{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:EL5EKZWEBAMOHNUCXSPJG22XIU","short_pith_number":"pith:EL5EKZWE","canonical_record":{"source":{"id":"2108.00895","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-07-30T12:02:33Z","cross_cats_sorted":["cs.AI","cs.DS"],"title_canon_sha256":"27e82a7fe3557cd8a4325c7f09d897dbd991ce8ac5f46072a01dd02720135e92","abstract_canon_sha256":"7ea9ddb636c320f5384cc76635cef7015fe5b5e159171bbef9569e52e56b4533"},"schema_version":"1.0"},"canonical_sha256":"22fa4566c40818e3b682bc9e936b574515f7170f1c0f15055595eea3b782e273","source":{"kind":"arxiv","id":"2108.00895","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2108.00895","created_at":"2026-07-05T03:02:27Z"},{"alias_kind":"arxiv_version","alias_value":"2108.00895v1","created_at":"2026-07-05T03:02:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.00895","created_at":"2026-07-05T03:02:27Z"},{"alias_kind":"pith_short_12","alias_value":"EL5EKZWEBAMO","created_at":"2026-07-05T03:02:27Z"},{"alias_kind":"pith_short_16","alias_value":"EL5EKZWEBAMOHNUC","created_at":"2026-07-05T03:02:27Z"},{"alias_kind":"pith_short_8","alias_value":"EL5EKZWE","created_at":"2026-07-05T03:02:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:EL5EKZWEBAMOHNUCXSPJG22XIU","target":"record","payload":{"canonical_record":{"source":{"id":"2108.00895","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-07-30T12:02:33Z","cross_cats_sorted":["cs.AI","cs.DS"],"title_canon_sha256":"27e82a7fe3557cd8a4325c7f09d897dbd991ce8ac5f46072a01dd02720135e92","abstract_canon_sha256":"7ea9ddb636c320f5384cc76635cef7015fe5b5e159171bbef9569e52e56b4533"},"schema_version":"1.0"},"canonical_sha256":"22fa4566c40818e3b682bc9e936b574515f7170f1c0f15055595eea3b782e273","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:02:27.965777Z","signature_b64":"b8WSvKteLLzhRjOzL9N4VQ5ZUHeORrHsvNT/HkuM50TKLqjTpINE0XEYyVaHFSHZGOiqUgHt5/YCXA11JIqIBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"22fa4566c40818e3b682bc9e936b574515f7170f1c0f15055595eea3b782e273","last_reissued_at":"2026-07-05T03:02:27.965364Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:02:27.965364Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2108.00895","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":"2026-07-05T03:02:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/uOnh1ETpleGWC8t4KiotzSs5CtArnlDUCG34YwovTjy/TwcLgv7ZmnS5DCEqkOWTmAviDwryPUHuHOnNPraCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T22:35:40.860615Z"},"content_sha256":"b4cdf73c343a3349102f54c62a7d54ab784c800b9d11495d1c67ee6eec183bd7","schema_version":"1.0","event_id":"sha256:b4cdf73c343a3349102f54c62a7d54ab784c800b9d11495d1c67ee6eec183bd7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:EL5EKZWEBAMOHNUCXSPJG22XIU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Efficient Sparse Spherical k-Means for Document Clustering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.DS"],"primary_cat":"cs.LG","authors_text":"Johannes Knittel, Steffen Koch, Thomas Ertl","submitted_at":"2021-07-30T12:02:33Z","abstract_excerpt":"Spherical k-Means is frequently used to cluster document collections because it performs reasonably well in many settings and is computationally efficient. However, the time complexity increases linearly with the number of clusters k, which limits the suitability of the algorithm for larger values of k depending on the size of the collection. Optimizations targeted at the Euclidean k-Means algorithm largely do not apply because the cosine distance is not a metric. We therefore propose an efficient indexing structure to improve the scalability of Spherical k-Means with respect to k. Our approac"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.00895","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/2108.00895/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":"2026-07-05T03:02:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Xvu/kBE9MV9UG2V/kh+Y+dTuEsbFYv7sJLxQaQ9osV/1VTG80d9ypMnTlMEglPMJ4ZoEyiKnRbNmyR5hKC+6Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T22:35:40.861110Z"},"content_sha256":"bb763230616700fa4c35a4defebccc44d478b226005f7642779f16875ec569b2","schema_version":"1.0","event_id":"sha256:bb763230616700fa4c35a4defebccc44d478b226005f7642779f16875ec569b2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EL5EKZWEBAMOHNUCXSPJG22XIU/bundle.json","state_url":"https://pith.science/pith/EL5EKZWEBAMOHNUCXSPJG22XIU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EL5EKZWEBAMOHNUCXSPJG22XIU/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":"2026-08-03T22:35:40Z","links":{"resolver":"https://pith.science/pith/EL5EKZWEBAMOHNUCXSPJG22XIU","bundle":"https://pith.science/pith/EL5EKZWEBAMOHNUCXSPJG22XIU/bundle.json","state":"https://pith.science/pith/EL5EKZWEBAMOHNUCXSPJG22XIU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EL5EKZWEBAMOHNUCXSPJG22XIU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:EL5EKZWEBAMOHNUCXSPJG22XIU","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":"7ea9ddb636c320f5384cc76635cef7015fe5b5e159171bbef9569e52e56b4533","cross_cats_sorted":["cs.AI","cs.DS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-07-30T12:02:33Z","title_canon_sha256":"27e82a7fe3557cd8a4325c7f09d897dbd991ce8ac5f46072a01dd02720135e92"},"schema_version":"1.0","source":{"id":"2108.00895","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2108.00895","created_at":"2026-07-05T03:02:27Z"},{"alias_kind":"arxiv_version","alias_value":"2108.00895v1","created_at":"2026-07-05T03:02:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.00895","created_at":"2026-07-05T03:02:27Z"},{"alias_kind":"pith_short_12","alias_value":"EL5EKZWEBAMO","created_at":"2026-07-05T03:02:27Z"},{"alias_kind":"pith_short_16","alias_value":"EL5EKZWEBAMOHNUC","created_at":"2026-07-05T03:02:27Z"},{"alias_kind":"pith_short_8","alias_value":"EL5EKZWE","created_at":"2026-07-05T03:02:27Z"}],"graph_snapshots":[{"event_id":"sha256:bb763230616700fa4c35a4defebccc44d478b226005f7642779f16875ec569b2","target":"graph","created_at":"2026-07-05T03:02:27Z","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/2108.00895/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Spherical k-Means is frequently used to cluster document collections because it performs reasonably well in many settings and is computationally efficient. However, the time complexity increases linearly with the number of clusters k, which limits the suitability of the algorithm for larger values of k depending on the size of the collection. Optimizations targeted at the Euclidean k-Means algorithm largely do not apply because the cosine distance is not a metric. We therefore propose an efficient indexing structure to improve the scalability of Spherical k-Means with respect to k. Our approac","authors_text":"Johannes Knittel, Steffen Koch, Thomas Ertl","cross_cats":["cs.AI","cs.DS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-07-30T12:02:33Z","title":"Efficient Sparse Spherical k-Means for Document Clustering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.00895","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:b4cdf73c343a3349102f54c62a7d54ab784c800b9d11495d1c67ee6eec183bd7","target":"record","created_at":"2026-07-05T03:02:27Z","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":"7ea9ddb636c320f5384cc76635cef7015fe5b5e159171bbef9569e52e56b4533","cross_cats_sorted":["cs.AI","cs.DS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-07-30T12:02:33Z","title_canon_sha256":"27e82a7fe3557cd8a4325c7f09d897dbd991ce8ac5f46072a01dd02720135e92"},"schema_version":"1.0","source":{"id":"2108.00895","kind":"arxiv","version":1}},"canonical_sha256":"22fa4566c40818e3b682bc9e936b574515f7170f1c0f15055595eea3b782e273","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"22fa4566c40818e3b682bc9e936b574515f7170f1c0f15055595eea3b782e273","first_computed_at":"2026-07-05T03:02:27.965364Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:02:27.965364Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"b8WSvKteLLzhRjOzL9N4VQ5ZUHeORrHsvNT/HkuM50TKLqjTpINE0XEYyVaHFSHZGOiqUgHt5/YCXA11JIqIBw==","signature_status":"signed_v1","signed_at":"2026-07-05T03:02:27.965777Z","signed_message":"canonical_sha256_bytes"},"source_id":"2108.00895","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b4cdf73c343a3349102f54c62a7d54ab784c800b9d11495d1c67ee6eec183bd7","sha256:bb763230616700fa4c35a4defebccc44d478b226005f7642779f16875ec569b2"],"state_sha256":"d55de6925083cc5b1192e88869be8462434cce286ce51065b35463d4272c4831"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"r8sKnB27fVVq2H6wxz8OGH0/hTaSu+EGlltWsRNQaHjM0jfp54mcON4r3xI4OjBUx9YseGe2lakPQLPQMfY+Bw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T22:35:40.864446Z","bundle_sha256":"bd7b32887d5c6f3c717bd42891250ae6053f7fc523ccac5210815c289e5a7a28"}}