{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:P3PLHHR64LWAFJEUNHBTR6A6SK","short_pith_number":"pith:P3PLHHR6","schema_version":"1.0","canonical_sha256":"7edeb39e3ee2ec02a49469c338f81e9281760dc1a7907535a5203c06faa556ca","source":{"kind":"arxiv","id":"2402.01514","version":2},"attestation_state":"computed","paper":{"title":"Mapping the Multiverse of Latent Representations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.AT","stat.ML"],"primary_cat":"cs.LG","authors_text":"Bastian Rieck, Corinna Coupette, Jeremy Wayland","submitted_at":"2024-02-02T15:54:53Z","abstract_excerpt":"Echoing recent calls to counter reliability and robustness concerns in machine learning via multiverse analysis, we present PRESTO, a principled framework for mapping the multiverse of machine-learning models that rely on latent representations. Although such models enjoy widespread adoption, the variability in their embeddings remains poorly understood, resulting in unnecessary complexity and untrustworthy representations. Our framework uses persistent homology to characterize the latent spaces arising from different combinations of diverse machine-learning methods, (hyper)parameter configura"},"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":"2402.01514","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-02T15:54:53Z","cross_cats_sorted":["math.AT","stat.ML"],"title_canon_sha256":"e689136e84137a067a3ce97dc802795fb4b176fdc99c536f32641ba22dea1eac","abstract_canon_sha256":"fb67b1622bfb49ce8a20ea2f27807b33b769ddb2c26f286064a7f0fe134ae1b2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:25:52.021817Z","signature_b64":"JN60GviMcIoSTIGOcQOK8yPcKtDum403sTCGlb7S4Y52hl+bgWfXJNPoIOQ0OQEAefHA6JOdlQXUzTX/hsQKAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7edeb39e3ee2ec02a49469c338f81e9281760dc1a7907535a5203c06faa556ca","last_reissued_at":"2026-07-05T08:25:52.021329Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:25:52.021329Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Mapping the Multiverse of Latent Representations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.AT","stat.ML"],"primary_cat":"cs.LG","authors_text":"Bastian Rieck, Corinna Coupette, Jeremy Wayland","submitted_at":"2024-02-02T15:54:53Z","abstract_excerpt":"Echoing recent calls to counter reliability and robustness concerns in machine learning via multiverse analysis, we present PRESTO, a principled framework for mapping the multiverse of machine-learning models that rely on latent representations. Although such models enjoy widespread adoption, the variability in their embeddings remains poorly understood, resulting in unnecessary complexity and untrustworthy representations. Our framework uses persistent homology to characterize the latent spaces arising from different combinations of diverse machine-learning methods, (hyper)parameter configura"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.01514","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2402.01514/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":"2402.01514","created_at":"2026-07-05T08:25:52.021387+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.01514v2","created_at":"2026-07-05T08:25:52.021387+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.01514","created_at":"2026-07-05T08:25:52.021387+00:00"},{"alias_kind":"pith_short_12","alias_value":"P3PLHHR64LWA","created_at":"2026-07-05T08:25:52.021387+00:00"},{"alias_kind":"pith_short_16","alias_value":"P3PLHHR64LWAFJEU","created_at":"2026-07-05T08:25:52.021387+00:00"},{"alias_kind":"pith_short_8","alias_value":"P3PLHHR6","created_at":"2026-07-05T08:25:52.021387+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/P3PLHHR64LWAFJEUNHBTR6A6SK","json":"https://pith.science/pith/P3PLHHR64LWAFJEUNHBTR6A6SK.json","graph_json":"https://pith.science/api/pith-number/P3PLHHR64LWAFJEUNHBTR6A6SK/graph.json","events_json":"https://pith.science/api/pith-number/P3PLHHR64LWAFJEUNHBTR6A6SK/events.json","paper":"https://pith.science/paper/P3PLHHR6"},"agent_actions":{"view_html":"https://pith.science/pith/P3PLHHR64LWAFJEUNHBTR6A6SK","download_json":"https://pith.science/pith/P3PLHHR64LWAFJEUNHBTR6A6SK.json","view_paper":"https://pith.science/paper/P3PLHHR6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.01514&json=true","fetch_graph":"https://pith.science/api/pith-number/P3PLHHR64LWAFJEUNHBTR6A6SK/graph.json","fetch_events":"https://pith.science/api/pith-number/P3PLHHR64LWAFJEUNHBTR6A6SK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/P3PLHHR64LWAFJEUNHBTR6A6SK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/P3PLHHR64LWAFJEUNHBTR6A6SK/action/storage_attestation","attest_author":"https://pith.science/pith/P3PLHHR64LWAFJEUNHBTR6A6SK/action/author_attestation","sign_citation":"https://pith.science/pith/P3PLHHR64LWAFJEUNHBTR6A6SK/action/citation_signature","submit_replication":"https://pith.science/pith/P3PLHHR64LWAFJEUNHBTR6A6SK/action/replication_record"}},"created_at":"2026-07-05T08:25:52.021387+00:00","updated_at":"2026-07-05T08:25:52.021387+00:00"}