{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:JCI4TNUDUIBRJAZLTKV7SDENKV","short_pith_number":"pith:JCI4TNUD","schema_version":"1.0","canonical_sha256":"4891c9b683a20314832b9aabf90c8d55558763d8d0fe72ef619b732317cf23b5","source":{"kind":"arxiv","id":"2410.08000","version":1},"attestation_state":"computed","paper":{"title":"AHA: Human-Assisted Out-of-Distribution Generalization and Detection","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Haoyue Bai, Jifan Zhang, Robert Nowak","submitted_at":"2024-10-10T14:57:11Z","abstract_excerpt":"Modern machine learning models deployed often encounter distribution shifts in real-world applications, manifesting as covariate or semantic out-of-distribution (OOD) shifts. These shifts give rise to challenges in OOD generalization and OOD detection. This paper introduces a novel, integrated approach AHA (Adaptive Human-Assisted OOD learning) to simultaneously address both OOD generalization and detection through a human-assisted framework by labeling data in the wild. Our approach strategically labels examples within a novel maximum disambiguation region, where the number of semantic and co"},"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":"2410.08000","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-10T14:57:11Z","cross_cats_sorted":[],"title_canon_sha256":"5e870dd042543ce53f828f657c681c629ab4403e0b226527c809dbaadeb79631","abstract_canon_sha256":"5899c26b22f7aebf82b8c36b003717563001cdbda417268378d514ba62eeec12"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:18:47.194436Z","signature_b64":"w93ymrrEKbe6gHYOO5zFHeGkJUZv2s/gB3EWCfCN7e24sGp3r94TCSNxApVk2c8LuxCRB5vx6uMOpbLQwV+ICA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4891c9b683a20314832b9aabf90c8d55558763d8d0fe72ef619b732317cf23b5","last_reissued_at":"2026-07-05T09:18:47.193989Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:18:47.193989Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AHA: Human-Assisted Out-of-Distribution Generalization and Detection","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Haoyue Bai, Jifan Zhang, Robert Nowak","submitted_at":"2024-10-10T14:57:11Z","abstract_excerpt":"Modern machine learning models deployed often encounter distribution shifts in real-world applications, manifesting as covariate or semantic out-of-distribution (OOD) shifts. These shifts give rise to challenges in OOD generalization and OOD detection. This paper introduces a novel, integrated approach AHA (Adaptive Human-Assisted OOD learning) to simultaneously address both OOD generalization and detection through a human-assisted framework by labeling data in the wild. Our approach strategically labels examples within a novel maximum disambiguation region, where the number of semantic and co"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.08000","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/2410.08000/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":"2410.08000","created_at":"2026-07-05T09:18:47.194049+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.08000v1","created_at":"2026-07-05T09:18:47.194049+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.08000","created_at":"2026-07-05T09:18:47.194049+00:00"},{"alias_kind":"pith_short_12","alias_value":"JCI4TNUDUIBR","created_at":"2026-07-05T09:18:47.194049+00:00"},{"alias_kind":"pith_short_16","alias_value":"JCI4TNUDUIBRJAZL","created_at":"2026-07-05T09:18:47.194049+00:00"},{"alias_kind":"pith_short_8","alias_value":"JCI4TNUD","created_at":"2026-07-05T09:18:47.194049+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.01596","citing_title":"FEVER-OOD: Free Energy Vulnerability Elimination for Robust Out-of-Distribution Detection","ref_index":2,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JCI4TNUDUIBRJAZLTKV7SDENKV","json":"https://pith.science/pith/JCI4TNUDUIBRJAZLTKV7SDENKV.json","graph_json":"https://pith.science/api/pith-number/JCI4TNUDUIBRJAZLTKV7SDENKV/graph.json","events_json":"https://pith.science/api/pith-number/JCI4TNUDUIBRJAZLTKV7SDENKV/events.json","paper":"https://pith.science/paper/JCI4TNUD"},"agent_actions":{"view_html":"https://pith.science/pith/JCI4TNUDUIBRJAZLTKV7SDENKV","download_json":"https://pith.science/pith/JCI4TNUDUIBRJAZLTKV7SDENKV.json","view_paper":"https://pith.science/paper/JCI4TNUD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.08000&json=true","fetch_graph":"https://pith.science/api/pith-number/JCI4TNUDUIBRJAZLTKV7SDENKV/graph.json","fetch_events":"https://pith.science/api/pith-number/JCI4TNUDUIBRJAZLTKV7SDENKV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JCI4TNUDUIBRJAZLTKV7SDENKV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JCI4TNUDUIBRJAZLTKV7SDENKV/action/storage_attestation","attest_author":"https://pith.science/pith/JCI4TNUDUIBRJAZLTKV7SDENKV/action/author_attestation","sign_citation":"https://pith.science/pith/JCI4TNUDUIBRJAZLTKV7SDENKV/action/citation_signature","submit_replication":"https://pith.science/pith/JCI4TNUDUIBRJAZLTKV7SDENKV/action/replication_record"}},"created_at":"2026-07-05T09:18:47.194049+00:00","updated_at":"2026-07-05T09:18:47.194049+00:00"}