{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:472GGWHTUIFTSREJ2C6BJWGFHW","short_pith_number":"pith:472GGWHT","schema_version":"1.0","canonical_sha256":"e7f46358f3a20b394489d0bc14d8c53db53c2eac19f7ff8fca7e2fca5d386f95","source":{"kind":"arxiv","id":"1908.07377","version":1},"attestation_state":"computed","paper":{"title":"Expected path length on random manifolds","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"David Eklund, S{\\o}ren Hauberg","submitted_at":"2019-08-20T14:14:43Z","abstract_excerpt":"Manifold learning seeks a low dimensional representation that faithfully captures the essence of data. Current methods can successfully learn such representations, but do not provide a meaningful set of operations that are associated with the representation. Working towards operational representation learning, we endow the latent space of a large class of generative models with a random Riemannian metric, which provides us with elementary operators. As computational tools are unavailable for random Riemannian manifolds, we study deterministic approximations and derive tight error bounds on exp"},"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":"1908.07377","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-08-20T14:14:43Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"5a85ca4d1476a21ee8e7c27db1dc82e937242e1d55fcf5b10bd0fd0ea8645e65","abstract_canon_sha256":"1502f1f9ae89b7c92bef1e9d79093d56ac291b4f80d9db4bf274a4bbe3d0cd53"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-04T23:58:33.808626Z","signature_b64":"v3LEHkb952H8ORNq1Caaw3WGCAL7uFMdEKF5J8pkyJumf18oORi9TucB+Yvz7ved45T9zJYyAkxsOtwXhoOhDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e7f46358f3a20b394489d0bc14d8c53db53c2eac19f7ff8fca7e2fca5d386f95","last_reissued_at":"2026-07-04T23:58:33.808280Z","signature_status":"signed_v1","first_computed_at":"2026-07-04T23:58:33.808280Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Expected path length on random manifolds","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"David Eklund, S{\\o}ren Hauberg","submitted_at":"2019-08-20T14:14:43Z","abstract_excerpt":"Manifold learning seeks a low dimensional representation that faithfully captures the essence of data. Current methods can successfully learn such representations, but do not provide a meaningful set of operations that are associated with the representation. Working towards operational representation learning, we endow the latent space of a large class of generative models with a random Riemannian metric, which provides us with elementary operators. As computational tools are unavailable for random Riemannian manifolds, we study deterministic approximations and derive tight error bounds on exp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.07377","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/1908.07377/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":"1908.07377","created_at":"2026-07-04T23:58:33.808343+00:00"},{"alias_kind":"arxiv_version","alias_value":"1908.07377v1","created_at":"2026-07-04T23:58:33.808343+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.07377","created_at":"2026-07-04T23:58:33.808343+00:00"},{"alias_kind":"pith_short_12","alias_value":"472GGWHTUIFT","created_at":"2026-07-04T23:58:33.808343+00:00"},{"alias_kind":"pith_short_16","alias_value":"472GGWHTUIFTSREJ","created_at":"2026-07-04T23:58:33.808343+00:00"},{"alias_kind":"pith_short_8","alias_value":"472GGWHT","created_at":"2026-07-04T23:58:33.808343+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.11405","citing_title":"Extended Neural Contractive Dynamical Systems: On Multiple Tasks and Riemannian Safety Regions","ref_index":12,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/472GGWHTUIFTSREJ2C6BJWGFHW","json":"https://pith.science/pith/472GGWHTUIFTSREJ2C6BJWGFHW.json","graph_json":"https://pith.science/api/pith-number/472GGWHTUIFTSREJ2C6BJWGFHW/graph.json","events_json":"https://pith.science/api/pith-number/472GGWHTUIFTSREJ2C6BJWGFHW/events.json","paper":"https://pith.science/paper/472GGWHT"},"agent_actions":{"view_html":"https://pith.science/pith/472GGWHTUIFTSREJ2C6BJWGFHW","download_json":"https://pith.science/pith/472GGWHTUIFTSREJ2C6BJWGFHW.json","view_paper":"https://pith.science/paper/472GGWHT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1908.07377&json=true","fetch_graph":"https://pith.science/api/pith-number/472GGWHTUIFTSREJ2C6BJWGFHW/graph.json","fetch_events":"https://pith.science/api/pith-number/472GGWHTUIFTSREJ2C6BJWGFHW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/472GGWHTUIFTSREJ2C6BJWGFHW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/472GGWHTUIFTSREJ2C6BJWGFHW/action/storage_attestation","attest_author":"https://pith.science/pith/472GGWHTUIFTSREJ2C6BJWGFHW/action/author_attestation","sign_citation":"https://pith.science/pith/472GGWHTUIFTSREJ2C6BJWGFHW/action/citation_signature","submit_replication":"https://pith.science/pith/472GGWHTUIFTSREJ2C6BJWGFHW/action/replication_record"}},"created_at":"2026-07-04T23:58:33.808343+00:00","updated_at":"2026-07-04T23:58:33.808343+00:00"}