{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:C75IV37RGOWHTI3P2GOFWKHV33","short_pith_number":"pith:C75IV37R","schema_version":"1.0","canonical_sha256":"17fa8aeff133ac79a36fd19c5b28f5dee4e45900566970b45030d89bee468bdd","source":{"kind":"arxiv","id":"2205.15236","version":2},"attestation_state":"computed","paper":{"title":"RankSim: Ranking Similarity Regularization for 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":"Frederick Tung, Greg Mori, Yu Gong","submitted_at":"2022-05-30T16:51:25Z","abstract_excerpt":"Data imbalance, in which a plurality of the data samples come from a small proportion of labels, poses a challenge in training deep neural networks. Unlike classification, in regression the labels are continuous, potentially boundless, and form a natural ordering. These distinct features of regression call for new techniques that leverage the additional information encoded in label-space relationships. This paper presents the RankSim (ranking similarity) regularizer for deep imbalanced regression, which encodes an inductive bias that samples that are closer in label space should also be closer"},"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":"2205.15236","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-05-30T16:51:25Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"d5cc19ab21710b04267acca4e164ac3f48b8513746e71d8a2adba40e445d08d7","abstract_canon_sha256":"3f7e1accf38c55890efeb68fe9ec0091b82e6d16b74105116a2750aeb4282e77"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:34:29.455487Z","signature_b64":"BpdnUdXYYq/q7GT8kq20vCv2s0qiHwTmo0aXlNA3bNqSfwIInJTLSs7W3U21CjrqbjSXNI5xJ1jH+mKHDti8CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"17fa8aeff133ac79a36fd19c5b28f5dee4e45900566970b45030d89bee468bdd","last_reissued_at":"2026-07-05T04:34:29.455043Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:34:29.455043Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RankSim: Ranking Similarity Regularization for 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":"Frederick Tung, Greg Mori, Yu Gong","submitted_at":"2022-05-30T16:51:25Z","abstract_excerpt":"Data imbalance, in which a plurality of the data samples come from a small proportion of labels, poses a challenge in training deep neural networks. Unlike classification, in regression the labels are continuous, potentially boundless, and form a natural ordering. These distinct features of regression call for new techniques that leverage the additional information encoded in label-space relationships. This paper presents the RankSim (ranking similarity) regularizer for deep imbalanced regression, which encodes an inductive bias that samples that are closer in label space should also be closer"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.15236","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/2205.15236/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":"2205.15236","created_at":"2026-07-05T04:34:29.455097+00:00"},{"alias_kind":"arxiv_version","alias_value":"2205.15236v2","created_at":"2026-07-05T04:34:29.455097+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.15236","created_at":"2026-07-05T04:34:29.455097+00:00"},{"alias_kind":"pith_short_12","alias_value":"C75IV37RGOWH","created_at":"2026-07-05T04:34:29.455097+00:00"},{"alias_kind":"pith_short_16","alias_value":"C75IV37RGOWHTI3P","created_at":"2026-07-05T04:34:29.455097+00:00"},{"alias_kind":"pith_short_8","alias_value":"C75IV37R","created_at":"2026-07-05T04:34:29.455097+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2511.04838","citing_title":"SPECTRA: Spectral Domain-Aware Graph Generation for Imbalanced Molecular Property Regression","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14654","citing_title":"Beyond Instance-Level Self-Supervision in 3D Multi-Modal Medical Imaging","ref_index":15,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/C75IV37RGOWHTI3P2GOFWKHV33","json":"https://pith.science/pith/C75IV37RGOWHTI3P2GOFWKHV33.json","graph_json":"https://pith.science/api/pith-number/C75IV37RGOWHTI3P2GOFWKHV33/graph.json","events_json":"https://pith.science/api/pith-number/C75IV37RGOWHTI3P2GOFWKHV33/events.json","paper":"https://pith.science/paper/C75IV37R"},"agent_actions":{"view_html":"https://pith.science/pith/C75IV37RGOWHTI3P2GOFWKHV33","download_json":"https://pith.science/pith/C75IV37RGOWHTI3P2GOFWKHV33.json","view_paper":"https://pith.science/paper/C75IV37R","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2205.15236&json=true","fetch_graph":"https://pith.science/api/pith-number/C75IV37RGOWHTI3P2GOFWKHV33/graph.json","fetch_events":"https://pith.science/api/pith-number/C75IV37RGOWHTI3P2GOFWKHV33/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/C75IV37RGOWHTI3P2GOFWKHV33/action/timestamp_anchor","attest_storage":"https://pith.science/pith/C75IV37RGOWHTI3P2GOFWKHV33/action/storage_attestation","attest_author":"https://pith.science/pith/C75IV37RGOWHTI3P2GOFWKHV33/action/author_attestation","sign_citation":"https://pith.science/pith/C75IV37RGOWHTI3P2GOFWKHV33/action/citation_signature","submit_replication":"https://pith.science/pith/C75IV37RGOWHTI3P2GOFWKHV33/action/replication_record"}},"created_at":"2026-07-05T04:34:29.455097+00:00","updated_at":"2026-07-05T04:34:29.455097+00:00"}