{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:IQ4AKB3JFBRGKKJMLKCNXIYCT6","short_pith_number":"pith:IQ4AKB3J","schema_version":"1.0","canonical_sha256":"4438050769286265292c5a84dba3029f8cbe062120287520ff2025ef84831b02","source":{"kind":"arxiv","id":"2104.05859","version":5},"attestation_state":"computed","paper":{"title":"Rapid Exploration for Open-World Navigation with Latent Goal Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.RO","authors_text":"Benjamin Eysenbach, Dhruv Shah, Gregory Kahn, Nicholas Rhinehart, Sergey Levine","submitted_at":"2021-04-12T23:14:41Z","abstract_excerpt":"We describe a robotic learning system for autonomous exploration and navigation in diverse, open-world environments. At the core of our method is a learned latent variable model of distances and actions, along with a non-parametric topological memory of images. We use an information bottleneck to regularize the learned policy, giving us (i) a compact visual representation of goals, (ii) improved generalization capabilities, and (iii) a mechanism for sampling feasible goals for exploration. Trained on a large offline dataset of prior experience, the model acquires a representation of visual goa"},"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":"2104.05859","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2021-04-12T23:14:41Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"c8fec9cc020da5cf975b939119d0b76b3779950130e61f0604af4e0c5595c4b1","abstract_canon_sha256":"8427903d3a4a2f52f301f4870d51e76fea50562012fa15c2487d51d345558274"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:59:26.384696Z","signature_b64":"ZWvjPMWRGk2CWRD9c61P1j2VLMVlJ/RSt3QKOXzRT+OI84JjwrL5q8qUHQQpjwDFfNBBOmuO+Lx/ESXVRE24DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4438050769286265292c5a84dba3029f8cbe062120287520ff2025ef84831b02","last_reissued_at":"2026-07-05T06:59:26.384282Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:59:26.384282Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Rapid Exploration for Open-World Navigation with Latent Goal Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.RO","authors_text":"Benjamin Eysenbach, Dhruv Shah, Gregory Kahn, Nicholas Rhinehart, Sergey Levine","submitted_at":"2021-04-12T23:14:41Z","abstract_excerpt":"We describe a robotic learning system for autonomous exploration and navigation in diverse, open-world environments. At the core of our method is a learned latent variable model of distances and actions, along with a non-parametric topological memory of images. We use an information bottleneck to regularize the learned policy, giving us (i) a compact visual representation of goals, (ii) improved generalization capabilities, and (iii) a mechanism for sampling feasible goals for exploration. Trained on a large offline dataset of prior experience, the model acquires a representation of visual goa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.05859","kind":"arxiv","version":5},"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/2104.05859/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":"2104.05859","created_at":"2026-07-05T06:59:26.384335+00:00"},{"alias_kind":"arxiv_version","alias_value":"2104.05859v5","created_at":"2026-07-05T06:59:26.384335+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.05859","created_at":"2026-07-05T06:59:26.384335+00:00"},{"alias_kind":"pith_short_12","alias_value":"IQ4AKB3JFBRG","created_at":"2026-07-05T06:59:26.384335+00:00"},{"alias_kind":"pith_short_16","alias_value":"IQ4AKB3JFBRGKKJM","created_at":"2026-07-05T06:59:26.384335+00:00"},{"alias_kind":"pith_short_8","alias_value":"IQ4AKB3J","created_at":"2026-07-05T06:59:26.384335+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":11,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.24101","citing_title":"NavWM: A Unified Navigation World Model for Foresight-Driven Planning","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2605.31314","citing_title":"AR Forcing: Towards Long-Horizon Robot Navigation World Model","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2605.24578","citing_title":"World Models as Group Actions","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2605.24761","citing_title":"Drift-Resistant Navigation World Model with Anchored Epipolar Guidance","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2509.14787","citing_title":"COMPASS: Confined-space Manipulation Planning with Active Sensing Strategy","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2508.09547","citing_title":"GoViG: Goal-Conditioned Visual Navigation Instruction Generation via Multimodal Reasoning","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2602.06974","citing_title":"FeudalNav: A Simple Framework for Visual Navigation","ref_index":52,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14350","citing_title":"Distributionally Robust Multi-Task Reinforcement Learning via Adaptive Task Sampling","ref_index":278,"is_internal_anchor":false},{"citing_arxiv_id":"2604.02829","citing_title":"STRNet: Visual Navigation with Spatio-Temporal Representation through Dynamic Graph Aggregation","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11367","citing_title":"3D-Belief: Embodied Belief Inference via Generative 3D World Modeling","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01862","citing_title":"QHyer: Q-conditioned Hybrid Attention-mamba Transformer for Offline Goal-conditioned RL","ref_index":170,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IQ4AKB3JFBRGKKJMLKCNXIYCT6","json":"https://pith.science/pith/IQ4AKB3JFBRGKKJMLKCNXIYCT6.json","graph_json":"https://pith.science/api/pith-number/IQ4AKB3JFBRGKKJMLKCNXIYCT6/graph.json","events_json":"https://pith.science/api/pith-number/IQ4AKB3JFBRGKKJMLKCNXIYCT6/events.json","paper":"https://pith.science/paper/IQ4AKB3J"},"agent_actions":{"view_html":"https://pith.science/pith/IQ4AKB3JFBRGKKJMLKCNXIYCT6","download_json":"https://pith.science/pith/IQ4AKB3JFBRGKKJMLKCNXIYCT6.json","view_paper":"https://pith.science/paper/IQ4AKB3J","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2104.05859&json=true","fetch_graph":"https://pith.science/api/pith-number/IQ4AKB3JFBRGKKJMLKCNXIYCT6/graph.json","fetch_events":"https://pith.science/api/pith-number/IQ4AKB3JFBRGKKJMLKCNXIYCT6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IQ4AKB3JFBRGKKJMLKCNXIYCT6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IQ4AKB3JFBRGKKJMLKCNXIYCT6/action/storage_attestation","attest_author":"https://pith.science/pith/IQ4AKB3JFBRGKKJMLKCNXIYCT6/action/author_attestation","sign_citation":"https://pith.science/pith/IQ4AKB3JFBRGKKJMLKCNXIYCT6/action/citation_signature","submit_replication":"https://pith.science/pith/IQ4AKB3JFBRGKKJMLKCNXIYCT6/action/replication_record"}},"created_at":"2026-07-05T06:59:26.384335+00:00","updated_at":"2026-07-05T06:59:26.384335+00:00"}