{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:K3VDOCHGZ4DLA3AJNHKIQKIPBX","short_pith_number":"pith:K3VDOCHG","schema_version":"1.0","canonical_sha256":"56ea3708e6cf06b06c0969d488290f0dec1c554d0e816c6bd74da307211039e4","source":{"kind":"arxiv","id":"2607.08109","version":1},"attestation_state":"computed","paper":{"title":"Contrastive Order Learning: A General Framework for Ordinal Regression","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"BeomJun Shim, Chaewon Lee, Chang-Su Kim, Kwang Pyo Choi","submitted_at":"2026-07-09T04:48:26Z","abstract_excerpt":"We propose contrastive order learning (ConOrd), a contrastive learning framework for ordinal regression that integrates the strengths of contrastive learning and order learning. While contrastive learning effectively leverages all samples in a batch, it typically ignores the inherent ordering among rank labels. Conversely, order learning explicitly models label ordinality but often relies on local, margin-based comparisons, limiting its ability to capture global ordinal structure. ConOrd addresses these limitations by introducing a contrastive order loss with soft affinity and disparity weight"},"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":"2607.08109","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-09T04:48:26Z","cross_cats_sorted":[],"title_canon_sha256":"831d9aa3f047f05a714de753962be9d049d66c9c694ec3df689486bc0319a1ea","abstract_canon_sha256":"e6749a6b03ce300b095023a7e01d288311a4f2dcc7876727de11a14ea329cb26"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-10T01:19:26.299751Z","signature_b64":"HNOzLXiwnUCHZ5MqqmLcnrdCC4rraT0Mb+ynGsuBKhuzjuFNGH7sDFsQSNd7bwleT5qbWrg1vHeofxCqTp4mDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"56ea3708e6cf06b06c0969d488290f0dec1c554d0e816c6bd74da307211039e4","last_reissued_at":"2026-07-10T01:19:26.299220Z","signature_status":"signed_v1","first_computed_at":"2026-07-10T01:19:26.299220Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Contrastive Order Learning: A General Framework for Ordinal Regression","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"BeomJun Shim, Chaewon Lee, Chang-Su Kim, Kwang Pyo Choi","submitted_at":"2026-07-09T04:48:26Z","abstract_excerpt":"We propose contrastive order learning (ConOrd), a contrastive learning framework for ordinal regression that integrates the strengths of contrastive learning and order learning. While contrastive learning effectively leverages all samples in a batch, it typically ignores the inherent ordering among rank labels. Conversely, order learning explicitly models label ordinality but often relies on local, margin-based comparisons, limiting its ability to capture global ordinal structure. ConOrd addresses these limitations by introducing a contrastive order loss with soft affinity and disparity weight"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.08109","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/2607.08109/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":"2607.08109","created_at":"2026-07-10T01:19:26.299282+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.08109v1","created_at":"2026-07-10T01:19:26.299282+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.08109","created_at":"2026-07-10T01:19:26.299282+00:00"},{"alias_kind":"pith_short_12","alias_value":"K3VDOCHGZ4DL","created_at":"2026-07-10T01:19:26.299282+00:00"},{"alias_kind":"pith_short_16","alias_value":"K3VDOCHGZ4DLA3AJ","created_at":"2026-07-10T01:19:26.299282+00:00"},{"alias_kind":"pith_short_8","alias_value":"K3VDOCHG","created_at":"2026-07-10T01:19:26.299282+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/K3VDOCHGZ4DLA3AJNHKIQKIPBX","json":"https://pith.science/pith/K3VDOCHGZ4DLA3AJNHKIQKIPBX.json","graph_json":"https://pith.science/api/pith-number/K3VDOCHGZ4DLA3AJNHKIQKIPBX/graph.json","events_json":"https://pith.science/api/pith-number/K3VDOCHGZ4DLA3AJNHKIQKIPBX/events.json","paper":"https://pith.science/paper/K3VDOCHG"},"agent_actions":{"view_html":"https://pith.science/pith/K3VDOCHGZ4DLA3AJNHKIQKIPBX","download_json":"https://pith.science/pith/K3VDOCHGZ4DLA3AJNHKIQKIPBX.json","view_paper":"https://pith.science/paper/K3VDOCHG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.08109&json=true","fetch_graph":"https://pith.science/api/pith-number/K3VDOCHGZ4DLA3AJNHKIQKIPBX/graph.json","fetch_events":"https://pith.science/api/pith-number/K3VDOCHGZ4DLA3AJNHKIQKIPBX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/K3VDOCHGZ4DLA3AJNHKIQKIPBX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/K3VDOCHGZ4DLA3AJNHKIQKIPBX/action/storage_attestation","attest_author":"https://pith.science/pith/K3VDOCHGZ4DLA3AJNHKIQKIPBX/action/author_attestation","sign_citation":"https://pith.science/pith/K3VDOCHGZ4DLA3AJNHKIQKIPBX/action/citation_signature","submit_replication":"https://pith.science/pith/K3VDOCHGZ4DLA3AJNHKIQKIPBX/action/replication_record"}},"created_at":"2026-07-10T01:19:26.299282+00:00","updated_at":"2026-07-10T01:19:26.299282+00:00"}