{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:M6MPXTKLKGMI5H4LKFLL6DL6HM","short_pith_number":"pith:M6MPXTKL","canonical_record":{"source":{"id":"2505.22991","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-29T01:58:44Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"071f704d158782c2a690802816e1a2eea25bf66594d985676978a83a126a17f0","abstract_canon_sha256":"fb47e4aba98561c5565a209aa78c05b51042fa689f54f4e8202990c9d565d928"},"schema_version":"1.0"},"canonical_sha256":"6798fbcd4b51988e9f8b5156bf0d7e3b3586a39c01c11cff8ac470ded9358031","source":{"kind":"arxiv","id":"2505.22991","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.22991","created_at":"2026-07-05T11:11:53Z"},{"alias_kind":"arxiv_version","alias_value":"2505.22991v1","created_at":"2026-07-05T11:11:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.22991","created_at":"2026-07-05T11:11:53Z"},{"alias_kind":"pith_short_12","alias_value":"M6MPXTKLKGMI","created_at":"2026-07-05T11:11:53Z"},{"alias_kind":"pith_short_16","alias_value":"M6MPXTKLKGMI5H4L","created_at":"2026-07-05T11:11:53Z"},{"alias_kind":"pith_short_8","alias_value":"M6MPXTKL","created_at":"2026-07-05T11:11:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:M6MPXTKLKGMI5H4LKFLL6DL6HM","target":"record","payload":{"canonical_record":{"source":{"id":"2505.22991","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-29T01:58:44Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"071f704d158782c2a690802816e1a2eea25bf66594d985676978a83a126a17f0","abstract_canon_sha256":"fb47e4aba98561c5565a209aa78c05b51042fa689f54f4e8202990c9d565d928"},"schema_version":"1.0"},"canonical_sha256":"6798fbcd4b51988e9f8b5156bf0d7e3b3586a39c01c11cff8ac470ded9358031","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:11:53.157870Z","signature_b64":"BtWPcZtUOkg/fS/ZsyA5vbGs4HMeCmIOXF+aqscVW5QMwBBYEtCrkOHrlNucBUQHzGm2Ouoi3Sj21woxX4lrDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6798fbcd4b51988e9f8b5156bf0d7e3b3586a39c01c11cff8ac470ded9358031","last_reissued_at":"2026-07-05T11:11:53.157388Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:11:53.157388Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.22991","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":"2026-07-05T11:11:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QMxGevGv/CPGB9oEsIw/AUImZ0vp2+y269Rbi6QcrFMaaipurO0yJ3OKUBX1daokB1cM6p76Q4fadTvsfvb1AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T20:58:02.586112Z"},"content_sha256":"fdd65a1751d6ee8c7d8f47572bb709b933233d97559405dd71b6a41140137682","schema_version":"1.0","event_id":"sha256:fdd65a1751d6ee8c7d8f47572bb709b933233d97559405dd71b6a41140137682"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:M6MPXTKLKGMI5H4LKFLL6DL6HM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Number of Clusters in a Dataset: A Regularized K-means Approach","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Behrooz Kamgar-Parsi, Behzad Kamgar-Parsi","submitted_at":"2025-05-29T01:58:44Z","abstract_excerpt":"Finding the number of meaningful clusters in an unlabeled dataset is important in many applications. Regularized k-means algorithm is a possible approach frequently used to find the correct number of distinct clusters in datasets. The most common formulation of the regularization function is the additive linear term $\\lambda k$, where $k$ is the number of clusters and $\\lambda$ a positive coefficient. Currently, there are no principled guidelines for setting a value for the critical hyperparameter $\\lambda$. In this paper, we derive rigorous bounds for $\\lambda$ assuming clusters are {\\em idea"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.22991","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/2505.22991/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":"2026-07-05T11:11:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Io7yXEiCcj95IGb0WJ6x1mAdbHWGchHV5Oq8hF6OP8C9ZbK2+hy0I+HNj7EdWovHnHsIeIZ2FHZzGpwtmDPNAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T20:58:02.586621Z"},"content_sha256":"e1c93e39e148d278a8d615591c362650ac00c84c2a9816bb4f76c7c816f30a07","schema_version":"1.0","event_id":"sha256:e1c93e39e148d278a8d615591c362650ac00c84c2a9816bb4f76c7c816f30a07"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/M6MPXTKLKGMI5H4LKFLL6DL6HM/bundle.json","state_url":"https://pith.