{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:CRE6EW4W73HDFJZGPACNTFO6OO","short_pith_number":"pith:CRE6EW4W","schema_version":"1.0","canonical_sha256":"1449e25b96fece32a7267804d995de739fe51ebf655a059b8a1676e465a93b1e","source":{"kind":"arxiv","id":"2311.08525","version":1},"attestation_state":"computed","paper":{"title":"Efficient Rotation Invariance in Deep Neural Networks through Artificial Mental Rotation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"J\\\"urgen Schmidhuber, Lukas Tuggener, Thilo Stadelmann","submitted_at":"2023-11-14T20:37:54Z","abstract_excerpt":"Humans and animals recognize objects irrespective of the beholder's point of view, which may drastically change their appearances. Artificial pattern recognizers also strive to achieve this, e.g., through translational invariance in convolutional neural networks (CNNs). However, both CNNs and vision transformers (ViTs) perform very poorly on rotated inputs. Here we present artificial mental rotation (AMR), a novel deep learning paradigm for dealing with in-plane rotations inspired by the neuro-psychological concept of mental rotation. Our simple AMR implementation works with all common CNN and"},"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":"2311.08525","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-11-14T20:37:54Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"1f52a56d3193e1bf53ce0890fc68a4ccf550d10dac95e5434159d1d7ecf0f0e7","abstract_canon_sha256":"27dc462b47c9e9d3972104231e9cb7d174c3f2a36ca9ada5f01d72eab41c438c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:12:58.318858Z","signature_b64":"pPgnEW738guKaRfqHJqh8QdXcHllrlPIGnZZPLFfLF17dfS++VfyQqCPUNRH1weSyqXhONcWRi8GzFX0Jtw+DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1449e25b96fece32a7267804d995de739fe51ebf655a059b8a1676e465a93b1e","last_reissued_at":"2026-07-05T07:12:58.318382Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:12:58.318382Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Efficient Rotation Invariance in Deep Neural Networks through Artificial Mental Rotation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"J\\\"urgen Schmidhuber, Lukas Tuggener, Thilo Stadelmann","submitted_at":"2023-11-14T20:37:54Z","abstract_excerpt":"Humans and animals recognize objects irrespective of the beholder's point of view, which may drastically change their appearances. Artificial pattern recognizers also strive to achieve this, e.g., through translational invariance in convolutional neural networks (CNNs). However, both CNNs and vision transformers (ViTs) perform very poorly on rotated inputs. Here we present artificial mental rotation (AMR), a novel deep learning paradigm for dealing with in-plane rotations inspired by the neuro-psychological concept of mental rotation. Our simple AMR implementation works with all common CNN and"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.08525","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/2311.08525/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":"2311.08525","created_at":"2026-07-05T07:12:58.318448+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.08525v1","created_at":"2026-07-05T07:12:58.318448+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.08525","created_at":"2026-07-05T07:12:58.318448+00:00"},{"alias_kind":"pith_short_12","alias_value":"CRE6EW4W73HD","created_at":"2026-07-05T07:12:58.318448+00:00"},{"alias_kind":"pith_short_16","alias_value":"CRE6EW4W73HDFJZG","created_at":"2026-07-05T07:12:58.318448+00:00"},{"alias_kind":"pith_short_8","alias_value":"CRE6EW4W","created_at":"2026-07-05T07:12:58.318448+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.11218","citing_title":"Geometrically Constrained and Token-Based Probabilistic Spatial Transformers","ref_index":25,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CRE6EW4W73HDFJZGPACNTFO6OO","json":"https://pith.science/pith/CRE6EW4W73HDFJZGPACNTFO6OO.json","graph_json":"https://pith.science/api/pith-number/CRE6EW4W73HDFJZGPACNTFO6OO/graph.json","events_json":"https://pith.science/api/pith-number/CRE6EW4W73HDFJZGPACNTFO6OO/events.json","paper":"https://pith.science/paper/CRE6EW4W"},"agent_actions":{"view_html":"https://pith.science/pith/CRE6EW4W73HDFJZGPACNTFO6OO","download_json":"https://pith.science/pith/CRE6EW4W73HDFJZGPACNTFO6OO.json","view_paper":"https://pith.science/paper/CRE6EW4W","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.08525&json=true","fetch_graph":"https://pith.science/api/pith-number/CRE6EW4W73HDFJZGPACNTFO6OO/graph.json","fetch_events":"https://pith.science/api/pith-number/CRE6EW4W73HDFJZGPACNTFO6OO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CRE6EW4W73HDFJZGPACNTFO6OO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CRE6EW4W73HDFJZGPACNTFO6OO/action/storage_attestation","attest_author":"https://pith.science/pith/CRE6EW4W73HDFJZGPACNTFO6OO/action/author_attestation","sign_citation":"https://pith.science/pith/CRE6EW4W73HDFJZGPACNTFO6OO/action/citation_signature","submit_replication":"https://pith.science/pith/CRE6EW4W73HDFJZGPACNTFO6OO/action/replication_record"}},"created_at":"2026-07-05T07:12:58.318448+00:00","updated_at":"2026-07-05T07:12:58.318448+00:00"}