{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2015:ERFNB4XDNMIKDBYGOSUDQ2ASQE","short_pith_number":"pith:ERFNB4XD","canonical_record":{"source":{"id":"1507.03067","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DS","submitted_at":"2015-07-11T06:21:19Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"d75a02b64be97262200d4bc056dd0389f08c61785d2b2e1e8ef101198f7cca2c","abstract_canon_sha256":"f7f25bd0e9c1647a5c5a1ff5328fa7774a940fa7b4bc4ddc0c1de9b1b3d916c0"},"schema_version":"1.0"},"canonical_sha256":"244ad0f2e36b10a1870674a8386812811c8bdb54fd39255f1cfdbc18548babc4","source":{"kind":"arxiv","id":"1507.03067","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1507.03067","created_at":"2026-05-18T01:12:55Z"},{"alias_kind":"arxiv_version","alias_value":"1507.03067v2","created_at":"2026-05-18T01:12:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1507.03067","created_at":"2026-05-18T01:12:55Z"},{"alias_kind":"pith_short_12","alias_value":"ERFNB4XDNMIK","created_at":"2026-05-18T12:29:19Z"},{"alias_kind":"pith_short_16","alias_value":"ERFNB4XDNMIKDBYG","created_at":"2026-05-18T12:29:19Z"},{"alias_kind":"pith_short_8","alias_value":"ERFNB4XD","created_at":"2026-05-18T12:29:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2015:ERFNB4XDNMIKDBYGOSUDQ2ASQE","target":"record","payload":{"canonical_record":{"source":{"id":"1507.03067","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DS","submitted_at":"2015-07-11T06:21:19Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"d75a02b64be97262200d4bc056dd0389f08c61785d2b2e1e8ef101198f7cca2c","abstract_canon_sha256":"f7f25bd0e9c1647a5c5a1ff5328fa7774a940fa7b4bc4ddc0c1de9b1b3d916c0"},"schema_version":"1.0"},"canonical_sha256":"244ad0f2e36b10a1870674a8386812811c8bdb54fd39255f1cfdbc18548babc4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:12:55.381480Z","signature_b64":"sajgQ/LCbwbkhfnZeN90e4lxRK9NOYiM3BN6JsfCKI6WMH2ddmRs//GUwu4rV+fDuTEU4Kg0sEUzdfzj+YMtBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"244ad0f2e36b10a1870674a8386812811c8bdb54fd39255f1cfdbc18548babc4","last_reissued_at":"2026-05-18T01:12:55.381133Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:12:55.381133Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1507.03067","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":"2026-05-18T01:12:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CQTqAfFX9FDn8IJ4nbGk/poZOidQDn2DMyTX9EuaMIbiwb68GG89qdpcXq6AV54dFfRJSufBm908BXUFeAyUBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T19:05:44.100096Z"},"content_sha256":"f5be65d8b7c71e707669dd25f1e0cac91ddbd3d8f28735617b1423e0938d1af9","schema_version":"1.0","event_id":"sha256:f5be65d8b7c71e707669dd25f1e0cac91ddbd3d8f28735617b1423e0938d1af9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2015:ERFNB4XDNMIKDBYGOSUDQ2ASQE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Micro-Clustering: Finding Small Clusters in Large Diversity","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.DS","authors_text":"Hiroki Maegawa, Makoto Tatsuta, Ryo Yoshinaka, Takanobu Nakahara, Takeaki Uno, Yukinobu Hamuro","submitted_at":"2015-07-11T06:21:19Z","abstract_excerpt":"We address the problem of un-supervised soft-clustering called micro-clustering. The aim of the problem is to enumerate all groups composed of records strongly related to each other, while standard clustering methods separate records at sparse parts. The problem formulation of micro-clustering is non-trivial. Clique mining in a similarity graph is a typical approach, but it results in a huge number of cliques that are of many similar cliques. We propose a new concept data polishing. The cause of huge solutions can be considered that the groups are not clear in the data, that is, the boundaries"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1507.03067","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":""},"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":"2026-05-18T01:12:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/BGx7bSupYBjxDUCmusqEtUa3oncWasgD7pQGjdDDH3T1SMWMECS4HY5t9JgUhvpPgYxgyWe5GGCArZaHSiuCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T19:05:44.100813Z"},"content_sha256":"d043c54eb91dae7a4cf4cf08da436035f011263f1d89ac57b54a9b8e0b77406f","schema_version":"1.0","event_id":"sha256:d043c54eb91dae7a4cf4cf08da436035f011263f1d89ac57b54a9b8e0b77406f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ERFNB4XDNMIKDBYGOSUDQ2ASQE/bundle.json","state_url":"https://pith.science