{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:M3QZCBNND6HM3LCA7VXSB2I7AV","short_pith_number":"pith:M3QZCBNN","canonical_record":{"source":{"id":"1809.03576","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-04T16:00:08Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"889cba1decd3f9bb2bf4998182bd839bd3e7c912cf7e1d977c6b61a2949f3758","abstract_canon_sha256":"ddd89c10328af2f9839e31a32f094913b0174babd1b6469075f882649511b20e"},"schema_version":"1.0"},"canonical_sha256":"66e19105ad1f8ecdac40fd6f20e91f0572c05ae9adf54a18442663ea1d31260e","source":{"kind":"arxiv","id":"1809.03576","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1809.03576","created_at":"2026-05-18T00:06:00Z"},{"alias_kind":"arxiv_version","alias_value":"1809.03576v1","created_at":"2026-05-18T00:06:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.03576","created_at":"2026-05-18T00:06:00Z"},{"alias_kind":"pith_short_12","alias_value":"M3QZCBNND6HM","created_at":"2026-05-18T12:32:37Z"},{"alias_kind":"pith_short_16","alias_value":"M3QZCBNND6HM3LCA","created_at":"2026-05-18T12:32:37Z"},{"alias_kind":"pith_short_8","alias_value":"M3QZCBNN","created_at":"2026-05-18T12:32:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:M3QZCBNND6HM3LCA7VXSB2I7AV","target":"record","payload":{"canonical_record":{"source":{"id":"1809.03576","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-04T16:00:08Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"889cba1decd3f9bb2bf4998182bd839bd3e7c912cf7e1d977c6b61a2949f3758","abstract_canon_sha256":"ddd89c10328af2f9839e31a32f094913b0174babd1b6469075f882649511b20e"},"schema_version":"1.0"},"canonical_sha256":"66e19105ad1f8ecdac40fd6f20e91f0572c05ae9adf54a18442663ea1d31260e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:06:00.431405Z","signature_b64":"q4KakBLXdDIp3RoWxqrslUjUt4Ljf4j02zOoBasruYGu6hoFIRh0N3/eg58wTRdQaxRjqHWlpr152DNSWod7AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"66e19105ad1f8ecdac40fd6f20e91f0572c05ae9adf54a18442663ea1d31260e","last_reissued_at":"2026-05-18T00:06:00.430749Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:06:00.430749Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1809.03576","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:06:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jXuOnQDOVIQfKcM2xUhPawwbptZO+ZPoowvI8pgSvAkV36SMTiR8UKWOriGSC70ooj4/nj2x2pPcpFD1xN/dDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-18T20:09:32.691974Z"},"content_sha256":"90a31e5e2623903206ea09286ca206e4b8e84e52e0fd7046659a3d16842e571b","schema_version":"1.0","event_id":"sha256:90a31e5e2623903206ea09286ca206e4b8e84e52e0fd7046659a3d16842e571b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:M3QZCBNND6HM3LCA7VXSB2I7AV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Out-of-Distribution Detection Using an Ensemble of Self Supervised Leave-out Classifiers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Apoorv Vyas, Bharat Kaul, Dipankar Das, Nataraj Jammalamadaka, Theodore L. Willke, Xia Zhu","submitted_at":"2018-09-04T16:00:08Z","abstract_excerpt":"As deep learning methods form a critical part in commercially important applications such as autonomous driving and medical diagnostics, it is important to reliably detect out-of-distribution (OOD) inputs while employing these algorithms. In this work, we propose an OOD detection algorithm which comprises of an ensemble of classifiers. We train each classifier in a self-supervised manner by leaving out a random subset of training data as OOD data and the rest as in-distribution (ID) data. We propose a novel margin-based loss over the softmax output which seeks to maintain at least a margin $m$"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.03576","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":""},"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:06:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7p5T6wqiPWhFrdhINJzOtNTT+Xwsa+F4ycOJ30JEPKSu5Ndq+1NrCkpDQe0VVWdJpRI88xZDKr8yXl8V8+dGDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-18T20:09:32.692670Z"},"content_sha256":"664fe09d54484d160285cd4281bceec88b6ada100d8f0f8e685702e165b17927","schema_version":"1.0","event_id":"sha256:664fe09d54484d160285cd4281bceec88b6ada100d8f0f8e685702e165b17927"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/M3QZCBNND6HM3LCA7VXSB2I7AV/bundle.json","state_url":"https://pith.science/pith