{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:YHQVDCRH43U3GUDDXIC4DJOUXQ","short_pith_number":"pith:YHQVDCRH","canonical_record":{"source":{"id":"1907.10421","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2019-07-24T13:05:15Z","cross_cats_sorted":["cs.DC","stat.ML"],"title_canon_sha256":"a8699d4066fc7a90ec75a19c3cc61be5489ffd1d89941e05584c50560a9a9cbe","abstract_canon_sha256":"c4867bc05195927fe70e06e255db3a6c0962bf25d39f9a0f263d9dd0906117d6"},"schema_version":"1.0"},"canonical_sha256":"c1e1518a27e6e9b35063ba05c1a5d4bc319ca270aa340b08010aa7a6e4e7b94f","source":{"kind":"arxiv","id":"1907.10421","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1907.10421","created_at":"2026-05-17T23:39:37Z"},{"alias_kind":"arxiv_version","alias_value":"1907.10421v1","created_at":"2026-05-17T23:39:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.10421","created_at":"2026-05-17T23:39:37Z"},{"alias_kind":"pith_short_12","alias_value":"YHQVDCRH43U3","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_16","alias_value":"YHQVDCRH43U3GUDD","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_8","alias_value":"YHQVDCRH","created_at":"2026-05-18T12:33:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:YHQVDCRH43U3GUDDXIC4DJOUXQ","target":"record","payload":{"canonical_record":{"source":{"id":"1907.10421","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2019-07-24T13:05:15Z","cross_cats_sorted":["cs.DC","stat.ML"],"title_canon_sha256":"a8699d4066fc7a90ec75a19c3cc61be5489ffd1d89941e05584c50560a9a9cbe","abstract_canon_sha256":"c4867bc05195927fe70e06e255db3a6c0962bf25d39f9a0f263d9dd0906117d6"},"schema_version":"1.0"},"canonical_sha256":"c1e1518a27e6e9b35063ba05c1a5d4bc319ca270aa340b08010aa7a6e4e7b94f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:39:37.988465Z","signature_b64":"k99Y3y82e6RxEpvWT1aiPw4vTThwrgs78OjiS3EuY+rRdqzQ/zSCQ5oLm7WZOSx7jgt7ZgBXlvuZWzPaWw1XAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c1e1518a27e6e9b35063ba05c1a5d4bc319ca270aa340b08010aa7a6e4e7b94f","last_reissued_at":"2026-05-17T23:39:37.987950Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:39:37.987950Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1907.10421","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":"2026-05-17T23:39:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1uKsCbxpujifOINBB2u4tXYFM3N8xAn9H14Fpdd8IIUAzYw5uIh2xzjIFDHTXcvd0O91nF6qCfRMe/uqGgb5AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T13:35:05.670254Z"},"content_sha256":"56a4379895c405713b38fd56675ac7ff1ecd0b5d9faf5c8c0fc5ee3b1fb3f408","schema_version":"1.0","event_id":"sha256:56a4379895c405713b38fd56675ac7ff1ecd0b5d9faf5c8c0fc5ee3b1fb3f408"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:YHQVDCRH43U3GUDDXIC4DJOUXQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A graphical heuristic for reduction and partitioning of large datasets for scalable supervised training","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Mathis Bode, Sumedh Yadav","submitted_at":"2019-07-24T13:05:15Z","abstract_excerpt":"A scalable graphical method is presented for selecting, and partitioning datasets for the training phase of a classification task. For the heuristic, a clustering algorithm is required to get its computation cost in a reasonable proportion to the task itself. This step is proceeded by construction of an information graph of the underlying classification patterns using approximate nearest neighbor methods. The presented method constitutes of two approaches, one for reducing a given training set, and another for partitioning the selected/reduced set. The heuristic targets large datasets, since t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.10421","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":""},"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":"2026-05-17T23:39:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sAdf5Z2mNeVglfvtZalnTgQbtPkpvlRI8JHyQSqDs45Krka6CkCazrQ6cOheJTp4xn8vB9ezTgZjMIdbMyCNCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T13:35:05.670920Z"},"content_sha256":"0a60fe2ad5b2954e5eb21826f5f8f36fff42e7fb69e690bf0af167763e16d5c4","schema_version":"1.0","event_id":"sha256:0a60fe2ad5b2954e5eb21826f5f8f36fff42e7fb69e690bf0af167763e16d5c4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YHQVDCRH43U3GUDDXIC4DJOUXQ/bundle.json","state_url":"https://pith.science/pith/YHQVDCRH43U3GUDDXIC4DJOUXQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YHQVDCRH43U3GUDDXIC4DJOUXQ/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":"2026-05-26T13:35:05Z","links":{"resolver":"https://pith.science/pith/YHQVDCRH43U3GUDDXIC4DJOUXQ","bundle":"https://pith.science/pith/YHQVDCRH43U3GUDDXIC4DJOUXQ/bundle.json","state":"https://pith.science/pith/YHQVDCRH43U3GUDDXIC4DJOUXQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YHQVDCRH43U3GUDDXIC4DJOUXQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:YHQVDCRH43U3GUDDXIC4DJOUXQ","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":"c4867bc05195927fe70e06e255db3a6c0962bf25d39f9a0f263d9dd0906117d6","cross_cats_sorted":["cs.DC","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2019-07-24T13:05:15Z","title_canon_sha256":"a8699d4066fc7a90ec75a19c3cc61be5489ffd1d89941e05584c50560a9a9cbe"},"schema_version":"1.0","source":{"id":"1907.10421","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1907.10421","created_at":"2026-05-17T23:39:37Z"},{"alias_kind":"arxiv_version","alias_value":"1907.10421v1","created_at":"2026-05-17T23:39:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.10421","created_at":"2026-05-17T23:39:37Z"},{"alias_kind":"pith_short_12","alias_value":"YHQVDCRH43U3","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_16","alias_value":"YHQVDCRH43U3GUDD","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_8","alias_value":"YHQVDCRH","created_at":"2026-05-18T12:33:33Z"}],"graph_snapshots":[{"event_id":"sha256:0a60fe2ad5b2954e5eb21826f5f8f36fff42e7fb69e690bf0af167763e16d5c4","target":"graph","created_at":"2026-05-17T23:39:37Z","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"},"paper":{"abstract_excerpt":"A scalable graphical method is presented for selecting, and partitioning datasets for the training phase of a classification task. For the heuristic, a clustering algorithm is required to get its computation cost in a reasonable proportion to the task itself. This step is proceeded by construction of an information graph of the underlying classification patterns using approximate nearest neighbor methods. The presented method constitutes of two approaches, one for reducing a given training set, and another for partitioning the selected/reduced set. The heuristic targets large datasets, since t","authors_text":"Mathis Bode, Sumedh Yadav","cross_cats":["cs.DC","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2019-07-24T13:05:15Z","title":"A graphical heuristic for reduction and partitioning of large datasets for scalable supervised training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.10421","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":"sha256:56a4379895c405713b38fd56675ac7ff1ecd0b5d9faf5c8c0fc5ee3b1fb3f408","target":"record","created_at":"2026-05-17T23:39:37Z","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":"c4867bc05195927fe70e06e255db3a6c0962bf25d39f9a0f263d9dd0906117d6","cross_cats_sorted":["cs.DC","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2019-07-24T13:05:15Z","title_canon_sha256":"a8699d4066fc7a90ec75a19c3cc61be5489ffd1d89941e05584c50560a9a9cbe"},"schema_version":"1.0","source":{"id":"1907.10421","kind":"arxiv","version":1}},"canonical_sha256":"c1e1518a27e6e9b35063ba05c1a5d4bc319ca270aa340b08010aa7a6e4e7b94f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c1e1518a27e6e9b35063ba05c1a5d4bc319ca270aa340b08010aa7a6e4e7b94f","first_computed_at":"2026-05-17T23:39:37.987950Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:39:37.987950Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"k99Y3y82e6RxEpvWT1aiPw4vTThwrgs78OjiS3EuY+rRdqzQ/zSCQ5oLm7WZOSx7jgt7ZgBXlvuZWzPaWw1XAA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:39:37.988465Z","signed_message":"canonical_sha256_bytes"},"source_id":"1907.10421","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:56a4379895c405713b38fd56675ac7ff1ecd0b5d9faf5c8c0fc5ee3b1fb3f408","sha256:0a60fe2ad5b2954e5eb21826f5f8f36fff42e7fb69e690bf0af167763e16d5c4"],"state_sha256":"c52745ea54c038213723d95e638b7f07a38ccdfd59e3417524116fe88b3bddaf"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MYh4Q5aeU5lqEEcMnL7cUj1+d8UCmaNTplxdPmI5cH4TwKwX56ZChs2hfDO274015nfoaRePKl1pOf5ESRzWBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T13:35:05.674217Z","bundle_sha256":"999ad28a2b2517ddb0c8eb709ca7cfe8ee112897f88d7e526d9b7302199a4102"}}