{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2003:QGZVEQ5KHWFVS7YBPNJFAHQJSH","short_pith_number":"pith:QGZVEQ5K","canonical_record":{"source":{"id":"cs/0312044","kind":"arxiv","version":2},"metadata":{"license":"","primary_cat":"cs.CV","submitted_at":"2003-12-19T18:41:29Z","cross_cats_sorted":["cond-mat.stat-mech","cs.AI","physics.data-an","q-bio.GN","q-bio.QM"],"title_canon_sha256":"88281e5f6beec4bdf03b5d3f86c49f4dd070bbac5d28def07e27cada6ed5902f","abstract_canon_sha256":"fcfb577b494ebf545c90d1b77b017182ea7699d9220c4bffe6b908319a9a0d71"},"schema_version":"1.0"},"canonical_sha256":"81b35243aa3d8b597f017b52501e0991c2daa3f0181be9440de90a702b38ad0e","source":{"kind":"arxiv","id":"cs/0312044","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"cs/0312044","created_at":"2026-07-04T14:49:38Z"},{"alias_kind":"arxiv_version","alias_value":"cs/0312044v2","created_at":"2026-07-04T14:49:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.cs/0312044","created_at":"2026-07-04T14:49:38Z"},{"alias_kind":"pith_short_12","alias_value":"QGZVEQ5KHWFV","created_at":"2026-07-04T14:49:38Z"},{"alias_kind":"pith_short_16","alias_value":"QGZVEQ5KHWFVS7YB","created_at":"2026-07-04T14:49:38Z"},{"alias_kind":"pith_short_8","alias_value":"QGZVEQ5K","created_at":"2026-07-04T14:49:38Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2003:QGZVEQ5KHWFVS7YBPNJFAHQJSH","target":"record","payload":{"canonical_record":{"source":{"id":"cs/0312044","kind":"arxiv","version":2},"metadata":{"license":"","primary_cat":"cs.CV","submitted_at":"2003-12-19T18:41:29Z","cross_cats_sorted":["cond-mat.stat-mech","cs.AI","physics.data-an","q-bio.GN","q-bio.QM"],"title_canon_sha256":"88281e5f6beec4bdf03b5d3f86c49f4dd070bbac5d28def07e27cada6ed5902f","abstract_canon_sha256":"fcfb577b494ebf545c90d1b77b017182ea7699d9220c4bffe6b908319a9a0d71"},"schema_version":"1.0"},"canonical_sha256":"81b35243aa3d8b597f017b52501e0991c2daa3f0181be9440de90a702b38ad0e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-04T14:49:38.971853Z","signature_b64":"j+Opf1OUbpb17uWVB/M/zIlSroDwiunvaATMX8UpksSlRBW8mHX7GZA9YGq1wSuvtmXZtywQi/JKHx38BWTHAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"81b35243aa3d8b597f017b52501e0991c2daa3f0181be9440de90a702b38ad0e","last_reissued_at":"2026-07-04T14:49:38.971511Z","signature_status":"signed_v1","first_computed_at":"2026-07-04T14:49:38.971511Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"cs/0312044","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-04T14:49:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mUt1xQeHbj3wa6WWIMK2wIMLE7KN0CejlUMO/NrIZGnfSC4o5OzbvAvIN7mpd09i2Fn7fSGKlilqnQhQHOhYCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T00:41:24.137978Z"},"content_sha256":"1936d5120c633cab87c6ab58cb14cee061c51a7d9d232ec547bc3a18c3b00f15","schema_version":"1.0","event_id":"sha256:1936d5120c633cab87c6ab58cb14cee061c51a7d9d232ec547bc3a18c3b00f15"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2003:QGZVEQ5KHWFVS7YBPNJFAHQJSH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Clustering by compression","license":"","headline":"","cross_cats":["cond-mat.stat-mech","cs.AI","physics.data-an","q-bio.GN","q-bio.QM"],"primary_cat":"cs.CV","authors_text":"Paul Vitanyi (CWI, Rudi Cilibrasi (CWI), University of Amsterdam)","submitted_at":"2003-12-19T18:41:29Z","abstract_excerpt":"We present a new method for clustering based on compression. The method doesn't use subject-specific features or background knowledge, and works as follows: First, we determine a universal similarity distance, the normalized compression distance or NCD, computed from the lengths of compressed data files (singly and in pairwise concatenation). Second, we apply a hierarchical clustering method. The NCD is universal in that it is not restricted to a specific application area, and works across application area boundaries. A theoretical precursor, the normalized information distance, co-developed b"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"cs/0312044","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/0312044/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-04T14:49:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UjbLXmaNA+jVlz5zCZyA2SzVSpVtbwDxw3pPJTrK7gIMKK3igbbN0awigwjLAl/hEX6gYlGPxm8G1ZAlAlwaBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T00:41:24.138488Z"},"content_sha256":"c3d1b621065e5f5e9bc078ad55814bf16b7731fe085a9d5d7dc490ef51f9fe8c","schema_version":"1.0","event_id":"sha256:c3d1b621065e5f5e9bc078ad55814bf16b7731fe085a9d5d7dc490ef51f9fe8c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QGZVEQ5KHWFVS7YBPNJFAHQJSH/bundle.json","state_url":"https://pith.science