{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:HOYPQXJU2B2D6S2DOEE63XN4GC","short_pith_number":"pith:HOYPQXJU","schema_version":"1.0","canonical_sha256":"3bb0f85d34d0743f4b437109edddbc3088f88d50f1db09a24f5ad7e8a11eed55","source":{"kind":"arxiv","id":"2605.23268","version":1},"attestation_state":"computed","paper":{"title":"Coupled Training with Privileged Information and Unlabeled Data","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Jason M. Klusowski, Jiahao Shi, Omar Hagrass","submitted_at":"2026-05-22T06:15:35Z","abstract_excerpt":"In many prediction problems, we have extra information during training (for example, measurements that are expensive or slow to collect) that will not be available when the model is deployed. A common strategy is to first train a model that uses all training information, then use its predictions on unlabeled examples to train a second model that only uses the inputs available at test time. However, when the extra training-only information is weak or noisy, this Two-Stage approach can mislead the deployment model and even hurt accuracy. We propose a joint training method that learns the two mod"},"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":"2605.23268","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"stat.ML","submitted_at":"2026-05-22T06:15:35Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"946f00df210ca1a45088d8fc2189b271030b6ffa80871004586ca7edf213980c","abstract_canon_sha256":"4a0542191625845f1379d77ab35b05790557c7b62e1b5fd1b2d77161e25ce889"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-25T02:01:46.469370Z","signature_b64":"fQTbY+OdDac+jBZ06+HLgn0cwQJKof7mOK9UMs2pgf8N4n0TBAb/bjY79L70ZOZcK4ZYVGwu531v2cJXAvxTBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3bb0f85d34d0743f4b437109edddbc3088f88d50f1db09a24f5ad7e8a11eed55","last_reissued_at":"2026-05-25T02:01:46.468840Z","signature_status":"signed_v1","first_computed_at":"2026-05-25T02:01:46.468840Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Coupled Training with Privileged Information and Unlabeled Data","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Jason M. Klusowski, Jiahao Shi, Omar Hagrass","submitted_at":"2026-05-22T06:15:35Z","abstract_excerpt":"In many prediction problems, we have extra information during training (for example, measurements that are expensive or slow to collect) that will not be available when the model is deployed. A common strategy is to first train a model that uses all training information, then use its predictions on unlabeled examples to train a second model that only uses the inputs available at test time. However, when the extra training-only information is weak or noisy, this Two-Stage approach can mislead the deployment model and even hurt accuracy. We propose a joint training method that learns the two mod"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.23268","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/2605.23268/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":"2605.23268","created_at":"2026-05-25T02:01:46.468925+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.23268v1","created_at":"2026-05-25T02:01:46.468925+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.23268","created_at":"2026-05-25T02:01:46.468925+00:00"},{"alias_kind":"pith_short_12","alias_value":"HOYPQXJU2B2D","created_at":"2026-05-25T02:01:46.468925+00:00"},{"alias_kind":"pith_short_16","alias_value":"HOYPQXJU2B2D6S2D","created_at":"2026-05-25T02:01:46.468925+00:00"},{"alias_kind":"pith_short_8","alias_value":"HOYPQXJU","created_at":"2026-05-25T02:01:46.468925+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/HOYPQXJU2B2D6S2DOEE63XN4GC","json":"https://pith.science/pith/HOYPQXJU2B2D6S2DOEE63XN4GC.json","graph_json":"https://pith.science/api/pith-number/HOYPQXJU2B2D6S2DOEE63XN4GC/graph.json","events_json":"https://pith.science/api/pith-number/HOYPQXJU2B2D6S2DOEE63XN4GC/events.json","paper":"https://pith.science/paper/HOYPQXJU"},"agent_actions":{"view_html":"https://pith.science/pith/HOYPQXJU2B2D6S2DOEE63XN4GC","download_json":"https://pith.science/pith/HOYPQXJU2B2D6S2DOEE63XN4GC.json","view_paper":"https://pith.science/paper/HOYPQXJU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.23268&json=true","fetch_graph":"https://pith.science/api/pith-number/HOYPQXJU2B2D6S2DOEE63XN4GC/graph.json","fetch_events":"https://pith.science/api/pith-number/HOYPQXJU2B2D6S2DOEE63XN4GC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HOYPQXJU2B2D6S2DOEE63XN4GC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HOYPQXJU2B2D6S2DOEE63XN4GC/action/storage_attestation","attest_author":"https://pith.science/pith/HOYPQXJU2B2D6S2DOEE63XN4GC/action/author_attestation","sign_citation":"https://pith.science/pith/HOYPQXJU2B2D6S2DOEE63XN4GC/action/citation_signature","submit_replication":"https://pith.science/pith/HOYPQXJU2B2D6S2DOEE63XN4GC/action/replication_record"}},"created_at":"2026-05-25T02:01:46.468925+00:00","updated_at":"2026-05-25T02:01:46.468925+00:00"}