{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:P4U43EWZO5EW3UFHCNAY65BVTH","short_pith_number":"pith:P4U43EWZ","schema_version":"1.0","canonical_sha256":"7f29cd92d977496dd0a713418f743599fe5c4b128df0eb3f96d10200542fc4ce","source":{"kind":"arxiv","id":"1803.06992","version":1},"attestation_state":"computed","paper":{"title":"Estimating the intrinsic dimension of datasets by a minimal neighborhood information","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Alessandro Laio, Alex Rodriguez, Elena Facco, Maria d'Errico","submitted_at":"2018-03-19T15:31:41Z","abstract_excerpt":"Analyzing large volumes of high-dimensional data is an issue of fundamental importance in data science, molecular simulations and beyond. Several approaches work on the assumption that the important content of a dataset belongs to a manifold whose Intrinsic Dimension (ID) is much lower than the crude large number of coordinates. Such manifold is generally twisted and curved, in addition points on it will be non-uniformly distributed: two factors that make the identification of the ID and its exploitation really hard. Here we propose a new ID estimator using only the distance of the first and t"},"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":"1803.06992","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-03-19T15:31:41Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"b0e44ada9b262e986d7827422963fdb37b267c6f30bbcccd8ecbf183aa324fd0","abstract_canon_sha256":"af90acc6f06b3b80868351318f72d05464360d8a86c32b1909611030da85f1fd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:20:40.623024Z","signature_b64":"i+F3+nFhb+thp0vb7cNdNvIYL5GRus2Keyd3Fs+4aLwwpQ0GSq//lnd1k7OQAEN6eyDgTYa08H8bS/tOU64oDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7f29cd92d977496dd0a713418f743599fe5c4b128df0eb3f96d10200542fc4ce","last_reissued_at":"2026-05-18T00:20:40.622373Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:20:40.622373Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Estimating the intrinsic dimension of datasets by a minimal neighborhood information","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Alessandro Laio, Alex Rodriguez, Elena Facco, Maria d'Errico","submitted_at":"2018-03-19T15:31:41Z","abstract_excerpt":"Analyzing large volumes of high-dimensional data is an issue of fundamental importance in data science, molecular simulations and beyond. Several approaches work on the assumption that the important content of a dataset belongs to a manifold whose Intrinsic Dimension (ID) is much lower than the crude large number of coordinates. Such manifold is generally twisted and curved, in addition points on it will be non-uniformly distributed: two factors that make the identification of the ID and its exploitation really hard. Here we propose a new ID estimator using only the distance of the first and t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.06992","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":""},"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":"1803.06992","created_at":"2026-05-18T00:20:40.622468+00:00"},{"alias_kind":"arxiv_version","alias_value":"1803.06992v1","created_at":"2026-05-18T00:20:40.622468+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.06992","created_at":"2026-05-18T00:20:40.622468+00:00"},{"alias_kind":"pith_short_12","alias_value":"P4U43EWZO5EW","created_at":"2026-05-18T12:32:43.782077+00:00"},{"alias_kind":"pith_short_16","alias_value":"P4U43EWZO5EW3UFH","created_at":"2026-05-18T12:32:43.782077+00:00"},{"alias_kind":"pith_short_8","alias_value":"P4U43EWZ","created_at":"2026-05-18T12:32:43.782077+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2606.00909","citing_title":"MLLM-Microscope: Unlocking Hidden Structure Within Multimodal Large Language Models","ref_index":10,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/P4U43EWZO5EW3UFHCNAY65BVTH","json":"https://pith.science/pith/P4U43EWZO5EW3UFHCNAY65BVTH.json","graph_json":"https://pith.science/api/pith-number/P4U43EWZO5EW3UFHCNAY65BVTH/graph.json","events_json":"https://pith.science/api/pith-number/P4U43EWZO5EW3UFHCNAY65BVTH/events.json","paper":"https://pith.science/paper/P4U43EWZ"},"agent_actions":{"view_html":"https://pith.science/pith/P4U43EWZO5EW3UFHCNAY65BVTH","download_json":"https://pith.science/pith/P4U43EWZO5EW3UFHCNAY65BVTH.json","view_paper":"https://pith.science/paper/P4U43EWZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1803.06992&json=true","fetch_graph":"https://pith.science/api/pith-number/P4U43EWZO5EW3UFHCNAY65BVTH/graph.json","fetch_events":"https://pith.science/api/pith-number/P4U43EWZO5EW3UFHCNAY65BVTH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/P4U43EWZO5EW3UFHCNAY65BVTH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/P4U43EWZO5EW3UFHCNAY65BVTH/action/storage_attestation","attest_author":"https://pith.science/pith/P4U43EWZO5EW3UFHCNAY65BVTH/action/author_attestation","sign_citation":"https://pith.science/pith/P4U43EWZO5EW3UFHCNAY65BVTH/action/citation_signature","submit_replication":"https://pith.science/pith/P4U43EWZO5EW3UFHCNAY65BVTH/action/replication_record"}},"created_at":"2026-05-18T00:20:40.622468+00:00","updated_at":"2026-05-18T00:20:40.622468+00:00"}