{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:KSQPANAA627KSTGJLVMRD3EAPY","short_pith_number":"pith:KSQPANAA","schema_version":"1.0","canonical_sha256":"54a0f03400f6bea94cc95d5911ec807e12c351ee1ebf70795b9f0e8afd8f724c","source":{"kind":"arxiv","id":"1909.04306","version":1},"attestation_state":"computed","paper":{"title":"Bayesian Relational Memory for Semantic Visual Navigation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.RO"],"primary_cat":"cs.CV","authors_text":"Aviv Tamar, Georgia Gkioxari, Stuart Russell, Yi Wu, Yuandong Tian, Yuxin Wu","submitted_at":"2019-09-10T06:02:15Z","abstract_excerpt":"We introduce a new memory architecture, Bayesian Relational Memory (BRM), to improve the generalization ability for semantic visual navigation agents in unseen environments, where an agent is given a semantic target to navigate towards. BRM takes the form of a probabilistic relation graph over semantic entities (e.g., room types), which allows (1) capturing the layout prior from training environments, i.e., prior knowledge, (2) estimating posterior layout at test time, i.e., memory update, and (3) efficient planning for navigation, altogether. We develop a BRM agent consisting of a BRM module "},"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":"1909.04306","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-09-10T06:02:15Z","cross_cats_sorted":["cs.LG","cs.RO"],"title_canon_sha256":"17259edb0a6016904c16a61ffa04f734e9f977f3722826d687f860db4a899d2d","abstract_canon_sha256":"ad403a11755eb9bea51ef4c1a1b1471b8ecb0e88af657e2468e53bf34c6fe93a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:03:20.754170Z","signature_b64":"DDT6mOxLMmKnx2zdtsSy3bVK2AfuWKqmmu8+6srqebeU/Mp9reH6p4mOEfk2rs0eyIPGuZ0igAgKxzNBm0TUAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"54a0f03400f6bea94cc95d5911ec807e12c351ee1ebf70795b9f0e8afd8f724c","last_reissued_at":"2026-07-05T00:03:20.753646Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:03:20.753646Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Bayesian Relational Memory for Semantic Visual Navigation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.RO"],"primary_cat":"cs.CV","authors_text":"Aviv Tamar, Georgia Gkioxari, Stuart Russell, Yi Wu, Yuandong Tian, Yuxin Wu","submitted_at":"2019-09-10T06:02:15Z","abstract_excerpt":"We introduce a new memory architecture, Bayesian Relational Memory (BRM), to improve the generalization ability for semantic visual navigation agents in unseen environments, where an agent is given a semantic target to navigate towards. BRM takes the form of a probabilistic relation graph over semantic entities (e.g., room types), which allows (1) capturing the layout prior from training environments, i.e., prior knowledge, (2) estimating posterior layout at test time, i.e., memory update, and (3) efficient planning for navigation, altogether. We develop a BRM agent consisting of a BRM module "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.04306","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/1909.04306/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":"1909.04306","created_at":"2026-07-05T00:03:20.753697+00:00"},{"alias_kind":"arxiv_version","alias_value":"1909.04306v1","created_at":"2026-07-05T00:03:20.753697+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.04306","created_at":"2026-07-05T00:03:20.753697+00:00"},{"alias_kind":"pith_short_12","alias_value":"KSQPANAA627K","created_at":"2026-07-05T00:03:20.753697+00:00"},{"alias_kind":"pith_short_16","alias_value":"KSQPANAA627KSTGJ","created_at":"2026-07-05T00:03:20.753697+00:00"},{"alias_kind":"pith_short_8","alias_value":"KSQPANAA","created_at":"2026-07-05T00:03:20.753697+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/KSQPANAA627KSTGJLVMRD3EAPY","json":"https://pith.science/pith/KSQPANAA627KSTGJLVMRD3EAPY.json","graph_json":"https://pith.science/api/pith-number/KSQPANAA627KSTGJLVMRD3EAPY/graph.json","events_json":"https://pith.science/api/pith-number/KSQPANAA627KSTGJLVMRD3EAPY/events.json","paper":"https://pith.science/paper/KSQPANAA"},"agent_actions":{"view_html":"https://pith.science/pith/KSQPANAA627KSTGJLVMRD3EAPY","download_json":"https://pith.science/pith/KSQPANAA627KSTGJLVMRD3EAPY.json","view_paper":"https://pith.science/paper/KSQPANAA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1909.04306&json=true","fetch_graph":"https://pith.science/api/pith-number/KSQPANAA627KSTGJLVMRD3EAPY/graph.json","fetch_events":"https://pith.science/api/pith-number/KSQPANAA627KSTGJLVMRD3EAPY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KSQPANAA627KSTGJLVMRD3EAPY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KSQPANAA627KSTGJLVMRD3EAPY/action/storage_attestation","attest_author":"https://pith.science/pith/KSQPANAA627KSTGJLVMRD3EAPY/action/author_attestation","sign_citation":"https://pith.science/pith/KSQPANAA627KSTGJLVMRD3EAPY/action/citation_signature","submit_replication":"https://pith.science/pith/KSQPANAA627KSTGJLVMRD3EAPY/action/replication_record"}},"created_at":"2026-07-05T00:03:20.753697+00:00","updated_at":"2026-07-05T00:03:20.753697+00:00"}