{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:ZJP7HFH4M4JLHWH47CKAGTVE2V","short_pith_number":"pith:ZJP7HFH4","schema_version":"1.0","canonical_sha256":"ca5ff394fc6712b3d8fcf894034ea4d576ad22c9e618bcb6a80d002eb4f12e92","source":{"kind":"arxiv","id":"2012.01644","version":3},"attestation_state":"computed","paper":{"title":"Capturing implicit hierarchical structure in 3D biomedical images with self-supervised hyperbolic representations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Gong-Her Wu, Jeffrey Gu, Joy Hsu, Serena Yeung, Wah Chiu","submitted_at":"2020-12-03T02:15:31Z","abstract_excerpt":"We consider the task of representation learning for unsupervised segmentation of 3D voxel-grid biomedical images. We show that models that capture implicit hierarchical relationships between subvolumes are better suited for this task. To that end, we consider encoder-decoder architectures with a hyperbolic latent space, to explicitly capture hierarchical relationships present in subvolumes of the data. We propose utilizing a 3D hyperbolic variational autoencoder with a novel gyroplane convolutional layer to map from the embedding space back to 3D images. To capture these relationships, we intr"},"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":"2012.01644","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-12-03T02:15:31Z","cross_cats_sorted":[],"title_canon_sha256":"377bb49fe91286b48b3cc6772e115a60b85109cce78dbbb9e528eed746e98039","abstract_canon_sha256":"9a7711bc8b7d0517b30784dc4636ac3c417f9ca3a6e92ca93036c0cbd02ca1e9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:25:29.522156Z","signature_b64":"Lma6jS2z+27VqFwDJAZHYK1LGZfI8qfGSppB/NXc5XxJfH53qkpPAl8cmOrKYOyL8gk2pft8Sq0oJMX1buibCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ca5ff394fc6712b3d8fcf894034ea4d576ad22c9e618bcb6a80d002eb4f12e92","last_reissued_at":"2026-07-05T03:25:29.520659Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:25:29.520659Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Capturing implicit hierarchical structure in 3D biomedical images with self-supervised hyperbolic representations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Gong-Her Wu, Jeffrey Gu, Joy Hsu, Serena Yeung, Wah Chiu","submitted_at":"2020-12-03T02:15:31Z","abstract_excerpt":"We consider the task of representation learning for unsupervised segmentation of 3D voxel-grid biomedical images. We show that models that capture implicit hierarchical relationships between subvolumes are better suited for this task. To that end, we consider encoder-decoder architectures with a hyperbolic latent space, to explicitly capture hierarchical relationships present in subvolumes of the data. We propose utilizing a 3D hyperbolic variational autoencoder with a novel gyroplane convolutional layer to map from the embedding space back to 3D images. To capture these relationships, we intr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.01644","kind":"arxiv","version":3},"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/2012.01644/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":"2012.01644","created_at":"2026-07-05T03:25:29.520717+00:00"},{"alias_kind":"arxiv_version","alias_value":"2012.01644v3","created_at":"2026-07-05T03:25:29.520717+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.01644","created_at":"2026-07-05T03:25:29.520717+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZJP7HFH4M4JL","created_at":"2026-07-05T03:25:29.520717+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZJP7HFH4M4JLHWH4","created_at":"2026-07-05T03:25:29.520717+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZJP7HFH4","created_at":"2026-07-05T03:25:29.520717+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/ZJP7HFH4M4JLHWH47CKAGTVE2V","json":"https://pith.science/pith/ZJP7HFH4M4JLHWH47CKAGTVE2V.json","graph_json":"https://pith.science/api/pith-number/ZJP7HFH4M4JLHWH47CKAGTVE2V/graph.json","events_json":"https://pith.science/api/pith-number/ZJP7HFH4M4JLHWH47CKAGTVE2V/events.json","paper":"https://pith.science/paper/ZJP7HFH4"},"agent_actions":{"view_html":"https://pith.science/pith/ZJP7HFH4M4JLHWH47CKAGTVE2V","download_json":"https://pith.science/pith/ZJP7HFH4M4JLHWH47CKAGTVE2V.json","view_paper":"https://pith.science/paper/ZJP7HFH4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2012.01644&json=true","fetch_graph":"https://pith.science/api/pith-number/ZJP7HFH4M4JLHWH47CKAGTVE2V/graph.json","fetch_events":"https://pith.science/api/pith-number/ZJP7HFH4M4JLHWH47CKAGTVE2V/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZJP7HFH4M4JLHWH47CKAGTVE2V/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZJP7HFH4M4JLHWH47CKAGTVE2V/action/storage_attestation","attest_author":"https://pith.science/pith/ZJP7HFH4M4JLHWH47CKAGTVE2V/action/author_attestation","sign_citation":"https://pith.science/pith/ZJP7HFH4M4JLHWH47CKAGTVE2V/action/citation_signature","submit_replication":"https://pith.science/pith/ZJP7HFH4M4JLHWH47CKAGTVE2V/action/replication_record"}},"created_at":"2026-07-05T03:25:29.520717+00:00","updated_at":"2026-07-05T03:25:29.520717+00:00"}