{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:E22USMWGJFFPVI2PRNEU74DXIC","short_pith_number":"pith:E22USMWG","canonical_record":{"source":{"id":"2607.04949","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-06T11:24:56Z","cross_cats_sorted":["cs.DS"],"title_canon_sha256":"65602cb3e699f6cda0da9ccb40974725aff28ded610c6360355c38ce8c1842a2","abstract_canon_sha256":"a1027d193179f2239dcdd85151de209db12d1aff0274a5e0b47d039c082132ad"},"schema_version":"1.0"},"canonical_sha256":"26b54932c6494afaa34f8b494ff077408e11f48568c88b9c75083a39017f2d28","source":{"kind":"arxiv","id":"2607.04949","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.04949","created_at":"2026-07-07T02:20:14Z"},{"alias_kind":"arxiv_version","alias_value":"2607.04949v1","created_at":"2026-07-07T02:20:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.04949","created_at":"2026-07-07T02:20:14Z"},{"alias_kind":"pith_short_12","alias_value":"E22USMWGJFFP","created_at":"2026-07-07T02:20:14Z"},{"alias_kind":"pith_short_16","alias_value":"E22USMWGJFFPVI2P","created_at":"2026-07-07T02:20:14Z"},{"alias_kind":"pith_short_8","alias_value":"E22USMWG","created_at":"2026-07-07T02:20:14Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:E22USMWGJFFPVI2PRNEU74DXIC","target":"record","payload":{"canonical_record":{"source":{"id":"2607.04949","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-06T11:24:56Z","cross_cats_sorted":["cs.DS"],"title_canon_sha256":"65602cb3e699f6cda0da9ccb40974725aff28ded610c6360355c38ce8c1842a2","abstract_canon_sha256":"a1027d193179f2239dcdd85151de209db12d1aff0274a5e0b47d039c082132ad"},"schema_version":"1.0"},"canonical_sha256":"26b54932c6494afaa34f8b494ff077408e11f48568c88b9c75083a39017f2d28","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-07T02:20:14.964164Z","signature_b64":"UnpyW4oYbr9O01TOoMZUNbZFCJuFsqo5y/7cKtjZQ8B3dKIbxH/b6FHFdsWlcrVZCVBTVqrRaDofV9lkiF2ICA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"26b54932c6494afaa34f8b494ff077408e11f48568c88b9c75083a39017f2d28","last_reissued_at":"2026-07-07T02:20:14.963325Z","signature_status":"signed_v1","first_computed_at":"2026-07-07T02:20:14.963325Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.04949","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":"2026-07-07T02:20:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IBQYyTSLwukJ5WZXPTCx29744iG/fK0QMOojquzLcpQjsyvO2b9ZFa+B0WodncTYIDHFsl+ab0DJlW52LwteBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T12:59:00.710251Z"},"content_sha256":"ac3b5d1abe57b46b7546f390cdd044cb7693d267069c66c7077c0ff460e54c82","schema_version":"1.0","event_id":"sha256:ac3b5d1abe57b46b7546f390cdd044cb7693d267069c66c7077c0ff460e54c82"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:E22USMWGJFFPVI2PRNEU74DXIC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Sensitivity Sampling with Predictions for k-Means Clustering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DS"],"primary_cat":"cs.LG","authors_text":"Cristian Boldrin, Fabio Vandin","submitted_at":"2026-07-06T11:24:56Z","abstract_excerpt":"We study the problem of k-means clustering on large datasets. The state-of-the-art for the problem is given by coresets-based approaches, which build small weighted summaries of the input and derive approximate solutions with rigorous quality guarantees from them. One of the most popular and advanced approaches to derive coresets for k-means is sensitivity sampling. However, sensitivity sampling requires to compute the importance of each input point with respect to the whole dataset over all possible choices of centers. Since the exact computation of such quantities is unfeasible, current appr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.04949","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/2607.04949/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":"2026-07-07T02:20:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uhCYuJ8KTvVn7pWBMseYQ7LmzOPeDu49PSW5LkwXNw6oKGz3V5seafeU3dFOmrBXqQf1y3h4ZAhC1Fa+vWG+Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T12:59:00.710798Z"},"content_sha256":"1734c4d7f0861e682bf8d0baa0f70ea5a8d3a64e05586d2094437b9ec2316eb5","schema_version":"1.0","event_id":"sha256:1734c4d7f0861e682bf8d0baa0f70ea5a8d3a64e05586d2094437b9ec2316eb5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/E22USMWGJFFPVI2PRNEU74DXIC/bundle.json","state_url":"https://pith.