{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:6OCJQ2DGAB6SMNKYGB7PSOUUQU","short_pith_number":"pith:6OCJQ2DG","canonical_record":{"source":{"id":"1903.07256","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-03-18T05:07:09Z","cross_cats_sorted":[],"title_canon_sha256":"938d99e22c34ae6a8f1459bd1d4e108b5cdead56bf7c0dc074c8f61ae5e3ab62","abstract_canon_sha256":"031a76ab6cecaa5520982a22ffc46c9e00ae962fd61a7ee435a1235ee684a885"},"schema_version":"1.0"},"canonical_sha256":"f384986866007d263558307ef93a94851d80e8ba5135135b54e0819db19fb554","source":{"kind":"arxiv","id":"1903.07256","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1903.07256","created_at":"2026-05-17T23:51:03Z"},{"alias_kind":"arxiv_version","alias_value":"1903.07256v1","created_at":"2026-05-17T23:51:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.07256","created_at":"2026-05-17T23:51:03Z"},{"alias_kind":"pith_short_12","alias_value":"6OCJQ2DGAB6S","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_16","alias_value":"6OCJQ2DGAB6SMNKY","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_8","alias_value":"6OCJQ2DG","created_at":"2026-05-18T12:33:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:6OCJQ2DGAB6SMNKYGB7PSOUUQU","target":"record","payload":{"canonical_record":{"source":{"id":"1903.07256","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-03-18T05:07:09Z","cross_cats_sorted":[],"title_canon_sha256":"938d99e22c34ae6a8f1459bd1d4e108b5cdead56bf7c0dc074c8f61ae5e3ab62","abstract_canon_sha256":"031a76ab6cecaa5520982a22ffc46c9e00ae962fd61a7ee435a1235ee684a885"},"schema_version":"1.0"},"canonical_sha256":"f384986866007d263558307ef93a94851d80e8ba5135135b54e0819db19fb554","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:51:03.812187Z","signature_b64":"vZB5W9IiI0FwxqUOEKfeTyuibJFZoF+U3zAL6hp2Q9SiNqR3uz6/Mf7tYrDPe7GjjkKXUsCM4hTuu9WwB+loCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f384986866007d263558307ef93a94851d80e8ba5135135b54e0819db19fb554","last_reissued_at":"2026-05-17T23:51:03.811645Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:51:03.811645Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1903.07256","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":"2026-05-17T23:51:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lvB3+KgQbFZmZc+Y6JbICN7tNFgMzo26q7NDsrHoDisRMuUnBLO3q9s/Haslv24y7foGzx0i4omlZqCAvRv3Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-23T15:17:11.820574Z"},"content_sha256":"137d79ca011aa242fbb08f30080ba13fc40e26e68d447f8ec3e5813150e9f63b","schema_version":"1.0","event_id":"sha256:137d79ca011aa242fbb08f30080ba13fc40e26e68d447f8ec3e5813150e9f63b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:6OCJQ2DGAB6SMNKYGB7PSOUUQU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Graph Convolutional Label Noise Cleaner: Train a Plug-and-play Action Classifier for Anomaly Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ge Li, Jia-Xing Zhong, Nannan Li, Shan Liu, Thomas H. Li, Weijie Kong","submitted_at":"2019-03-18T05:07:09Z","abstract_excerpt":"Video anomaly detection under weak labels is formulated as a typical multiple-instance learning problem in previous works. In this paper, we provide a new perspective, i.e., a supervised learning task under noisy labels. In such a viewpoint, as long as cleaning away label noise, we can directly apply fully supervised action classifiers to weakly supervised anomaly detection, and take maximum advantage of these well-developed classifiers. For this purpose, we devise a graph convolutional network to correct noisy labels. Based upon feature similarity and temporal consistency, our network propaga"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.07256","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":""},"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":"2026-05-17T23:51:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CfpF3i/mba1baByIbRVlSYfGMBA0Ti4GqlbHygh1lHP/5UJyv4DSfQ3RFZwZCptI2RjfebcvrmDAaWDb4LbkCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-23T15:17:11.821302Z"},"content_sha256":"4961b79e04e32d8f01b0c2d7e6eb9e4626c2f09138d625b4a7e2fd5ddf796578","schema_version":"1.0","event_id":"sha256:4961b79e04e32d8f01b0c2d7e6eb9e4626c2f09138d625b4a7e2fd5ddf796578"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6OCJQ2DGAB6SMNKYGB7PSOUUQU/bundle.json","state_url