{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:5D3MMOKLHWAADBRSSWTIGDWKQL","short_pith_number":"pith:5D3MMOKL","schema_version":"1.0","canonical_sha256":"e8f6c6394b3d8001863295a6830eca82d1551c93794a703bab478f535b342f06","source":{"kind":"arxiv","id":"2407.09297","version":2},"attestation_state":"computed","paper":{"title":"Learning Distances from Data with Normalizing Flows and Score Matching","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Christoph Schn\\\"orr, Daniel Behrend-Uriarte, Peter Sorrenson, Ullrich K\\\"othe","submitted_at":"2024-07-12T14:30:41Z","abstract_excerpt":"Density-based distances (DBDs) provide a principled approach to metric learning by defining distances in terms of the underlying data distribution. By employing a Riemannian metric that increases in regions of low probability density, shortest paths naturally follow the data manifold. Fermat distances, a specific type of DBD, have attractive properties, but existing estimators based on nearest neighbor graphs suffer from poor convergence due to inaccurate density estimates. Moreover, graph-based methods scale poorly to high dimensions, as the proposed geodesics are often insufficiently smooth."},"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":"2407.09297","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-07-12T14:30:41Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"bf3d0bf9723e23e039aa33109a125eac520194da43d8ee06b4955993ea1d1e5d","abstract_canon_sha256":"a036abc2a703f7ca75d0294b52b654a267c8a01ec687866d3a2b5af2170f812e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:12:18.667550Z","signature_b64":"bhbEkCJ4bTHpyfe/PVnN0L7M49oKqxEab+nEVegTYP7NDc0RrhpZ6PP54tRE6f6ReG0f0ZAdxreQ3M0bEZ+eCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e8f6c6394b3d8001863295a6830eca82d1551c93794a703bab478f535b342f06","last_reissued_at":"2026-07-05T11:12:18.666958Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:12:18.666958Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Distances from Data with Normalizing Flows and Score Matching","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Christoph Schn\\\"orr, Daniel Behrend-Uriarte, Peter Sorrenson, Ullrich K\\\"othe","submitted_at":"2024-07-12T14:30:41Z","abstract_excerpt":"Density-based distances (DBDs) provide a principled approach to metric learning by defining distances in terms of the underlying data distribution. By employing a Riemannian metric that increases in regions of low probability density, shortest paths naturally follow the data manifold. Fermat distances, a specific type of DBD, have attractive properties, but existing estimators based on nearest neighbor graphs suffer from poor convergence due to inaccurate density estimates. Moreover, graph-based methods scale poorly to high dimensions, as the proposed geodesics are often insufficiently smooth."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.09297","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/2407.09297/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":"2407.09297","created_at":"2026-07-05T11:12:18.667023+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.09297v2","created_at":"2026-07-05T11:12:18.667023+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.09297","created_at":"2026-07-05T11:12:18.667023+00:00"},{"alias_kind":"pith_short_12","alias_value":"5D3MMOKLHWAA","created_at":"2026-07-05T11:12:18.667023+00:00"},{"alias_kind":"pith_short_16","alias_value":"5D3MMOKLHWAADBRS","created_at":"2026-07-05T11:12:18.667023+00:00"},{"alias_kind":"pith_short_8","alias_value":"5D3MMOKL","created_at":"2026-07-05T11:12:18.667023+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/5D3MMOKLHWAADBRSSWTIGDWKQL","json":"https://pith.science/pith/5D3MMOKLHWAADBRSSWTIGDWKQL.json","graph_json":"https://pith.science/api/pith-number/5D3MMOKLHWAADBRSSWTIGDWKQL/graph.json","events_json":"https://pith.science/api/pith-number/5D3MMOKLHWAADBRSSWTIGDWKQL/events.json","paper":"https://pith.science/paper/5D3MMOKL"},"agent_actions":{"view_html":"https://pith.science/pith/5D3MMOKLHWAADBRSSWTIGDWKQL","download_json":"https://pith.science/pith/5D3MMOKLHWAADBRSSWTIGDWKQL.json","view_paper":"https://pith.science/paper/5D3MMOKL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.09297&json=true","fetch_graph":"https://pith.science/api/pith-number/5D3MMOKLHWAADBRSSWTIGDWKQL/graph.json","fetch_events":"https://pith.science/api/pith-number/5D3MMOKLHWAADBRSSWTIGDWKQL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5D3MMOKLHWAADBRSSWTIGDWKQL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5D3MMOKLHWAADBRSSWTIGDWKQL/action/storage_attestation","attest_author":"https://pith.science/pith/5D3MMOKLHWAADBRSSWTIGDWKQL/action/author_attestation","sign_citation":"https://pith.science/pith/5D3MMOKLHWAADBRSSWTIGDWKQL/action/citation_signature","submit_replication":"https://pith.science/pith/5D3MMOKLHWAADBRSSWTIGDWKQL/action/replication_record"}},"created_at":"2026-07-05T11:12:18.667023+00:00","updated_at":"2026-07-05T11:12:18.667023+00:00"}