/pith/QGZVEQ5KHWFVS7YBPNJFAHQJSH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QGZVEQ5KHWFVS7YBPNJFAHQJSH/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":"2026-08-20T00:41:24Z","links":{"resolver":"https://pith.science/pith/QGZVEQ5KHWFVS7YBPNJFAHQJSH","bundle":"https://pith.science/pith/QGZVEQ5KHWFVS7YBPNJFAHQJSH/bundle.json","state":"https://pith.science/pith/QGZVEQ5KHWFVS7YBPNJFAHQJSH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QGZVEQ5KHWFVS7YBPNJFAHQJSH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2003:QGZVEQ5KHWFVS7YBPNJFAHQJSH","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":"fcfb577b494ebf545c90d1b77b017182ea7699d9220c4bffe6b908319a9a0d71","cross_cats_sorted":["cond-mat.stat-mech","cs.AI","physics.data-an","q-bio.GN","q-bio.QM"],"license":"","primary_cat":"cs.CV","submitted_at":"2003-12-19T18:41:29Z","title_canon_sha256":"88281e5f6beec4bdf03b5d3f86c49f4dd070bbac5d28def07e27cada6ed5902f"},"schema_version":"1.0","source":{"id":"cs/0312044","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"cs/0312044","created_at":"2026-07-04T14:49:38Z"},{"alias_kind":"arxiv_version","alias_value":"cs/0312044v2","created_at":"2026-07-04T14:49:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.cs/0312044","created_at":"2026-07-04T14:49:38Z"},{"alias_kind":"pith_short_12","alias_value":"QGZVEQ5KHWFV","created_at":"2026-07-04T14:49:38Z"},{"alias_kind":"pith_short_16","alias_value":"QGZVEQ5KHWFVS7YB","created_at":"2026-07-04T14:49:38Z"},{"alias_kind":"pith_short_8","alias_value":"QGZVEQ5K","created_at":"2026-07-04T14:49:38Z"}],"graph_snapshots":[{"event_id":"sha256:c3d1b621065e5f5e9bc078ad55814bf16b7731fe085a9d5d7dc490ef51f9fe8c","target":"graph","created_at":"2026-07-04T14:49:38Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/cs/0312044/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present a new method for clustering based on compression. The method doesn't use subject-specific features or background knowledge, and works as follows: First, we determine a universal similarity distance, the normalized compression distance or NCD, computed from the lengths of compressed data files (singly and in pairwise concatenation). Second, we apply a hierarchical clustering method. The NCD is universal in that it is not restricted to a specific application area, and works across application area boundaries. A theoretical precursor, the normalized information distance, co-developed b","authors_text":"Paul Vitanyi (CWI, Rudi Cilibrasi (CWI), University of Amsterdam)","cross_cats":["cond-mat.stat-mech","cs.AI","physics.data-an","q-bio.GN","q-bio.QM"],"headline":"","license":"","primary_cat":"cs.CV","submitted_at":"2003-12-19T18:41:29Z","title":"Clustering by compression"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"cs/0312044","kind":"arxiv","version":2},"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":"sha256:1936d5120c633cab87c6ab58cb14cee061c51a7d9d232ec547bc3a18c3b00f15","target":"record","created_at":"2026-07-04T14:49:38Z","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":"fcfb577b494ebf545c90d1b77b017182ea7699d9220c4bffe6b908319a9a0d71","cross_cats_sorted":["cond-mat.stat-mech","cs.AI","physics.data-an","q-bio.GN","q-bio.QM"],"license":"","primary_cat":"cs.CV","submitted_at":"2003-12-19T18:41:29Z","title_canon_sha256":"88281e5f6beec4bdf03b5d3f86c49f4dd070bbac5d28def07e27cada6ed5902f"},"schema_version":"1.0","source":{"id":"cs/0312044","kind":"arxiv","version":2}},"canonical_sha256":"81b35243aa3d8b597f017b52501e0991c2daa3f0181be9440de90a702b38ad0e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"81b35243aa3d8b597f017b52501e0991c2daa3f0181be9440de90a702b38ad0e","first_computed_at":"2026-07-04T14:49:38.971511Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-04T14:49:38.971511Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"j+Opf1OUbpb17uWVB/M/zIlSroDwiunvaATMX8UpksSlRBW8mHX7GZA9YGq1wSuvtmXZtywQi/JKHx38BWTHAA==","signature_status":"signed_v1","signed_at":"2026-07-04T14:49:38.971853Z","signed_message":"canonical_sha256_bytes"},"source_id":"cs/0312044","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1936d5120c633cab87c6ab58cb14cee061c51a7d9d232ec547bc3a18c3b00f15","sha256:c3d1b621065e5f5e9bc078ad55814bf16b7731fe085a9d5d7dc490ef51f9fe8c"],"state_sha256":"d9f41f829ca0f57cad4ed459df6b8c8595692f68df9690f5511f5709386d3ec4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fLv1jLZTm5E+diiYs9yyhxZgHKMdXNLdBn3CED3WrZZAm26Z9f1umGAYi3caBsJvflX9oeFzDuEBs3b7P+dDDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-20T00:41:24.144127Z","bundle_sha256":"83d5513454f8dc9beb4bf46a06293b194ec769886a6d3bf07fcd3104700575d9"}}