{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:U6C3IQZ3VSFRZINVDCYU2VZ3YA","short_pith_number":"pith:U6C3IQZ3","canonical_record":{"source":{"id":"2105.14737","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-05-31T07:02:20Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"b75d704d7b68ad61363279c9483979ed94fdc7e19d3c4e0276ff6038d76ca989","abstract_canon_sha256":"e9691ce85078705b5151bf70b0f39fdca154fd8e735115d38b87b6a2d86f3f10"},"schema_version":"1.0"},"canonical_sha256":"a785b4433bac8b1ca1b518b14d573bc013dd6c38816b22bf75054faba138604c","source":{"kind":"arxiv","id":"2105.14737","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2105.14737","created_at":"2026-07-05T02:44:40Z"},{"alias_kind":"arxiv_version","alias_value":"2105.14737v1","created_at":"2026-07-05T02:44:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.14737","created_at":"2026-07-05T02:44:40Z"},{"alias_kind":"pith_short_12","alias_value":"U6C3IQZ3VSFR","created_at":"2026-07-05T02:44:40Z"},{"alias_kind":"pith_short_16","alias_value":"U6C3IQZ3VSFRZINV","created_at":"2026-07-05T02:44:40Z"},{"alias_kind":"pith_short_8","alias_value":"U6C3IQZ3","created_at":"2026-07-05T02:44:40Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:U6C3IQZ3VSFRZINVDCYU2VZ3YA","target":"record","payload":{"canonical_record":{"source":{"id":"2105.14737","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-05-31T07:02:20Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"b75d704d7b68ad61363279c9483979ed94fdc7e19d3c4e0276ff6038d76ca989","abstract_canon_sha256":"e9691ce85078705b5151bf70b0f39fdca154fd8e735115d38b87b6a2d86f3f10"},"schema_version":"1.0"},"canonical_sha256":"a785b4433bac8b1ca1b518b14d573bc013dd6c38816b22bf75054faba138604c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:44:40.826346Z","signature_b64":"kj9e+kYd7fcMIJ5lE7F2EM5l0e06UUjTQJIhAEJiA+F9TfCj033+TalelShXifhN52Z4Zt88Sb7UwZsNVZ8QCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a785b4433bac8b1ca1b518b14d573bc013dd6c38816b22bf75054faba138604c","last_reissued_at":"2026-07-05T02:44:40.825918Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:44:40.825918Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2105.14737","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":"2026-07-05T02:44:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ffxqQGifcmwUSENvRVTmR7tURpNuFtrxxkdeCEc4tKe6mvB1hIw2qjVxKjLK6p6V5BrMRI0Xs+RudvKhKmwGDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T13:30:18.913686Z"},"content_sha256":"839c9fecbb23d3170a581c0d1631745538c41f2b49b2fe09ca5578acc143b463","schema_version":"1.0","event_id":"sha256:839c9fecbb23d3170a581c0d1631745538c41f2b49b2fe09ca5578acc143b463"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:U6C3IQZ3VSFRZINVDCYU2VZ3YA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Semi-orthogonal Embedding for Efficient Unsupervised Anomaly Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Do-Hyeong Kim, Jin-Hwa Kim, Saehoon Yi, Taehoon Lee","submitted_at":"2021-05-31T07:02:20Z","abstract_excerpt":"We present the efficiency of semi-orthogonal embedding for unsupervised anomaly segmentation. The multi-scale features from pre-trained CNNs are recently used for the localized Mahalanobis distances with significant performance. However, the increased feature size is problematic to scale up to the bigger CNNs, since it requires the batch-inverse of multi-dimensional covariance tensor. Here, we generalize an ad-hoc method, random feature selection, into semi-orthogonal embedding for robust approximation, cubically reducing the computational cost for the inverse of multi-dimensional covariance t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.14737","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/2105.14737/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:44:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nQxl5mvAcvkliAPUwFg62EqMDTG1SM5XAvRG+nCmZeC1HvVkVEHSTlcw1CVk1Te0sVSo0dwayNKrY9BgRJ1ABA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T13:30:18.914189Z"},"content_sha256":"14e51ab15d05776fbf4a23bb0b9ccc7556f97ff3da54e7eafe8f9f27aafc5f19","schema_version":"1.0","event_id":"sha256:14e51ab15d05776fbf4a23bb0b9ccc7556f97ff3da54e7eafe8f9f27aafc5f19"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/U6C3IQZ3VSFRZINVDCYU2VZ3YA/bundle.json","state_url":"https://pith.science/pith/U6