{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:VFS2QMABFSRMBXR46YDPR5J24V","short_pith_number":"pith:VFS2QMAB","canonical_record":{"source":{"id":"2602.18435","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2026-02-20T18:59:53Z","cross_cats_sorted":[],"title_canon_sha256":"b7d9c9eba794fe3dc30e824dee097064c4b62035aecf959122567021766972b4","abstract_canon_sha256":"f81c4229b79ba2d5321eae8789a01d2d098ed22ba0d943fa4004e672e47a38b7"},"schema_version":"1.0"},"canonical_sha256":"a965a830012ca2c0de3cf606f8f53ae549d168222aaec9f756f57e3da549b337","source":{"kind":"arxiv","id":"2602.18435","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2602.18435","created_at":"2026-05-17T23:38:59Z"},{"alias_kind":"arxiv_version","alias_value":"2602.18435v2","created_at":"2026-05-17T23:38:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.18435","created_at":"2026-05-17T23:38:59Z"},{"alias_kind":"pith_short_12","alias_value":"VFS2QMABFSRM","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"VFS2QMABFSRMBXR4","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"VFS2QMAB","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:VFS2QMABFSRMBXR46YDPR5J24V","target":"record","payload":{"canonical_record":{"source":{"id":"2602.18435","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2026-02-20T18:59:53Z","cross_cats_sorted":[],"title_canon_sha256":"b7d9c9eba794fe3dc30e824dee097064c4b62035aecf959122567021766972b4","abstract_canon_sha256":"f81c4229b79ba2d5321eae8789a01d2d098ed22ba0d943fa4004e672e47a38b7"},"schema_version":"1.0"},"canonical_sha256":"a965a830012ca2c0de3cf606f8f53ae549d168222aaec9f756f57e3da549b337","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:38:59.912140Z","signature_b64":"doPXoolvb2EpsyV1eVueSfnx9r8VHjAw+uvFfcLq6Xa8d70bRYBSN7tqpt0FBZD/BB9fh5nR8MqERx5X43EnCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a965a830012ca2c0de3cf606f8f53ae549d168222aaec9f756f57e3da549b337","last_reissued_at":"2026-05-17T23:38:59.911407Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:38:59.911407Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2602.18435","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":"2026-05-17T23:38:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0oDKIZCtwb2KLyqLrcVWaTX2U1DTaQCZeO/u+Vme9CXr1BaNpAqwosFPIfNlEXFoyk3yOVvUMk76dIqE4dB0DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T15:43:21.049792Z"},"content_sha256":"ca44d4cfbc75ec876564e69caad3ade4c89b01a749622f895ed17ab905f07450","schema_version":"1.0","event_id":"sha256:ca44d4cfbc75ec876564e69caad3ade4c89b01a749622f895ed17ab905f07450"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:VFS2QMABFSRMBXR46YDPR5J24V","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"CAKE: Confidence in Assignments via K-partition Ensembles","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"CAKE assigns each clustering point a score in [0,1] by combining its stability across multiple k-partition runs with the consistency of its geometric fit to the assigned cluster.","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Aggelos Semoglou, John Pavlopoulos","submitted_at":"2026-02-20T18:59:53Z","abstract_excerpt":"Clustering is widely used for unsupervised structure discovery, yet it offers limited insight into how reliable each individual assignment is. Diagnostics, such as convergence behavior or objective values, may reflect global quality, but they do not indicate whether particular instances are assigned confidently, especially for initialization-sensitive algorithms like k-means. This assignment-level instability can undermine both accuracy and robustness. Ensemble approaches improve global consistency by aggregating multiple runs, but they typically lack tools for quantifying pointwise confidence"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"The theoretical analysis shows that CAKE remains effective under noise and separates stable from unstable points.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That an ensemble of k-partitions generated by an initialization-sensitive algorithm such as k-means will produce stability and geometric-fit statistics that meaningfully reflect true assignment reliability rather than artifacts of the chosen distance metric or initialization distribution.