{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:IEFRZGWURRC2JC45M2MO2PPU7N","short_pith_number":"pith:IEFRZGWU","schema_version":"1.0","canonical_sha256":"410b1c9ad48c45a48b9d6698ed3df4fb4a93c487c516bef99aee1694a88f190c","source":{"kind":"arxiv","id":"2605.01221","version":2},"attestation_state":"computed","paper":{"title":"Local Hessian Spectral Filtering for Robust Intrinsic Dimension Estimation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Spectral filtering on the log-density Hessian counts only tangent directions to estimate local intrinsic dimension even when noise fills most of high-dimensional space.","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Genki Osada","submitted_at":"2026-05-02T03:30:55Z","abstract_excerpt":"While diffusion models enable new approaches for estimating Local Intrinsic Dimension (LID), existing methods fail in high-dimensional spaces where noise from vast normal directions overwhelms the tangent signal. We propose Local Hessian Spectral Dimension (LHSD), which resolves this by applying spectral filtering to the log-density Hessian, explicitly cutting off large eigenvalues associated with normal directions to count zero-curvature tangent directions. Implemented using Stochastic Lanczos Quadrature (SLQ), LHSD avoids full Hessian construction, achieving linear scalability with dimension"},"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":"2605.01221","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-02T03:30:55Z","cross_cats_sorted":[],"title_canon_sha256":"ebc936ae33f4a20b982d25965bf77207ce3d7a80f1957d24d95fcf93509e1e5b","abstract_canon_sha256":"fde7e1acb8f2c26671760df365b2c1d97c1b2033bf117fae7789e9945af279ee"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T02:13:24.479828Z","signature_b64":"oAFSMlrnqyoCr6JIt1V8Y7YICEL5NMFqEXtjHa2Zxvnh18f8caQ8Pyni5ouec4gLEcMzJEXod2sw0DRQlO8CCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"410b1c9ad48c45a48b9d6698ed3df4fb4a93c487c516bef99aee1694a88f190c","last_reissued_at":"2026-06-23T02:13:24.479379Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T02:13:24.479379Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Local Hessian Spectral Filtering for Robust Intrinsic Dimension Estimation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Spectral filtering on the log-density Hessian counts only tangent directions to estimate local intrinsic dimension even when noise fills most of high-dimensional space.","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Genki Osada","submitted_at":"2026-05-02T03:30:55Z","abstract_excerpt":"While diffusion models enable new approaches for estimating Local Intrinsic Dimension (LID), existing methods fail in high-dimensional spaces where noise from vast normal directions overwhelms the tangent signal. We propose Local Hessian Spectral Dimension (LHSD), which resolves this by applying spectral filtering to the log-density Hessian, explicitly cutting off large eigenvalues associated with normal directions to count zero-curvature tangent directions. Implemented using Stochastic Lanczos Quadrature (SLQ), LHSD avoids full Hessian construction, achieving linear scalability with dimension"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"We propose Local Hessian Spectral Dimension (LHSD), which resolves this by applying spectral filtering to the log-density Hessian, explicitly cutting off large eigenvalues associated with normal directions to count zero-curvature tangent directions. Implemented using Stochastic Lanczos Quadrature (SLQ), LHSD avoids full Hessian construction, achieving linear scalability with dimension D.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the log-density Hessian exhibits a clear spectral separation where large eigenvalues reliably correspond to noise-dominated normal directions and near-zero eigenvalues to the tangent space, and that a fixed or simple cutoff can be applied without losing signal or introducing bias.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"LHSD uses spectral filtering on the log-density Hessian to isolate tangent directions from noise and estimate local intrinsic dimension scalably via Stochastic Lanczos Quadrature.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Spectral filtering on the log-density Hessian counts only tangent directions to estimate local intrinsic dimension even when noise fills most of high-dimensional space.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"67a4acd3a96eddba98add11cb5e6959878fd0f3601a1ebb28438b3587b955470"},"source":{"id":"2605.01221","kind":"arxiv","version":2},"verdict":{"id":"d4554f45-abde-4905-b453-fbb6f68a0849","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-09T14:06:53.178279Z","strongest_claim":"We propose Local Hessian Spectral Dimension (LHSD), which resolves this by applying spectral filtering to the log-density Hessian, explicitly cutting off large eigenvalues associated with normal directions to count zero-curvature tangent directions. Implemented using Stochastic Lanczos Quadrature (SLQ), LHSD avoids full Hessian construction, achieving linear scalability with dimension D.","one_line_summary":"LHSD uses spectral filtering on the log-density Hessian to isolate tangent directions from noise and estimate local intrinsic dimension scalably via Stochastic Lanczos Quadrature.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the log-density Hessian exhibits a clear spectral separation where large eigenvalues reliably correspond to noise-dominated normal directions and near-zero eigenvalues to the tangent space, and that a fixed or simple cutoff can be applied without losing signal or introducing bias.","pith_extraction_headline":"Spectral filtering on the log-density Hessian counts only tangent directions to estimate local intrinsic dimension even when noise fills most of high-dimensional space."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.01221/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-20T18:36:38.660101Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T17:29:15.746858Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"e21d451e4b114d82946817b282c1d913694d1a201ad9fccd2d1ccd9f14ba43fe"},"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":"2605.01221","created_at":"2026-06-23T02:13:24.479436+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.01221v2","created_at":"2026-06-23T02:13:24.479436+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.01221","created_at":"2026-06-23T02:13:24.479436+00:00"},{"alias_kind":"pith_short_12","alias_value":"IEFRZGWURRC2","created_at":"2026-06-23T02:13:24.479436+00:00"},{"alias_kind":"pith_short_16","alias_value":"IEFRZGWURRC2JC45","created_at":"2026-06-23T02:13:24.479436+00:00"},{"alias_kind":"pith_short_8","alias_value":"IEFRZGWU","created_at":"2026-06-23T02:13:24.479436+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/IEFRZGWURRC2JC45M2MO2PPU7N","json":"https://pith.science/pith/IEFRZGWURRC2JC45M2MO2PPU7N.json","graph_json":"https://pith.science/api/pith-number/IEFRZGWURRC2JC45M2MO2PPU7N/graph.json","events_json":"https://pith.science/api/pith-number/IEFRZGWURRC2JC45M2MO2PPU7N/events.json","paper":"https://pith.science/paper/IEFRZGWU"},"agent_actions":{"view_html":"https://pith.science/pith/IEFRZGWURRC2JC45M2MO2PPU7N","download_json":"https://pith.science/pith/IEFRZGWURRC2JC45M2MO2PPU7N.json","view_paper":"https://pith.science/paper/IEFRZGWU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.01221&json=true","fetch_graph":"https://pith.science/api/pith-number/IEFRZGWURRC2JC45M2MO2PPU7N/graph.json","fetch_events":"https://pith.science/api/pith-number/IEFRZGWURRC2JC45M2MO2PPU7N/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IEFRZGWURRC2JC45M2MO2PPU7N/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IEFRZGWURRC2JC45M2MO2PPU7N/action/storage_attestation","attest_author":"https://pith.science/pith/IEFRZGWURRC2JC45M2MO2PPU7N/action/author_attestation","sign_citation":"https://pith.science/pith/IEFRZGWURRC2JC45M2MO2PPU7N/action/citation_signature","submit_replication":"https://pith.science/pith/IEFRZGWURRC2JC45M2MO2PPU7N/action/replication_record"}},"created_at":"2026-06-23T02:13:24.479436+00:00","updated_at":"2026-06-23T02:13:24.479436+00:00"}