{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:QJCZFLB4PS2EURLHUQL6NWE6ZD","short_pith_number":"pith:QJCZFLB4","canonical_record":{"source":{"id":"1812.04606","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-11T18:49:50Z","cross_cats_sorted":["cs.CL","cs.CV","stat.ML"],"title_canon_sha256":"776905fdeccc63ef00c2538919b205d737c778b9b83f2e163d2cfc015313f38f","abstract_canon_sha256":"ef5f962e246b82118a3579aab5333356755075d960470da3071e08a3a739c049"},"schema_version":"1.0"},"canonical_sha256":"824592ac3c7cb44a4567a417e6d89ec8fab4fec91ea49738c16a6da5e5e8bfd0","source":{"kind":"arxiv","id":"1812.04606","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1812.04606","created_at":"2026-05-17T23:55:18Z"},{"alias_kind":"arxiv_version","alias_value":"1812.04606v3","created_at":"2026-05-17T23:55:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.04606","created_at":"2026-05-17T23:55:18Z"},{"alias_kind":"pith_short_12","alias_value":"QJCZFLB4PS2E","created_at":"2026-05-18T12:32:46Z"},{"alias_kind":"pith_short_16","alias_value":"QJCZFLB4PS2EURLH","created_at":"2026-05-18T12:32:46Z"},{"alias_kind":"pith_short_8","alias_value":"QJCZFLB4","created_at":"2026-05-18T12:32:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:QJCZFLB4PS2EURLHUQL6NWE6ZD","target":"record","payload":{"canonical_record":{"source":{"id":"1812.04606","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-11T18:49:50Z","cross_cats_sorted":["cs.CL","cs.CV","stat.ML"],"title_canon_sha256":"776905fdeccc63ef00c2538919b205d737c778b9b83f2e163d2cfc015313f38f","abstract_canon_sha256":"ef5f962e246b82118a3579aab5333356755075d960470da3071e08a3a739c049"},"schema_version":"1.0"},"canonical_sha256":"824592ac3c7cb44a4567a417e6d89ec8fab4fec91ea49738c16a6da5e5e8bfd0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:55:18.818643Z","signature_b64":"jGmo2PDQgOydVEovXuN/rhW9VVPAwE3cYwo+hwqRF6hs5AIleOAU9bUNI7cEZupBiCle5G5Opy9YnKFxaBnbAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"824592ac3c7cb44a4567a417e6d89ec8fab4fec91ea49738c16a6da5e5e8bfd0","last_reissued_at":"2026-05-17T23:55:18.818049Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:55:18.818049Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1812.04606","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:55:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hd4dTPy3pj6Qmk0+SHZyewOvDOyM5D+SLxkWj6yYaahgkNmXIgAeuc9/L2az+W3Uz0pFYhcwtEiR/u1ifDf3Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T19:41:58.975079Z"},"content_sha256":"505da20a924f52294482e012e2795664efbc3ae5c690b7179ad5c0f4c118cadc","schema_version":"1.0","event_id":"sha256:505da20a924f52294482e012e2795664efbc3ae5c690b7179ad5c0f4c118cadc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:QJCZFLB4PS2EURLHUQL6NWE6ZD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Deep Anomaly Detection with Outlier Exposure","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Dan Hendrycks, Mantas Mazeika, Thomas Dietterich","submitted_at":"2018-12-11T18:49:50Z","abstract_excerpt":"It is important to detect anomalous inputs when deploying machine learning systems. The use of larger and more complex inputs in deep learning magnifies the difficulty of distinguishing between anomalous and in-distribution examples. At the same time, diverse image and text data are available in enormous quantities. We propose leveraging these data to improve deep anomaly detection by training anomaly detectors against an auxiliary dataset of outliers, an approach we call Outlier Exposure (OE). This enables anomaly detectors to generalize and detect unseen anomalies. In extensive experiments o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.04606","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":""},"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":"2026-05-17T23:55:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ts841jV5YK3yi0EDXVha2koYy3VDPM2f2Tcl2SqatTHhPvYj2iQwW1HH1vghi5vkGkUIYRKS6cKPHOjAfgsCDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T19:41:58.975767Z"},"content_sha256":"ea8d428e185aa662955ab967b5d7a8ba4cd1336d46c8a22d676ec673f4a96b69","schema_version":"1.0","event_id":"sha256:ea8d428e185aa662955ab967b5d7a8ba4cd1336d46c8a22d676ec673f4a96b69"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QJCZFLB4PS2EURLHUQL6NWE6ZD/bundle.json","state_url":"https://pith.science/pith/QJCZFLB4PS2EURLHUQL6NWE6ZD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QJCZFLB4PS2EURLHUQL6NWE6ZD/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":"2026-06-05T19:41:58Z","links":{"resolver":"https://pith.science/pith/QJCZFLB4PS2EURLHUQL6NWE6ZD","bundle":"https://pith.science/pith/QJCZFLB4PS2EURLHUQL6NWE6ZD/bundle.json","state":"https://pith.science/pith/QJCZFLB4PS2EURLHUQL6NWE6ZD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QJCZFLB4PS2EURLHUQL6NWE6ZD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:QJCZFLB4PS2EURLHUQL6NWE6ZD","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":"ef5f962e246b82118a3579aab5333356755075d960470da3071e08a3a739c049","cross_cats_sorted":["cs.CL","cs.CV","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-11T18:49:50Z","title_canon_sha256":"776905fdeccc63ef00c2538919b205d737c778b9b83f2e163d2cfc015313f38f"},"schema_version":"1.0","source":{"id":"1812.04606","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1812.04606","created_at":"2026-05-17T23:55:18Z"},{"alias_kind":"arxiv_version","alias_value":"1812.04606v3","created_at":"2026-05-17T23:55:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.04606","created_at":"2026-05-17T23:55:18Z"},{"alias_kind":"pith_short_12","alias_value":"QJCZFLB4PS2E","created_at":"2026-05-18T12:32:46Z"},{"alias_kind":"pith_short_16","alias_value":"QJCZFLB4PS2EURLH","created_at":"2026-05-18T12:32:46Z"},{"alias_kind":"pith_short_8","alias_value":"QJCZFLB4","created_at":"2026-05-18T12:32:46Z"}],"graph_snapshots":[{"event_id":"sha256:ea8d428e185aa662955ab967b5d7a8ba4cd1336d46c8a22d676ec673f4a96b69","target":"graph","created_at":"2026-05-17T23:55:18Z","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":"It is important to detect anomalous inputs when deploying machine learning systems. The use of larger and more complex inputs in deep learning magnifies the difficulty of distinguishing between anomalous and in-distribution examples. At the same time, diverse image and text data are available in enormous quantities. We propose leveraging these data to improve deep anomaly detection by training anomaly detectors against an auxiliary dataset of outliers, an approach we call Outlier Exposure (OE). This enables anomaly detectors to generalize and detect unseen anomalies. In extensive experiments o","authors_text":"Dan Hendrycks, Mantas Mazeika, Thomas Dietterich","cross_cats":["cs.CL","cs.CV","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-11T18:49:50Z","title":"Deep Anomaly Detection with Outlier Exposure"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.04606","kind":"arxiv","version":3},"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":"sha256:505da20a924f52294482e012e2795664efbc3ae5c690b7179ad5c0f4c118cadc","target":"record","created_at":"2026-05-17T23:55:18Z","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":"ef5f962e246b82118a3579aab5333356755075d960470da3071e08a3a739c049","cross_cats_sorted":["cs.CL","cs.CV","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-11T18:49:50Z","title_canon_sha256":"776905fdeccc63ef00c2538919b205d737c778b9b83f2e163d2cfc015313f38f"},"schema_version":"1.0","source":{"id":"1812.04606","kind":"arxiv","version":3}},"canonical_sha256":"824592ac3c7cb44a4567a417e6d89ec8fab4fec91ea49738c16a6da5e5e8bfd0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"824592ac3c7cb44a4567a417e6d89ec8fab4fec91ea49738c16a6da5e5e8bfd0","first_computed_at":"2026-05-17T23:55:18.818049Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:55:18.818049Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jGmo2PDQgOydVEovXuN/rhW9VVPAwE3cYwo+hwqRF6hs5AIleOAU9bUNI7cEZupBiCle5G5Opy9YnKFxaBnbAg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:55:18.818643Z","signed_message":"canonical_sha256_bytes"},"source_id":"1812.04606","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:505da20a924f52294482e012e2795664efbc3ae5c690b7179ad5c0f4c118cadc","sha256:ea8d428e185aa662955ab967b5d7a8ba4cd1336d46c8a22d676ec673f4a96b69"],"state_sha256":"86108c526e7765c4ef1d8d47414315d5bec0662f92743aff9c09269371ae4ca3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+rz7cRmjGitTlRvyN1MjHncQ5JPUVBrJv6fMJOFDiCmkPWa0uu3mUGrxWS0MH6b+oE3htu47vnT1jfMvzWMoDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-05T19:41:58.980405Z","bundle_sha256":"239e81efba4f735b2c3e223fbefc13cd67a73ee44b16124424618ff8e4eba5c5"}}