":"https://pith.science/pith/6OCJQ2DGAB6SMNKYGB7PSOUUQU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6OCJQ2DGAB6SMNKYGB7PSOUUQU/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":"2026-05-23T15:17:11Z","links":{"resolver":"https://pith.science/pith/6OCJQ2DGAB6SMNKYGB7PSOUUQU","bundle":"https://pith.science/pith/6OCJQ2DGAB6SMNKYGB7PSOUUQU/bundle.json","state":"https://pith.science/pith/6OCJQ2DGAB6SMNKYGB7PSOUUQU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6OCJQ2DGAB6SMNKYGB7PSOUUQU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:6OCJQ2DGAB6SMNKYGB7PSOUUQU","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":"031a76ab6cecaa5520982a22ffc46c9e00ae962fd61a7ee435a1235ee684a885","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-03-18T05:07:09Z","title_canon_sha256":"938d99e22c34ae6a8f1459bd1d4e108b5cdead56bf7c0dc074c8f61ae5e3ab62"},"schema_version":"1.0","source":{"id":"1903.07256","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1903.07256","created_at":"2026-05-17T23:51:03Z"},{"alias_kind":"arxiv_version","alias_value":"1903.07256v1","created_at":"2026-05-17T23:51:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.07256","created_at":"2026-05-17T23:51:03Z"},{"alias_kind":"pith_short_12","alias_value":"6OCJQ2DGAB6S","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_16","alias_value":"6OCJQ2DGAB6SMNKY","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_8","alias_value":"6OCJQ2DG","created_at":"2026-05-18T12:33:10Z"}],"graph_snapshots":[{"event_id":"sha256:4961b79e04e32d8f01b0c2d7e6eb9e4626c2f09138d625b4a7e2fd5ddf796578","target":"graph","created_at":"2026-05-17T23:51:03Z","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":"Video anomaly detection under weak labels is formulated as a typical multiple-instance learning problem in previous works. In this paper, we provide a new perspective, i.e., a supervised learning task under noisy labels. In such a viewpoint, as long as cleaning away label noise, we can directly apply fully supervised action classifiers to weakly supervised anomaly detection, and take maximum advantage of these well-developed classifiers. For this purpose, we devise a graph convolutional network to correct noisy labels. Based upon feature similarity and temporal consistency, our network propaga","authors_text":"Ge Li, Jia-Xing Zhong, Nannan Li, Shan Liu, Thomas H. Li, Weijie Kong","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-03-18T05:07:09Z","title":"Graph Convolutional Label Noise Cleaner: Train a Plug-and-play Action Classifier for Anomaly Detection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.07256","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":"sha256:137d79ca011aa242fbb08f30080ba13fc40e26e68d447f8ec3e5813150e9f63b","target":"record","created_at":"2026-05-17T23:51:03Z","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":"031a76ab6cecaa5520982a22ffc46c9e00ae962fd61a7ee435a1235ee684a885","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-03-18T05:07:09Z","title_canon_sha256":"938d99e22c34ae6a8f1459bd1d4e108b5cdead56bf7c0dc074c8f61ae5e3ab62"},"schema_version":"1.0","source":{"id":"1903.07256","kind":"arxiv","version":1}},"canonical_sha256":"f384986866007d263558307ef93a94851d80e8ba5135135b54e0819db19fb554","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f384986866007d263558307ef93a94851d80e8ba5135135b54e0819db19fb554","first_computed_at":"2026-05-17T23:51:03.811645Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:51:03.811645Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vZB5W9IiI0FwxqUOEKfeTyuibJFZoF+U3zAL6hp2Q9SiNqR3uz6/Mf7tYrDPe7GjjkKXUsCM4hTuu9WwB+loCg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:51:03.812187Z","signed_message":"canonical_sha256_bytes"},"source_id":"1903.07256","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:137d79ca011aa242fbb08f30080ba13fc40e26e68d447f8ec3e5813150e9f63b","sha256:4961b79e04e32d8f01b0c2d7e6eb9e4626c2f09138d625b4a7e2fd5ddf796578"],"state_sha256":"f0007784217aa8597229922a809421826cdd2dba1bc32d70b282c3408df3cd86"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"q4XpJotGx4h5wUJgRBj0p4N/6YKcFV51EgphVLbZRSsYojNHgx2ipMTsH/+B1h2aIWEcO7eY4gPcEaJnfw5bBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-23T15:17:11.824927Z","bundle_sha256":"bedd0173d58bc8929078eace4e805d69db2ada87c234fc416059c36603d47df9"}}