{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:LIZSHHFVEBCKUH2GERB56ICMUF","short_pith_number":"pith:LIZSHHFV","schema_version":"1.0","canonical_sha256":"5a33239cb52044aa1f462443df204ca14afafedcc75eaee6f29ac7680048196b","source":{"kind":"arxiv","id":"2210.03112","version":3},"attestation_state":"computed","paper":{"title":"A New Path: Scaling Vision-and-Language Navigation with Synthetic Instructions and Imitation Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.CV","cs.RO"],"primary_cat":"cs.LG","authors_text":"Aishwarya Kamath, Alexander Ku, Austin Waters, Jason Baldridge, Jing Yu Koh, Peter Anderson, Su Wang, Yinfei Yang, Zarana Parekh","submitted_at":"2022-10-06T17:59:08Z","abstract_excerpt":"Recent studies in Vision-and-Language Navigation (VLN) train RL agents to execute natural-language navigation instructions in photorealistic environments, as a step towards robots that can follow human instructions. However, given the scarcity of human instruction data and limited diversity in the training environments, these agents still struggle with complex language grounding and spatial language understanding. Pretraining on large text and image-text datasets from the web has been extensively explored but the improvements are limited. We investigate large-scale augmentation with synthetic "},"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":"2210.03112","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-10-06T17:59:08Z","cross_cats_sorted":["cs.CL","cs.CV","cs.RO"],"title_canon_sha256":"8e61292e3cf6de79fd45c64abc92c59d47efa769e7365b2e22d70efb75b92c8b","abstract_canon_sha256":"88b446f0395a3d30b53e1b443c90455362adb7da86ab05be01d7ea5bea3afea7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:01:35.509457Z","signature_b64":"6zkWdyIhsBbq/F+IPaOq3ejdddduhdf8bhJisumeUjCjDD8s/zq1arwid/fU1dnEsdgKsGzuUtBIooFkPKyNAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5a33239cb52044aa1f462443df204ca14afafedcc75eaee6f29ac7680048196b","last_reissued_at":"2026-07-05T06:01:35.509002Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:01:35.509002Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A New Path: Scaling Vision-and-Language Navigation with Synthetic Instructions and Imitation Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.CV","cs.RO"],"primary_cat":"cs.LG","authors_text":"Aishwarya Kamath, Alexander Ku, Austin Waters, Jason Baldridge, Jing Yu Koh, Peter Anderson, Su Wang, Yinfei Yang, Zarana Parekh","submitted_at":"2022-10-06T17:59:08Z","abstract_excerpt":"Recent studies in Vision-and-Language Navigation (VLN) train RL agents to execute natural-language navigation instructions in photorealistic environments, as a step towards robots that can follow human instructions. However, given the scarcity of human instruction data and limited diversity in the training environments, these agents still struggle with complex language grounding and spatial language understanding. Pretraining on large text and image-text datasets from the web has been extensively explored but the improvements are limited. We investigate large-scale augmentation with synthetic "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.03112","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/2210.03112/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":"2210.03112","created_at":"2026-07-05T06:01:35.509066+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.03112v3","created_at":"2026-07-05T06:01:35.509066+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.03112","created_at":"2026-07-05T06:01:35.509066+00:00"},{"alias_kind":"pith_short_12","alias_value":"LIZSHHFVEBCK","created_at":"2026-07-05T06:01:35.509066+00:00"},{"alias_kind":"pith_short_16","alias_value":"LIZSHHFVEBCKUH2G","created_at":"2026-07-05T06:01:35.509066+00:00"},{"alias_kind":"pith_short_8","alias_value":"LIZSHHFV","created_at":"2026-07-05T06:01:35.509066+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2402.15852","citing_title":"NaVid: Video-based VLM Plans the Next Step for Vision-and-Language Navigation","ref_index":41,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LIZSHHFVEBCKUH2GERB56ICMUF","json":"https://pith.science/pith/LIZSHHFVEBCKUH2GERB56ICMUF.json","graph_json":"https://pith.science/api/pith-number/LIZSHHFVEBCKUH2GERB56ICMUF/graph.json","events_json":"https://pith.science/api/pith-number/LIZSHHFVEBCKUH2GERB56ICMUF/events.json","paper":"https://pith.science/paper/LIZSHHFV"},"agent_actions":{"view_html":"https://pith.science/pith/LIZSHHFVEBCKUH2GERB56ICMUF","download_json":"https://pith.science/pith/LIZSHHFVEBCKUH2GERB56ICMUF.json","view_paper":"https://pith.science/paper/LIZSHHFV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.03112&json=true","fetch_graph":"https://pith.science/api/pith-number/LIZSHHFVEBCKUH2GERB56ICMUF/graph.json","fetch_events":"https://pith.science/api/pith-number/LIZSHHFVEBCKUH2GERB56ICMUF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LIZSHHFVEBCKUH2GERB56ICMUF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LIZSHHFVEBCKUH2GERB56ICMUF/action/storage_attestation","attest_author":"https://pith.science/pith/LIZSHHFVEBCKUH2GERB56ICMUF/action/author_attestation","sign_citation":"https://pith.science/pith/LIZSHHFVEBCKUH2GERB56ICMUF/action/citation_signature","submit_replication":"https://pith.science/pith/LIZSHHFVEBCKUH2GERB56ICMUF/action/replication_record"}},"created_at":"2026-07-05T06:01:35.509066+00:00","updated_at":"2026-07-05T06:01:35.509066+00:00"}