{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:3NIWC5MBZJVOV7JSNWKCX65VQS","short_pith_number":"pith:3NIWC5MB","schema_version":"1.0","canonical_sha256":"db51617581ca6aeafd326d942bfbb58480d6a3e1c6a9e89f980486ed3549a953","source":{"kind":"arxiv","id":"2109.15207","version":1},"attestation_state":"computed","paper":{"title":"Language-Aligned Waypoint (LAW) Supervision for Vision-and-Language Navigation in Continuous Environments","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.RO"],"primary_cat":"cs.CV","authors_text":"Angel X. Chang, Saim Wani, Shivansh Patel, Sonia Raychaudhuri, Unnat Jain","submitted_at":"2021-09-30T15:28:24Z","abstract_excerpt":"In the Vision-and-Language Navigation (VLN) task an embodied agent navigates a 3D environment, following natural language instructions. A challenge in this task is how to handle 'off the path' scenarios where an agent veers from a reference path. Prior work supervises the agent with actions based on the shortest path from the agent's location to the goal, but such goal-oriented supervision is often not in alignment with the instruction. Furthermore, the evaluation metrics employed by prior work do not measure how much of a language instruction the agent is able to follow. In this work, we prop"},"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":"2109.15207","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-09-30T15:28:24Z","cross_cats_sorted":["cs.CL","cs.RO"],"title_canon_sha256":"d96402095d4b37466a4a0029f4c279c7e62aab01afeeb59c2eabd182210e7f98","abstract_canon_sha256":"ec4c1ebe8d83f62ef532759ee7cf32ac8cb5286af578e0e9ab2c3a6419c49763"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:18:56.669189Z","signature_b64":"jTd0l+ey4CZ32Gr//EqD+3zcanvVoj0/oS62leuu/1RJskfwlSR212EOAampD57jbS53yb7NLTwa6rmUsBuvAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"db51617581ca6aeafd326d942bfbb58480d6a3e1c6a9e89f980486ed3549a953","last_reissued_at":"2026-07-05T03:18:56.668771Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:18:56.668771Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Language-Aligned Waypoint (LAW) Supervision for Vision-and-Language Navigation in Continuous Environments","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.RO"],"primary_cat":"cs.CV","authors_text":"Angel X. Chang, Saim Wani, Shivansh Patel, Sonia Raychaudhuri, Unnat Jain","submitted_at":"2021-09-30T15:28:24Z","abstract_excerpt":"In the Vision-and-Language Navigation (VLN) task an embodied agent navigates a 3D environment, following natural language instructions. A challenge in this task is how to handle 'off the path' scenarios where an agent veers from a reference path. Prior work supervises the agent with actions based on the shortest path from the agent's location to the goal, but such goal-oriented supervision is often not in alignment with the instruction. Furthermore, the evaluation metrics employed by prior work do not measure how much of a language instruction the agent is able to follow. In this work, we prop"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.15207","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2109.15207/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":"2109.15207","created_at":"2026-07-05T03:18:56.668830+00:00"},{"alias_kind":"arxiv_version","alias_value":"2109.15207v1","created_at":"2026-07-05T03:18:56.668830+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.15207","created_at":"2026-07-05T03:18:56.668830+00:00"},{"alias_kind":"pith_short_12","alias_value":"3NIWC5MBZJVO","created_at":"2026-07-05T03:18:56.668830+00:00"},{"alias_kind":"pith_short_16","alias_value":"3NIWC5MBZJVOV7JS","created_at":"2026-07-05T03:18:56.668830+00:00"},{"alias_kind":"pith_short_8","alias_value":"3NIWC5MB","created_at":"2026-07-05T03:18:56.668830+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"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":78,"is_internal_anchor":false},{"citing_arxiv_id":"2412.06224","citing_title":"Uni-NaVid: A Video-based Vision-Language-Action Model for Unifying Embodied Navigation Tasks","ref_index":73,"is_internal_anchor":false},{"citing_arxiv_id":"2512.21714","citing_title":"AstraNav-World: World Model for Foresight Control and Consistency","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17190","citing_title":"LookasideVLN: Direction-Aware Aerial Vision-and-Language Navigation","ref_index":32,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3NIWC5MBZJVOV7JSNWKCX65VQS","json":"https://pith.science/pith/3NIWC5MBZJVOV7JSNWKCX65VQS.json","graph_json":"https://pith.science/api/pith-number/3NIWC5MBZJVOV7JSNWKCX65VQS/graph.json","events_json":"https://pith.science/api/pith-number/3NIWC5MBZJVOV7JSNWKCX65VQS/events.json","paper":"https://pith.science/paper/3NIWC5MB"},"agent_actions":{"view_html":"https://pith.science/pith/3NIWC5MBZJVOV7JSNWKCX65VQS","download_json":"https://pith.science/pith/3NIWC5MBZJVOV7JSNWKCX65VQS.json","view_paper":"https://pith.science/paper/3NIWC5MB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2109.15207&json=true","fetch_graph":"https://pith.science/api/pith-number/3NIWC5MBZJVOV7JSNWKCX65VQS/graph.json","fetch_events":"https://pith.science/api/pith-number/3NIWC5MBZJVOV7JSNWKCX65VQS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3NIWC5MBZJVOV7JSNWKCX65VQS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3NIWC5MBZJVOV7JSNWKCX65VQS/action/storage_attestation","attest_author":"https://pith.science/pith/3NIWC5MBZJVOV7JSNWKCX65VQS/action/author_attestation","sign_citation":"https://pith.science/pith/3NIWC5MBZJVOV7JSNWKCX65VQS/action/citation_signature","submit_replication":"https://pith.science/pith/3NIWC5MBZJVOV7JSNWKCX65VQS/action/replication_record"}},"created_at":"2026-07-05T03:18:56.668830+00:00","updated_at":"2026-07-05T03:18:56.668830+00:00"}