{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:IJW2CTINVHJCMIDPGN5Y4FOF72","short_pith_number":"pith:IJW2CTIN","schema_version":"1.0","canonical_sha256":"426da14d0da9d226206f337b8e15c5fe9267ade87a43ab67ef081e4f3031d488","source":{"kind":"arxiv","id":"2101.09193","version":3},"attestation_state":"computed","paper":{"title":"Dense outlier detection and open-set recognition based on training with noisy negative images","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ivan Kre\\v{s}o, Marin Or\\v{s}i\\'c, Petra Bevandi\\'c, Sini\\v{s}a \\v{S}egvi\\'c","submitted_at":"2021-01-22T16:31:36Z","abstract_excerpt":"Deep convolutional models often produce inadequate predictions for inputs foreign to the training distribution. Consequently, the problem of detecting outlier images has recently been receiving a lot of attention. Unlike most previous work, we address this problem in the dense prediction context in order to be able to locate outlier objects in front of in-distribution background. Our approach is based on two reasonable assumptions. First, we assume that the inlier dataset is related to some narrow application field (e.g.~road driving). Second, we assume that there exists a general-purpose data"},"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":"2101.09193","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-01-22T16:31:36Z","cross_cats_sorted":[],"title_canon_sha256":"0b3ef68fe9799c7afce0be9cf98a7f0853062bd04c4c014b6ac4f4a88e229e2a","abstract_canon_sha256":"f9acec45c7a6eafda75616e1fb5c115d56f325ed6c1982dd721da49540b26466"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:54:46.050007Z","signature_b64":"iooO7wcrCLceAlMmBOKPU8+wi3pcU1ipyZCWXRewCV/JYB96QDfHFJR0LjL39OUXcQvXLGpPElWP6puu2bYYDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"426da14d0da9d226206f337b8e15c5fe9267ade87a43ab67ef081e4f3031d488","last_reissued_at":"2026-07-05T07:54:46.049626Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:54:46.049626Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dense outlier detection and open-set recognition based on training with noisy negative images","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ivan Kre\\v{s}o, Marin Or\\v{s}i\\'c, Petra Bevandi\\'c, Sini\\v{s}a \\v{S}egvi\\'c","submitted_at":"2021-01-22T16:31:36Z","abstract_excerpt":"Deep convolutional models often produce inadequate predictions for inputs foreign to the training distribution. Consequently, the problem of detecting outlier images has recently been receiving a lot of attention. Unlike most previous work, we address this problem in the dense prediction context in order to be able to locate outlier objects in front of in-distribution background. Our approach is based on two reasonable assumptions. First, we assume that the inlier dataset is related to some narrow application field (e.g.~road driving). Second, we assume that there exists a general-purpose data"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2101.09193","kind":"arxiv","version":3},"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/2101.09193/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":"2101.09193","created_at":"2026-07-05T07:54:46.049685+00:00"},{"alias_kind":"arxiv_version","alias_value":"2101.09193v3","created_at":"2026-07-05T07:54:46.049685+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2101.09193","created_at":"2026-07-05T07:54:46.049685+00:00"},{"alias_kind":"pith_short_12","alias_value":"IJW2CTINVHJC","created_at":"2026-07-05T07:54:46.049685+00:00"},{"alias_kind":"pith_short_16","alias_value":"IJW2CTINVHJCMIDP","created_at":"2026-07-05T07:54:46.049685+00:00"},{"alias_kind":"pith_short_8","alias_value":"IJW2CTIN","created_at":"2026-07-05T07:54:46.049685+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2501.08083","citing_title":"Benchmarking Vision Foundation Models for Input Monitoring in Autonomous Driving","ref_index":5,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IJW2CTINVHJCMIDPGN5Y4FOF72","json":"https://pith.science/pith/IJW2CTINVHJCMIDPGN5Y4FOF72.json","graph_json":"https://pith.science/api/pith-number/IJW2CTINVHJCMIDPGN5Y4FOF72/graph.json","events_json":"https://pith.science/api/pith-number/IJW2CTINVHJCMIDPGN5Y4FOF72/events.json","paper":"https://pith.science/paper/IJW2CTIN"},"agent_actions":{"view_html":"https://pith.science/pith/IJW2CTINVHJCMIDPGN5Y4FOF72","download_json":"https://pith.science/pith/IJW2CTINVHJCMIDPGN5Y4FOF72.json","view_paper":"https://pith.science/paper/IJW2CTIN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2101.09193&json=true","fetch_graph":"https://pith.science/api/pith-number/IJW2CTINVHJCMIDPGN5Y4FOF72/graph.json","fetch_events":"https://pith.science/api/pith-number/IJW2CTINVHJCMIDPGN5Y4FOF72/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IJW2CTINVHJCMIDPGN5Y4FOF72/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IJW2CTINVHJCMIDPGN5Y4FOF72/action/storage_attestation","attest_author":"https://pith.science/pith/IJW2CTINVHJCMIDPGN5Y4FOF72/action/author_attestation","sign_citation":"https://pith.science/pith/IJW2CTINVHJCMIDPGN5Y4FOF72/action/citation_signature","submit_replication":"https://pith.science/pith/IJW2CTINVHJCMIDPGN5Y4FOF72/action/replication_record"}},"created_at":"2026-07-05T07:54:46.049685+00:00","updated_at":"2026-07-05T07:54:46.049685+00:00"}