{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:H75I2NVFT4QQJE272R25HBMTQ6","short_pith_number":"pith:H75I2NVF","canonical_record":{"source":{"id":"2104.05591","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-04-12T16:08:05Z","cross_cats_sorted":[],"title_canon_sha256":"da3e71d3ecbfd946e5eeb38591374ddfbf03e87331e50d7ab47423c84e204389","abstract_canon_sha256":"32e641279e0f9a4a6af1d7eedcd274982ebc03cdaa6f40769c994c474c4a05e7"},"schema_version":"1.0"},"canonical_sha256":"3ffa8d36a59f2104935fd475d3859387a1b5081e6e073628423359f6a8679103","source":{"kind":"arxiv","id":"2104.05591","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.05591","created_at":"2026-07-05T02:31:14Z"},{"alias_kind":"arxiv_version","alias_value":"2104.05591v1","created_at":"2026-07-05T02:31:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.05591","created_at":"2026-07-05T02:31:14Z"},{"alias_kind":"pith_short_12","alias_value":"H75I2NVFT4QQ","created_at":"2026-07-05T02:31:14Z"},{"alias_kind":"pith_short_16","alias_value":"H75I2NVFT4QQJE27","created_at":"2026-07-05T02:31:14Z"},{"alias_kind":"pith_short_8","alias_value":"H75I2NVF","created_at":"2026-07-05T02:31:14Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:H75I2NVFT4QQJE272R25HBMTQ6","target":"record","payload":{"canonical_record":{"source":{"id":"2104.05591","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-04-12T16:08:05Z","cross_cats_sorted":[],"title_canon_sha256":"da3e71d3ecbfd946e5eeb38591374ddfbf03e87331e50d7ab47423c84e204389","abstract_canon_sha256":"32e641279e0f9a4a6af1d7eedcd274982ebc03cdaa6f40769c994c474c4a05e7"},"schema_version":"1.0"},"canonical_sha256":"3ffa8d36a59f2104935fd475d3859387a1b5081e6e073628423359f6a8679103","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:31:14.363646Z","signature_b64":"v0NRYCqVR3Z7cMMUXGnCKbR28kbI2Mp843ZCXXNvEExATo0qwoE3xmP0IMoFP+zRyvDcSRcTlVVjXEc5lnJHAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3ffa8d36a59f2104935fd475d3859387a1b5081e6e073628423359f6a8679103","last_reissued_at":"2026-07-05T02:31:14.363089Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:31:14.363089Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2104.05591","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":"2026-07-05T02:31:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"drjFOgV5hMWalFxjAy/AZzGadKILvdOBGAAI9E+IaD+5tom57KkkENka64ibPhkk1QKadOvkKSTshPTuoGB6Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T14:41:51.827418Z"},"content_sha256":"3dfa87fcb981712943cd4be6fc3da18ea3d222d163843c131eb5b8205c167e8d","schema_version":"1.0","event_id":"sha256:3dfa87fcb981712943cd4be6fc3da18ea3d222d163843c131eb5b8205c167e8d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:H75I2NVFT4QQJE272R25HBMTQ6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"DATE: Detecting Anomalies in Text via Self-Supervision of Transformers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Andrei Manolache, Elena Burceanu, Florin Brad","submitted_at":"2021-04-12T16:08:05Z","abstract_excerpt":"Leveraging deep learning models for Anomaly Detection (AD) has seen widespread use in recent years due to superior performances over traditional methods. Recent deep methods for anomalies in images learn better features of normality in an end-to-end self-supervised setting. These methods train a model to discriminate between different transformations applied to visual data and then use the output to compute an anomaly score. We use this approach for AD in text, by introducing a novel pretext task on text sequences. We learn our DATE model end-to-end, enforcing two independent and complementary"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.05591","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/2104.05591/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":"2026-07-05T02:31:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wxCrI14xYBYxqJYeoAuLE9QP2x4oYe63hIs7sbsHLtQpjhwpbyLDkCyDHZJBXPBUQxRj1s7aqeMvOBmDvFSjBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T14:41:51.828012Z"},"content_sha256":"5ab4d1fef6cd3e303012def216fae584cd8a56fd81d4151b9acc8027603a3a71","schema_version":"1.0","event_id":"sha256:5ab4d1fef6cd3e303012def216fae584cd8a56fd81d4151b9acc8027603a3a71"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/H75I2NVFT4QQJE272R25HBMTQ6/bundle.json","state_url":"https://pith.science/pith/H75I2NVFT4QQJE272R25HBMTQ6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/H75I2NVFT4QQJE272R25HBMTQ6/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":"2026-08-10T14:41:51Z","links":{"resolver":"https://pith.science/pith/H75I2NVFT4QQJE272R25HBMTQ6","bundle":"https://pith.science/pith/H75I2NVFT4QQJE272R25HBMTQ6/bundle.json","state":"https://pith.science/pith/H75I2NVFT4QQJE272R25HBMTQ6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/H75I2NVFT4QQJE272R25HBMTQ6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:H75I2NVFT4QQJE272R25HBMTQ6","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":"32e641279e0f9a4a6af1d7eedcd274982ebc03cdaa6f40769c994c474c4a05e7","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-04-12T16:08:05Z","title_canon_sha256":"da3e71d3ecbfd946e5eeb38591374ddfbf03e87331e50d7ab47423c84e204389"},"schema_version":"1.0","source":{"id":"2104.05591","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.05591","created_at":"2026-07-05T02:31:14Z"},{"alias_kind":"arxiv_version","alias_value":"2104.05591v1","created_at":"2026-07-05T02:31:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.05591","created_at":"2026-07-05T02:31:14Z"},{"alias_kind":"pith_short_12","alias_value":"H75I2NVFT4QQ","created_at":"2026-07-05T02:31:14Z"},{"alias_kind":"pith_short_16","alias_value":"H75I2NVFT4QQJE27","created_at":"2026-07-05T02:31:14Z"},{"alias_kind":"pith_short_8","alias_value":"H75I2NVF","created_at":"2026-07-05T02:31:14Z"}],"graph_snapshots":[{"event_id":"sha256:5ab4d1fef6cd3e303012def216fae584cd8a56fd81d4151b9acc8027603a3a71","target":"graph","created_at":"2026-07-05T02:31:14Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2104.05591/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Leveraging deep learning models for Anomaly Detection (AD) has seen widespread use in recent years due to superior performances over traditional methods. Recent deep methods for anomalies in images learn better features of normality in an end-to-end self-supervised setting. These methods train a model to discriminate between different transformations applied to visual data and then use the output to compute an anomaly score. We use this approach for AD in text, by introducing a novel pretext task on text sequences. We learn our DATE model end-to-end, enforcing two independent and complementary","authors_text":"Andrei Manolache, Elena Burceanu, Florin Brad","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-04-12T16:08:05Z","title":"DATE: Detecting Anomalies in Text via Self-Supervision of Transformers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.05591","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":"sha256:3dfa87fcb981712943cd4be6fc3da18ea3d222d163843c131eb5b8205c167e8d","target":"record","created_at":"2026-07-05T02:31:14Z","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":"32e641279e0f9a4a6af1d7eedcd274982ebc03cdaa6f40769c994c474c4a05e7","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-04-12T16:08:05Z","title_canon_sha256":"da3e71d3ecbfd946e5eeb38591374ddfbf03e87331e50d7ab47423c84e204389"},"schema_version":"1.0","source":{"id":"2104.05591","kind":"arxiv","version":1}},"canonical_sha256":"3ffa8d36a59f2104935fd475d3859387a1b5081e6e073628423359f6a8679103","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3ffa8d36a59f2104935fd475d3859387a1b5081e6e073628423359f6a8679103","first_computed_at":"2026-07-05T02:31:14.363089Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:31:14.363089Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"v0NRYCqVR3Z7cMMUXGnCKbR28kbI2Mp843ZCXXNvEExATo0qwoE3xmP0IMoFP+zRyvDcSRcTlVVjXEc5lnJHAw==","signature_status":"signed_v1","signed_at":"2026-07-05T02:31:14.363646Z","signed_message":"canonical_sha256_bytes"},"source_id":"2104.05591","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3dfa87fcb981712943cd4be6fc3da18ea3d222d163843c131eb5b8205c167e8d","sha256:5ab4d1fef6cd3e303012def216fae584cd8a56fd81d4151b9acc8027603a3a71"],"state_sha256":"e1bb5415fe862e5df2074e71607eda16f9077026b2683c35554787f18f50f9be"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oQ+QLKlSVVnlHoM9ijVWhRJ5cH2nMWlEHkqO13NOfZGyzMIlR78yZGa9WWyZl5/TO3x9XjXqMHuA/2PcXkQ0DA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T14:41:51.831633Z","bundle_sha256":"479ae00536a974197a734524adfe542dee8f286370c6c7ed81fb7b8cad587d98"}}