{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:PAXIB36SNBZ3UFUFDYQE5BYREN","short_pith_number":"pith:PAXIB36S","canonical_record":{"source":{"id":"2606.27061","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-25T14:07:17Z","cross_cats_sorted":[],"title_canon_sha256":"9e0a9b0721a35e8799deb2948bd70e6b529a5bcea3ee975d3146333fee181e8b","abstract_canon_sha256":"2998046dff9debadef364fa955ad270ffa90370b6e4909341de7078bb1d1108d"},"schema_version":"1.0"},"canonical_sha256":"782e80efd26873ba16851e204e871123624131c78775c89416e0a0991f0e4049","source":{"kind":"arxiv","id":"2606.27061","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.27061","created_at":"2026-06-26T01:16:08Z"},{"alias_kind":"arxiv_version","alias_value":"2606.27061v1","created_at":"2026-06-26T01:16:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.27061","created_at":"2026-06-26T01:16:08Z"},{"alias_kind":"pith_short_12","alias_value":"PAXIB36SNBZ3","created_at":"2026-06-26T01:16:08Z"},{"alias_kind":"pith_short_16","alias_value":"PAXIB36SNBZ3UFUF","created_at":"2026-06-26T01:16:08Z"},{"alias_kind":"pith_short_8","alias_value":"PAXIB36S","created_at":"2026-06-26T01:16:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:PAXIB36SNBZ3UFUFDYQE5BYREN","target":"record","payload":{"canonical_record":{"source":{"id":"2606.27061","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-25T14:07:17Z","cross_cats_sorted":[],"title_canon_sha256":"9e0a9b0721a35e8799deb2948bd70e6b529a5bcea3ee975d3146333fee181e8b","abstract_canon_sha256":"2998046dff9debadef364fa955ad270ffa90370b6e4909341de7078bb1d1108d"},"schema_version":"1.0"},"canonical_sha256":"782e80efd26873ba16851e204e871123624131c78775c89416e0a0991f0e4049","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-26T01:16:08.495126Z","signature_b64":"GcOOQuf00u3Ig/ft3obCmsEDuQJd5GM72gZUpWnu2x4u5JFcGD9orAWXZzDg3py8KNCWCClAeV827fAGLsjNAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"782e80efd26873ba16851e204e871123624131c78775c89416e0a0991f0e4049","last_reissued_at":"2026-06-26T01:16:08.494720Z","signature_status":"signed_v1","first_computed_at":"2026-06-26T01:16:08.494720Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.27061","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":"2026-06-26T01:16:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aOxgFGyK3JCIuvyTWDaHS4eZLEMZrSfrhukcOCbLS4+RrW3baxF48W10/Hsn1IpQeeLvf9Pu7vqzFtz4JdtOBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T17:21:59.568462Z"},"content_sha256":"fd90736a874d4efec843adab24a6048e66007932a5c3a17c9ee6c183b3cf1be0","schema_version":"1.0","event_id":"sha256:fd90736a874d4efec843adab24a6048e66007932a5c3a17c9ee6c183b3cf1be0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:PAXIB36SNBZ3UFUFDYQE5BYREN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"How to evaluate clustering with ground truth?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Pasi Fr\\\"anti","submitted_at":"2026-06-25T14:07:17Z","abstract_excerpt":"External indexes can be used for cluster evaluation when ground truth is available. We review the most common external validity indexes focusing on set-matching-based measures. We recommend centroid index (CI), because it is an intuitive cluster-level measure with an explainable result. If we need a more fine-tuned, point-level measure, there are more choices. Pair-set index (PSI) provides a normalized score which is not biased by cluster sizes. If all points should matter equally, then clustering accuracy (ACC) or any other set-matching measure is suitable."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.27061","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2606.27061/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":"2026-06-26T01:16:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"g/ettZxapOTavDsDND6ynTAkzUpmAqpQn/PScgQtJAlL0yNUPOc8Qyi9nhAdejbFgiMkMwDB68fGVIkK6rs6AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T17:21:59.568944Z"},"content_sha256":"34ea8bff07004f4e5c442b035cea59878831f94e1194eae0639b0498d17ff31a","schema_version":"1.0","event_id":"sha256:34ea8bff07004f4e5c442b035cea59878831f94e1194eae0639b0498d17ff31a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PAXIB36SNBZ3UFUFDYQE5BYREN/bundle.json","state_url":"https