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"CAKE produces per-point confidence scores in [0,1] for clustering assignments by combining cross-run stability with local geometric consistency over an ensemble of k-partitions.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"CAKE assigns each clustering point a score in [0,1] by combining its stability across multiple k-partition runs with the consistency of its geometric fit to the assigned cluster.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"b24ed5a40630bcc91b5427aec371b0c58676dff514e1341abfa82b3e31627f43"},"source":{"id":"2602.18435","kind":"arxiv","version":2},"verdict":{"id":"c4237d26-b4c9-44f4-ad60-3f96d54521ae","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T20:13:46.205779Z","strongest_claim":"The theoretical analysis shows that CAKE remains effective under noise and separates stable from unstable points.","one_line_summary":"CAKE produces per-point confidence scores in [0,1] for clustering assignments by combining cross-run stability with local geometric consistency over an ensemble of k-partitions.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That an ensemble of k-partitions generated by an initialization-sensitive algorithm such as k-means will produce stability and geometric-fit statistics that meaningfully reflect true assignment reliability rather than artifacts of the chosen distance metric or initialization distribution.","pith_extraction_headline":"CAKE assigns each clustering point a score in [0,1] by combining its stability across multiple k-partition runs with the consistency of its geometric fit to the assigned cluster."},"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":"c4237d26-b4c9-44f4-ad60-3f96d54521ae"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:38:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0AokQlues3bL/pV1aIBudy/bTe7KANpcmkWYZNbB6yLsacOLrIbKSAwoeXR2HO31Clb6Eo4iiKh2gz1rhcTmCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T15:43:21.050251Z"},"content_sha256":"2684335142e5fe798c9063594a447686698d2ae8b0a3918edcc2573e081ec2b0","schema_version":"1.0","event_id":"sha256:2684335142e5fe798c9063594a447686698d2ae8b0a3918edcc2573e081ec2b0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VFS2QMABFSRMBXR46YDPR5J24V/bundle.json","state_url":"https://pith.science/pith/VFS2QMABFSRMBXR46YDPR5J24V/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VFS2QMABFSRMBXR46YDPR5J24V/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":"2026-06-05T15:43:21Z","links":{"resolver":"https://pith.science/pith/VFS2QMABFSRMBXR46YDPR5J24V","bundle":"https://pith.science/pith/VFS2QMABFSRMBXR46YDPR5J24V/bundle.json","state":"https://pith.science/pith/VFS2QMABFSRMBXR46YDPR5J24V/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VFS2QMABFSRMBXR46YDPR5J24V/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:VFS2QMABFSRMBXR46YDPR5J24V","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":"f81c4229b79ba2d5321eae8789a01d2d098ed22ba0d943fa4004e672e47a38b7","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2026-02-20T18:59:53Z","title_canon_sha256":"b7d9c9eba794fe3dc30e824dee097064c4b62035aecf959122567021766972b4"},"schema_version":"1.0","source":{"id":"2602.18435","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2602.18435","created_at":"2026-05-17T23:38:59Z"},{"alias_kind":"arxiv_version","alias_value":"2602.18435v2","created_at":"2026-05-17T23:38:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.18435","created_at":"2026-05-17T23:38:59Z"},{"alias_kind":"pith_short_12","alias_value":"VFS2QMABFSRM","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"VFS2QMABFSRMBXR4","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"VFS2QMAB","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:2684335142e5fe798c9063594a447686698d2ae8b0a3918edcc2573e081ec2b0","target":"graph","created_at":"2026-05-17T23:38:59Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"The theoretical analysis shows that CAKE remains effective under noise and separates stable from unstable points."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That an ensemble of k-partitions generated by an initialization-sensitive algorithm such as k-means will produce stability and geometric-fit statistics that meaningfully reflect true assignment reliability rather than artifacts of the chosen distance metric or initialization distribution."