{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:I6Z2DGXSMQYKQT6P2AJXJ3VARR","short_pith_number":"pith:I6Z2DGXS","schema_version":"1.0","canonical_sha256":"47b3a19af26430a84fcfd01374eea08c6136a986b23cdba946eb256321eb87dd","source":{"kind":"arxiv","id":"2408.07507","version":1},"attestation_state":"computed","paper":{"title":"Decoder ensembling for learned latent geometries","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Pablo Moreno-Mu\\~noz, S{\\o}ren Hauberg, Stas Syrota","submitted_at":"2024-08-14T12:35:41Z","abstract_excerpt":"Latent space geometry provides a rigorous and empirically valuable framework for interacting with the latent variables of deep generative models. This approach reinterprets Euclidean latent spaces as Riemannian through a pull-back metric, allowing for a standard differential geometric analysis of the latent space. Unfortunately, data manifolds are generally compact and easily disconnected or filled with holes, suggesting a topological mismatch to the Euclidean latent space. The most established solution to this mismatch is to let uncertainty be a proxy for topology, but in neural network model"},"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":"2408.07507","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2024-08-14T12:35:41Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"bf017bd6c72fbb0474e8a20b7febb217b20346dc32452adc07e0931717a9d3e1","abstract_canon_sha256":"daec4efdc91660966c322be63802c67e7420377edaa41e18d695f8511be19798"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:55:26.385362Z","signature_b64":"WI9tC03ZR2FZC4pvEXxrm0TN9maL0b04tTG8FcUOPGnb1pg+u3emH+BwseOGN3HVuSq+hnl2qOL58XfirgfpCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"47b3a19af26430a84fcfd01374eea08c6136a986b23cdba946eb256321eb87dd","last_reissued_at":"2026-07-05T08:55:26.384719Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:55:26.384719Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Decoder ensembling for learned latent geometries","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Pablo Moreno-Mu\\~noz, S{\\o}ren Hauberg, Stas Syrota","submitted_at":"2024-08-14T12:35:41Z","abstract_excerpt":"Latent space geometry provides a rigorous and empirically valuable framework for interacting with the latent variables of deep generative models. This approach reinterprets Euclidean latent spaces as Riemannian through a pull-back metric, allowing for a standard differential geometric analysis of the latent space. Unfortunately, data manifolds are generally compact and easily disconnected or filled with holes, suggesting a topological mismatch to the Euclidean latent space. The most established solution to this mismatch is to let uncertainty be a proxy for topology, but in neural network model"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.07507","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/2408.07507/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":"2408.07507","created_at":"2026-07-05T08:55:26.384796+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.07507v1","created_at":"2026-07-05T08:55:26.384796+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.07507","created_at":"2026-07-05T08:55:26.384796+00:00"},{"alias_kind":"pith_short_12","alias_value":"I6Z2DGXSMQYK","created_at":"2026-07-05T08:55:26.384796+00:00"},{"alias_kind":"pith_short_16","alias_value":"I6Z2DGXSMQYKQT6P","created_at":"2026-07-05T08:55:26.384796+00:00"},{"alias_kind":"pith_short_8","alias_value":"I6Z2DGXS","created_at":"2026-07-05T08:55:26.384796+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.26893","citing_title":"GeoFaith: A Spatio-Temporal Dual View of Faithful Chain-of-Thought","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/I6Z2DGXSMQYKQT6P2AJXJ3VARR","json":"https://pith.science/pith/I6Z2DGXSMQYKQT6P2AJXJ3VARR.json","graph_json":"https://pith.science/api/pith-number/I6Z2DGXSMQYKQT6P2AJXJ3VARR/graph.json","events_json":"https://pith.science/api/pith-number/I6Z2DGXSMQYKQT6P2AJXJ3VARR/events.json","paper":"https://pith.science/paper/I6Z2DGXS"},"agent_actions":{"view_html":"https://pith.science/pith/I6Z2DGXSMQYKQT6P2AJXJ3VARR","download_json":"https://pith.science/pith/I6Z2DGXSMQYKQT6P2AJXJ3VARR.json","view_paper":"https://pith.science/paper/I6Z2DGXS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.07507&json=true","fetch_graph":"https://pith.science/api/pith-number/I6Z2DGXSMQYKQT6P2AJXJ3VARR/graph.json","fetch_events":"https://pith.science/api/pith-number/I6Z2DGXSMQYKQT6P2AJXJ3VARR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/I6Z2DGXSMQYKQT6P2AJXJ3VARR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/I6Z2DGXSMQYKQT6P2AJXJ3VARR/action/storage_attestation","attest_author":"https://pith.science/pith/I6Z2DGXSMQYKQT6P2AJXJ3VARR/action/author_attestation","sign_citation":"https://pith.science/pith/I6Z2DGXSMQYKQT6P2AJXJ3VARR/action/citation_signature","submit_replication":"https://pith.science/pith/I6Z2DGXSMQYKQT6P2AJXJ3VARR/action/replication_record"}},"created_at":"2026-07-05T08:55:26.384796+00:00","updated_at":"2026-07-05T08:55:26.384796+00:00"}