{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:VN7MW3VAKAW2DXAPB4UV7RDXLA","short_pith_number":"pith:VN7MW3VA","canonical_record":{"source":{"id":"1805.10917","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-28T13:37:39Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"1f62a79daa8c59774decc42ecf359634613d3eb485bbadf3c80ea72d556ead26","abstract_canon_sha256":"aefba691513cf279187659a51d95706e56da605afbcfa61f60e773b686f2b98d"},"schema_version":"1.0"},"canonical_sha256":"ab7ecb6ea0502da1dc0f0f295fc477582a480c29f462a86dd923e2be32343491","source":{"kind":"arxiv","id":"1805.10917","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.10917","created_at":"2026-05-18T00:01:14Z"},{"alias_kind":"arxiv_version","alias_value":"1805.10917v2","created_at":"2026-05-18T00:01:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.10917","created_at":"2026-05-18T00:01:14Z"},{"alias_kind":"pith_short_12","alias_value":"VN7MW3VAKAW2","created_at":"2026-05-18T12:32:59Z"},{"alias_kind":"pith_short_16","alias_value":"VN7MW3VAKAW2DXAP","created_at":"2026-05-18T12:32:59Z"},{"alias_kind":"pith_short_8","alias_value":"VN7MW3VA","created_at":"2026-05-18T12:32:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:VN7MW3VAKAW2DXAPB4UV7RDXLA","target":"record","payload":{"canonical_record":{"source":{"id":"1805.10917","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-28T13:37:39Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"1f62a79daa8c59774decc42ecf359634613d3eb485bbadf3c80ea72d556ead26","abstract_canon_sha256":"aefba691513cf279187659a51d95706e56da605afbcfa61f60e773b686f2b98d"},"schema_version":"1.0"},"canonical_sha256":"ab7ecb6ea0502da1dc0f0f295fc477582a480c29f462a86dd923e2be32343491","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:01:14.976857Z","signature_b64":"YdS/lQplaL25SRGp8Fv2ql8Mzo7yHI1tMG2wWr4YqjYGLokLqshCX6GGHCEiTOGQTnaZmLhI22U+gaVesepVDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ab7ecb6ea0502da1dc0f0f295fc477582a480c29f462a86dd923e2be32343491","last_reissued_at":"2026-05-18T00:01:14.976436Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:01:14.976436Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1805.10917","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:01:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VHOdf6YqALbfioMyJTE1n8c3y43BffIuXJsWudurhuta1aXEbwlZhAzs9L6F0cONXxXqwf8H/Ko2MPdivKwcBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T11:55:07.381572Z"},"content_sha256":"9ae96d28b5c613921d1786f611d4a317cce12b1f2ac85e7eeaa45f92b9e30af5","schema_version":"1.0","event_id":"sha256:9ae96d28b5c613921d1786f611d4a317cce12b1f2ac85e7eeaa45f92b9e30af5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:VN7MW3VAKAW2DXAPB4UV7RDXLA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Deep Anomaly Detection Using Geometric Transformations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Izhak Golan, Ran El-Yaniv","submitted_at":"2018-05-28T13:37:39Z","abstract_excerpt":"We consider the problem of anomaly detection in images, and present a new detection technique. Given a sample of images, all known to belong to a \"normal\" class (e.g., dogs), we show how to train a deep neural model that can detect out-of-distribution images (i.e., non-dog objects). The main idea behind our scheme is to train a multi-class model to discriminate between dozens of geometric transformations applied on all the given images. The auxiliary expertise learned by the model generates feature detectors that effectively identify, at test time, anomalous images based on the softmax activat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.10917","kind":"arxiv","version":2},"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":"2026-05-18T00:01:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"39T8LO1pF8cEzyR7P7I0AlWdXv7la2B3ffX7m5lPL2uvl7LXQ6sl28xztmBM3K6fnFUzH5UAVWIv+Zht2Te2BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T11:55:07.381937Z"},"content_sha256":"fe5bde74a31b2a2340e467d93f9bc7cfb6e8b35bcc6f314ae590761ed6b2fb8f","schema_version":"1.0","event_id":"sha256:fe5bde74a31b2a2340e467d93f9bc7cfb6e8b35bcc6f314ae590761ed6b2fb8f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VN7MW3VAKAW2DXAPB4UV7RDXLA/bundle.json","state_url":"https://pith.science/pith