C3IQZ3VSFRZINVDCYU2VZ3YA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/U6C3IQZ3VSFRZINVDCYU2VZ3YA/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":"2026-08-14T13:30:18Z","links":{"resolver":"https://pith.science/pith/U6C3IQZ3VSFRZINVDCYU2VZ3YA","bundle":"https://pith.science/pith/U6C3IQZ3VSFRZINVDCYU2VZ3YA/bundle.json","state":"https://pith.science/pith/U6C3IQZ3VSFRZINVDCYU2VZ3YA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/U6C3IQZ3VSFRZINVDCYU2VZ3YA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:U6C3IQZ3VSFRZINVDCYU2VZ3YA","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":"e9691ce85078705b5151bf70b0f39fdca154fd8e735115d38b87b6a2d86f3f10","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-05-31T07:02:20Z","title_canon_sha256":"b75d704d7b68ad61363279c9483979ed94fdc7e19d3c4e0276ff6038d76ca989"},"schema_version":"1.0","source":{"id":"2105.14737","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2105.14737","created_at":"2026-07-05T02:44:40Z"},{"alias_kind":"arxiv_version","alias_value":"2105.14737v1","created_at":"2026-07-05T02:44:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.14737","created_at":"2026-07-05T02:44:40Z"},{"alias_kind":"pith_short_12","alias_value":"U6C3IQZ3VSFR","created_at":"2026-07-05T02:44:40Z"},{"alias_kind":"pith_short_16","alias_value":"U6C3IQZ3VSFRZINV","created_at":"2026-07-05T02:44:40Z"},{"alias_kind":"pith_short_8","alias_value":"U6C3IQZ3","created_at":"2026-07-05T02:44:40Z"}],"graph_snapshots":[{"event_id":"sha256:14e51ab15d05776fbf4a23bb0b9ccc7556f97ff3da54e7eafe8f9f27aafc5f19","target":"graph","created_at":"2026-07-05T02:44:40Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2105.14737/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present the efficiency of semi-orthogonal embedding for unsupervised anomaly segmentation. The multi-scale features from pre-trained CNNs are recently used for the localized Mahalanobis distances with significant performance. However, the increased feature size is problematic to scale up to the bigger CNNs, since it requires the batch-inverse of multi-dimensional covariance tensor. Here, we generalize an ad-hoc method, random feature selection, into semi-orthogonal embedding for robust approximation, cubically reducing the computational cost for the inverse of multi-dimensional covariance t","authors_text":"Do-Hyeong Kim, Jin-Hwa Kim, Saehoon Yi, Taehoon Lee","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-05-31T07:02:20Z","title":"Semi-orthogonal Embedding for Efficient Unsupervised Anomaly Segmentation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.14737","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":"sha256:839c9fecbb23d3170a581c0d1631745538c41f2b49b2fe09ca5578acc143b463","target":"record","created_at":"2026-07-05T02:44:40Z","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":"e9691ce85078705b5151bf70b0f39fdca154fd8e735115d38b87b6a2d86f3f10","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-05-31T07:02:20Z","title_canon_sha256":"b75d704d7b68ad61363279c9483979ed94fdc7e19d3c4e0276ff6038d76ca989"},"schema_version":"1.0","source":{"id":"2105.14737","kind":"arxiv","version":1}},"canonical_sha256":"a785b4433bac8b1ca1b518b14d573bc013dd6c38816b22bf75054faba138604c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a785b4433bac8b1ca1b518b14d573bc013dd6c38816b22bf75054faba138604c","first_computed_at":"2026-07-05T02:44:40.825918Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:44:40.825918Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kj9e+kYd7fcMIJ5lE7F2EM5l0e06UUjTQJIhAEJiA+F9TfCj033+TalelShXifhN52Z4Zt88Sb7UwZsNVZ8QCg==","signature_status":"signed_v1","signed_at":"2026-07-05T02:44:40.826346Z","signed_message":"canonical_sha256_bytes"},"source_id":"2105.14737","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:839c9fecbb23d3170a581c0d1631745538c41f2b49b2fe09ca5578acc143b463","sha256:14e51ab15d05776fbf4a23bb0b9ccc7556f97ff3da54e7eafe8f9f27aafc5f19"],"state_sha256":"e3d8a55b20799339369b63370e1671505439f4568f0d1b75b5c62862ac261774"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PS70gGdOB3xkn1gzG///GXMbmU8YeK2i6IinwtJ5MJwD6b9eBtLvWAqm5z4ECMAPa/F3OxmtmnFTS8PqBHvTDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T13:30:18.923387Z","bundle_sha256":"f6235fd137cdc1dde2642a745e1007d71618d1c2dd01e05897199eff9b14f529"}}