science/pith/E22USMWGJFFPVI2PRNEU74DXIC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/E22USMWGJFFPVI2PRNEU74DXIC/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":"2026-08-06T12:59:00Z","links":{"resolver":"https://pith.science/pith/E22USMWGJFFPVI2PRNEU74DXIC","bundle":"https://pith.science/pith/E22USMWGJFFPVI2PRNEU74DXIC/bundle.json","state":"https://pith.science/pith/E22USMWGJFFPVI2PRNEU74DXIC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/E22USMWGJFFPVI2PRNEU74DXIC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:E22USMWGJFFPVI2PRNEU74DXIC","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":"a1027d193179f2239dcdd85151de209db12d1aff0274a5e0b47d039c082132ad","cross_cats_sorted":["cs.DS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-06T11:24:56Z","title_canon_sha256":"65602cb3e699f6cda0da9ccb40974725aff28ded610c6360355c38ce8c1842a2"},"schema_version":"1.0","source":{"id":"2607.04949","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.04949","created_at":"2026-07-07T02:20:14Z"},{"alias_kind":"arxiv_version","alias_value":"2607.04949v1","created_at":"2026-07-07T02:20:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.04949","created_at":"2026-07-07T02:20:14Z"},{"alias_kind":"pith_short_12","alias_value":"E22USMWGJFFP","created_at":"2026-07-07T02:20:14Z"},{"alias_kind":"pith_short_16","alias_value":"E22USMWGJFFPVI2P","created_at":"2026-07-07T02:20:14Z"},{"alias_kind":"pith_short_8","alias_value":"E22USMWG","created_at":"2026-07-07T02:20:14Z"}],"graph_snapshots":[{"event_id":"sha256:1734c4d7f0861e682bf8d0baa0f70ea5a8d3a64e05586d2094437b9ec2316eb5","target":"graph","created_at":"2026-07-07T02:20:14Z","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/2607.04949/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study the problem of k-means clustering on large datasets. The state-of-the-art for the problem is given by coresets-based approaches, which build small weighted summaries of the input and derive approximate solutions with rigorous quality guarantees from them. One of the most popular and advanced approaches to derive coresets for k-means is sensitivity sampling. However, sensitivity sampling requires to compute the importance of each input point with respect to the whole dataset over all possible choices of centers. Since the exact computation of such quantities is unfeasible, current appr","authors_text":"Cristian Boldrin, Fabio Vandin","cross_cats":["cs.DS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-06T11:24:56Z","title":"Sensitivity Sampling with Predictions for k-Means Clustering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.04949","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:ac3b5d1abe57b46b7546f390cdd044cb7693d267069c66c7077c0ff460e54c82","target":"record","created_at":"2026-07-07T02:20:14Z","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":"a1027d193179f2239dcdd85151de209db12d1aff0274a5e0b47d039c082132ad","cross_cats_sorted":["cs.DS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-06T11:24:56Z","title_canon_sha256":"65602cb3e699f6cda0da9ccb40974725aff28ded610c6360355c38ce8c1842a2"},"schema_version":"1.0","source":{"id":"2607.04949","kind":"arxiv","version":1}},"canonical_sha256":"26b54932c6494afaa34f8b494ff077408e11f48568c88b9c75083a39017f2d28","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"26b54932c6494afaa34f8b494ff077408e11f48568c88b9c75083a39017f2d28","first_computed_at":"2026-07-07T02:20:14.963325Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-07T02:20:14.963325Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UnpyW4oYbr9O01TOoMZUNbZFCJuFsqo5y/7cKtjZQ8B3dKIbxH/b6FHFdsWlcrVZCVBTVqrRaDofV9lkiF2ICA==","signature_status":"signed_v1","signed_at":"2026-07-07T02:20:14.964164Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.04949","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ac3b5d1abe57b46b7546f390cdd044cb7693d267069c66c7077c0ff460e54c82","sha256:1734c4d7f0861e682bf8d0baa0f70ea5a8d3a64e05586d2094437b9ec2316eb5"],"state_sha256":"4490090e0141cc1c98710901d4618fdb1e4dc710bc5e06cfe49c5ce1d06073c0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AQ/avW3avtioQZeUn+Ft9tgRCAYHgER9eaB3k/f50IEvZrIbVxs9PC+PiZM1nmGjIbdUbwiZqKpqwir+j8u0BQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T12:59:00.717981Z","bundle_sha256":"b0aa35c00013391429c7f7c2642d24b921d761a7bb4c4814941172116de56b71"}}