{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:ETYBWGU44JZLYSE2XTEGR2FJLU","short_pith_number":"pith:ETYBWGU4","schema_version":"1.0","canonical_sha256":"24f01b1a9ce272bc489abcc868e8a95d21964e21f597c821dbc811a2dcb19a26","source":{"kind":"arxiv","id":"2109.01394","version":2},"attestation_state":"computed","paper":{"title":"Topographic VAEs learn Equivariant Capsules","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.NE"],"primary_cat":"cs.LG","authors_text":"Max Welling, T. Anderson Keller","submitted_at":"2021-09-03T09:25:57Z","abstract_excerpt":"In this work we seek to bridge the concepts of topographic organization and equivariance in neural networks. To accomplish this, we introduce the Topographic VAE: a novel method for efficiently training deep generative models with topographically organized latent variables. We show that such a model indeed learns to organize its activations according to salient characteristics such as digit class, width, and style on MNIST. Furthermore, through topographic organization over time (i.e. temporal coherence), we demonstrate how predefined latent space transformation operators can be encouraged 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":"2109.01394","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-09-03T09:25:57Z","cross_cats_sorted":["cs.AI","cs.NE"],"title_canon_sha256":"d4f8c8673e4a5535569b1da5c468768f610fa79834959e15935a5321736e5391","abstract_canon_sha256":"8f6d046a7bf655f9e59845de9f111b95e427058f30c2f460f895547e5bc8ffaf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:47:00.601038Z","signature_b64":"pquWPitf5uUPaV/qENAfaZ8YF1S4TakNYNUdm7YHLjNnYy94A43c2HPBs+jXHhW5SaLJS1hrSqyKPpf23rRBBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"24f01b1a9ce272bc489abcc868e8a95d21964e21f597c821dbc811a2dcb19a26","last_reissued_at":"2026-07-05T03:47:00.600592Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:47:00.600592Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Topographic VAEs learn Equivariant Capsules","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.NE"],"primary_cat":"cs.LG","authors_text":"Max Welling, T. Anderson Keller","submitted_at":"2021-09-03T09:25:57Z","abstract_excerpt":"In this work we seek to bridge the concepts of topographic organization and equivariance in neural networks. To accomplish this, we introduce the Topographic VAE: a novel method for efficiently training deep generative models with topographically organized latent variables. We show that such a model indeed learns to organize its activations according to salient characteristics such as digit class, width, and style on MNIST. Furthermore, through topographic organization over time (i.e. temporal coherence), we demonstrate how predefined latent space transformation operators can be encouraged for"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.01394","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/2109.01394/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":"2109.01394","created_at":"2026-07-05T03:47:00.600647+00:00"},{"alias_kind":"arxiv_version","alias_value":"2109.01394v2","created_at":"2026-07-05T03:47:00.600647+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.01394","created_at":"2026-07-05T03:47:00.600647+00:00"},{"alias_kind":"pith_short_12","alias_value":"ETYBWGU44JZL","created_at":"2026-07-05T03:47:00.600647+00:00"},{"alias_kind":"pith_short_16","alias_value":"ETYBWGU44JZLYSE2","created_at":"2026-07-05T03:47:00.600647+00:00"},{"alias_kind":"pith_short_8","alias_value":"ETYBWGU4","created_at":"2026-07-05T03:47:00.600647+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/ETYBWGU44JZLYSE2XTEGR2FJLU","json":"https://pith.science/pith/ETYBWGU44JZLYSE2XTEGR2FJLU.json","graph_json":"https://pith.science/api/pith-number/ETYBWGU44JZLYSE2XTEGR2FJLU/graph.json","events_json":"https://pith.science/api/pith-number/ETYBWGU44JZLYSE2XTEGR2FJLU/events.json","paper":"https://pith.science/paper/ETYBWGU4"},"agent_actions":{"view_html":"https://pith.science/pith/ETYBWGU44JZLYSE2XTEGR2FJLU","download_json":"https://pith.science/pith/ETYBWGU44JZLYSE2XTEGR2FJLU.json","view_paper":"https://pith.science/paper/ETYBWGU4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2109.01394&json=true","fetch_graph":"https://pith.science/api/pith-number/ETYBWGU44JZLYSE2XTEGR2FJLU/graph.json","fetch_events":"https://pith.science/api/pith-number/ETYBWGU44JZLYSE2XTEGR2FJLU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ETYBWGU44JZLYSE2XTEGR2FJLU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ETYBWGU44JZLYSE2XTEGR2FJLU/action/storage_attestation","attest_author":"https://pith.science/pith/ETYBWGU44JZLYSE2XTEGR2FJLU/action/author_attestation","sign_citation":"https://pith.science/pith/ETYBWGU44JZLYSE2XTEGR2FJLU/action/citation_signature","submit_replication":"https://pith.science/pith/ETYBWGU44JZLYSE2XTEGR2FJLU/action/replication_record"}},"created_at":"2026-07-05T03:47:00.600647+00:00","updated_at":"2026-07-05T03:47:00.600647+00:00"}