{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:BG55URFQAWHVP7IMZFJXCJXCXG","short_pith_number":"pith:BG55URFQ","canonical_record":{"source":{"id":"1901.03360","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-01-10T19:58:16Z","cross_cats_sorted":[],"title_canon_sha256":"fa41257777a67046f35812d6c0682bfea5adf6e3bcf37e7a3d140e38a59aae7c","abstract_canon_sha256":"8065fae22eb0e058475f1c71385858027da69933e55fe5aa8d5a14c9df64b631"},"schema_version":"1.0"},"canonical_sha256":"09bbda44b0058f57fd0cc9537126e2b998b7f53d94d3275b8fb768ff69b5ca18","source":{"kind":"arxiv","id":"1901.03360","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1901.03360","created_at":"2026-05-17T23:48:39Z"},{"alias_kind":"arxiv_version","alias_value":"1901.03360v2","created_at":"2026-05-17T23:48:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.03360","created_at":"2026-05-17T23:48:39Z"},{"alias_kind":"pith_short_12","alias_value":"BG55URFQAWHV","created_at":"2026-05-18T12:33:12Z"},{"alias_kind":"pith_short_16","alias_value":"BG55URFQAWHVP7IM","created_at":"2026-05-18T12:33:12Z"},{"alias_kind":"pith_short_8","alias_value":"BG55URFQ","created_at":"2026-05-18T12:33:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:BG55URFQAWHVP7IMZFJXCJXCXG","target":"record","payload":{"canonical_record":{"source":{"id":"1901.03360","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-01-10T19:58:16Z","cross_cats_sorted":[],"title_canon_sha256":"fa41257777a67046f35812d6c0682bfea5adf6e3bcf37e7a3d140e38a59aae7c","abstract_canon_sha256":"8065fae22eb0e058475f1c71385858027da69933e55fe5aa8d5a14c9df64b631"},"schema_version":"1.0"},"canonical_sha256":"09bbda44b0058f57fd0cc9537126e2b998b7f53d94d3275b8fb768ff69b5ca18","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:48:39.583934Z","signature_b64":"+FrZXRR7nFU3T1W8nyPuJ1xp7Buw96M1/nF+gQtgkNcMQ+hps9Vt+7hewOuPryvRqy6mc0SCTXZwIfxO8cr+CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"09bbda44b0058f57fd0cc9537126e2b998b7f53d94d3275b8fb768ff69b5ca18","last_reissued_at":"2026-05-17T23:48:39.583367Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:48:39.583367Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1901.03360","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":"2026-05-17T23:48:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zySe/SPmAuqok/Tqc1IccgPUg4zEUco5wCNNoDUqA8JvzaXUuquQyKlPC0MDzDsZUngcvK+HxfbXjfIKALykAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-20T01:41:40.905007Z"},"content_sha256":"38f3fe1cb07f7aa0e866253de6d56f49cb7ea373c246f2d24b06839a8967d4f3","schema_version":"1.0","event_id":"sha256:38f3fe1cb07f7aa0e866253de6d56f49cb7ea373c246f2d24b06839a8967d4f3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:BG55URFQAWHVP7IMZFJXCJXCXG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Unsupervised Moving Object Detection via Contextual Information Separation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Antonio Loquercio, Davide Scaramuzza, Stefano Soatto, Yanchao Yang","submitted_at":"2019-01-10T19:58:16Z","abstract_excerpt":"We propose an adversarial contextual model for detecting moving objects in images. A deep neural network is trained to predict the optical flow in a region using information from everywhere else but that region (context), while another network attempts to make such context as uninformative as possible. The result is a model where hypotheses naturally compete with no need for explicit regularization or hyper-parameter tuning. Although our method requires no supervision whatsoever, it outperforms several methods that are pre-trained on large annotated datasets. Our model can be thought of as a g"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.03360","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":""},"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":"2026-05-17T23:48:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DwHiSmYrIg2Bmq/yf2f14zPRL5R0FUthneVieQ4QIFyiRp4pZvpwv2ahWlcmRfdGJYb7cOSV2SMJEaeKTAztCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-20T01:41:40.905384Z"},"content_sha256":"2a13b0bced3374d7d7fc0bf919390ad5461e9356c91db0483dd81f0f2661f0bc","schema_version":"1.0","event_id":"sha256:2a13b0bced3374d7d7fc0bf919390ad5461e9356c91db0483dd81f0f2661f0bc"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BG55URFQAWHVP7IMZFJXCJXCXG/bundle.json","state