{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:3O6BHSXA66V6DBTFPKOFJYVL2A","short_pith_number":"pith:3O6BHSXA","schema_version":"1.0","canonical_sha256":"dbbc13cae0f7abe186657a9c54e2abd015d44eceb65d1df937635c230926b97a","source":{"kind":"arxiv","id":"2106.03917","version":4},"attestation_state":"computed","paper":{"title":"Mixture Outlier Exposure: Towards Out-of-Distribution Detection in Fine-grained Environments","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Hai Li, Jingyang Zhang, Nathan Inkawhich, Randolph Linderman, Yiran Chen","submitted_at":"2021-06-07T19:01:17Z","abstract_excerpt":"Many real-world scenarios in which DNN-based recognition systems are deployed have inherently fine-grained attributes (e.g., bird-species recognition, medical image classification). In addition to achieving reliable accuracy, a critical subtask for these models is to detect Out-of-distribution (OOD) inputs. Given the nature of the deployment environment, one may expect such OOD inputs to also be fine-grained w.r.t. the known classes (e.g., a novel bird species), which are thus extremely difficult to identify. Unfortunately, OOD detection in fine-grained scenarios remains largely underexplored."},"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":"2106.03917","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-06-07T19:01:17Z","cross_cats_sorted":[],"title_canon_sha256":"73c395e7588c5da3adaba252eadc7d091f531d95e1fc8c16341ecc4ff3635a2a","abstract_canon_sha256":"ac53c548adeb070e9be7447412e1488d1ef6c8a3de3631aaa4db3b9426db385d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:08:25.053836Z","signature_b64":"Wzv3nY3FKfpZLBx6NfmqyeMGnNB1QAZLn2c+pfUSXw2fj5qzytrcYKsg46me9nviSuJOJ6rtrCdo15qbbeSiAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dbbc13cae0f7abe186657a9c54e2abd015d44eceb65d1df937635c230926b97a","last_reissued_at":"2026-07-05T05:08:25.053432Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:08:25.053432Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Mixture Outlier Exposure: Towards Out-of-Distribution Detection in Fine-grained Environments","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Hai Li, Jingyang Zhang, Nathan Inkawhich, Randolph Linderman, Yiran Chen","submitted_at":"2021-06-07T19:01:17Z","abstract_excerpt":"Many real-world scenarios in which DNN-based recognition systems are deployed have inherently fine-grained attributes (e.g., bird-species recognition, medical image classification). In addition to achieving reliable accuracy, a critical subtask for these models is to detect Out-of-distribution (OOD) inputs. Given the nature of the deployment environment, one may expect such OOD inputs to also be fine-grained w.r.t. the known classes (e.g., a novel bird species), which are thus extremely difficult to identify. Unfortunately, OOD detection in fine-grained scenarios remains largely underexplored."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.03917","kind":"arxiv","version":4},"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/2106.03917/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":"2106.03917","created_at":"2026-07-05T05:08:25.053495+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.03917v4","created_at":"2026-07-05T05:08:25.053495+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.03917","created_at":"2026-07-05T05:08:25.053495+00:00"},{"alias_kind":"pith_short_12","alias_value":"3O6BHSXA66V6","created_at":"2026-07-05T05:08:25.053495+00:00"},{"alias_kind":"pith_short_16","alias_value":"3O6BHSXA66V6DBTF","created_at":"2026-07-05T05:08:25.053495+00:00"},{"alias_kind":"pith_short_8","alias_value":"3O6BHSXA","created_at":"2026-07-05T05:08:25.053495+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/3O6BHSXA66V6DBTFPKOFJYVL2A","json":"https://pith.science/pith/3O6BHSXA66V6DBTFPKOFJYVL2A.json","graph_json":"https://pith.science/api/pith-number/3O6BHSXA66V6DBTFPKOFJYVL2A/graph.json","events_json":"https://pith.science/api/pith-number/3O6BHSXA66V6DBTFPKOFJYVL2A/events.json","paper":"https://pith.science/paper/3O6BHSXA"},"agent_actions":{"view_html":"https://pith.science/pith/3O6BHSXA66V6DBTFPKOFJYVL2A","download_json":"https://pith.science/pith/3O6BHSXA66V6DBTFPKOFJYVL2A.json","view_paper":"https://pith.science/paper/3O6BHSXA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.03917&json=true","fetch_graph":"https://pith.science/api/pith-number/3O6BHSXA66V6DBTFPKOFJYVL2A/graph.json","fetch_events":"https://pith.science/api/pith-number/3O6BHSXA66V6DBTFPKOFJYVL2A/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3O6BHSXA66V6DBTFPKOFJYVL2A/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3O6BHSXA66V6DBTFPKOFJYVL2A/action/storage_attestation","attest_author":"https://pith.science/pith/3O6BHSXA66V6DBTFPKOFJYVL2A/action/author_attestation","sign_citation":"https://pith.science/pith/3O6BHSXA66V6DBTFPKOFJYVL2A/action/citation_signature","submit_replication":"https://pith.science/pith/3O6BHSXA66V6DBTFPKOFJYVL2A/action/replication_record"}},"created_at":"2026-07-05T05:08:25.053495+00:00","updated_at":"2026-07-05T05:08:25.053495+00:00"}