{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:NZCSUGPFLAVO5XWTTZAC4OJKRN","short_pith_number":"pith:NZCSUGPF","schema_version":"1.0","canonical_sha256":"6e452a19e5582aeeded39e402e392a8b46007c52badb5494c956e0d524da54e9","source":{"kind":"arxiv","id":"2402.12067","version":1},"attestation_state":"computed","paper":{"title":"Interpretable Brain-Inspired Representations Improve RL Performance on Visual Navigation Tasks","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.NE","cs.RO"],"primary_cat":"cs.LG","authors_text":"Laurenz Wiskott, Moritz Lange, Raphael C. Engelhardt, Wolfgang Konen","submitted_at":"2024-02-19T11:35:01Z","abstract_excerpt":"Visual navigation requires a whole range of capabilities. A crucial one of these is the ability of an agent to determine its own location and heading in an environment. Prior works commonly assume this information as given, or use methods which lack a suitable inductive bias and accumulate error over time. In this work, we show how the method of slow feature analysis (SFA), inspired by neuroscience research, overcomes both limitations by generating interpretable representations of visual data that encode location and heading of an agent. We employ SFA in a modern reinforcement learning context"},"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":"2402.12067","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-19T11:35:01Z","cross_cats_sorted":["cs.NE","cs.RO"],"title_canon_sha256":"5880c8a991021e850acef7c098c6c56f3c2050a797ba46027c6f84398f217fba","abstract_canon_sha256":"222505cff305e6e37946018347ae77bba5966c20c038e33f0cd3224ba4a74152"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:46:48.274777Z","signature_b64":"+f1H3bv2Enbpl7WzNBYqqk7CJyN7urFqikBRsWCRBjt129fktJOQWBZSflCAtmn9lIcNseIVV88qPqPs5YJVAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6e452a19e5582aeeded39e402e392a8b46007c52badb5494c956e0d524da54e9","last_reissued_at":"2026-07-05T07:46:48.274340Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:46:48.274340Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Interpretable Brain-Inspired Representations Improve RL Performance on Visual Navigation Tasks","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.NE","cs.RO"],"primary_cat":"cs.LG","authors_text":"Laurenz Wiskott, Moritz Lange, Raphael C. Engelhardt, Wolfgang Konen","submitted_at":"2024-02-19T11:35:01Z","abstract_excerpt":"Visual navigation requires a whole range of capabilities. A crucial one of these is the ability of an agent to determine its own location and heading in an environment. Prior works commonly assume this information as given, or use methods which lack a suitable inductive bias and accumulate error over time. In this work, we show how the method of slow feature analysis (SFA), inspired by neuroscience research, overcomes both limitations by generating interpretable representations of visual data that encode location and heading of an agent. We employ SFA in a modern reinforcement learning context"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.12067","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/2402.12067/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":"2402.12067","created_at":"2026-07-05T07:46:48.274397+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.12067v1","created_at":"2026-07-05T07:46:48.274397+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.12067","created_at":"2026-07-05T07:46:48.274397+00:00"},{"alias_kind":"pith_short_12","alias_value":"NZCSUGPFLAVO","created_at":"2026-07-05T07:46:48.274397+00:00"},{"alias_kind":"pith_short_16","alias_value":"NZCSUGPFLAVO5XWT","created_at":"2026-07-05T07:46:48.274397+00:00"},{"alias_kind":"pith_short_8","alias_value":"NZCSUGPF","created_at":"2026-07-05T07:46:48.274397+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.00726","citing_title":"Perspectives for Direct Interpretability in Multi-Agent Deep Reinforcement Learning","ref_index":70,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NZCSUGPFLAVO5XWTTZAC4OJKRN","json":"https://pith.science/pith/NZCSUGPFLAVO5XWTTZAC4OJKRN.json","graph_json":"https://pith.science/api/pith-number/NZCSUGPFLAVO5XWTTZAC4OJKRN/graph.json","events_json":"https://pith.science/api/pith-number/NZCSUGPFLAVO5XWTTZAC4OJKRN/events.json","paper":"https://pith.science/paper/NZCSUGPF"},"agent_actions":{"view_html":"https://pith.science/pith/NZCSUGPFLAVO5XWTTZAC4OJKRN","download_json":"https://pith.science/pith/NZCSUGPFLAVO5XWTTZAC4OJKRN.json","view_paper":"https://pith.science/paper/NZCSUGPF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.12067&json=true","fetch_graph":"https://pith.science/api/pith-number/NZCSUGPFLAVO5XWTTZAC4OJKRN/graph.json","fetch_events":"https://pith.science/api/pith-number/NZCSUGPFLAVO5XWTTZAC4OJKRN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NZCSUGPFLAVO5XWTTZAC4OJKRN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NZCSUGPFLAVO5XWTTZAC4OJKRN/action/storage_attestation","attest_author":"https://pith.science/pith/NZCSUGPFLAVO5XWTTZAC4OJKRN/action/author_attestation","sign_citation":"https://pith.science/pith/NZCSUGPFLAVO5XWTTZAC4OJKRN/action/citation_signature","submit_replication":"https://pith.science/pith/NZCSUGPFLAVO5XWTTZAC4OJKRN/action/replication_record"}},"created_at":"2026-07-05T07:46:48.274397+00:00","updated_at":"2026-07-05T07:46:48.274397+00:00"}