/M3QZCBNND6HM3LCA7VXSB2I7AV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/M3QZCBNND6HM3LCA7VXSB2I7AV/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-18T20:09:32Z","links":{"resolver":"https://pith.science/pith/M3QZCBNND6HM3LCA7VXSB2I7AV","bundle":"https://pith.science/pith/M3QZCBNND6HM3LCA7VXSB2I7AV/bundle.json","state":"https://pith.science/pith/M3QZCBNND6HM3LCA7VXSB2I7AV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/M3QZCBNND6HM3LCA7VXSB2I7AV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:M3QZCBNND6HM3LCA7VXSB2I7AV","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"ddd89c10328af2f9839e31a32f094913b0174babd1b6469075f882649511b20e","cross_cats_sorted":["cs.CV","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-04T16:00:08Z","title_canon_sha256":"889cba1decd3f9bb2bf4998182bd839bd3e7c912cf7e1d977c6b61a2949f3758"},"schema_version":"1.0","source":{"id":"1809.03576","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1809.03576","created_at":"2026-05-18T00:06:00Z"},{"alias_kind":"arxiv_version","alias_value":"1809.03576v1","created_at":"2026-05-18T00:06:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.03576","created_at":"2026-05-18T00:06:00Z"},{"alias_kind":"pith_short_12","alias_value":"M3QZCBNND6HM","created_at":"2026-05-18T12:32:37Z"},{"alias_kind":"pith_short_16","alias_value":"M3QZCBNND6HM3LCA","created_at":"2026-05-18T12:32:37Z"},{"alias_kind":"pith_short_8","alias_value":"M3QZCBNN","created_at":"2026-05-18T12:32:37Z"}],"graph_snapshots":[{"event_id":"sha256:664fe09d54484d160285cd4281bceec88b6ada100d8f0f8e685702e165b17927","target":"graph","created_at":"2026-05-18T00:06:00Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"As deep learning methods form a critical part in commercially important applications such as autonomous driving and medical diagnostics, it is important to reliably detect out-of-distribution (OOD) inputs while employing these algorithms. In this work, we propose an OOD detection algorithm which comprises of an ensemble of classifiers. We train each classifier in a self-supervised manner by leaving out a random subset of training data as OOD data and the rest as in-distribution (ID) data. We propose a novel margin-based loss over the softmax output which seeks to maintain at least a margin $m$","authors_text":"Apoorv Vyas, Bharat Kaul, Dipankar Das, Nataraj Jammalamadaka, Theodore L. Willke, Xia Zhu","cross_cats":["cs.CV","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-04T16:00:08Z","title":"Out-of-Distribution Detection Using an Ensemble of Self Supervised Leave-out Classifiers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.03576","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:90a31e5e2623903206ea09286ca206e4b8e84e52e0fd7046659a3d16842e571b","target":"record","created_at":"2026-05-18T00:06:00Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"ddd89c10328af2f9839e31a32f094913b0174babd1b6469075f882649511b20e","cross_cats_sorted":["cs.CV","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-04T16:00:08Z","title_canon_sha256":"889cba1decd3f9bb2bf4998182bd839bd3e7c912cf7e1d977c6b61a2949f3758"},"schema_version":"1.0","source":{"id":"1809.03576","kind":"arxiv","version":1}},"canonical_sha256":"66e19105ad1f8ecdac40fd6f20e91f0572c05ae9adf54a18442663ea1d31260e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"66e19105ad1f8ecdac40fd6f20e91f0572c05ae9adf54a18442663ea1d31260e","first_computed_at":"2026-05-18T00:06:00.430749Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:06:00.430749Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"q4KakBLXdDIp3RoWxqrslUjUt4Ljf4j02zOoBasruYGu6hoFIRh0N3/eg58wTRdQaxRjqHWlpr152DNSWod7AA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:06:00.431405Z","signed_message":"canonical_sha256_bytes"},"source_id":"1809.03576","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:90a31e5e2623903206ea09286ca206e4b8e84e52e0fd7046659a3d16842e571b","sha256:664fe09d54484d160285cd4281bceec88b6ada100d8f0f8e685702e165b17927"],"state_sha256":"07f65ec8c740e9d5eba037a395c328d0be5b76486f827e44296ab394fa537ac9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wW49daewsFvJ6MFxW02fpTsWBfcuNAMTXFTiHxAUSz042b1IGRHIHs5EC0iGq5rVFfoO4ws71Q3DUWA+BBpeAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-18T20:09:32.694811Z","bundle_sha256":"1b46ec24c556ff0ad5ae9e41ef1078191bacc70e5c5706df6415c500f1bbfe48"}}