{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:OER45WRJ55F3EYD2JFCVWRSDVF","short_pith_number":"pith:OER45WRJ","schema_version":"1.0","canonical_sha256":"7123ceda29ef4bb2607a49455b4643a9444f02debf99c629223305aa235f96f2","source":{"kind":"arxiv","id":"2411.06353","version":2},"attestation_state":"computed","paper":{"title":"Deep Active Learning in the Open World","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Haoyue Bai, Jifan Zhang, Robert Nowak, Tian Xie","submitted_at":"2024-11-10T04:04:20Z","abstract_excerpt":"Machine learning models deployed in open-world scenarios often encounter unfamiliar conditions and perform poorly in unanticipated situations. As AI systems advance and find application in safety-critical domains, effectively handling out-of-distribution (OOD) data is crucial to building open-world learning systems. In this work, we introduce ALOE, a novel active learning algorithm for open-world environments designed to enhance model adaptation by incorporating new OOD classes via a two-stage approach. First, diversity sampling selects a representative set of examples, followed by energy-base"},"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":"2411.06353","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-10T04:04:20Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"1b2c3510059165d7dc8d0a8e92daa22f51d1c6a009adbe27c0f60e70ce1ca084","abstract_canon_sha256":"c14bcd3fe1af823d981e1819249eeb78b5a5f2b9796491fd0563697adcd38610"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:51:04.745621Z","signature_b64":"B8pIT2sJSQi0ntvpAtIX1kNeDVw+OQCTqKt/dQU3tfCZJmbvI/v0z5eOjpEYVyJTfHLWJdm3mNzJ39jFXpauAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7123ceda29ef4bb2607a49455b4643a9444f02debf99c629223305aa235f96f2","last_reissued_at":"2026-07-05T10:51:04.745095Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:51:04.745095Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep Active Learning in the Open World","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Haoyue Bai, Jifan Zhang, Robert Nowak, Tian Xie","submitted_at":"2024-11-10T04:04:20Z","abstract_excerpt":"Machine learning models deployed in open-world scenarios often encounter unfamiliar conditions and perform poorly in unanticipated situations. As AI systems advance and find application in safety-critical domains, effectively handling out-of-distribution (OOD) data is crucial to building open-world learning systems. In this work, we introduce ALOE, a novel active learning algorithm for open-world environments designed to enhance model adaptation by incorporating new OOD classes via a two-stage approach. First, diversity sampling selects a representative set of examples, followed by energy-base"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.06353","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/2411.06353/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":"2411.06353","created_at":"2026-07-05T10:51:04.745157+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.06353v2","created_at":"2026-07-05T10:51:04.745157+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.06353","created_at":"2026-07-05T10:51:04.745157+00:00"},{"alias_kind":"pith_short_12","alias_value":"OER45WRJ55F3","created_at":"2026-07-05T10:51:04.745157+00:00"},{"alias_kind":"pith_short_16","alias_value":"OER45WRJ55F3EYD2","created_at":"2026-07-05T10:51:04.745157+00:00"},{"alias_kind":"pith_short_8","alias_value":"OER45WRJ","created_at":"2026-07-05T10:51:04.745157+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.14762","citing_title":"OmniGCD: Abstracting Generalized Category Discovery for Modality Agnosticism","ref_index":62,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OER45WRJ55F3EYD2JFCVWRSDVF","json":"https://pith.science/pith/OER45WRJ55F3EYD2JFCVWRSDVF.json","graph_json":"https://pith.science/api/pith-number/OER45WRJ55F3EYD2JFCVWRSDVF/graph.json","events_json":"https://pith.science/api/pith-number/OER45WRJ55F3EYD2JFCVWRSDVF/events.json","paper":"https://pith.science/paper/OER45WRJ"},"agent_actions":{"view_html":"https://pith.science/pith/OER45WRJ55F3EYD2JFCVWRSDVF","download_json":"https://pith.science/pith/OER45WRJ55F3EYD2JFCVWRSDVF.json","view_paper":"https://pith.science/paper/OER45WRJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.06353&json=true","fetch_graph":"https://pith.science/api/pith-number/OER45WRJ55F3EYD2JFCVWRSDVF/graph.json","fetch_events":"https://pith.science/api/pith-number/OER45WRJ55F3EYD2JFCVWRSDVF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OER45WRJ55F3EYD2JFCVWRSDVF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OER45WRJ55F3EYD2JFCVWRSDVF/action/storage_attestation","attest_author":"https://pith.science/pith/OER45WRJ55F3EYD2JFCVWRSDVF/action/author_attestation","sign_citation":"https://pith.science/pith/OER45WRJ55F3EYD2JFCVWRSDVF/action/citation_signature","submit_replication":"https://pith.science/pith/OER45WRJ55F3EYD2JFCVWRSDVF/action/replication_record"}},"created_at":"2026-07-05T10:51:04.745157+00:00","updated_at":"2026-07-05T10:51:04.745157+00:00"}