{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2005:6GBWR6DJESN634SALV64QJI4SI","short_pith_number":"pith:6GBWR6DJ","schema_version":"1.0","canonical_sha256":"f18368f869249bedf2405d7dc8251c923755c962079b9f738cd12e4ea6cc52f3","source":{"kind":"arxiv","id":"cs/0508122","version":2},"attestation_state":"computed","paper":{"title":"Streaming and Sublinear Approximation of Entropy and Information Distances","license":"","headline":"","cross_cats":["cs.IT","math.IT"],"primary_cat":"cs.DS","authors_text":"Andrew McGregor, Sudipto Guha, Suresh Venkatasubramanian","submitted_at":"2005-08-27T23:10:52Z","abstract_excerpt":"In many problems in data mining and machine learning, data items that need to be clustered or classified are not points in a high-dimensional space, but are distributions (points on a high dimensional simplex). For distributions, natural measures of distance are not the $\\ell_p$ norms and variants, but information-theoretic measures like the Kullback-Leibler distance, the Hellinger distance, and others. Efficient estimation of these distances is a key component in algorithms for manipulating distributions. Thus, sublinear resource constraints, either in time (property testing) or space (stream"},"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":"cs/0508122","kind":"arxiv","version":2},"metadata":{"license":"","primary_cat":"cs.DS","submitted_at":"2005-08-27T23:10:52Z","cross_cats_sorted":["cs.IT","math.IT"],"title_canon_sha256":"33fd76b2081f2729bc29ee3a0411ce7deae38f75b4a104f7789b67a8c74fe47f","abstract_canon_sha256":"e4b5cdebbafbdedb73cbc19014203e2e5b9b48194c8d9847b2009a0f0b00d4e1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-04T15:02:46.579255Z","signature_b64":"lSw21BrPEtrTPgtjEDvSpZBPVQOo/F5wr6lNu2+CoSsenh5tmnAmmiWbkWqeoMnyomiPiz3Id2WBsqBAAlTlDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f18368f869249bedf2405d7dc8251c923755c962079b9f738cd12e4ea6cc52f3","last_reissued_at":"2026-07-04T15:02:46.578891Z","signature_status":"signed_v1","first_computed_at":"2026-07-04T15:02:46.578891Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Streaming and Sublinear Approximation of Entropy and Information Distances","license":"","headline":"","cross_cats":["cs.IT","math.IT"],"primary_cat":"cs.DS","authors_text":"Andrew McGregor, Sudipto Guha, Suresh Venkatasubramanian","submitted_at":"2005-08-27T23:10:52Z","abstract_excerpt":"In many problems in data mining and machine learning, data items that need to be clustered or classified are not points in a high-dimensional space, but are distributions (points on a high dimensional simplex). For distributions, natural measures of distance are not the $\\ell_p$ norms and variants, but information-theoretic measures like the Kullback-Leibler distance, the Hellinger distance, and others. Efficient estimation of these distances is a key component in algorithms for manipulating distributions. Thus, sublinear resource constraints, either in time (property testing) or space (stream"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"cs/0508122","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/cs/0508122/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":"cs/0508122","created_at":"2026-07-04T15:02:46.578951+00:00"},{"alias_kind":"arxiv_version","alias_value":"cs/0508122v2","created_at":"2026-07-04T15:02:46.578951+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.cs/0508122","created_at":"2026-07-04T15:02:46.578951+00:00"},{"alias_kind":"pith_short_12","alias_value":"6GBWR6DJESN6","created_at":"2026-07-04T15:02:46.578951+00:00"},{"alias_kind":"pith_short_16","alias_value":"6GBWR6DJESN634SA","created_at":"2026-07-04T15:02:46.578951+00:00"},{"alias_kind":"pith_short_8","alias_value":"6GBWR6DJ","created_at":"2026-07-04T15:02:46.578951+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.11963","citing_title":"Approximating the Top Eigenvector in Random Order Streams","ref_index":10,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6GBWR6DJESN634SALV64QJI4SI","json":"https://pith.science/pith/6GBWR6DJESN634SALV64QJI4SI.json","graph_json":"https://pith.science/api/pith-number/6GBWR6DJESN634SALV64QJI4SI/graph.json","events_json":"https://pith.science/api/pith-number/6GBWR6DJESN634SALV64QJI4SI/events.json","paper":"https://pith.science/paper/6GBWR6DJ"},"agent_actions":{"view_html":"https://pith.science/pith/6GBWR6DJESN634SALV64QJI4SI","download_json":"https://pith.science/pith/6GBWR6DJESN634SALV64QJI4SI.json","view_paper":"https://pith.science/paper/6GBWR6DJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=cs/0508122&json=true","fetch_graph":"https://pith.science/api/pith-number/6GBWR6DJESN634SALV64QJI4SI/graph.json","fetch_events":"https://pith.science/api/pith-number/6GBWR6DJESN634SALV64QJI4SI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6GBWR6DJESN634SALV64QJI4SI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6GBWR6DJESN634SALV64QJI4SI/action/storage_attestation","attest_author":"https://pith.science/pith/6GBWR6DJESN634SALV64QJI4SI/action/author_attestation","sign_citation":"https://pith.science/pith/6GBWR6DJESN634SALV64QJI4SI/action/citation_signature","submit_replication":"https://pith.science/pith/6GBWR6DJESN634SALV64QJI4SI/action/replication_record"}},"created_at":"2026-07-04T15:02:46.578951+00:00","updated_at":"2026-07-04T15:02:46.578951+00:00"}