{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:J6QC2RR7G6BTQ7KXC6Y3AMG6Z6","short_pith_number":"pith:J6QC2RR7","schema_version":"1.0","canonical_sha256":"4fa02d463f3783387d5717b1b030decf90e384d1d6e956ca6ad259bcaf11557f","source":{"kind":"arxiv","id":"1805.07621","version":2},"attestation_state":"computed","paper":{"title":"CapProNet: Deep Feature Learning via Orthogonal Projections onto Capsule Subspaces","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Guo-jun Qi, Liheng Zhang, Marzieh Edraki","submitted_at":"2018-05-19T16:50:37Z","abstract_excerpt":"In this paper, we formalize the idea behind capsule nets of using a capsule vector rather than a neuron activation to predict the label of samples. To this end, we propose to learn a group of capsule subspaces onto which an input feature vector is projected. Then the lengths of resultant capsules are used to score the probability of belonging to different classes. We train such a Capsule Projection Network (CapProNet) by learning an orthogonal projection matrix for each capsule subspace, and show that each capsule subspace is updated until it contains input feature vectors corresponding to the"},"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":"1805.07621","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-05-19T16:50:37Z","cross_cats_sorted":[],"title_canon_sha256":"278785216d8765abc17c30fce5476d04a617bf2779cc1560e019b7c73a4fc10d","abstract_canon_sha256":"d576213a28ae2cd048c0e636cbfdf5d87f1a82cfaa2d1198c6fadd2f943897db"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:02:44.834000Z","signature_b64":"6ZzbFGfKG2aXgu8JU7vpIlmLU45Bjs5AQc0KM6N5+HEpvDu2fi+k4ffM28Tklu0HKOFxdT/1tFBTdDrjEuL/Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4fa02d463f3783387d5717b1b030decf90e384d1d6e956ca6ad259bcaf11557f","last_reissued_at":"2026-05-18T00:02:44.833519Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:02:44.833519Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CapProNet: Deep Feature Learning via Orthogonal Projections onto Capsule Subspaces","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Guo-jun Qi, Liheng Zhang, Marzieh Edraki","submitted_at":"2018-05-19T16:50:37Z","abstract_excerpt":"In this paper, we formalize the idea behind capsule nets of using a capsule vector rather than a neuron activation to predict the label of samples. To this end, we propose to learn a group of capsule subspaces onto which an input feature vector is projected. Then the lengths of resultant capsules are used to score the probability of belonging to different classes. We train such a Capsule Projection Network (CapProNet) by learning an orthogonal projection matrix for each capsule subspace, and show that each capsule subspace is updated until it contains input feature vectors corresponding to the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.07621","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":""},"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":"1805.07621","created_at":"2026-05-18T00:02:44.833592+00:00"},{"alias_kind":"arxiv_version","alias_value":"1805.07621v2","created_at":"2026-05-18T00:02:44.833592+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.07621","created_at":"2026-05-18T00:02:44.833592+00:00"},{"alias_kind":"pith_short_12","alias_value":"J6QC2RR7G6BT","created_at":"2026-05-18T12:32:31.084164+00:00"},{"alias_kind":"pith_short_16","alias_value":"J6QC2RR7G6BTQ7KX","created_at":"2026-05-18T12:32:31.084164+00:00"},{"alias_kind":"pith_short_8","alias_value":"J6QC2RR7","created_at":"2026-05-18T12:32:31.084164+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/J6QC2RR7G6BTQ7KXC6Y3AMG6Z6","json":"https://pith.science/pith/J6QC2RR7G6BTQ7KXC6Y3AMG6Z6.json","graph_json":"https://pith.science/api/pith-number/J6QC2RR7G6BTQ7KXC6Y3AMG6Z6/graph.json","events_json":"https://pith.science/api/pith-number/J6QC2RR7G6BTQ7KXC6Y3AMG6Z6/events.json","paper":"https://pith.science/paper/J6QC2RR7"},"agent_actions":{"view_html":"https://pith.science/pith/J6QC2RR7G6BTQ7KXC6Y3AMG6Z6","download_json":"https://pith.science/pith/J6QC2RR7G6BTQ7KXC6Y3AMG6Z6.json","view_paper":"https://pith.science/paper/J6QC2RR7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1805.07621&json=true","fetch_graph":"https://pith.science/api/pith-number/J6QC2RR7G6BTQ7KXC6Y3AMG6Z6/graph.json","fetch_events":"https://pith.science/api/pith-number/J6QC2RR7G6BTQ7KXC6Y3AMG6Z6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/J6QC2RR7G6BTQ7KXC6Y3AMG6Z6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/J6QC2RR7G6BTQ7KXC6Y3AMG6Z6/action/storage_attestation","attest_author":"https://pith.science/pith/J6QC2RR7G6BTQ7KXC6Y3AMG6Z6/action/author_attestation","sign_citation":"https://pith.science/pith/J6QC2RR7G6BTQ7KXC6Y3AMG6Z6/action/citation_signature","submit_replication":"https://pith.science/pith/J6QC2RR7G6BTQ7KXC6Y3AMG6Z6/action/replication_record"}},"created_at":"2026-05-18T00:02:44.833592+00:00","updated_at":"2026-05-18T00:02:44.833592+00:00"}