{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:K5TDF2SJGQME2THRBM2DBT3U54","short_pith_number":"pith:K5TDF2SJ","canonical_record":{"source":{"id":"1902.01480","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-04T22:19:10Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"1d713affaaf9d8105907eae8f4adae52f16e1926e63fb763301c01bef92d9f6b","abstract_canon_sha256":"95b44f783599239a7a4ec35d1c3c8cd0fd48d4aad0a87e54a6da636fc21feb9c"},"schema_version":"1.0"},"canonical_sha256":"576632ea4934184d4cf10b3430cf74ef3a1d3b2b091596b3de51950b4708a527","source":{"kind":"arxiv","id":"1902.01480","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1902.01480","created_at":"2026-05-17T23:54:47Z"},{"alias_kind":"arxiv_version","alias_value":"1902.01480v1","created_at":"2026-05-17T23:54:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.01480","created_at":"2026-05-17T23:54:47Z"},{"alias_kind":"pith_short_12","alias_value":"K5TDF2SJGQME","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_16","alias_value":"K5TDF2SJGQME2THR","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_8","alias_value":"K5TDF2SJ","created_at":"2026-05-18T12:33:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:K5TDF2SJGQME2THRBM2DBT3U54","target":"record","payload":{"canonical_record":{"source":{"id":"1902.01480","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-04T22:19:10Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"1d713affaaf9d8105907eae8f4adae52f16e1926e63fb763301c01bef92d9f6b","abstract_canon_sha256":"95b44f783599239a7a4ec35d1c3c8cd0fd48d4aad0a87e54a6da636fc21feb9c"},"schema_version":"1.0"},"canonical_sha256":"576632ea4934184d4cf10b3430cf74ef3a1d3b2b091596b3de51950b4708a527","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:54:47.590077Z","signature_b64":"3mbp2KPt7XxibL0y/2JRRN5gi7nuyQX1fBHmlHWAoDyhG5lkAp5zsFZecQ5ZLLTY4kR8JWOw0OfLuZkVRQFOCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"576632ea4934184d4cf10b3430cf74ef3a1d3b2b091596b3de51950b4708a527","last_reissued_at":"2026-05-17T23:54:47.589546Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:54:47.589546Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1902.01480","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:54:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nVDi3C+CFFYH23O91Zp2QwCWdhoPJuhDw3nhjLxIZE1Zx7yeRpX11JbQdQdjBo663E4TbVb+EqINgG/7FzBbDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T12:32:52.384301Z"},"content_sha256":"bd18bb1dbb3745a6b9f4309288f11c26ec1fbea290a740996691e09a91e31074","schema_version":"1.0","event_id":"sha256:bd18bb1dbb3745a6b9f4309288f11c26ec1fbea290a740996691e09a91e31074"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:K5TDF2SJGQME2THRBM2DBT3U54","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"What is the dimension of your binary data?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Aristides Gionis, Heikki Mannila, Nikolaj Tatti, Taneli Mielikainen","submitted_at":"2019-02-04T22:19:10Z","abstract_excerpt":"Many 0/1 datasets have a very large number of variables; on the other hand, they are sparse and the dependency structure of the variables is simpler than the number of variables would suggest. Defining the effective dimensionality of such a dataset is a nontrivial problem. We consider the problem of defining a robust measure of dimension for 0/1 datasets, and show that the basic idea of fractal dimension can be adapted for binary data. However, as such the fractal dimension is difficult to interpret. Hence we introduce the concept of normalized fractal dimension. For a dataset $D$, its normali"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.01480","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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:54:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"f3jZL9u8Pf2f3t+a9b4jb+llmdtF4LF94DvIHoxnlXUlbg/PXpqcUabJ0a8RXjxlMtTGeVNoC3ao74mYAqIoBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T12:32:52.384973Z"},"content_sha256":"2709956addcb7d07536133fe4a4916d83e03ff2998ab0d55031e90986769f4c5","schema_version":"1.0","event_id":"sha256:2709956addcb7d07536133fe4a4916d83e03ff2998ab0d55031e90986769f4c5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/K5TDF2SJGQME2THRBM2DBT3U54/bundle.json","state_url