://pith.science/pith/PAXIB36SNBZ3UFUFDYQE5BYREN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PAXIB36SNBZ3UFUFDYQE5BYREN/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":"2026-08-05T17:21:59Z","links":{"resolver":"https://pith.science/pith/PAXIB36SNBZ3UFUFDYQE5BYREN","bundle":"https://pith.science/pith/PAXIB36SNBZ3UFUFDYQE5BYREN/bundle.json","state":"https://pith.science/pith/PAXIB36SNBZ3UFUFDYQE5BYREN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PAXIB36SNBZ3UFUFDYQE5BYREN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:PAXIB36SNBZ3UFUFDYQE5BYREN","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":"2998046dff9debadef364fa955ad270ffa90370b6e4909341de7078bb1d1108d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-25T14:07:17Z","title_canon_sha256":"9e0a9b0721a35e8799deb2948bd70e6b529a5bcea3ee975d3146333fee181e8b"},"schema_version":"1.0","source":{"id":"2606.27061","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.27061","created_at":"2026-06-26T01:16:08Z"},{"alias_kind":"arxiv_version","alias_value":"2606.27061v1","created_at":"2026-06-26T01:16:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.27061","created_at":"2026-06-26T01:16:08Z"},{"alias_kind":"pith_short_12","alias_value":"PAXIB36SNBZ3","created_at":"2026-06-26T01:16:08Z"},{"alias_kind":"pith_short_16","alias_value":"PAXIB36SNBZ3UFUF","created_at":"2026-06-26T01:16:08Z"},{"alias_kind":"pith_short_8","alias_value":"PAXIB36S","created_at":"2026-06-26T01:16:08Z"}],"graph_snapshots":[{"event_id":"sha256:34ea8bff07004f4e5c442b035cea59878831f94e1194eae0639b0498d17ff31a","target":"graph","created_at":"2026-06-26T01:16:08Z","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/2606.27061/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"External indexes can be used for cluster evaluation when ground truth is available. We review the most common external validity indexes focusing on set-matching-based measures. We recommend centroid index (CI), because it is an intuitive cluster-level measure with an explainable result. If we need a more fine-tuned, point-level measure, there are more choices. Pair-set index (PSI) provides a normalized score which is not biased by cluster sizes. If all points should matter equally, then clustering accuracy (ACC) or any other set-matching measure is suitable.","authors_text":"Pasi Fr\\\"anti","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-25T14:07:17Z","title":"How to evaluate clustering with ground truth?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.27061","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:fd90736a874d4efec843adab24a6048e66007932a5c3a17c9ee6c183b3cf1be0","target":"record","created_at":"2026-06-26T01:16:08Z","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":"2998046dff9debadef364fa955ad270ffa90370b6e4909341de7078bb1d1108d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-25T14:07:17Z","title_canon_sha256":"9e0a9b0721a35e8799deb2948bd70e6b529a5bcea3ee975d3146333fee181e8b"},"schema_version":"1.0","source":{"id":"2606.27061","kind":"arxiv","version":1}},"canonical_sha256":"782e80efd26873ba16851e204e871123624131c78775c89416e0a0991f0e4049","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"782e80efd26873ba16851e204e871123624131c78775c89416e0a0991f0e4049","first_computed_at":"2026-06-26T01:16:08.494720Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-26T01:16:08.494720Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GcOOQuf00u3Ig/ft3obCmsEDuQJd5GM72gZUpWnu2x4u5JFcGD9orAWXZzDg3py8KNCWCClAeV827fAGLsjNAw==","signature_status":"signed_v1","signed_at":"2026-06-26T01:16:08.495126Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.27061","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fd90736a874d4efec843adab24a6048e66007932a5c3a17c9ee6c183b3cf1be0","sha256:34ea8bff07004f4e5c442b035cea59878831f94e1194eae0639b0498d17ff31a"],"state_sha256":"b227d6bc8e201b8c93f9b2be2cf3a1f698b6924953040da96de51f2610963679"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qIF4h4S93AVy1QYS5Br9PQIULv8foYxCD1mLIZDPAWCG5AczwN+nm6CkyMOSJNq2H/lvaFbex/Y8ErGsaUnWAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T17:21:59.572204Z","bundle_sha256":"f81d161db0cb53db37c06d37b937b4361971804ab70e2e7d9c3831f95dee0280"}}