{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:TXNBMBSCUFJNNRDPFK5B7SDKRT","short_pith_number":"pith:TXNBMBSC","schema_version":"1.0","canonical_sha256":"9dda160642a152d6c46f2aba1fc86a8ce6f18b21c99738bfea0ee5b4f439aea3","source":{"kind":"arxiv","id":"2506.01414","version":1},"attestation_state":"computed","paper":{"title":"Self-supervised Latent Space Optimization with Nebula Variational Coding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IT","math.IT"],"primary_cat":"cs.LG","authors_text":"David Joseph Tan, Federico Tombari, Nassir Navab, Yida Wang","submitted_at":"2025-06-02T08:13:32Z","abstract_excerpt":"Deep learning approaches process data in a layer-by-layer way with intermediate (or latent) features. We aim at designing a general solution to optimize the latent manifolds to improve the performance on classification, segmentation, completion and/or reconstruction through probabilistic models. This paper proposes a variational inference model which leads to a clustered embedding. We introduce additional variables in the latent space, called \\textbf{nebula anchors}, that guide the latent variables to form clusters during training. To prevent the anchors from clustering among themselves, we em"},"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":"2506.01414","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-02T08:13:32Z","cross_cats_sorted":["cs.IT","math.IT"],"title_canon_sha256":"3a624ad241c9aa1a161f5c854ed064a53fc07d7601ea91dae5ee6ccd73091f91","abstract_canon_sha256":"af5703f8247b1bfc82469f6ab12e10b5a1f56065164bd729e076a980bb6b65ae"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:14:12.846035Z","signature_b64":"twmT8/+OHnu3GqwQYFfBGcg5tPw43YIJjaxRDDoa/5B6mFH4nAfjpmsjPNIAZbfZtSzjLTpuogEr1zd6bE0GBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9dda160642a152d6c46f2aba1fc86a8ce6f18b21c99738bfea0ee5b4f439aea3","last_reissued_at":"2026-07-05T11:14:12.845593Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:14:12.845593Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Self-supervised Latent Space Optimization with Nebula Variational Coding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IT","math.IT"],"primary_cat":"cs.LG","authors_text":"David Joseph Tan, Federico Tombari, Nassir Navab, Yida Wang","submitted_at":"2025-06-02T08:13:32Z","abstract_excerpt":"Deep learning approaches process data in a layer-by-layer way with intermediate (or latent) features. We aim at designing a general solution to optimize the latent manifolds to improve the performance on classification, segmentation, completion and/or reconstruction through probabilistic models. This paper proposes a variational inference model which leads to a clustered embedding. We introduce additional variables in the latent space, called \\textbf{nebula anchors}, that guide the latent variables to form clusters during training. To prevent the anchors from clustering among themselves, we em"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.01414","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/2506.01414/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":"2506.01414","created_at":"2026-07-05T11:14:12.845650+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.01414v1","created_at":"2026-07-05T11:14:12.845650+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.01414","created_at":"2026-07-05T11:14:12.845650+00:00"},{"alias_kind":"pith_short_12","alias_value":"TXNBMBSCUFJN","created_at":"2026-07-05T11:14:12.845650+00:00"},{"alias_kind":"pith_short_16","alias_value":"TXNBMBSCUFJNNRDP","created_at":"2026-07-05T11:14:12.845650+00:00"},{"alias_kind":"pith_short_8","alias_value":"TXNBMBSC","created_at":"2026-07-05T11:14:12.845650+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/TXNBMBSCUFJNNRDPFK5B7SDKRT","json":"https://pith.science/pith/TXNBMBSCUFJNNRDPFK5B7SDKRT.json","graph_json":"https://pith.science/api/pith-number/TXNBMBSCUFJNNRDPFK5B7SDKRT/graph.json","events_json":"https://pith.science/api/pith-number/TXNBMBSCUFJNNRDPFK5B7SDKRT/events.json","paper":"https://pith.science/paper/TXNBMBSC"},"agent_actions":{"view_html":"https://pith.science/pith/TXNBMBSCUFJNNRDPFK5B7SDKRT","download_json":"https://pith.science/pith/TXNBMBSCUFJNNRDPFK5B7SDKRT.json","view_paper":"https://pith.science/paper/TXNBMBSC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.01414&json=true","fetch_graph":"https://pith.science/api/pith-number/TXNBMBSCUFJNNRDPFK5B7SDKRT/graph.json","fetch_events":"https://pith.science/api/pith-number/TXNBMBSCUFJNNRDPFK5B7SDKRT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TXNBMBSCUFJNNRDPFK5B7SDKRT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TXNBMBSCUFJNNRDPFK5B7SDKRT/action/storage_attestation","attest_author":"https://pith.science/pith/TXNBMBSCUFJNNRDPFK5B7SDKRT/action/author_attestation","sign_citation":"https://pith.science/pith/TXNBMBSCUFJNNRDPFK5B7SDKRT/action/citation_signature","submit_replication":"https://pith.science/pith/TXNBMBSCUFJNNRDPFK5B7SDKRT/action/replication_record"}},"created_at":"2026-07-05T11:14:12.845650+00:00","updated_at":"2026-07-05T11:14:12.845650+00:00"}