":"https://pith.science/pith/K5TDF2SJGQME2THRBM2DBT3U54/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/K5TDF2SJGQME2THRBM2DBT3U54/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-26T12:32:52Z","links":{"resolver":"https://pith.science/pith/K5TDF2SJGQME2THRBM2DBT3U54","bundle":"https://pith.science/pith/K5TDF2SJGQME2THRBM2DBT3U54/bundle.json","state":"https://pith.science/pith/K5TDF2SJGQME2THRBM2DBT3U54/state.json","well_known_bundle":"https://pith.science/.well-known/pith/K5TDF2SJGQME2THRBM2DBT3U54/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:K5TDF2SJGQME2THRBM2DBT3U54","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"95b44f783599239a7a4ec35d1c3c8cd0fd48d4aad0a87e54a6da636fc21feb9c","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-04T22:19:10Z","title_canon_sha256":"1d713affaaf9d8105907eae8f4adae52f16e1926e63fb763301c01bef92d9f6b"},"schema_version":"1.0","source":{"id":"1902.01480","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1902.01480","created_at":"2026-05-17T23:54:47Z"},{"alias_kind":"arxiv_version","alias_value":"1902.01480v1","created_at":"2026-05-17T23:54:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.01480","created_at":"2026-05-17T23:54:47Z"},{"alias_kind":"pith_short_12","alias_value":"K5TDF2SJGQME","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_16","alias_value":"K5TDF2SJGQME2THR","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_8","alias_value":"K5TDF2SJ","created_at":"2026-05-18T12:33:21Z"}],"graph_snapshots":[{"event_id":"sha256:2709956addcb7d07536133fe4a4916d83e03ff2998ab0d55031e90986769f4c5","target":"graph","created_at":"2026-05-17T23:54:47Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"Many 0/1 datasets have a very large number of variables; on the other hand, they are sparse and the dependency structure of the variables is simpler than the number of variables would suggest. Defining the effective dimensionality of such a dataset is a nontrivial problem. We consider the problem of defining a robust measure of dimension for 0/1 datasets, and show that the basic idea of fractal dimension can be adapted for binary data. However, as such the fractal dimension is difficult to interpret. Hence we introduce the concept of normalized fractal dimension. For a dataset $D$, its normali","authors_text":"Aristides Gionis, Heikki Mannila, Nikolaj Tatti, Taneli Mielikainen","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-04T22:19:10Z","title":"What is the dimension of your binary data?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.01480","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:bd18bb1dbb3745a6b9f4309288f11c26ec1fbea290a740996691e09a91e31074","target":"record","created_at":"2026-05-17T23:54:47Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"95b44f783599239a7a4ec35d1c3c8cd0fd48d4aad0a87e54a6da636fc21feb9c","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-04T22:19:10Z","title_canon_sha256":"1d713affaaf9d8105907eae8f4adae52f16e1926e63fb763301c01bef92d9f6b"},"schema_version":"1.0","source":{"id":"1902.01480","kind":"arxiv","version":1}},"canonical_sha256":"576632ea4934184d4cf10b3430cf74ef3a1d3b2b091596b3de51950b4708a527","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"576632ea4934184d4cf10b3430cf74ef3a1d3b2b091596b3de51950b4708a527","first_computed_at":"2026-05-17T23:54:47.589546Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:54:47.589546Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3mbp2KPt7XxibL0y/2JRRN5gi7nuyQX1fBHmlHWAoDyhG5lkAp5zsFZecQ5ZLLTY4kR8JWOw0OfLuZkVRQFOCQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:54:47.590077Z","signed_message":"canonical_sha256_bytes"},"source_id":"1902.01480","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bd18bb1dbb3745a6b9f4309288f11c26ec1fbea290a740996691e09a91e31074","sha256:2709956addcb7d07536133fe4a4916d83e03ff2998ab0d55031e90986769f4c5"],"state_sha256":"fec6947a4b1eb4389b61a94af63eb11c84db3091e07d92349f6a9ab1381c3501"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"J509q+EP93ebFnI/kHPq5zCFeJ9P5JI0zU+mshzXZu3nAkhR/9Cf0sviQufSsngrwXjsZXwHx44AMSOCvq0TBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T12:32:52.388389Z","bundle_sha256":"723a283502d0a4300a4d520a04ae7f6176dfe056191f27e80cfb62fccf50d4bf"}}