{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:LQLYWEXF6R4CBITDYAYDOH3END","short_pith_number":"pith:LQLYWEXF","canonical_record":{"source":{"id":"2107.07820","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-07-16T11:04:35Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"2c8ae459295f0e3e9d2e1b6e0ea34c485f1867f9d0cd79db93c3e96ffab06f48","abstract_canon_sha256":"730df4385f618f70a48000f4d9c585949ff4c5514d46ce70d862608efac765da"},"schema_version":"1.0"},"canonical_sha256":"5c178b12e5f47820a263c030371f6468ec306141dc032b020a4e1897aeefd827","source":{"kind":"arxiv","id":"2107.07820","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2107.07820","created_at":"2026-07-05T02:58:29Z"},{"alias_kind":"arxiv_version","alias_value":"2107.07820v1","created_at":"2026-07-05T02:58:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.07820","created_at":"2026-07-05T02:58:29Z"},{"alias_kind":"pith_short_12","alias_value":"LQLYWEXF6R4C","created_at":"2026-07-05T02:58:29Z"},{"alias_kind":"pith_short_16","alias_value":"LQLYWEXF6R4CBITD","created_at":"2026-07-05T02:58:29Z"},{"alias_kind":"pith_short_8","alias_value":"LQLYWEXF","created_at":"2026-07-05T02:58:29Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:LQLYWEXF6R4CBITDYAYDOH3END","target":"record","payload":{"canonical_record":{"source":{"id":"2107.07820","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-07-16T11:04:35Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"2c8ae459295f0e3e9d2e1b6e0ea34c485f1867f9d0cd79db93c3e96ffab06f48","abstract_canon_sha256":"730df4385f618f70a48000f4d9c585949ff4c5514d46ce70d862608efac765da"},"schema_version":"1.0"},"canonical_sha256":"5c178b12e5f47820a263c030371f6468ec306141dc032b020a4e1897aeefd827","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:58:29.602094Z","signature_b64":"296z+/A7p+kggkjHkcjhvyaEE7U6I39KKU7TL2RDX9oIx++SVs9Gqu9B0CxjmO4Tqeg3iR4A8JSalSVwhKgIBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5c178b12e5f47820a263c030371f6468ec306141dc032b020a4e1897aeefd827","last_reissued_at":"2026-07-05T02:58:29.601737Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:58:29.601737Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2107.07820","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":"2026-07-05T02:58:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7SvqOkAm5WxNa3MSEX2C9XnliM959tLFknWxEWsV/d++HZHZE8RJdmbK8SFu5PDkWDvLSOXgJVrm/lxeJ+icDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T14:42:24.801055Z"},"content_sha256":"62e99316dbc9009d045937bd988c454d400cec13fa12f5d792578b2a4559b59d","schema_version":"1.0","event_id":"sha256:62e99316dbc9009d045937bd988c454d400cec13fa12f5d792578b2a4559b59d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:LQLYWEXF6R4CBITDYAYDOH3END","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Contrastive Predictive Coding for Anomaly Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Puck de Haan, Sindy L\\\"owe","submitted_at":"2021-07-16T11:04:35Z","abstract_excerpt":"Reliable detection of anomalies is crucial when deploying machine learning models in practice, but remains challenging due to the lack of labeled data. To tackle this challenge, contrastive learning approaches are becoming increasingly popular, given the impressive results they have achieved in self-supervised representation learning settings. However, while most existing contrastive anomaly detection and segmentation approaches have been applied to images, none of them can use the contrastive losses directly for both anomaly detection and segmentation. In this paper, we close this gap by maki"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.07820","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/2107.07820/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":"2026-07-05T02:58:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oV1xsmoC1q77N/MKp4FO01cG5jiAMjmVn0EcflDw1l66ZZAY1FS49v5Q6nsAmeof7QycL55BUKvS3ZVJz4QSAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T14:42:24.801579Z"},"content_sha256":"e66f2b41ff15b13edce8850b832219c5be7f168c5316302f403b4d3aaa946956","schema_version":"1.0","event_id":"sha256:e66f2b41ff15b13edce8850b832219c5be7f168c5316302f403b4d3aaa946956"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LQLYWEXF6R4CBITDYAYDOH3END/bundle.json","state_url":"https://pith.science/pith