{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:63PEAGMKZATJ4ZNXBL2WJV6HWV","short_pith_number":"pith:63PEAGMK","schema_version":"1.0","canonical_sha256":"f6de40198ac8269e65b70af564d7c7b56f93ae26d3c5c9f6718c3538e8def649","source":{"kind":"arxiv","id":"2108.05713","version":2},"attestation_state":"computed","paper":{"title":"Towards real-world navigation with deep differentiable planners","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.LG"],"primary_cat":"cs.RO","authors_text":"Jo\\~ao F. Henriques, Shu Ishida","submitted_at":"2021-08-08T11:29:16Z","abstract_excerpt":"We train embodied neural networks to plan and navigate unseen complex 3D environments, emphasising real-world deployment. Rather than requiring prior knowledge of the agent or environment, the planner learns to model the state transitions and rewards. To avoid the potentially hazardous trial-and-error of reinforcement learning, we focus on differentiable planners such as Value Iteration Networks (VIN), which are trained offline from safe expert demonstrations. Although they work well in small simulations, we address two major limitations that hinder their deployment. First, we observed that cu"},"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":"2108.05713","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2021-08-08T11:29:16Z","cross_cats_sorted":["cs.AI","cs.CV","cs.LG"],"title_canon_sha256":"fd791f9485ecfbceb14c4da028b8a6d4ebf162458e709ababbb1463e7b2ea762","abstract_canon_sha256":"73b6e7c66c08461cf64dc8792e76cb034e5edbc83e4cc5d977d08d73dba493c6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:28:26.897443Z","signature_b64":"U8/gQFk0bKIDbHrUb+y3ntDf7DhTQ4MdlDL/x9SaegY9n6g2ueIGXycPfQxWC9q8Wi0jk/kK74uf0FiR62IxBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f6de40198ac8269e65b70af564d7c7b56f93ae26d3c5c9f6718c3538e8def649","last_reissued_at":"2026-07-05T04:28:26.897059Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:28:26.897059Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards real-world navigation with deep differentiable planners","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.LG"],"primary_cat":"cs.RO","authors_text":"Jo\\~ao F. Henriques, Shu Ishida","submitted_at":"2021-08-08T11:29:16Z","abstract_excerpt":"We train embodied neural networks to plan and navigate unseen complex 3D environments, emphasising real-world deployment. Rather than requiring prior knowledge of the agent or environment, the planner learns to model the state transitions and rewards. To avoid the potentially hazardous trial-and-error of reinforcement learning, we focus on differentiable planners such as Value Iteration Networks (VIN), which are trained offline from safe expert demonstrations. Although they work well in small simulations, we address two major limitations that hinder their deployment. First, we observed that cu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.05713","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2108.05713/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":"2108.05713","created_at":"2026-07-05T04:28:26.897109+00:00"},{"alias_kind":"arxiv_version","alias_value":"2108.05713v2","created_at":"2026-07-05T04:28:26.897109+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.05713","created_at":"2026-07-05T04:28:26.897109+00:00"},{"alias_kind":"pith_short_12","alias_value":"63PEAGMKZATJ","created_at":"2026-07-05T04:28:26.897109+00:00"},{"alias_kind":"pith_short_16","alias_value":"63PEAGMKZATJ4ZNX","created_at":"2026-07-05T04:28:26.897109+00:00"},{"alias_kind":"pith_short_8","alias_value":"63PEAGMK","created_at":"2026-07-05T04:28:26.897109+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/63PEAGMKZATJ4ZNXBL2WJV6HWV","json":"https://pith.science/pith/63PEAGMKZATJ4ZNXBL2WJV6HWV.json","graph_json":"https://pith.science/api/pith-number/63PEAGMKZATJ4ZNXBL2WJV6HWV/graph.json","events_json":"https://pith.science/api/pith-number/63PEAGMKZATJ4ZNXBL2WJV6HWV/events.json","paper":"https://pith.science/paper/63PEAGMK"},"agent_actions":{"view_html":"https://pith.science/pith/63PEAGMKZATJ4ZNXBL2WJV6HWV","download_json":"https://pith.science/pith/63PEAGMKZATJ4ZNXBL2WJV6HWV.json","view_paper":"https://pith.science/paper/63PEAGMK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2108.05713&json=true","fetch_graph":"https://pith.science/api/pith-number/63PEAGMKZATJ4ZNXBL2WJV6HWV/graph.json","fetch_events":"https://pith.science/api/pith-number/63PEAGMKZATJ4ZNXBL2WJV6HWV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/63PEAGMKZATJ4ZNXBL2WJV6HWV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/63PEAGMKZATJ4ZNXBL2WJV6HWV/action/storage_attestation","attest_author":"https://pith.science/pith/63PEAGMKZATJ4ZNXBL2WJV6HWV/action/author_attestation","sign_citation":"https://pith.science/pith/63PEAGMKZATJ4ZNXBL2WJV6HWV/action/citation_signature","submit_replication":"https://pith.science/pith/63PEAGMKZATJ4ZNXBL2WJV6HWV/action/replication_record"}},"created_at":"2026-07-05T04:28:26.897109+00:00","updated_at":"2026-07-05T04:28:26.897109+00:00"}