{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:IRPAYV2HZOMVWOKHHCUR5YVX6Y","short_pith_number":"pith:IRPAYV2H","canonical_record":{"source":{"id":"2505.11904","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-17T08:41:07Z","cross_cats_sorted":["cs.AI","cs.IT","math.IT"],"title_canon_sha256":"769c511d7451f8920e09135fbcde99383bd917a2072dbd941f408a5862e7adc2","abstract_canon_sha256":"4305d1926043cc9172696682a4926e9d420c236ace7d4711d49214b93c74f90c"},"schema_version":"1.0"},"canonical_sha256":"445e0c5747cb995b394738a91ee2b7f615b20ee92a3de3e1fe03248398125d83","source":{"kind":"arxiv","id":"2505.11904","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.11904","created_at":"2026-07-05T11:04:54Z"},{"alias_kind":"arxiv_version","alias_value":"2505.11904v1","created_at":"2026-07-05T11:04:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.11904","created_at":"2026-07-05T11:04:54Z"},{"alias_kind":"pith_short_12","alias_value":"IRPAYV2HZOMV","created_at":"2026-07-05T11:04:54Z"},{"alias_kind":"pith_short_16","alias_value":"IRPAYV2HZOMVWOKH","created_at":"2026-07-05T11:04:54Z"},{"alias_kind":"pith_short_8","alias_value":"IRPAYV2H","created_at":"2026-07-05T11:04:54Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:IRPAYV2HZOMVWOKHHCUR5YVX6Y","target":"record","payload":{"canonical_record":{"source":{"id":"2505.11904","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-17T08:41:07Z","cross_cats_sorted":["cs.AI","cs.IT","math.IT"],"title_canon_sha256":"769c511d7451f8920e09135fbcde99383bd917a2072dbd941f408a5862e7adc2","abstract_canon_sha256":"4305d1926043cc9172696682a4926e9d420c236ace7d4711d49214b93c74f90c"},"schema_version":"1.0"},"canonical_sha256":"445e0c5747cb995b394738a91ee2b7f615b20ee92a3de3e1fe03248398125d83","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:04:54.319843Z","signature_b64":"95bQNK0XEnL5bzAgji2OPMbzC/HSNOekl5po92o2lMVGuO/saW8K4dKzp9JHjlHCzIoD+dkwBNd7gmaZahBEDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"445e0c5747cb995b394738a91ee2b7f615b20ee92a3de3e1fe03248398125d83","last_reissued_at":"2026-07-05T11:04:54.319170Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:04:54.319170Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.11904","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":"2026-07-05T11:04:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DGwn9BMBcNn0TatyQXWlHzhCXSYZUyGiM71487fQOvEq7iYqasg+2YpCRn2MtXvQ5RM917+RWQRgLpxJd1JuAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T23:35:46.854892Z"},"content_sha256":"e2e59a3284888898b9bda0f5c1c0338c3c8c21887602b258259d74b3826f17ad","schema_version":"1.0","event_id":"sha256:e2e59a3284888898b9bda0f5c1c0338c3c8c21887602b258259d74b3826f17ad"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:IRPAYV2HZOMVWOKHHCUR5YVX6Y","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"K*-Means: A Parameter-free Clustering Algorithm","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.IT","math.IT"],"primary_cat":"cs.LG","authors_text":"Louis Mahon, Mirella Lapata","submitted_at":"2025-05-17T08:41:07Z","abstract_excerpt":"Clustering is a widely used and powerful machine learning technique, but its effectiveness is often limited by the need to specify the number of clusters, k, or by relying on thresholds that implicitly determine k. We introduce k*-means, a novel clustering algorithm that eliminates the need to set k or any other parameters. Instead, it uses the minimum description length principle to automatically determine the optimal number of clusters, k*, by splitting and merging clusters while also optimising the standard k-means objective. We prove that k*-means is guaranteed to converge and demonstrate "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.11904","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/2505.11904/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":"2026-07-05T11:04:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3z0ncH+pZVjH2SzOPchP1JLg1/DqWc2TQJSKjpGfkqU2vDD2Y6v8NT3b8S0VYtp2wxjw3qcxT41qJmb7P7LbBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T23:35:46.855432Z"},"content_sha256":"e73c7f71d77d6ce4040c705ad6e4556994af3a9e93dd147e26ec86e2468ad3e0","schema_version":"1.0","event_id":"sha256:e73c7f71d77d6ce4040c705ad6e4556994af3a9e93dd147e26ec86e2468ad3e0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IRPAYV2HZOMVWOKHHCUR5YVX6Y/bundle.json","state_url":"https://pith.science/