version","alias_value":"1806.02724v2","created_at":"2026-05-18T00:02:09.799470+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.02724","created_at":"2026-05-18T00:02:09.799470+00:00"},{"alias_kind":"pith_short_12","alias_value":"LRJNCYY2XPMN","created_at":"2026-05-18T12:32:37.024351+00:00"},{"alias_kind":"pith_short_16","alias_value":"LRJNCYY2XPMNDL3J","created_at":"2026-05-18T12:32:37.024351+00:00"},{"alias_kind":"pith_short_8","alias_value":"LRJNCYY2","created_at":"2026-05-18T12:32:37.024351+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.09547","citing_title":"GoViG: Goal-Conditioned Visual Navigation Instruction Generation via Multimodal Reasoning","ref_index":7,"is_internal_anchor":true},{"citing_arxiv_id":"2604.16298","citing_title":"FineCog-Nav: Integrating Fine-grained Cognitive Modules for Zero-shot Multimodal UAV Navigation","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LRJNCYY2XPMNDL3JVFFS3YQL3C","json":"https://pith.science/pith/LRJNCYY2XPMNDL3JVFFS3YQL3C.json","graph_json":"https://pith.science/api/pith-number/LRJNCYY2XPMNDL3JVFFS3YQL3C/graph.json","events_json":"https://pith.science/api/pith-number/LRJNCYY2XPMNDL3JVFFS3YQL3C/events.json","paper":"https://pith.science/paper/LRJNCYY2"},"agent_actions":{"view_html":"https://pith.science/pith/LRJNCYY2XPMNDL3JVFFS3YQL3C","download_json":"https://pith.science/pith/LRJNCYY2XPMNDL3JVFFS3YQL3C.json","view_paper":"https://pith.science/paper/LRJNCYY2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1806.02724&json=true","fetch_graph":"https://pith.science/api/pith-number/LRJNCYY2XPMNDL3JVFFS3YQL3C/graph.json","fetch_events":"https://pith.science/api/pith-number/LRJNCYY2XPMNDL3JVFFS3YQL3C/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LRJNCYY2XPMNDL3JVFFS3YQL3C/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LRJNCYY2XPMNDL3JVFFS3YQL3C/action/storage_attestation","attest_author":"https://pith.science/pith/LRJNCYY2XPMNDL3JVFFS3YQL3C/action/author_attestation","sign_citation":"https://pith.science/pith/LRJNCYY2XPMNDL3JVFFS3YQL3C/action/citation_signature","submit_replication":"https://pith.science/pith/LRJNCYY2XPMNDL3JVFFS3YQL3C/action/replication_record"}},"created_at":"2026-05-18T00:02:09.799470+00:00","updated_at":"2026-05-18T00:02:09.799470+00:00"}