{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:AUKRHC7OZXS2TMP2WFXENWHBNA","short_pith_number":"pith:AUKRHC7O","canonical_record":{"source":{"id":"2402.11963","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-19T09:06:26Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a92a3a09e02a713c2456ca2abd45a44c2063909248dc98938a870a8063d5cfa9","abstract_canon_sha256":"87f8709d29cf79db3c0e7c18e466c014328adeefe8a9dce79abc631e7fea0734"},"schema_version":"1.0"},"canonical_sha256":"0515138beecde5a9b1fab16e46d8e168065759abef7a9636f206f61c3c4959a1","source":{"kind":"arxiv","id":"2402.11963","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.11963","created_at":"2026-07-05T07:46:46Z"},{"alias_kind":"arxiv_version","alias_value":"2402.11963v1","created_at":"2026-07-05T07:46:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.11963","created_at":"2026-07-05T07:46:46Z"},{"alias_kind":"pith_short_12","alias_value":"AUKRHC7OZXS2","created_at":"2026-07-05T07:46:46Z"},{"alias_kind":"pith_short_16","alias_value":"AUKRHC7OZXS2TMP2","created_at":"2026-07-05T07:46:46Z"},{"alias_kind":"pith_short_8","alias_value":"AUKRHC7O","created_at":"2026-07-05T07:46:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:AUKRHC7OZXS2TMP2WFXENWHBNA","target":"record","payload":{"canonical_record":{"source":{"id":"2402.11963","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-19T09:06:26Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a92a3a09e02a713c2456ca2abd45a44c2063909248dc98938a870a8063d5cfa9","abstract_canon_sha256":"87f8709d29cf79db3c0e7c18e466c014328adeefe8a9dce79abc631e7fea0734"},"schema_version":"1.0"},"canonical_sha256":"0515138beecde5a9b1fab16e46d8e168065759abef7a9636f206f61c3c4959a1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:46:46.709566Z","signature_b64":"F6g/d53/riS4dwyfhjanpStKHXAGtKQ1KJQ71B+tTnzJMEp2nqS36ba34goT3A7nT+XG2Ie2VXmB2DcDajKVDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0515138beecde5a9b1fab16e46d8e168065759abef7a9636f206f61c3c4959a1","last_reissued_at":"2026-07-05T07:46:46.708986Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:46:46.708986Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.11963","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":"2026-07-05T07:46:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qKDDqdrEKNOKaSiVWiaKMKmXNWQ4E8g+WHYtehJRatnrUckkhn4bjFHXElC/6HhQY7sOMoQtxd4ivteDLz4WBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T09:33:15.477618Z"},"content_sha256":"022c5637f1d6ae2bc59ca4cecfaeb686db7e0fc25acc329fc1fd61e7521b0928","schema_version":"1.0","event_id":"sha256:022c5637f1d6ae2bc59ca4cecfaeb686db7e0fc25acc329fc1fd61e7521b0928"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:AUKRHC7OZXS2TMP2WFXENWHBNA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Imbalance in Regression Datasets","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Daniel Kowatsch, Kilian Tscharke, Konstantin B\\\"otinger, Nicolas M. M\\\"uller, Philip Sperl","submitted_at":"2024-02-19T09:06:26Z","abstract_excerpt":"For classification, the problem of class imbalance is well known and has been extensively studied. In this paper, we argue that imbalance in regression is an equally important problem which has so far been overlooked: Due to under- and over-representations in a data set's target distribution, regressors are prone to degenerate to naive models, systematically neglecting uncommon training data and over-representing targets seen often during training. We analyse this problem theoretically and use resulting insights to develop a first definition of imbalance in regression, which we show to be a ge"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.11963","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/2402.11963/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":"2026-07-05T07:46:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2MHa1BCRrUS915nDWChEScBjjX7xepLfLfMglnYRRlLYS0Ssxap9C0MriOjPBYZl2rt6cvMy9oSsDAiLvqyoAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T09:33:15.478129Z"},"content_sha256":"8385f6f795f7997b7eab065522a06430204935ba7fec38405fdab9e59ffe8ca7","schema_version":"1.0","event_id":"sha256:8385f6f795f7997b7eab065522a06430204935ba7fec38405fdab9e59ffe8ca7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AUKRHC7OZXS2TMP2WFXENWHBNA/bundle.json","state_url":"https://pith