{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:476HBFWOJDFAKCZSPDR7B75IYS","short_pith_number":"pith:476HBFWO","canonical_record":{"source":{"id":"1808.00525","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2018-07-30T14:29:27Z","cross_cats_sorted":["cs.CL","cs.DL","cs.LG","stat.ML"],"title_canon_sha256":"c82fd6fef01c073c37e4f550b17324e7627caecc1fe736369865c9f1c2c33e33","abstract_canon_sha256":"3b5edff5bd86f73bd3afca4bd567fdd083834754a11ec6a59f4e4f5c8f439731"},"schema_version":"1.0"},"canonical_sha256":"e7fc7096ce48ca050b3278e3f0ffa8c486d26d6ae2340a419c772d3e02a7b19e","source":{"kind":"arxiv","id":"1808.00525","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1808.00525","created_at":"2026-05-18T00:08:59Z"},{"alias_kind":"arxiv_version","alias_value":"1808.00525v2","created_at":"2026-05-18T00:08:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.00525","created_at":"2026-05-18T00:08:59Z"},{"alias_kind":"pith_short_12","alias_value":"476HBFWOJDFA","created_at":"2026-05-18T12:32:05Z"},{"alias_kind":"pith_short_16","alias_value":"476HBFWOJDFAKCZS","created_at":"2026-05-18T12:32:05Z"},{"alias_kind":"pith_short_8","alias_value":"476HBFWO","created_at":"2026-05-18T12:32:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:476HBFWOJDFAKCZSPDR7B75IYS","target":"record","payload":{"canonical_record":{"source":{"id":"1808.00525","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2018-07-30T14:29:27Z","cross_cats_sorted":["cs.CL","cs.DL","cs.LG","stat.ML"],"title_canon_sha256":"c82fd6fef01c073c37e4f550b17324e7627caecc1fe736369865c9f1c2c33e33","abstract_canon_sha256":"3b5edff5bd86f73bd3afca4bd567fdd083834754a11ec6a59f4e4f5c8f439731"},"schema_version":"1.0"},"canonical_sha256":"e7fc7096ce48ca050b3278e3f0ffa8c486d26d6ae2340a419c772d3e02a7b19e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:08:59.546005Z","signature_b64":"IK4X6gDDR9ebS91lVqv1t/sy0bp59dfC7hLFVIrQeGNJ4/pQOVupLdECmfhCm6jduzl6zOPxEOeUg6+wO7MSAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e7fc7096ce48ca050b3278e3f0ffa8c486d26d6ae2340a419c772d3e02a7b19e","last_reissued_at":"2026-05-18T00:08:59.545415Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:08:59.545415Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1808.00525","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":"2026-05-18T00:08:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zelgOnRWokQgdu96eGJY+2Vn25cxeQMxMfgLQsA1vEQaTB48EphToHhWWzu0SzLJ7OUoQTmTOzxa+APld4ZMDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T07:34:39.003532Z"},"content_sha256":"1b8e5c99d1f6ec2d62f2efb31dd543f89d6a3f2930bc8a3317c2121e04f45385","schema_version":"1.0","event_id":"sha256:1b8e5c99d1f6ec2d62f2efb31dd543f89d6a3f2930bc8a3317c2121e04f45385"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:476HBFWOJDFAKCZSPDR7B75IYS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"The impact of imbalanced training data on machine learning for author name disambiguation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.DL","cs.LG","stat.ML"],"primary_cat":"cs.IR","authors_text":"Jenna Kim, Jinseok Kim","submitted_at":"2018-07-30T14:29:27Z","abstract_excerpt":"In supervised machine learning for author name disambiguation, negative training data are often dominantly larger than positive training data. This paper examines how the ratios of negative to positive training data can affect the performance of machine learning algorithms to disambiguate author names in bibliographic records. On multiple labeled datasets, three classifiers - Logistic Regression, Na\\\"ive Bayes, and Random Forest - are trained through representative features such as coauthor names, and title words extracted from the same training data but with various positive-negative training"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.00525","kind":"arxiv","version":2},"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":"2026-05-18T00:08:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZNXrA6GTPZHRnCU8KmjqgHPzkdAgm+mcdNUyq0DxgznVrGp9xS7ZgM4QBBWpYlpyu7bCiLkiSNmrBh13d/rDAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T07:34:39.004108Z"},"content_sha256":"734bda61fc3af9e9388c1fc86ae291d1ed0b7d14c8ff45e995b5c007ef73f67c","schema_version":"1.0","event_id":"sha256:734bda61fc3af9e9388c1fc86ae291d1ed0b7d14c8ff45e995b5c007ef73f67c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/476HBFWOJDFAKCZSPDR7B75IYS/bundle.json","state_url":"https://pith.science/pith/476HBFWOJDFAKCZSPDR