{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:4UFCUCV6M75RSPX2JGXVN2XBYB","short_pith_number":"pith:4UFCUCV6","canonical_record":{"source":{"id":"2208.14024","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-08-30T07:00:46Z","cross_cats_sorted":[],"title_canon_sha256":"baeddb71e20c9a7f1fc548959c7ace87f9d5bcb6b33fcb264a3dde10d22334de","abstract_canon_sha256":"91a08c1eb7fa229b4f7628ebfa4ad4fc267f25255bd1b0f32ebf5a472460b1dc"},"schema_version":"1.0"},"canonical_sha256":"e50a2a0abe67fb193efa49af56eae1c05fb67cce145e304bf7f0c10e37a8ffb3","source":{"kind":"arxiv","id":"2208.14024","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2208.14024","created_at":"2026-07-05T06:04:51Z"},{"alias_kind":"arxiv_version","alias_value":"2208.14024v2","created_at":"2026-07-05T06:04:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.14024","created_at":"2026-07-05T06:04:51Z"},{"alias_kind":"pith_short_12","alias_value":"4UFCUCV6M75R","created_at":"2026-07-05T06:04:51Z"},{"alias_kind":"pith_short_16","alias_value":"4UFCUCV6M75RSPX2","created_at":"2026-07-05T06:04:51Z"},{"alias_kind":"pith_short_8","alias_value":"4UFCUCV6","created_at":"2026-07-05T06:04:51Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:4UFCUCV6M75RSPX2JGXVN2XBYB","target":"record","payload":{"canonical_record":{"source":{"id":"2208.14024","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-08-30T07:00:46Z","cross_cats_sorted":[],"title_canon_sha256":"baeddb71e20c9a7f1fc548959c7ace87f9d5bcb6b33fcb264a3dde10d22334de","abstract_canon_sha256":"91a08c1eb7fa229b4f7628ebfa4ad4fc267f25255bd1b0f32ebf5a472460b1dc"},"schema_version":"1.0"},"canonical_sha256":"e50a2a0abe67fb193efa49af56eae1c05fb67cce145e304bf7f0c10e37a8ffb3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:04:51.635830Z","signature_b64":"C3s/GqVkT5QUni5+ovTj7iNGr72pPUhp3APy7yrNd1uW0a9ew7kAq26aLF93mUllF0xQG8QbB7s5wt2qqKO+Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e50a2a0abe67fb193efa49af56eae1c05fb67cce145e304bf7f0c10e37a8ffb3","last_reissued_at":"2026-07-05T06:04:51.635404Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:04:51.635404Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2208.14024","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":"2026-07-05T06:04:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aBsdLdRcr21grbfaEb2VTD4JO9BsrSjhXG0QVo0BM8bjySDraW5sD8SzAelsFATu+p1kdZOkZc4LQX7zMJ0DCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T09:56:20.670025Z"},"content_sha256":"86a68698566ccf90772863c2bf47f58e1b8ffbd2ec7bdb02fa8c92b550c43c31","schema_version":"1.0","event_id":"sha256:86a68698566ccf90772863c2bf47f58e1b8ffbd2ec7bdb02fa8c92b550c43c31"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:4UFCUCV6M75RSPX2JGXVN2XBYB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Positive Difference Distribution for Image Outlier Detection using Normalizing Flows and Contrastive Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Christoph-Nikolas Straehle, Robert Schmier, Ullrich K\\\"othe","submitted_at":"2022-08-30T07:00:46Z","abstract_excerpt":"Detecting test data deviating from training data is a central problem for safe and robust machine learning. Likelihoods learned by a generative model, e.g., a normalizing flow via standard log-likelihood training, perform poorly as an outlier score. We propose to use an unlabelled auxiliary dataset and a probabilistic outlier score for outlier detection. We use a self-supervised feature extractor trained on the auxiliary dataset and train a normalizing flow on the extracted features by maximizing the likelihood on in-distribution data and minimizing the likelihood on the contrastive dataset. W"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.14024","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2208.14024/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":"2026-07-05T06:04:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9LRtO01Rl7aF1NsbGTQt4xPzvBLG/ZYkKJzeIMx6NjMkazN6USDT5vOLNaWC9yGtMW5q2D5AtZK2FbnS8uVWCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T09:56:20.670568Z"},"content_sha256":"551bd3593c679be957e1e3f67ee8c93ff25c74180dfd56c18871d50d1395c7e6","schema_version":"1.0","event_id":"sha256:551bd3593c679be957e1e3f67ee8c93ff25c74180dfd56c18871d50d1395c7e6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4UFCUCV6M75RSPX2JGXVN2XBYB/bundle.json","state_url":"https://pith.science/pith/4UFCUCV6M75RSPX2JGXVN2XBYB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4UFCUCV6M75RSPX2JGXVN2XBYB/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":"2026-08-16T09:56:20Z","links":{"resolver":"https://pith.science/pith/4UFCUCV6M75RSPX2JGXVN2XBYB","bundle":"https://pith.science/pith/4UFCUCV6M75RSPX2JGXVN2XBYB/bundle.json","state":"https://pith.science/pith/4UFCUCV6M75RSPX2JGXVN2XBYB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4UFCUCV6M75RSPX2JGXVN2XBYB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:4UFCUCV6M75RSPX2JGXVN2XBYB","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":"91a08c1eb7fa229b4f7628ebfa4ad4fc267f25255bd1b0f32ebf5a472460b1dc","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-08-30T07:00:46Z","title_canon_sha256":"baeddb71e20c9a7f1fc548959c7ace87f9d5bcb6b33fcb264a3dde10d22334de"},"schema_version":"1.0","source":{"id":"2208.14024","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2208.14024","created_at":"2026-07-05T06:04:51Z"},{"alias_kind":"arxiv_version","alias_value":"2208.14024v2","created_at":"2026-07-05T06:04:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.14024","created_at":"2026-07-05T06:04:51Z"},{"alias_kind":"pith_short_12","alias_value":"4UFCUCV6M75R","created_at":"2026-07-05T06:04:51Z"},{"alias_kind":"pith_short_16","alias_value":"4UFCUCV6M75RSPX2","created_at":"2026-07-05T06:04:51Z"},{"alias_kind":"pith_short_8","alias_value":"4UFCUCV6","created_at":"2026-07-05T06:04:51Z"}],"graph_snapshots":[{"event_id":"sha256:551bd3593c679be957e1e3f67ee8c93ff25c74180dfd56c18871d50d1395c7e6","target":"graph","created_at":"2026-07-05T06:04:51Z","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/2208.14024/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Detecting test data deviating from training data is a central problem for safe and robust machine learning. Likelihoods learned by a generative model, e.g., a normalizing flow via standard log-likelihood training, perform poorly as an outlier score. We propose to use an unlabelled auxiliary dataset and a probabilistic outlier score for outlier detection. We use a self-supervised feature extractor trained on the auxiliary dataset and train a normalizing flow on the extracted features by maximizing the likelihood on in-distribution data and minimizing the likelihood on the contrastive dataset. W","authors_text":"Christoph-Nikolas Straehle, Robert Schmier, Ullrich K\\\"othe","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-08-30T07:00:46Z","title":"Positive Difference Distribution for Image Outlier Detection using Normalizing Flows and Contrastive Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.14024","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":"sha256:86a68698566ccf90772863c2bf47f58e1b8ffbd2ec7bdb02fa8c92b550c43c31","target":"record","created_at":"2026-07-05T06:04:51Z","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":"91a08c1eb7fa229b4f7628ebfa4ad4fc267f25255bd1b0f32ebf5a472460b1dc","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-08-30T07:00:46Z","title_canon_sha256":"baeddb71e20c9a7f1fc548959c7ace87f9d5bcb6b33fcb264a3dde10d22334de"},"schema_version":"1.0","source":{"id":"2208.14024","kind":"arxiv","version":2}},"canonical_sha256":"e50a2a0abe67fb193efa49af56eae1c05fb67cce145e304bf7f0c10e37a8ffb3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e50a2a0abe67fb193efa49af56eae1c05fb67cce145e304bf7f0c10e37a8ffb3","first_computed_at":"2026-07-05T06:04:51.635404Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:04:51.635404Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"C3s/GqVkT5QUni5+ovTj7iNGr72pPUhp3APy7yrNd1uW0a9ew7kAq26aLF93mUllF0xQG8QbB7s5wt2qqKO+Dg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:04:51.635830Z","signed_message":"canonical_sha256_bytes"},"source_id":"2208.14024","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:86a68698566ccf90772863c2bf47f58e1b8ffbd2ec7bdb02fa8c92b550c43c31","sha256:551bd3593c679be957e1e3f67ee8c93ff25c74180dfd56c18871d50d1395c7e6"],"state_sha256":"ff13bd80310fc920e8ef3444bf013b4eaa3f52aefcee9de565d46e4139f432e4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PwnqOX+CmCyjh5uXkD1Rhvo6TSelRK58dBEqS81Nl1R/A5y7AZnhu/wQmtN7XSlkZGj4uGwmDZdoeQOmkJkaBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-16T09:56:20.675826Z","bundle_sha256":"da4d02159d83071420ff793e10190ef0206b37b79ba4eaef5278275a00d8ad7a"}}