{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:R4UCIOI27KVVTVS7PZFARJ5LF5","short_pith_number":"pith:R4UCIOI2","schema_version":"1.0","canonical_sha256":"8f2824391afaab59d65f7e4a08a7ab2f5bbd3e675cdd2f44cd40a3ff182bc9b3","source":{"kind":"arxiv","id":"2108.01176","version":2},"attestation_state":"computed","paper":{"title":"Hierarchical Representations and Explicit Memory: Learning Effective Navigation Policies on 3D Scene Graphs using Graph Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"J. Daniel Griffith, Lisa Peng, Luca Carlone, Nathan Hughes, Zachary Ravichandran","submitted_at":"2021-08-02T21:21:27Z","abstract_excerpt":"Representations are crucial for a robot to learn effective navigation policies. Recent work has shown that mid-level perceptual abstractions, such as depth estimates or 2D semantic segmentation, lead to more effective policies when provided as observations in place of raw sensor data (e.g., RGB images). However, such policies must still learn latent three-dimensional scene properties from mid-level abstractions. In contrast, high-level, hierarchical representations such as 3D scene graphs explicitly provide a scene's geometry, topology, and semantics, making them compelling representations for"},"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":"2108.01176","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2021-08-02T21:21:27Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"cbc7bb16002934e0cfb5cd141316a6fbbaf178182c210eb38b7171ffb8ebfa6a","abstract_canon_sha256":"2e99f67ace65a68577f68d430fe8197be58753ee4bb24ad403d2348cc8c70297"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:20:42.909385Z","signature_b64":"p0QS1mwYBiYAPWgzPmCAFg0Psyp8FfDopFdwMh3ACdkrDMw+fN4ffL7gCF+iY1z04aqaRKPJ11y2GYygoN7rDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8f2824391afaab59d65f7e4a08a7ab2f5bbd3e675cdd2f44cd40a3ff182bc9b3","last_reissued_at":"2026-07-05T04:20:42.908918Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:20:42.908918Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hierarchical Representations and Explicit Memory: Learning Effective Navigation Policies on 3D Scene Graphs using Graph Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"J. Daniel Griffith, Lisa Peng, Luca Carlone, Nathan Hughes, Zachary Ravichandran","submitted_at":"2021-08-02T21:21:27Z","abstract_excerpt":"Representations are crucial for a robot to learn effective navigation policies. Recent work has shown that mid-level perceptual abstractions, such as depth estimates or 2D semantic segmentation, lead to more effective policies when provided as observations in place of raw sensor data (e.g., RGB images). However, such policies must still learn latent three-dimensional scene properties from mid-level abstractions. In contrast, high-level, hierarchical representations such as 3D scene graphs explicitly provide a scene's geometry, topology, and semantics, making them compelling representations for"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.01176","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/2108.01176/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":"2108.01176","created_at":"2026-07-05T04:20:42.908984+00:00"},{"alias_kind":"arxiv_version","alias_value":"2108.01176v2","created_at":"2026-07-05T04:20:42.908984+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.01176","created_at":"2026-07-05T04:20:42.908984+00:00"},{"alias_kind":"pith_short_12","alias_value":"R4UCIOI27KVV","created_at":"2026-07-05T04:20:42.908984+00:00"},{"alias_kind":"pith_short_16","alias_value":"R4UCIOI27KVVTVS7","created_at":"2026-07-05T04:20:42.908984+00:00"},{"alias_kind":"pith_short_8","alias_value":"R4UCIOI2","created_at":"2026-07-05T04:20:42.908984+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/R4UCIOI27KVVTVS7PZFARJ5LF5","json":"https://pith.science/pith/R4UCIOI27KVVTVS7PZFARJ5LF5.json","graph_json":"https://pith.science/api/pith-number/R4UCIOI27KVVTVS7PZFARJ5LF5/graph.json","events_json":"https://pith.science/api/pith-number/R4UCIOI27KVVTVS7PZFARJ5LF5/events.json","paper":"https://pith.science/paper/R4UCIOI2"},"agent_actions":{"view_html":"https://pith.science/pith/R4UCIOI27KVVTVS7PZFARJ5LF5","download_json":"https://pith.science/pith/R4UCIOI27KVVTVS7PZFARJ5LF5.json","view_paper":"https://pith.science/paper/R4UCIOI2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2108.01176&json=true","fetch_graph":"https://pith.science/api/pith-number/R4UCIOI27KVVTVS7PZFARJ5LF5/graph.json","fetch_events":"https://pith.science/api/pith-number/R4UCIOI27KVVTVS7PZFARJ5LF5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/R4UCIOI27KVVTVS7PZFARJ5LF5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/R4UCIOI27KVVTVS7PZFARJ5LF5/action/storage_attestation","attest_author":"https://pith.science/pith/R4UCIOI27KVVTVS7PZFARJ5LF5/action/author_attestation","sign_citation":"https://pith.science/pith/R4UCIOI27KVVTVS7PZFARJ5LF5/action/citation_signature","submit_replication":"https://pith.science/pith/R4UCIOI27KVVTVS7PZFARJ5LF5/action/replication_record"}},"created_at":"2026-07-05T04:20:42.908984+00:00","updated_at":"2026-07-05T04:20:42.908984+00:00"}