7B75IYS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/476HBFWOJDFAKCZSPDR7B75IYS/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":"2026-05-31T07:34:39Z","links":{"resolver":"https://pith.science/pith/476HBFWOJDFAKCZSPDR7B75IYS","bundle":"https://pith.science/pith/476HBFWOJDFAKCZSPDR7B75IYS/bundle.json","state":"https://pith.science/pith/476HBFWOJDFAKCZSPDR7B75IYS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/476HBFWOJDFAKCZSPDR7B75IYS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:476HBFWOJDFAKCZSPDR7B75IYS","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":"3b5edff5bd86f73bd3afca4bd567fdd083834754a11ec6a59f4e4f5c8f439731","cross_cats_sorted":["cs.CL","cs.DL","cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2018-07-30T14:29:27Z","title_canon_sha256":"c82fd6fef01c073c37e4f550b17324e7627caecc1fe736369865c9f1c2c33e33"},"schema_version":"1.0","source":{"id":"1808.00525","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1808.00525","created_at":"2026-05-18T00:08:59Z"},{"alias_kind":"arxiv_version","alias_value":"1808.00525v2","created_at":"2026-05-18T00:08:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.00525","created_at":"2026-05-18T00:08:59Z"},{"alias_kind":"pith_short_12","alias_value":"476HBFWOJDFA","created_at":"2026-05-18T12:32:05Z"},{"alias_kind":"pith_short_16","alias_value":"476HBFWOJDFAKCZS","created_at":"2026-05-18T12:32:05Z"},{"alias_kind":"pith_short_8","alias_value":"476HBFWO","created_at":"2026-05-18T12:32:05Z"}],"graph_snapshots":[{"event_id":"sha256:734bda61fc3af9e9388c1fc86ae291d1ed0b7d14c8ff45e995b5c007ef73f67c","target":"graph","created_at":"2026-05-18T00:08:59Z","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":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"In supervised machine learning for author name disambiguation, negative training data are often dominantly larger than positive training data. This paper examines how the ratios of negative to positive training data can affect the performance of machine learning algorithms to disambiguate author names in bibliographic records. On multiple labeled datasets, three classifiers - Logistic Regression, Na\\\"ive Bayes, and Random Forest - are trained through representative features such as coauthor names, and title words extracted from the same training data but with various positive-negative training","authors_text":"Jenna Kim, Jinseok Kim","cross_cats":["cs.CL","cs.DL","cs.LG","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2018-07-30T14:29:27Z","title":"The impact of imbalanced training data on machine learning for author name disambiguation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.00525","kind":"arxiv","version":2},"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":"sha256:1b8e5c99d1f6ec2d62f2efb31dd543f89d6a3f2930bc8a3317c2121e04f45385","target":"record","created_at":"2026-05-18T00:08:59Z","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":"3b5edff5bd86f73bd3afca4bd567fdd083834754a11ec6a59f4e4f5c8f439731","cross_cats_sorted":["cs.CL","cs.DL","cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2018-07-30T14:29:27Z","title_canon_sha256":"c82fd6fef01c073c37e4f550b17324e7627caecc1fe736369865c9f1c2c33e33"},"schema_version":"1.0","source":{"id":"1808.00525","kind":"arxiv","version":2}},"canonical_sha256":"e7fc7096ce48ca050b3278e3f0ffa8c486d26d6ae2340a419c772d3e02a7b19e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e7fc7096ce48ca050b3278e3f0ffa8c486d26d6ae2340a419c772d3e02a7b19e","first_computed_at":"2026-05-18T00:08:59.545415Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:08:59.545415Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"IK4X6gDDR9ebS91lVqv1t/sy0bp59dfC7hLFVIrQeGNJ4/pQOVupLdECmfhCm6jduzl6zOPxEOeUg6+wO7MSAw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:08:59.546005Z","signed_message":"canonical_sha256_bytes"},"source_id":"1808.00525","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1b8e5c99d1f6ec2d62f2efb31dd543f89d6a3f2930bc8a3317c2121e04f45385","sha256:734bda61fc3af9e9388c1fc86ae291d1ed0b7d14c8ff45e995b5c007ef73f67c"],"state_sha256":"4a9a11b0f4caad370efa7438c739bc3555d99bc7b504e0305182e0608954c573"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ou2h3XwXQ/YVsQlms1OqKOEEw+T/6PzqGOmVEWW0fwV/H0X7FRh4iBPVfBSm+eCLuZWF+RRYL+YNSui1PlxMBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-31T07:34:39.007532Z","bundle_sha256":"dc742110a73474ccb3c80cc7d1fac2f78dea6f74d153bd4d7f457c41e30c81e3"}}