{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:HH3SM3L32V6GH2CU77CFFVTZQB","short_pith_number":"pith:HH3SM3L3","schema_version":"1.0","canonical_sha256":"39f7266d7bd57c63e854ffc452d679805871fe9a08212b067236a4078f93ddc9","source":{"kind":"arxiv","id":"2007.04391","version":1},"attestation_state":"computed","paper":{"title":"A Critical Evaluation of Open-World Machine Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.LG","authors_text":"Arjun Nitin Bhagoji, Liwei Song, Prateek Mittal, Vikash Sehwag","submitted_at":"2020-07-08T19:40:07Z","abstract_excerpt":"Open-world machine learning (ML) combines closed-world models trained on in-distribution data with out-of-distribution (OOD) detectors, which aim to detect and reject OOD inputs. Previous works on open-world ML systems usually fail to test their reliability under diverse, and possibly adversarial conditions. Therefore, in this paper, we seek to understand how resilient are state-of-the-art open-world ML systems to changes in system components? With our evaluation across 6 OOD detectors, we find that the choice of in-distribution data, model architecture and OOD data have a strong impact on OOD"},"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":"2007.04391","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-08T19:40:07Z","cross_cats_sorted":["cs.CR"],"title_canon_sha256":"b92802963861b4bbd9ba4185c1556bc79bfadb1c22b516e540fe43caa7ee14b1","abstract_canon_sha256":"d4156434bc2bc63a7be8410644d81b9581450cd8cda89404bac3f8dd1050a939"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:17:29.794071Z","signature_b64":"kOaQJCO4Jsdx1qTOF8u8Q6T7JH08qo4rlU/5B28TY5OHQ1Y7nQn63iks2yf3QCxi91qXSmqO/6eYgGYxIL0vCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"39f7266d7bd57c63e854ffc452d679805871fe9a08212b067236a4078f93ddc9","last_reissued_at":"2026-07-05T01:17:29.793713Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:17:29.793713Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Critical Evaluation of Open-World Machine Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.LG","authors_text":"Arjun Nitin Bhagoji, Liwei Song, Prateek Mittal, Vikash Sehwag","submitted_at":"2020-07-08T19:40:07Z","abstract_excerpt":"Open-world machine learning (ML) combines closed-world models trained on in-distribution data with out-of-distribution (OOD) detectors, which aim to detect and reject OOD inputs. Previous works on open-world ML systems usually fail to test their reliability under diverse, and possibly adversarial conditions. Therefore, in this paper, we seek to understand how resilient are state-of-the-art open-world ML systems to changes in system components? With our evaluation across 6 OOD detectors, we find that the choice of in-distribution data, model architecture and OOD data have a strong impact on OOD"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.04391","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/2007.04391/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":"2007.04391","created_at":"2026-07-05T01:17:29.793769+00:00"},{"alias_kind":"arxiv_version","alias_value":"2007.04391v1","created_at":"2026-07-05T01:17:29.793769+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.04391","created_at":"2026-07-05T01:17:29.793769+00:00"},{"alias_kind":"pith_short_12","alias_value":"HH3SM3L32V6G","created_at":"2026-07-05T01:17:29.793769+00:00"},{"alias_kind":"pith_short_16","alias_value":"HH3SM3L32V6GH2CU","created_at":"2026-07-05T01:17:29.793769+00:00"},{"alias_kind":"pith_short_8","alias_value":"HH3SM3L3","created_at":"2026-07-05T01:17:29.793769+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/HH3SM3L32V6GH2CU77CFFVTZQB","json":"https://pith.science/pith/HH3SM3L32V6GH2CU77CFFVTZQB.json","graph_json":"https://pith.science/api/pith-number/HH3SM3L32V6GH2CU77CFFVTZQB/graph.json","events_json":"https://pith.science/api/pith-number/HH3SM3L32V6GH2CU77CFFVTZQB/events.json","paper":"https://pith.science/paper/HH3SM3L3"},"agent_actions":{"view_html":"https://pith.science/pith/HH3SM3L32V6GH2CU77CFFVTZQB","download_json":"https://pith.science/pith/HH3SM3L32V6GH2CU77CFFVTZQB.json","view_paper":"https://pith.science/paper/HH3SM3L3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2007.04391&json=true","fetch_graph":"https://pith.science/api/pith-number/HH3SM3L32V6GH2CU77CFFVTZQB/graph.json","fetch_events":"https://pith.science/api/pith-number/HH3SM3L32V6GH2CU77CFFVTZQB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HH3SM3L32V6GH2CU77CFFVTZQB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HH3SM3L32V6GH2CU77CFFVTZQB/action/storage_attestation","attest_author":"https://pith.science/pith/HH3SM3L32V6GH2CU77CFFVTZQB/action/author_attestation","sign_citation":"https://pith.science/pith/HH3SM3L32V6GH2CU77CFFVTZQB/action/citation_signature","submit_replication":"https://pith.science/pith/HH3SM3L32V6GH2CU77CFFVTZQB/action/replication_record"}},"created_at":"2026-07-05T01:17:29.793769+00:00","updated_at":"2026-07-05T01:17:29.793769+00:00"}