{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:F4G3UVNYZC7AEEGHATRECYXIEC","short_pith_number":"pith:F4G3UVNY","schema_version":"1.0","canonical_sha256":"2f0dba55b8c8be0210c704e24162e820869a382fcc5dd37a1e58b153bb822fb9","source":{"kind":"arxiv","id":"2502.16819","version":2},"attestation_state":"computed","paper":{"title":"Fast, Accurate Manifold Denoising by Tunneling Riemannian Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC"],"primary_cat":"cs.LG","authors_text":"Arnaud Lamy, John Wright, Mariam Avagyan, Shiyu Wang, Szabolcs M\\'arka, Tingran Wang, Yihan Shen, Zsuzsa M\\'arka","submitted_at":"2025-02-24T04:02:16Z","abstract_excerpt":"Learned denoisers play a fundamental role in various signal generation (e.g., diffusion models) and reconstruction (e.g., compressed sensing) architectures, whose success derives from their ability to leverage low-dimensional structure in data. Existing denoising methods, however, either rely on local approximations that require a linear scan of the entire dataset or treat denoising as generic function approximation problems, often sacrificing efficiency and interpretability. We consider the problem of efficiently denoising a new noisy data point sampled from an unknown $d$-dimensional manifol"},"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":"2502.16819","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-02-24T04:02:16Z","cross_cats_sorted":["math.OC"],"title_canon_sha256":"a3f31a83f341753247842d2bbb8e46385e9672c81441fe9d22a3ea7cc8a77145","abstract_canon_sha256":"1d67af89f85f028d20399b11797d033c0f135f8d1ff0d418327134872fff5bcb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:52:59.737900Z","signature_b64":"E5/Ya3xybF2eTzjaHyavasV4pNzww9h8DBiwPV26IwQp8OF0bCwKLSylFx9gpkjXe1E4bWqV0f6Yy9xJWSKJDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2f0dba55b8c8be0210c704e24162e820869a382fcc5dd37a1e58b153bb822fb9","last_reissued_at":"2026-07-05T11:52:59.737418Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:52:59.737418Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fast, Accurate Manifold Denoising by Tunneling Riemannian Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC"],"primary_cat":"cs.LG","authors_text":"Arnaud Lamy, John Wright, Mariam Avagyan, Shiyu Wang, Szabolcs M\\'arka, Tingran Wang, Yihan Shen, Zsuzsa M\\'arka","submitted_at":"2025-02-24T04:02:16Z","abstract_excerpt":"Learned denoisers play a fundamental role in various signal generation (e.g., diffusion models) and reconstruction (e.g., compressed sensing) architectures, whose success derives from their ability to leverage low-dimensional structure in data. Existing denoising methods, however, either rely on local approximations that require a linear scan of the entire dataset or treat denoising as generic function approximation problems, often sacrificing efficiency and interpretability. We consider the problem of efficiently denoising a new noisy data point sampled from an unknown $d$-dimensional manifol"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.16819","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/2502.16819/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":"2502.16819","created_at":"2026-07-05T11:52:59.737477+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.16819v2","created_at":"2026-07-05T11:52:59.737477+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.16819","created_at":"2026-07-05T11:52:59.737477+00:00"},{"alias_kind":"pith_short_12","alias_value":"F4G3UVNYZC7A","created_at":"2026-07-05T11:52:59.737477+00:00"},{"alias_kind":"pith_short_16","alias_value":"F4G3UVNYZC7AEEGH","created_at":"2026-07-05T11:52:59.737477+00:00"},{"alias_kind":"pith_short_8","alias_value":"F4G3UVNY","created_at":"2026-07-05T11:52:59.737477+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.18761","citing_title":"Local Averaging Accurately Distills Manifold Structure From Noisy Data","ref_index":10,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/F4G3UVNYZC7AEEGHATRECYXIEC","json":"https://pith.science/pith/F4G3UVNYZC7AEEGHATRECYXIEC.json","graph_json":"https://pith.science/api/pith-number/F4G3UVNYZC7AEEGHATRECYXIEC/graph.json","events_json":"https://pith.science/api/pith-number/F4G3UVNYZC7AEEGHATRECYXIEC/events.json","paper":"https://pith.science/paper/F4G3UVNY"},"agent_actions":{"view_html":"https://pith.science/pith/F4G3UVNYZC7AEEGHATRECYXIEC","download_json":"https://pith.science/pith/F4G3UVNYZC7AEEGHATRECYXIEC.json","view_paper":"https://pith.science/paper/F4G3UVNY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.16819&json=true","fetch_graph":"https://pith.science/api/pith-number/F4G3UVNYZC7AEEGHATRECYXIEC/graph.json","fetch_events":"https://pith.science/api/pith-number/F4G3UVNYZC7AEEGHATRECYXIEC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/F4G3UVNYZC7AEEGHATRECYXIEC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/F4G3UVNYZC7AEEGHATRECYXIEC/action/storage_attestation","attest_author":"https://pith.science/pith/F4G3UVNYZC7AEEGHATRECYXIEC/action/author_attestation","sign_citation":"https://pith.science/pith/F4G3UVNYZC7AEEGHATRECYXIEC/action/citation_signature","submit_replication":"https://pith.science/pith/F4G3UVNYZC7AEEGHATRECYXIEC/action/replication_record"}},"created_at":"2026-07-05T11:52:59.737477+00:00","updated_at":"2026-07-05T11:52:59.737477+00:00"}