{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:G2QVHSDMEW2MLEBQBF5PX6FCQU","short_pith_number":"pith:G2QVHSDM","schema_version":"1.0","canonical_sha256":"36a153c86c25b4c59030097afbf8a285367b6133cf337818dbb9faecf2cfa01a","source":{"kind":"arxiv","id":"2607.23575","version":1},"attestation_state":"computed","paper":{"title":"D3O: Dynamic Distribution Distillation for Ordinal Regression","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chunlai Dong, Haochao Ying, Jian Wu, Yaojun Hu, Yuyang Xu","submitted_at":"2026-07-26T09:58:04Z","abstract_excerpt":"Ordinal regression is widely used in scenarios where labels are discrete yet inherently ordered. In practice, however, ordinal labels are often obtained by discretizing underlying continuous semantics through subjective human judgment, resulting in ambiguous boundaries and annotation noise. Such uncertainty challenges existing methods that rely on fixed supervision targets, which may reinforce biased ordering under subjective annotations. To address this limitation, we propose D3O, a dynamic distribution distillation framework that replaces static supervision with training-driven evolution of "},"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":"2607.23575","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-26T09:58:04Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a30c8e0a545f866bce464df11eec51c8fa54299852307f8b71f63025b2930f42","abstract_canon_sha256":"b61de7038315e3acb8c1ffc2822686bdb3b4ab0e44c598ccbb2196bfc1804cd4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-28T01:23:00.169034Z","signature_b64":"hvtI7UIiKkuocBRB4xMvasH0YqeHMxwBP28Aszex4W0FxLWTLyURM55HpGc1Bylrp66Ukw+Jlamewii5Em4pAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"36a153c86c25b4c59030097afbf8a285367b6133cf337818dbb9faecf2cfa01a","last_reissued_at":"2026-07-28T01:23:00.168220Z","signature_status":"signed_v1","first_computed_at":"2026-07-28T01:23:00.168220Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"D3O: Dynamic Distribution Distillation for Ordinal Regression","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chunlai Dong, Haochao Ying, Jian Wu, Yaojun Hu, Yuyang Xu","submitted_at":"2026-07-26T09:58:04Z","abstract_excerpt":"Ordinal regression is widely used in scenarios where labels are discrete yet inherently ordered. In practice, however, ordinal labels are often obtained by discretizing underlying continuous semantics through subjective human judgment, resulting in ambiguous boundaries and annotation noise. Such uncertainty challenges existing methods that rely on fixed supervision targets, which may reinforce biased ordering under subjective annotations. To address this limitation, we propose D3O, a dynamic distribution distillation framework that replaces static supervision with training-driven evolution of "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.23575","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/2607.23575/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":"2607.23575","created_at":"2026-07-28T01:23:00.168650+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.23575v1","created_at":"2026-07-28T01:23:00.168650+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.23575","created_at":"2026-07-28T01:23:00.168650+00:00"},{"alias_kind":"pith_short_12","alias_value":"G2QVHSDMEW2M","created_at":"2026-07-28T01:23:00.168650+00:00"},{"alias_kind":"pith_short_16","alias_value":"G2QVHSDMEW2MLEBQ","created_at":"2026-07-28T01:23:00.168650+00:00"},{"alias_kind":"pith_short_8","alias_value":"G2QVHSDM","created_at":"2026-07-28T01:23:00.168650+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/G2QVHSDMEW2MLEBQBF5PX6FCQU","json":"https://pith.science/pith/G2QVHSDMEW2MLEBQBF5PX6FCQU.json","graph_json":"https://pith.science/api/pith-number/G2QVHSDMEW2MLEBQBF5PX6FCQU/graph.json","events_json":"https://pith.science/api/pith-number/G2QVHSDMEW2MLEBQBF5PX6FCQU/events.json","paper":"https://pith.science/paper/G2QVHSDM"},"agent_actions":{"view_html":"https://pith.science/pith/G2QVHSDMEW2MLEBQBF5PX6FCQU","download_json":"https://pith.science/pith/G2QVHSDMEW2MLEBQBF5PX6FCQU.json","view_paper":"https://pith.science/paper/G2QVHSDM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.23575&json=true","fetch_graph":"https://pith.science/api/pith-number/G2QVHSDMEW2MLEBQBF5PX6FCQU/graph.json","fetch_events":"https://pith.science/api/pith-number/G2QVHSDMEW2MLEBQBF5PX6FCQU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/G2QVHSDMEW2MLEBQBF5PX6FCQU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/G2QVHSDMEW2MLEBQBF5PX6FCQU/action/storage_attestation","attest_author":"https://pith.science/pith/G2QVHSDMEW2MLEBQBF5PX6FCQU/action/author_attestation","sign_citation":"https://pith.science/pith/G2QVHSDMEW2MLEBQBF5PX6FCQU/action/citation_signature","submit_replication":"https://pith.science/pith/G2QVHSDMEW2MLEBQBF5PX6FCQU/action/replication_record"}},"created_at":"2026-07-28T01:23:00.168650+00:00","updated_at":"2026-07-28T01:23:00.168650+00:00"}