/VN7MW3VAKAW2DXAPB4UV7RDXLA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VN7MW3VAKAW2DXAPB4UV7RDXLA/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":"2026-07-05T11:55:07Z","links":{"resolver":"https://pith.science/pith/VN7MW3VAKAW2DXAPB4UV7RDXLA","bundle":"https://pith.science/pith/VN7MW3VAKAW2DXAPB4UV7RDXLA/bundle.json","state":"https://pith.science/pith/VN7MW3VAKAW2DXAPB4UV7RDXLA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VN7MW3VAKAW2DXAPB4UV7RDXLA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:VN7MW3VAKAW2DXAPB4UV7RDXLA","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":"aefba691513cf279187659a51d95706e56da605afbcfa61f60e773b686f2b98d","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-28T13:37:39Z","title_canon_sha256":"1f62a79daa8c59774decc42ecf359634613d3eb485bbadf3c80ea72d556ead26"},"schema_version":"1.0","source":{"id":"1805.10917","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.10917","created_at":"2026-05-18T00:01:14Z"},{"alias_kind":"arxiv_version","alias_value":"1805.10917v2","created_at":"2026-05-18T00:01:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.10917","created_at":"2026-05-18T00:01:14Z"},{"alias_kind":"pith_short_12","alias_value":"VN7MW3VAKAW2","created_at":"2026-05-18T12:32:59Z"},{"alias_kind":"pith_short_16","alias_value":"VN7MW3VAKAW2DXAP","created_at":"2026-05-18T12:32:59Z"},{"alias_kind":"pith_short_8","alias_value":"VN7MW3VA","created_at":"2026-05-18T12:32:59Z"}],"graph_snapshots":[{"event_id":"sha256:fe5bde74a31b2a2340e467d93f9bc7cfb6e8b35bcc6f314ae590761ed6b2fb8f","target":"graph","created_at":"2026-05-18T00:01:14Z","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":"We consider the problem of anomaly detection in images, and present a new detection technique. Given a sample of images, all known to belong to a \"normal\" class (e.g., dogs), we show how to train a deep neural model that can detect out-of-distribution images (i.e., non-dog objects). The main idea behind our scheme is to train a multi-class model to discriminate between dozens of geometric transformations applied on all the given images. The auxiliary expertise learned by the model generates feature detectors that effectively identify, at test time, anomalous images based on the softmax activat","authors_text":"Izhak Golan, Ran El-Yaniv","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-28T13:37:39Z","title":"Deep Anomaly Detection Using Geometric Transformations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.10917","kind":"arxiv","version":2},"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":"sha256:9ae96d28b5c613921d1786f611d4a317cce12b1f2ac85e7eeaa45f92b9e30af5","target":"record","created_at":"2026-05-18T00:01:14Z","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":"aefba691513cf279187659a51d95706e56da605afbcfa61f60e773b686f2b98d","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-28T13:37:39Z","title_canon_sha256":"1f62a79daa8c59774decc42ecf359634613d3eb485bbadf3c80ea72d556ead26"},"schema_version":"1.0","source":{"id":"1805.10917","kind":"arxiv","version":2}},"canonical_sha256":"ab7ecb6ea0502da1dc0f0f295fc477582a480c29f462a86dd923e2be32343491","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ab7ecb6ea0502da1dc0f0f295fc477582a480c29f462a86dd923e2be32343491","first_computed_at":"2026-05-18T00:01:14.976436Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:01:14.976436Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YdS/lQplaL25SRGp8Fv2ql8Mzo7yHI1tMG2wWr4YqjYGLokLqshCX6GGHCEiTOGQTnaZmLhI22U+gaVesepVDQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:01:14.976857Z","signed_message":"canonical_sha256_bytes"},"source_id":"1805.10917","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9ae96d28b5c613921d1786f611d4a317cce12b1f2ac85e7eeaa45f92b9e30af5","sha256:fe5bde74a31b2a2340e467d93f9bc7cfb6e8b35bcc6f314ae590761ed6b2fb8f"],"state_sha256":"5b87d21e58d883b25354bb71b5730b744a26e599635dd4a0280db9a6c2836c59"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xHoLYcVJG6/h+7T05GeDumXKKvt8FvRAhHdL+QQPP1oTnJ9cmekebjT43OrA569GPzubbIfkUWOCn9Y8hfINBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-05T11:55:07.384258Z","bundle_sha256":"97795f6fc4b2448d7138e5ce14b651d32782caa13fc1441745bc0f0ce37ca272"}}