science/pith/M6MPXTKLKGMI5H4LKFLL6DL6HM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/M6MPXTKLKGMI5H4LKFLL6DL6HM/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":"2026-08-07T20:58:02Z","links":{"resolver":"https://pith.science/pith/M6MPXTKLKGMI5H4LKFLL6DL6HM","bundle":"https://pith.science/pith/M6MPXTKLKGMI5H4LKFLL6DL6HM/bundle.json","state":"https://pith.science/pith/M6MPXTKLKGMI5H4LKFLL6DL6HM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/M6MPXTKLKGMI5H4LKFLL6DL6HM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:M6MPXTKLKGMI5H4LKFLL6DL6HM","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":"fb47e4aba98561c5565a209aa78c05b51042fa689f54f4e8202990c9d565d928","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-29T01:58:44Z","title_canon_sha256":"071f704d158782c2a690802816e1a2eea25bf66594d985676978a83a126a17f0"},"schema_version":"1.0","source":{"id":"2505.22991","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.22991","created_at":"2026-07-05T11:11:53Z"},{"alias_kind":"arxiv_version","alias_value":"2505.22991v1","created_at":"2026-07-05T11:11:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.22991","created_at":"2026-07-05T11:11:53Z"},{"alias_kind":"pith_short_12","alias_value":"M6MPXTKLKGMI","created_at":"2026-07-05T11:11:53Z"},{"alias_kind":"pith_short_16","alias_value":"M6MPXTKLKGMI5H4L","created_at":"2026-07-05T11:11:53Z"},{"alias_kind":"pith_short_8","alias_value":"M6MPXTKL","created_at":"2026-07-05T11:11:53Z"}],"graph_snapshots":[{"event_id":"sha256:e1c93e39e148d278a8d615591c362650ac00c84c2a9816bb4f76c7c816f30a07","target":"graph","created_at":"2026-07-05T11:11:53Z","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/2505.22991/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Finding the number of meaningful clusters in an unlabeled dataset is important in many applications. Regularized k-means algorithm is a possible approach frequently used to find the correct number of distinct clusters in datasets. The most common formulation of the regularization function is the additive linear term $\\lambda k$, where $k$ is the number of clusters and $\\lambda$ a positive coefficient. Currently, there are no principled guidelines for setting a value for the critical hyperparameter $\\lambda$. In this paper, we derive rigorous bounds for $\\lambda$ assuming clusters are {\\em idea","authors_text":"Behrooz Kamgar-Parsi, Behzad Kamgar-Parsi","cross_cats":["cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-29T01:58:44Z","title":"Number of Clusters in a Dataset: A Regularized K-means Approach"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.22991","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:fdd65a1751d6ee8c7d8f47572bb709b933233d97559405dd71b6a41140137682","target":"record","created_at":"2026-07-05T11:11:53Z","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":"fb47e4aba98561c5565a209aa78c05b51042fa689f54f4e8202990c9d565d928","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-29T01:58:44Z","title_canon_sha256":"071f704d158782c2a690802816e1a2eea25bf66594d985676978a83a126a17f0"},"schema_version":"1.0","source":{"id":"2505.22991","kind":"arxiv","version":1}},"canonical_sha256":"6798fbcd4b51988e9f8b5156bf0d7e3b3586a39c01c11cff8ac470ded9358031","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6798fbcd4b51988e9f8b5156bf0d7e3b3586a39c01c11cff8ac470ded9358031","first_computed_at":"2026-07-05T11:11:53.157388Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:11:53.157388Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BtWPcZtUOkg/fS/ZsyA5vbGs4HMeCmIOXF+aqscVW5QMwBBYEtCrkOHrlNucBUQHzGm2Ouoi3Sj21woxX4lrDw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:11:53.157870Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.22991","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fdd65a1751d6ee8c7d8f47572bb709b933233d97559405dd71b6a41140137682","sha256:e1c93e39e148d278a8d615591c362650ac00c84c2a9816bb4f76c7c816f30a07"],"state_sha256":"c299b4a809c4b8c438b575d70f18fe7ce0d1371e021a03c3dd9b9ff1b1418a56"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"K+CKYPhGuVHA6vYPSLVmd5iovLNl2sZK7nM+omBfI2ReKhjB2S6I8VTT31Gnu7AqCe8oAirnH/K+9cCdj0O2BA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T20:58:02.591932Z","bundle_sha256":"d9180798ae8fd331d27ca5cb093a948448440f265f3f8f4687f3d58a79476de1"}}