{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:KSTY44GUN3GF72W6RI6OKMJ27Z","short_pith_number":"pith:KSTY44GU","schema_version":"1.0","canonical_sha256":"54a78e70d46ecc5feade8a3ce5313afe7d73baa10a9e08ec954dbf1fc6232630","source":{"kind":"arxiv","id":"2102.09554","version":2},"attestation_state":"computed","paper":{"title":"Delving into Deep Imbalanced Regression","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Dina Katabi, Hao Wang, Kaiwen Zha, Ying-Cong Chen, Yuzhe Yang","submitted_at":"2021-02-18T18:56:03Z","abstract_excerpt":"Real-world data often exhibit imbalanced distributions, where certain target values have significantly fewer observations. Existing techniques for dealing with imbalanced data focus on targets with categorical indices, i.e., different classes. However, many tasks involve continuous targets, where hard boundaries between classes do not exist. We define Deep Imbalanced Regression (DIR) as learning from such imbalanced data with continuous targets, dealing with potential missing data for certain target values, and generalizing to the entire target range. Motivated by the intrinsic difference betw"},"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":"2102.09554","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-18T18:56:03Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"e06cd5e18b8a272ad5b9882c160d08fa7e55d4349f9791dbb5588b86b53d96ef","abstract_canon_sha256":"70ca343770e82c94bc364b0efa362ac528f236eafa7f39de96ed59b48b08575e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:39:58.632962Z","signature_b64":"MujyiUa9bCEYo/cRcXL+dRcjb5yRv0yrTGojxZ/meLVarFhgNIEPx7BJiI5QCUfhg9P3Sljt/NU60KcC8pmYCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"54a78e70d46ecc5feade8a3ce5313afe7d73baa10a9e08ec954dbf1fc6232630","last_reissued_at":"2026-07-05T02:39:58.632467Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:39:58.632467Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Delving into Deep Imbalanced Regression","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Dina Katabi, Hao Wang, Kaiwen Zha, Ying-Cong Chen, Yuzhe Yang","submitted_at":"2021-02-18T18:56:03Z","abstract_excerpt":"Real-world data often exhibit imbalanced distributions, where certain target values have significantly fewer observations. Existing techniques for dealing with imbalanced data focus on targets with categorical indices, i.e., different classes. However, many tasks involve continuous targets, where hard boundaries between classes do not exist. We define Deep Imbalanced Regression (DIR) as learning from such imbalanced data with continuous targets, dealing with potential missing data for certain target values, and generalizing to the entire target range. Motivated by the intrinsic difference betw"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.09554","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/2102.09554/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":"2102.09554","created_at":"2026-07-05T02:39:58.632529+00:00"},{"alias_kind":"arxiv_version","alias_value":"2102.09554v2","created_at":"2026-07-05T02:39:58.632529+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.09554","created_at":"2026-07-05T02:39:58.632529+00:00"},{"alias_kind":"pith_short_12","alias_value":"KSTY44GUN3GF","created_at":"2026-07-05T02:39:58.632529+00:00"},{"alias_kind":"pith_short_16","alias_value":"KSTY44GUN3GF72W6","created_at":"2026-07-05T02:39:58.632529+00:00"},{"alias_kind":"pith_short_8","alias_value":"KSTY44GU","created_at":"2026-07-05T02:39:58.632529+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.08277","citing_title":"Enhancing deep learning of ammonia/natural gas combustion kinetics via physics-aware data augmentation and scale separation","ref_index":40,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KSTY44GUN3GF72W6RI6OKMJ27Z","json":"https://pith.science/pith/KSTY44GUN3GF72W6RI6OKMJ27Z.json","graph_json":"https://pith.science/api/pith-number/KSTY44GUN3GF72W6RI6OKMJ27Z/graph.json","events_json":"https://pith.science/api/pith-number/KSTY44GUN3GF72W6RI6OKMJ27Z/events.json","paper":"https://pith.science/paper/KSTY44GU"},"agent_actions":{"view_html":"https://pith.science/pith/KSTY44GUN3GF72W6RI6OKMJ27Z","download_json":"https://pith.science/pith/KSTY44GUN3GF72W6RI6OKMJ27Z.json","view_paper":"https://pith.science/paper/KSTY44GU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2102.09554&json=true","fetch_graph":"https://pith.science/api/pith-number/KSTY44GUN3GF72W6RI6OKMJ27Z/graph.json","fetch_events":"https://pith.science/api/pith-number/KSTY44GUN3GF72W6RI6OKMJ27Z/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KSTY44GUN3GF72W6RI6OKMJ27Z/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KSTY44GUN3GF72W6RI6OKMJ27Z/action/storage_attestation","attest_author":"https://pith.science/pith/KSTY44GUN3GF72W6RI6OKMJ27Z/action/author_attestation","sign_citation":"https://pith.science/pith/KSTY44GUN3GF72W6RI6OKMJ27Z/action/citation_signature","submit_replication":"https://pith.science/pith/KSTY44GUN3GF72W6RI6OKMJ27Z/action/replication_record"}},"created_at":"2026-07-05T02:39:58.632529+00:00","updated_at":"2026-07-05T02:39:58.632529+00:00"}