/LQLYWEXF6R4CBITDYAYDOH3END/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LQLYWEXF6R4CBITDYAYDOH3END/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":"2026-08-11T14:42:24Z","links":{"resolver":"https://pith.science/pith/LQLYWEXF6R4CBITDYAYDOH3END","bundle":"https://pith.science/pith/LQLYWEXF6R4CBITDYAYDOH3END/bundle.json","state":"https://pith.science/pith/LQLYWEXF6R4CBITDYAYDOH3END/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LQLYWEXF6R4CBITDYAYDOH3END/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:LQLYWEXF6R4CBITDYAYDOH3END","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":"730df4385f618f70a48000f4d9c585949ff4c5514d46ce70d862608efac765da","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-07-16T11:04:35Z","title_canon_sha256":"2c8ae459295f0e3e9d2e1b6e0ea34c485f1867f9d0cd79db93c3e96ffab06f48"},"schema_version":"1.0","source":{"id":"2107.07820","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2107.07820","created_at":"2026-07-05T02:58:29Z"},{"alias_kind":"arxiv_version","alias_value":"2107.07820v1","created_at":"2026-07-05T02:58:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.07820","created_at":"2026-07-05T02:58:29Z"},{"alias_kind":"pith_short_12","alias_value":"LQLYWEXF6R4C","created_at":"2026-07-05T02:58:29Z"},{"alias_kind":"pith_short_16","alias_value":"LQLYWEXF6R4CBITD","created_at":"2026-07-05T02:58:29Z"},{"alias_kind":"pith_short_8","alias_value":"LQLYWEXF","created_at":"2026-07-05T02:58:29Z"}],"graph_snapshots":[{"event_id":"sha256:e66f2b41ff15b13edce8850b832219c5be7f168c5316302f403b4d3aaa946956","target":"graph","created_at":"2026-07-05T02:58:29Z","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/2107.07820/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reliable detection of anomalies is crucial when deploying machine learning models in practice, but remains challenging due to the lack of labeled data. To tackle this challenge, contrastive learning approaches are becoming increasingly popular, given the impressive results they have achieved in self-supervised representation learning settings. However, while most existing contrastive anomaly detection and segmentation approaches have been applied to images, none of them can use the contrastive losses directly for both anomaly detection and segmentation. In this paper, we close this gap by maki","authors_text":"Puck de Haan, Sindy L\\\"owe","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-07-16T11:04:35Z","title":"Contrastive Predictive Coding for Anomaly Detection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.07820","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":"sha256:62e99316dbc9009d045937bd988c454d400cec13fa12f5d792578b2a4559b59d","target":"record","created_at":"2026-07-05T02:58:29Z","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":"730df4385f618f70a48000f4d9c585949ff4c5514d46ce70d862608efac765da","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-07-16T11:04:35Z","title_canon_sha256":"2c8ae459295f0e3e9d2e1b6e0ea34c485f1867f9d0cd79db93c3e96ffab06f48"},"schema_version":"1.0","source":{"id":"2107.07820","kind":"arxiv","version":1}},"canonical_sha256":"5c178b12e5f47820a263c030371f6468ec306141dc032b020a4e1897aeefd827","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5c178b12e5f47820a263c030371f6468ec306141dc032b020a4e1897aeefd827","first_computed_at":"2026-07-05T02:58:29.601737Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:58:29.601737Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"296z+/A7p+kggkjHkcjhvyaEE7U6I39KKU7TL2RDX9oIx++SVs9Gqu9B0CxjmO4Tqeg3iR4A8JSalSVwhKgIBA==","signature_status":"signed_v1","signed_at":"2026-07-05T02:58:29.602094Z","signed_message":"canonical_sha256_bytes"},"source_id":"2107.07820","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:62e99316dbc9009d045937bd988c454d400cec13fa12f5d792578b2a4559b59d","sha256:e66f2b41ff15b13edce8850b832219c5be7f168c5316302f403b4d3aaa946956"],"state_sha256":"a6829df81b4d8d7d9e1903e874e7043ebb2d819b29c71fb88bb9410113709d54"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eXBO0KLnbRmP7licPJvYNO3G5+AYMWXXddkMgMtsI+ogkJZnqX+ghNQ4P8IY5AKil0Fr0CV3oMhfCUtwNekjDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T14:42:24.805797Z","bundle_sha256":"5b3c7c0cc60609df82d98ea3f0e52248c7bb4cd84eebaf83e059eeb85d853950"}}