.science/pith/AUKRHC7OZXS2TMP2WFXENWHBNA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AUKRHC7OZXS2TMP2WFXENWHBNA/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":"2026-08-08T09:33:15Z","links":{"resolver":"https://pith.science/pith/AUKRHC7OZXS2TMP2WFXENWHBNA","bundle":"https://pith.science/pith/AUKRHC7OZXS2TMP2WFXENWHBNA/bundle.json","state":"https://pith.science/pith/AUKRHC7OZXS2TMP2WFXENWHBNA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AUKRHC7OZXS2TMP2WFXENWHBNA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:AUKRHC7OZXS2TMP2WFXENWHBNA","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":"87f8709d29cf79db3c0e7c18e466c014328adeefe8a9dce79abc631e7fea0734","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-19T09:06:26Z","title_canon_sha256":"a92a3a09e02a713c2456ca2abd45a44c2063909248dc98938a870a8063d5cfa9"},"schema_version":"1.0","source":{"id":"2402.11963","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.11963","created_at":"2026-07-05T07:46:46Z"},{"alias_kind":"arxiv_version","alias_value":"2402.11963v1","created_at":"2026-07-05T07:46:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.11963","created_at":"2026-07-05T07:46:46Z"},{"alias_kind":"pith_short_12","alias_value":"AUKRHC7OZXS2","created_at":"2026-07-05T07:46:46Z"},{"alias_kind":"pith_short_16","alias_value":"AUKRHC7OZXS2TMP2","created_at":"2026-07-05T07:46:46Z"},{"alias_kind":"pith_short_8","alias_value":"AUKRHC7O","created_at":"2026-07-05T07:46:46Z"}],"graph_snapshots":[{"event_id":"sha256:8385f6f795f7997b7eab065522a06430204935ba7fec38405fdab9e59ffe8ca7","target":"graph","created_at":"2026-07-05T07:46:46Z","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/2402.11963/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"For classification, the problem of class imbalance is well known and has been extensively studied. In this paper, we argue that imbalance in regression is an equally important problem which has so far been overlooked: Due to under- and over-representations in a data set's target distribution, regressors are prone to degenerate to naive models, systematically neglecting uncommon training data and over-representing targets seen often during training. We analyse this problem theoretically and use resulting insights to develop a first definition of imbalance in regression, which we show to be a ge","authors_text":"Daniel Kowatsch, Kilian Tscharke, Konstantin B\\\"otinger, Nicolas M. M\\\"uller, Philip Sperl","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-19T09:06:26Z","title":"Imbalance in Regression Datasets"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.11963","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":"sha256:022c5637f1d6ae2bc59ca4cecfaeb686db7e0fc25acc329fc1fd61e7521b0928","target":"record","created_at":"2026-07-05T07:46:46Z","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":"87f8709d29cf79db3c0e7c18e466c014328adeefe8a9dce79abc631e7fea0734","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-19T09:06:26Z","title_canon_sha256":"a92a3a09e02a713c2456ca2abd45a44c2063909248dc98938a870a8063d5cfa9"},"schema_version":"1.0","source":{"id":"2402.11963","kind":"arxiv","version":1}},"canonical_sha256":"0515138beecde5a9b1fab16e46d8e168065759abef7a9636f206f61c3c4959a1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0515138beecde5a9b1fab16e46d8e168065759abef7a9636f206f61c3c4959a1","first_computed_at":"2026-07-05T07:46:46.708986Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:46:46.708986Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"F6g/d53/riS4dwyfhjanpStKHXAGtKQ1KJQ71B+tTnzJMEp2nqS36ba34goT3A7nT+XG2Ie2VXmB2DcDajKVDg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:46:46.709566Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.11963","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:022c5637f1d6ae2bc59ca4cecfaeb686db7e0fc25acc329fc1fd61e7521b0928","sha256:8385f6f795f7997b7eab065522a06430204935ba7fec38405fdab9e59ffe8ca7"],"state_sha256":"1ea3ddf964e3182378a517f21894f855d2fc41791fcc50939554a64eac8e8b68"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nWONfJCvmVS1EUDP9wrxeOW2v7/ptkLoqAW3Qjpci51AeLtEx6Ahjd29xkoFXyRqMO0E/hDWnjZJ6eDyGwnrCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T09:33:15.482791Z","bundle_sha256":"c40b9a5b3d438db4e16c5ef0fe4d50a4e056848d4d65d232973ddc4d8f0e9abf"}}