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"CAKE produces per-point confidence scores in [0,1] for clustering assignments by combining cross-run stability with local geometric consistency over an ensemble of k-partitions."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"CAKE assigns each clustering point a score in [0,1] by combining its stability across multiple k-partition runs with the consistency of its geometric fit to the assigned cluster."}],"snapshot_sha256":"b24ed5a40630bcc91b5427aec371b0c58676dff514e1341abfa82b3e31627f43"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"Clustering is widely used for unsupervised structure discovery, yet it offers limited insight into how reliable each individual assignment is. Diagnostics, such as convergence behavior or objective values, may reflect global quality, but they do not indicate whether particular instances are assigned confidently, especially for initialization-sensitive algorithms like k-means. This assignment-level instability can undermine both accuracy and robustness. Ensemble approaches improve global consistency by aggregating multiple runs, but they typically lack tools for quantifying pointwise confidence","authors_text":"Aggelos Semoglou, John Pavlopoulos","cross_cats":[],"headline":"CAKE assigns each clustering point a score in [0,1] by combining its stability across multiple k-partition runs with the consistency of its geometric fit to the assigned cluster.","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2026-02-20T18:59:53Z","title":"CAKE: Confidence in Assignments via K-partition Ensembles"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.18435","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-15T20:13:46.205779Z","id":"c4237d26-b4c9-44f4-ad60-3f96d54521ae","model_set":{"reader":"grok-4.3"},"one_line_summary":"CAKE produces per-point confidence scores in [0,1] for clustering assignments by combining cross-run stability with local geometric consistency over an ensemble of k-partitions.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"CAKE assigns each clustering point a score in [0,1] by combining its stability across multiple k-partition runs with the consistency of its geometric fit to the assigned cluster.","strongest_claim":"The theoretical analysis shows that CAKE remains effective under noise and separates stable from unstable points.","weakest_assumption":"That an ensemble of k-partitions generated by an initialization-sensitive algorithm such as k-means will produce stability and geometric-fit statistics that meaningfully reflect true assignment reliability rather than artifacts of the chosen distance metric or initialization distribution."}},"verdict_id":"c4237d26-b4c9-44f4-ad60-3f96d54521ae"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:ca44d4cfbc75ec876564e69caad3ade4c89b01a749622f895ed17ab905f07450","target":"record","created_at":"2026-05-17T23:38:59Z","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":"f81c4229b79ba2d5321eae8789a01d2d098ed22ba0d943fa4004e672e47a38b7","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2026-02-20T18:59:53Z","title_canon_sha256":"b7d9c9eba794fe3dc30e824dee097064c4b62035aecf959122567021766972b4"},"schema_version":"1.0","source":{"id":"2602.18435","kind":"arxiv","version":2}},"canonical_sha256":"a965a830012ca2c0de3cf606f8f53ae549d168222aaec9f756f57e3da549b337","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a965a830012ca2c0de3cf606f8f53ae549d168222aaec9f756f57e3da549b337","first_computed_at":"2026-05-17T23:38:59.911407Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:38:59.911407Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"doPXoolvb2EpsyV1eVueSfnx9r8VHjAw+uvFfcLq6Xa8d70bRYBSN7tqpt0FBZD/BB9fh5nR8MqERx5X43EnCA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:38:59.912140Z","signed_message":"canonical_sha256_bytes"},"source_id":"2602.18435","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ca44d4cfbc75ec876564e69caad3ade4c89b01a749622f895ed17ab905f07450","sha256:2684335142e5fe798c9063594a447686698d2ae8b0a3918edcc2573e081ec2b0"],"state_sha256":"5b7387e20d4dcf2f0432cfa3a7181888a0a92380f609d2d63b6e1abb28541536"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RXAH5lEy5S1kMj2SZKB+TBDK1Vhr5zZShe3QfyRuKMgNXN91tPi2fQaQcz8dnACIpok9hMsn9tZK3p6minpKBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-05T15:43:21.052734Z","bundle_sha256":"37499a266e26fdb0c5674a8420c1a943a97a6c02e0abb810b1b42401fcc41d46"}}