{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:TXNBMBSCUFJNNRDPFK5B7SDKRT","short_pith_number":"pith:TXNBMBSC","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"},"canonical_sha256":"9dda160642a152d6c46f2aba1fc86a8ce6f18b21c99738bfea0ee5b4f439aea3","source":{"kind":"arxiv","id":"2506.01414","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.01414","created_at":"2026-07-05T11:14:12Z"},{"alias_kind":"arxiv_version","alias_value":"2506.01414v1","created_at":"2026-07-05T11:14:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.01414","created_at":"2026-07-05T11:14:12Z"},{"alias_kind":"pith_short_12","alias_value":"TXNBMBSCUFJN","created_at":"2026-07-05T11:14:12Z"},{"alias_kind":"pith_short_16","alias_value":"TXNBMBSCUFJNNRDP","created_at":"2026-07-05T11:14:12Z"},{"alias_kind":"pith_short_8","alias_value":"TXNBMBSC","created_at":"2026-07-05T11:14:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:TXNBMBSCUFJNNRDPFK5B7SDKRT","target":"record","payload":{"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"},"canonical_sha256":"9dda160642a152d6c46f2aba1fc86a8ce6f18b21c99738bfea0ee5b4f439aea3","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"},"source_kind":"arxiv","source_id":"2506.01414","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:14:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Av0nTjFv5wTL+4XTb4wAe1tGqlQGnTjwEBOojCKKh2qsOkqJV+Q4U7Lk35O6Li5dAwOGF8GSNpm9YbEVDqrQCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T11:46:46.885455Z"},"content_sha256":"9717917b9b6f0fb7d65378093eef75bb19028539f48a8d9dd256982c34f89e02","schema_version":"1.0","event_id":"sha256:9717917b9b6f0fb7d65378093eef75bb19028539f48a8d9dd256982c34f89e02"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:TXNBMBSCUFJNNRDPFK5B7SDKRT","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:14:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CQA9k3yypzNTr1YYnFgBMoUYYCwKKUFYU1k+2yRudYWL0Ag5ehbEXobHffwdKAJc8WEr2Z8Wx98m1Bmxhth+BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T11:46:46.886708Z"},"content_sha256":"4ffb420ff1e5ded4362b8113adc87c5211ff4f4ef40b10b7c90ec62846d59ca7","schema_version":"1.0","event_id":"sha256:4ffb420ff1e5ded4362b8113adc87c5211ff4f4ef40b10b7c90ec62846d59ca7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TXNBMBSCUFJNNRDPFK5B7SDKRT/bundle.json","state_url":"https://pith.science/pith/TXNBMBSCUFJNNRDPFK5B7SDKRT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TXNBMBSCUFJNNRDPFK5B7SDKRT/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-09T11:46:46Z","links":{"resolver":"https://pith.science/pith/TXNBMBSCUFJNNRDPFK5B7SDKRT","bundle":"https://pith.science/pith/TXNBMBSCUFJNNRDPFK5B7SDKRT/bundle.json","state":"https://pith.science/pith/TXNBMBSCUFJNNRDPFK5B7SDKRT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TXNBMBSCUFJNNRDPFK5B7SDKRT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:TXNBMBSCUFJNNRDPFK5B7SDKRT","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"af5703f8247b1bfc82469f6ab12e10b5a1f56065164bd729e076a980bb6b65ae","cross_cats_sorted":["cs.IT","math.IT"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-02T08:13:32Z","title_canon_sha256":"3a624ad241c9aa1a161f5c854ed064a53fc07d7601ea91dae5ee6ccd73091f91"},"schema_version":"1.0","source":{"id":"2506.01414","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.01414","created_at":"2026-07-05T11:14:12Z"},{"alias_kind":"arxiv_version","alias_value":"2506.01414v1","created_at":"2026-07-05T11:14:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.01414","created_at":"2026-07-05T11:14:12Z"},{"alias_kind":"pith_short_12","alias_value":"TXNBMBSCUFJN","created_at":"2026-07-05T11:14:12Z"},{"alias_kind":"pith_short_16","alias_value":"TXNBMBSCUFJNNRDP","created_at":"2026-07-05T11:14:12Z"},{"alias_kind":"pith_short_8","alias_value":"TXNBMBSC","created_at":"2026-07-05T11:14:12Z"}],"graph_snapshots":[{"event_id":"sha256:4ffb420ff1e5ded4362b8113adc87c5211ff4f4ef40b10b7c90ec62846d59ca7","target":"graph","created_at":"2026-07-05T11:14:12Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2506.01414/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"David Joseph Tan, Federico Tombari, Nassir Navab, Yida Wang","cross_cats":["cs.IT","math.IT"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-02T08:13:32Z","title":"Self-supervised Latent Space Optimization with Nebula Variational Coding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.01414","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:9717917b9b6f0fb7d65378093eef75bb19028539f48a8d9dd256982c34f89e02","target":"record","created_at":"2026-07-05T11:14:12Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"af5703f8247b1bfc82469f6ab12e10b5a1f56065164bd729e076a980bb6b65ae","cross_cats_sorted":["cs.IT","math.IT"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-02T08:13:32Z","title_canon_sha256":"3a624ad241c9aa1a161f5c854ed064a53fc07d7601ea91dae5ee6ccd73091f91"},"schema_version":"1.0","source":{"id":"2506.01414","kind":"arxiv","version":1}},"canonical_sha256":"9dda160642a152d6c46f2aba1fc86a8ce6f18b21c99738bfea0ee5b4f439aea3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9dda160642a152d6c46f2aba1fc86a8ce6f18b21c99738bfea0ee5b4f439aea3","first_computed_at":"2026-07-05T11:14:12.845593Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:14:12.845593Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"twmT8/+OHnu3GqwQYFfBGcg5tPw43YIJjaxRDDoa/5B6mFH4nAfjpmsjPNIAZbfZtSzjLTpuogEr1zd6bE0GBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:14:12.846035Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.01414","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9717917b9b6f0fb7d65378093eef75bb19028539f48a8d9dd256982c34f89e02","sha256:4ffb420ff1e5ded4362b8113adc87c5211ff4f4ef40b10b7c90ec62846d59ca7"],"state_sha256":"48abc9eb9fed474822d183b99c11aacb24a53fe3643f1075c7aa8e6acf1cd7ce"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"36avLDrXd4V6DpJMNLroVAQ42ncihMWKcs3ukX2xAOoVsaiJ7cxQk4nlm4ZxuGonuyDAQAJpZXYhg2JKBN5qCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T11:46:46.894296Z","bundle_sha256":"4254caf313453e267eb364ceab3da02f7128dcd3810bed39b54be5423bb8c2b6"}}