/pith/ERFNB4XDNMIKDBYGOSUDQ2ASQE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ERFNB4XDNMIKDBYGOSUDQ2ASQE/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":"2026-05-28T19:05:44Z","links":{"resolver":"https://pith.science/pith/ERFNB4XDNMIKDBYGOSUDQ2ASQE","bundle":"https://pith.science/pith/ERFNB4XDNMIKDBYGOSUDQ2ASQE/bundle.json","state":"https://pith.science/pith/ERFNB4XDNMIKDBYGOSUDQ2ASQE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ERFNB4XDNMIKDBYGOSUDQ2ASQE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:ERFNB4XDNMIKDBYGOSUDQ2ASQE","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":"f7f25bd0e9c1647a5c5a1ff5328fa7774a940fa7b4bc4ddc0c1de9b1b3d916c0","cross_cats_sorted":["cs.IR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DS","submitted_at":"2015-07-11T06:21:19Z","title_canon_sha256":"d75a02b64be97262200d4bc056dd0389f08c61785d2b2e1e8ef101198f7cca2c"},"schema_version":"1.0","source":{"id":"1507.03067","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1507.03067","created_at":"2026-05-18T01:12:55Z"},{"alias_kind":"arxiv_version","alias_value":"1507.03067v2","created_at":"2026-05-18T01:12:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1507.03067","created_at":"2026-05-18T01:12:55Z"},{"alias_kind":"pith_short_12","alias_value":"ERFNB4XDNMIK","created_at":"2026-05-18T12:29:19Z"},{"alias_kind":"pith_short_16","alias_value":"ERFNB4XDNMIKDBYG","created_at":"2026-05-18T12:29:19Z"},{"alias_kind":"pith_short_8","alias_value":"ERFNB4XD","created_at":"2026-05-18T12:29:19Z"}],"graph_snapshots":[{"event_id":"sha256:d043c54eb91dae7a4cf4cf08da436035f011263f1d89ac57b54a9b8e0b77406f","target":"graph","created_at":"2026-05-18T01:12:55Z","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":"We address the problem of un-supervised soft-clustering called micro-clustering. The aim of the problem is to enumerate all groups composed of records strongly related to each other, while standard clustering methods separate records at sparse parts. The problem formulation of micro-clustering is non-trivial. Clique mining in a similarity graph is a typical approach, but it results in a huge number of cliques that are of many similar cliques. We propose a new concept data polishing. The cause of huge solutions can be considered that the groups are not clear in the data, that is, the boundaries","authors_text":"Hiroki Maegawa, Makoto Tatsuta, Ryo Yoshinaka, Takanobu Nakahara, Takeaki Uno, Yukinobu Hamuro","cross_cats":["cs.IR"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DS","submitted_at":"2015-07-11T06:21:19Z","title":"Micro-Clustering: Finding Small Clusters in Large Diversity"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1507.03067","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:f5be65d8b7c71e707669dd25f1e0cac91ddbd3d8f28735617b1423e0938d1af9","target":"record","created_at":"2026-05-18T01:12:55Z","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":"f7f25bd0e9c1647a5c5a1ff5328fa7774a940fa7b4bc4ddc0c1de9b1b3d916c0","cross_cats_sorted":["cs.IR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DS","submitted_at":"2015-07-11T06:21:19Z","title_canon_sha256":"d75a02b64be97262200d4bc056dd0389f08c61785d2b2e1e8ef101198f7cca2c"},"schema_version":"1.0","source":{"id":"1507.03067","kind":"arxiv","version":2}},"canonical_sha256":"244ad0f2e36b10a1870674a8386812811c8bdb54fd39255f1cfdbc18548babc4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"244ad0f2e36b10a1870674a8386812811c8bdb54fd39255f1cfdbc18548babc4","first_computed_at":"2026-05-18T01:12:55.381133Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:12:55.381133Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"sajgQ/LCbwbkhfnZeN90e4lxRK9NOYiM3BN6JsfCKI6WMH2ddmRs//GUwu4rV+fDuTEU4Kg0sEUzdfzj+YMtBA==","signature_status":"signed_v1","signed_at":"2026-05-18T01:12:55.381480Z","signed_message":"canonical_sha256_bytes"},"source_id":"1507.03067","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f5be65d8b7c71e707669dd25f1e0cac91ddbd3d8f28735617b1423e0938d1af9","sha256:d043c54eb91dae7a4cf4cf08da436035f011263f1d89ac57b54a9b8e0b77406f"],"state_sha256":"0490e0bcd50beb6b687f1296a57c17dc69b617672fad6b996637ce968cd269e9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tHBQN4x4NYzk6yNG7Eh8t+lnPKpJ7EzI9nNcP0dZki1STKqvY1xMkKs3cdOulnCv6SeROGmj6QoRdc3biTgcBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T19:05:44.104403Z","bundle_sha256":"7ab4571a501855c1700bc376246abb7abeab04dcaa5592f436fb75b97ac6e30b"}}