{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:C7LKRDQTC53LOYDYTWNOKT7HPG","short_pith_number":"pith:C7LKRDQT","schema_version":"1.0","canonical_sha256":"17d6a88e131776b760789d9ae54fe7798f59245f7d3605177e388cf22914f103","source":{"kind":"arxiv","id":"2301.01583","version":1},"attestation_state":"computed","paper":{"title":"Why Capsule Neural Networks Do Not Scale: Challenging the Dynamic Parse-Tree Assumption","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Joachim Giesen, Marcel Koch, Matthias Mitterreiter, S\\\"oren Laue","submitted_at":"2023-01-04T12:59:51Z","abstract_excerpt":"Capsule neural networks replace simple, scalar-valued neurons with vector-valued capsules. They are motivated by the pattern recognition system in the human brain, where complex objects are decomposed into a hierarchy of simpler object parts. Such a hierarchy is referred to as a parse-tree. Conceptually, capsule neural networks have been defined to realize such parse-trees. The capsule neural network (CapsNet), by Sabour, Frosst, and Hinton, is the first actual implementation of the conceptual idea of capsule neural networks. CapsNets achieved state-of-the-art performance on simple image recog"},"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":"2301.01583","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-01-04T12:59:51Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"fea097054f86eb2aae82a7e0d25f8a2b11ea6d6e440c3de04a00db1cdb5049b4","abstract_canon_sha256":"7730d2816330634c43190a9ebf2a9150ada10865a2a0062953f4913aa2957e7c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:30:38.230841Z","signature_b64":"DMw45jBEFL1Mx791puGTAqpWOqJB9WxVH1vHI6avlWp4TrYDJNMK5pog64vUVHKhAt6fNEMfiog83bE2BWs4CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"17d6a88e131776b760789d9ae54fe7798f59245f7d3605177e388cf22914f103","last_reissued_at":"2026-07-05T05:30:38.230436Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:30:38.230436Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Why Capsule Neural Networks Do Not Scale: Challenging the Dynamic Parse-Tree Assumption","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Joachim Giesen, Marcel Koch, Matthias Mitterreiter, S\\\"oren Laue","submitted_at":"2023-01-04T12:59:51Z","abstract_excerpt":"Capsule neural networks replace simple, scalar-valued neurons with vector-valued capsules. They are motivated by the pattern recognition system in the human brain, where complex objects are decomposed into a hierarchy of simpler object parts. Such a hierarchy is referred to as a parse-tree. Conceptually, capsule neural networks have been defined to realize such parse-trees. The capsule neural network (CapsNet), by Sabour, Frosst, and Hinton, is the first actual implementation of the conceptual idea of capsule neural networks. CapsNets achieved state-of-the-art performance on simple image recog"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.01583","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/2301.01583/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":"2301.01583","created_at":"2026-07-05T05:30:38.230490+00:00"},{"alias_kind":"arxiv_version","alias_value":"2301.01583v1","created_at":"2026-07-05T05:30:38.230490+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.01583","created_at":"2026-07-05T05:30:38.230490+00:00"},{"alias_kind":"pith_short_12","alias_value":"C7LKRDQTC53L","created_at":"2026-07-05T05:30:38.230490+00:00"},{"alias_kind":"pith_short_16","alias_value":"C7LKRDQTC53LOYDY","created_at":"2026-07-05T05:30:38.230490+00:00"},{"alias_kind":"pith_short_8","alias_value":"C7LKRDQT","created_at":"2026-07-05T05:30:38.230490+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.05689","citing_title":"Equivariant Imaging Biomarkers for Robust Unsupervised Segmentation of Histopathology","ref_index":28,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/C7LKRDQTC53LOYDYTWNOKT7HPG","json":"https://pith.science/pith/C7LKRDQTC53LOYDYTWNOKT7HPG.json","graph_json":"https://pith.science/api/pith-number/C7LKRDQTC53LOYDYTWNOKT7HPG/graph.json","events_json":"https://pith.science/api/pith-number/C7LKRDQTC53LOYDYTWNOKT7HPG/events.json","paper":"https://pith.science/paper/C7LKRDQT"},"agent_actions":{"view_html":"https://pith.science/pith/C7LKRDQTC53LOYDYTWNOKT7HPG","download_json":"https://pith.science/pith/C7LKRDQTC53LOYDYTWNOKT7HPG.json","view_paper":"https://pith.science/paper/C7LKRDQT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2301.01583&json=true","fetch_graph":"https://pith.science/api/pith-number/C7LKRDQTC53LOYDYTWNOKT7HPG/graph.json","fetch_events":"https://pith.science/api/pith-number/C7LKRDQTC53LOYDYTWNOKT7HPG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/C7LKRDQTC53LOYDYTWNOKT7HPG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/C7LKRDQTC53LOYDYTWNOKT7HPG/action/storage_attestation","attest_author":"https://pith.science/pith/C7LKRDQTC53LOYDYTWNOKT7HPG/action/author_attestation","sign_citation":"https://pith.science/pith/C7LKRDQTC53LOYDYTWNOKT7HPG/action/citation_signature","submit_replication":"https://pith.science/pith/C7LKRDQTC53LOYDYTWNOKT7HPG/action/replication_record"}},"created_at":"2026-07-05T05:30:38.230490+00:00","updated_at":"2026-07-05T05:30:38.230490+00:00"}