pith/IRPAYV2HZOMVWOKHHCUR5YVX6Y/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IRPAYV2HZOMVWOKHHCUR5YVX6Y/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":"2026-08-04T23:35:46Z","links":{"resolver":"https://pith.science/pith/IRPAYV2HZOMVWOKHHCUR5YVX6Y","bundle":"https://pith.science/pith/IRPAYV2HZOMVWOKHHCUR5YVX6Y/bundle.json","state":"https://pith.science/pith/IRPAYV2HZOMVWOKHHCUR5YVX6Y/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IRPAYV2HZOMVWOKHHCUR5YVX6Y/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:IRPAYV2HZOMVWOKHHCUR5YVX6Y","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":"4305d1926043cc9172696682a4926e9d420c236ace7d4711d49214b93c74f90c","cross_cats_sorted":["cs.AI","cs.IT","math.IT"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-17T08:41:07Z","title_canon_sha256":"769c511d7451f8920e09135fbcde99383bd917a2072dbd941f408a5862e7adc2"},"schema_version":"1.0","source":{"id":"2505.11904","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.11904","created_at":"2026-07-05T11:04:54Z"},{"alias_kind":"arxiv_version","alias_value":"2505.11904v1","created_at":"2026-07-05T11:04:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.11904","created_at":"2026-07-05T11:04:54Z"},{"alias_kind":"pith_short_12","alias_value":"IRPAYV2HZOMV","created_at":"2026-07-05T11:04:54Z"},{"alias_kind":"pith_short_16","alias_value":"IRPAYV2HZOMVWOKH","created_at":"2026-07-05T11:04:54Z"},{"alias_kind":"pith_short_8","alias_value":"IRPAYV2H","created_at":"2026-07-05T11:04:54Z"}],"graph_snapshots":[{"event_id":"sha256:e73c7f71d77d6ce4040c705ad6e4556994af3a9e93dd147e26ec86e2468ad3e0","target":"graph","created_at":"2026-07-05T11:04:54Z","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/2505.11904/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Clustering is a widely used and powerful machine learning technique, but its effectiveness is often limited by the need to specify the number of clusters, k, or by relying on thresholds that implicitly determine k. We introduce k*-means, a novel clustering algorithm that eliminates the need to set k or any other parameters. Instead, it uses the minimum description length principle to automatically determine the optimal number of clusters, k*, by splitting and merging clusters while also optimising the standard k-means objective. We prove that k*-means is guaranteed to converge and demonstrate ","authors_text":"Louis Mahon, Mirella Lapata","cross_cats":["cs.AI","cs.IT","math.IT"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-17T08:41:07Z","title":"K*-Means: A Parameter-free Clustering Algorithm"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.11904","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:e2e59a3284888898b9bda0f5c1c0338c3c8c21887602b258259d74b3826f17ad","target":"record","created_at":"2026-07-05T11:04:54Z","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":"4305d1926043cc9172696682a4926e9d420c236ace7d4711d49214b93c74f90c","cross_cats_sorted":["cs.AI","cs.IT","math.IT"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-17T08:41:07Z","title_canon_sha256":"769c511d7451f8920e09135fbcde99383bd917a2072dbd941f408a5862e7adc2"},"schema_version":"1.0","source":{"id":"2505.11904","kind":"arxiv","version":1}},"canonical_sha256":"445e0c5747cb995b394738a91ee2b7f615b20ee92a3de3e1fe03248398125d83","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"445e0c5747cb995b394738a91ee2b7f615b20ee92a3de3e1fe03248398125d83","first_computed_at":"2026-07-05T11:04:54.319170Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:04:54.319170Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"95bQNK0XEnL5bzAgji2OPMbzC/HSNOekl5po92o2lMVGuO/saW8K4dKzp9JHjlHCzIoD+dkwBNd7gmaZahBEDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:04:54.319843Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.11904","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e2e59a3284888898b9bda0f5c1c0338c3c8c21887602b258259d74b3826f17ad","sha256:e73c7f71d77d6ce4040c705ad6e4556994af3a9e93dd147e26ec86e2468ad3e0"],"state_sha256":"9618a75f92a3c8c3c94c6e6494b1e81db0683164fcd282a010d8d5737535b633"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HFV8wMWYQ/yOIYzWihcE3N1L8dmgTi+If2IJtfi5F0D2Le8ePEUA6SBdTp/8jqlZPEM2FYQHy2xHqA3eAxh1DA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T23:35:46.861083Z","bundle_sha256":"bdb857c64259917a59c632638dc6ff8d30886f534b42782e9f4aeea6bda0d6e2"}}