_url":"https://pith.science/pith/BG55URFQAWHVP7IMZFJXCJXCXG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BG55URFQAWHVP7IMZFJXCJXCXG/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":"2026-06-20T01:41:40Z","links":{"resolver":"https://pith.science/pith/BG55URFQAWHVP7IMZFJXCJXCXG","bundle":"https://pith.science/pith/BG55URFQAWHVP7IMZFJXCJXCXG/bundle.json","state":"https://pith.science/pith/BG55URFQAWHVP7IMZFJXCJXCXG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BG55URFQAWHVP7IMZFJXCJXCXG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:BG55URFQAWHVP7IMZFJXCJXCXG","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":"8065fae22eb0e058475f1c71385858027da69933e55fe5aa8d5a14c9df64b631","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-01-10T19:58:16Z","title_canon_sha256":"fa41257777a67046f35812d6c0682bfea5adf6e3bcf37e7a3d140e38a59aae7c"},"schema_version":"1.0","source":{"id":"1901.03360","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1901.03360","created_at":"2026-05-17T23:48:39Z"},{"alias_kind":"arxiv_version","alias_value":"1901.03360v2","created_at":"2026-05-17T23:48:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.03360","created_at":"2026-05-17T23:48:39Z"},{"alias_kind":"pith_short_12","alias_value":"BG55URFQAWHV","created_at":"2026-05-18T12:33:12Z"},{"alias_kind":"pith_short_16","alias_value":"BG55URFQAWHVP7IM","created_at":"2026-05-18T12:33:12Z"},{"alias_kind":"pith_short_8","alias_value":"BG55URFQ","created_at":"2026-05-18T12:33:12Z"}],"graph_snapshots":[{"event_id":"sha256:2a13b0bced3374d7d7fc0bf919390ad5461e9356c91db0483dd81f0f2661f0bc","target":"graph","created_at":"2026-05-17T23:48:39Z","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":"We propose an adversarial contextual model for detecting moving objects in images. A deep neural network is trained to predict the optical flow in a region using information from everywhere else but that region (context), while another network attempts to make such context as uninformative as possible. The result is a model where hypotheses naturally compete with no need for explicit regularization or hyper-parameter tuning. Although our method requires no supervision whatsoever, it outperforms several methods that are pre-trained on large annotated datasets. Our model can be thought of as a g","authors_text":"Antonio Loquercio, Davide Scaramuzza, Stefano Soatto, Yanchao Yang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-01-10T19:58:16Z","title":"Unsupervised Moving Object Detection via Contextual Information Separation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.03360","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":"sha256:38f3fe1cb07f7aa0e866253de6d56f49cb7ea373c246f2d24b06839a8967d4f3","target":"record","created_at":"2026-05-17T23:48:39Z","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":"8065fae22eb0e058475f1c71385858027da69933e55fe5aa8d5a14c9df64b631","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-01-10T19:58:16Z","title_canon_sha256":"fa41257777a67046f35812d6c0682bfea5adf6e3bcf37e7a3d140e38a59aae7c"},"schema_version":"1.0","source":{"id":"1901.03360","kind":"arxiv","version":2}},"canonical_sha256":"09bbda44b0058f57fd0cc9537126e2b998b7f53d94d3275b8fb768ff69b5ca18","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"09bbda44b0058f57fd0cc9537126e2b998b7f53d94d3275b8fb768ff69b5ca18","first_computed_at":"2026-05-17T23:48:39.583367Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:48:39.583367Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+FrZXRR7nFU3T1W8nyPuJ1xp7Buw96M1/nF+gQtgkNcMQ+hps9Vt+7hewOuPryvRqy6mc0SCTXZwIfxO8cr+CA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:48:39.583934Z","signed_message":"canonical_sha256_bytes"},"source_id":"1901.03360","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:38f3fe1cb07f7aa0e866253de6d56f49cb7ea373c246f2d24b06839a8967d4f3","sha256:2a13b0bced3374d7d7fc0bf919390ad5461e9356c91db0483dd81f0f2661f0bc"],"state_sha256":"775992cbe5518e6b92d124c233141a0330b8cf5b195f28ee9800962727ca06f9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8n50nNPmZ97kxgqvIZI1zqR952/HRBpGM+tu+rhMGOABTOEiLI4jG9tGHLQTsps06Q7XAxPFvrgFyScwrajZDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-20T01:41:40.907346Z","bundle_sha256":"38d84c3b0d6518f1e57284367e6237f3380b90a57c53895233ffc840f331aa0f"}}