{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:44RERZMUOWTAID6AWTLNKNKBZQ","short_pith_number":"pith:44RERZMU","schema_version":"1.0","canonical_sha256":"e72248e59475a6040fc0b4d6d53541cc1f9981a0e420a5b3fc98d5865ac11e21","source":{"kind":"arxiv","id":"2501.17568","version":2},"attestation_state":"computed","paper":{"title":"Histogram Approaches for Imbalanced Data Streams Regression","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ehsan Aminian, Joao Gama, Rita P. Ribeiro","submitted_at":"2025-01-29T11:03:02Z","abstract_excerpt":"Imbalanced domains pose a significant challenge in real-world predictive analytics, particularly in the context of regression. While existing research has primarily focused on batch learning from static datasets, limited attention has been given to imbalanced regression in online learning scenarios. Intending to address this gap, in prior work, we proposed sampling strategies based on Chebyshevs inequality as the first methodologies designed explicitly for data streams. However, these approaches operated under the restrictive assumption that rare instances exclusively reside at distribution ex"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2501.17568","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-29T11:03:02Z","cross_cats_sorted":[],"title_canon_sha256":"d6c3e83fcf27d70553beeed3f9e2b76372488e59a867fd9f0445d6a441ef86b0","abstract_canon_sha256":"5b721c2bc093424cb7880c008b936384b6afe2e042ad999c022bed0bd65749b7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:30:30.530680Z","signature_b64":"vrLAGFtD+MckCe3Hx778AIrsAOLkgIOEtzD61V+cRNQq6EF1YuAp1DUL2YOjWeVZSprki63dP+u2DJoR2OtKDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e72248e59475a6040fc0b4d6d53541cc1f9981a0e420a5b3fc98d5865ac11e21","last_reissued_at":"2026-07-05T10:30:30.530042Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:30:30.530042Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Histogram Approaches for Imbalanced Data Streams Regression","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ehsan Aminian, Joao Gama, Rita P. Ribeiro","submitted_at":"2025-01-29T11:03:02Z","abstract_excerpt":"Imbalanced domains pose a significant challenge in real-world predictive analytics, particularly in the context of regression. While existing research has primarily focused on batch learning from static datasets, limited attention has been given to imbalanced regression in online learning scenarios. Intending to address this gap, in prior work, we proposed sampling strategies based on Chebyshevs inequality as the first methodologies designed explicitly for data streams. However, these approaches operated under the restrictive assumption that rare instances exclusively reside at distribution ex"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.17568","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2501.17568/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2501.17568","created_at":"2026-07-05T10:30:30.530118+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.17568v2","created_at":"2026-07-05T10:30:30.530118+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.17568","created_at":"2026-07-05T10:30:30.530118+00:00"},{"alias_kind":"pith_short_12","alias_value":"44RERZMUOWTA","created_at":"2026-07-05T10:30:30.530118+00:00"},{"alias_kind":"pith_short_16","alias_value":"44RERZMUOWTAID6A","created_at":"2026-07-05T10:30:30.530118+00:00"},{"alias_kind":"pith_short_8","alias_value":"44RERZMU","created_at":"2026-07-05T10:30:30.530118+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.01486","citing_title":"Model-agnostic Mitigation Strategies of Data Imbalance for Regression","ref_index":6,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/44RERZMUOWTAID6AWTLNKNKBZQ","json":"https://pith.science/pith/44RERZMUOWTAID6AWTLNKNKBZQ.json","graph_json":"https://pith.science/api/pith-number/44RERZMUOWTAID6AWTLNKNKBZQ/graph.json","events_json":"https://pith.science/api/pith-number/44RERZMUOWTAID6AWTLNKNKBZQ/events.json","paper":"https://pith.science/paper/44RERZMU"},"agent_actions":{"view_html":"https://pith.science/pith/44RERZMUOWTAID6AWTLNKNKBZQ","download_json":"https://pith.science/pith/44RERZMUOWTAID6AWTLNKNKBZQ.json","view_paper":"https://pith.science/paper/44RERZMU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.17568&json=true","fetch_graph":"https://pith.science/api/pith-number/44RERZMUOWTAID6AWTLNKNKBZQ/graph.json","fetch_events":"https://pith.science/api/pith-number/44RERZMUOWTAID6AWTLNKNKBZQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/44RERZMUOWTAID6AWTLNKNKBZQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/44RERZMUOWTAID6AWTLNKNKBZQ/action/storage_attestation","attest_author":"https://pith.science/pith/44RERZMUOWTAID6AWTLNKNKBZQ/action/author_attestation","sign_citation":"https://pith.science/pith/44RERZMUOWTAID6AWTLNKNKBZQ/action/citation_signature","submit_replication":"https://pith.science/pith/44RERZMUOWTAID6AWTLNKNKBZQ/action/replication_record"}},"created_at":"2026-07-05T10:30:30.530118+00:00","updated_at":"2026-07-05T10:30:30.530118+00:00"}