{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:5Q72JMTEXG2CADKCOMPYXTPAQO","short_pith_number":"pith:5Q72JMTE","schema_version":"1.0","canonical_sha256":"ec3fa4b264b9b4200d42731f8bcde083adb72ae9f634a0dbc21429c59f0a087c","source":{"kind":"arxiv","id":"1706.09520","version":7},"attestation_state":"computed","paper":{"title":"Neural SLAM: Learning to Explore with External Memory","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Jingwei Zhang, Joschka Boedecker, Lei Tai, Ming Liu, Wolfram Burgard","submitted_at":"2017-06-29T00:14:15Z","abstract_excerpt":"We present an approach for agents to learn representations of a global map from sensor data, to aid their exploration in new environments. To achieve this, we embed procedures mimicking that of traditional Simultaneous Localization and Mapping (SLAM) into the soft attention based addressing of external memory architectures, in which the external memory acts as an internal representation of the environment. This structure encourages the evolution of SLAM-like behaviors inside a completely differentiable deep neural network. We show that this approach can help reinforcement learning agents to su"},"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":"1706.09520","kind":"arxiv","version":7},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-06-29T00:14:15Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"a3f7d7931c5ef8e182a8cb9a75bd51da8d390caf10fdc03905c10c63219c256e","abstract_canon_sha256":"827b1f78d53adecb23dd0524b0ab8e8a7f3f51716bed76ffe809c403c5b6221b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:02:48.684130Z","signature_b64":"rC8bmaFP/eAGKZHD+y5wdb0SX16JOUqy+KL7nWEyIIDA0SLbntiED5q9o5mrM1fjzSIxzvTZ/a+PQE/vINlgCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ec3fa4b264b9b4200d42731f8bcde083adb72ae9f634a0dbc21429c59f0a087c","last_reissued_at":"2026-07-05T02:02:48.683648Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:02:48.683648Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Neural SLAM: Learning to Explore with External Memory","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Jingwei Zhang, Joschka Boedecker, Lei Tai, Ming Liu, Wolfram Burgard","submitted_at":"2017-06-29T00:14:15Z","abstract_excerpt":"We present an approach for agents to learn representations of a global map from sensor data, to aid their exploration in new environments. To achieve this, we embed procedures mimicking that of traditional Simultaneous Localization and Mapping (SLAM) into the soft attention based addressing of external memory architectures, in which the external memory acts as an internal representation of the environment. This structure encourages the evolution of SLAM-like behaviors inside a completely differentiable deep neural network. We show that this approach can help reinforcement learning agents to su"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1706.09520","kind":"arxiv","version":7},"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/1706.09520/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":"1706.09520","created_at":"2026-07-05T02:02:48.683707+00:00"},{"alias_kind":"arxiv_version","alias_value":"1706.09520v7","created_at":"2026-07-05T02:02:48.683707+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1706.09520","created_at":"2026-07-05T02:02:48.683707+00:00"},{"alias_kind":"pith_short_12","alias_value":"5Q72JMTEXG2C","created_at":"2026-07-05T02:02:48.683707+00:00"},{"alias_kind":"pith_short_16","alias_value":"5Q72JMTEXG2CADKC","created_at":"2026-07-05T02:02:48.683707+00:00"},{"alias_kind":"pith_short_8","alias_value":"5Q72JMTE","created_at":"2026-07-05T02:02:48.683707+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.31404","citing_title":"The Sword, Shield, and Achilles' Heel: Characterizing the Linguistic Inductive Bias of Large Language Models for Spatial Reasoning in Navigation Planning","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2605.27686","citing_title":"Tensor Memory: Fixed-Size Recurrent State for Long-Horizon Transformers","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"1906.09237","citing_title":"Shaping Belief States with Generative Environment Models for RL","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"1907.05310","citing_title":"Aerial Animal Biometrics: Individual Friesian Cattle Recovery and Visual Identification via an Autonomous UAV with Onboard Deep Inference","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"1907.11770","citing_title":"To Learn or Not to Learn: Analyzing the Role of Learning for Navigation in Virtual Environments","ref_index":37,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5Q72JMTEXG2CADKCOMPYXTPAQO","json":"https://pith.science/pith/5Q72JMTEXG2CADKCOMPYXTPAQO.json","graph_json":"https://pith.science/api/pith-number/5Q72JMTEXG2CADKCOMPYXTPAQO/graph.json","events_json":"https://pith.science/api/pith-number/5Q72JMTEXG2CADKCOMPYXTPAQO/events.json","paper":"https://pith.science/paper/5Q72JMTE"},"agent_actions":{"view_html":"https://pith.science/pith/5Q72JMTEXG2CADKCOMPYXTPAQO","download_json":"https://pith.science/pith/5Q72JMTEXG2CADKCOMPYXTPAQO.json","view_paper":"https://pith.science/paper/5Q72JMTE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1706.09520&json=true","fetch_graph":"https://pith.science/api/pith-number/5Q72JMTEXG2CADKCOMPYXTPAQO/graph.json","fetch_events":"https://pith.science/api/pith-number/5Q72JMTEXG2CADKCOMPYXTPAQO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5Q72JMTEXG2CADKCOMPYXTPAQO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5Q72JMTEXG2CADKCOMPYXTPAQO/action/storage_attestation","attest_author":"https://pith.science/pith/5Q72JMTEXG2CADKCOMPYXTPAQO/action/author_attestation","sign_citation":"https://pith.science/pith/5Q72JMTEXG2CADKCOMPYXTPAQO/action/citation_signature","submit_replication":"https://pith.science/pith/5Q72JMTEXG2CADKCOMPYXTPAQO/action/replication_record"}},"created_at":"2026-07-05T02:02:48.683707+00:00","updated_at":"2026-07-05T02:02:48.683707+00:00"}