{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:5EQDZZXXA7HXLLIRVQWSJULDZQ","short_pith_number":"pith:5EQDZZXX","canonical_record":{"source":{"id":"1811.03575","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-11-08T17:56:43Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"2abc9af106b69e3d2cde01f2dc313a2f14d0f8f6dc93489b6c53992872c4b8f4","abstract_canon_sha256":"4d9a1e3384f0e1e28083c51fc9dc969c644b07e98101106e7c55a206854f2a60"},"schema_version":"1.0"},"canonical_sha256":"e9203ce6f707cf75ad11ac2d24d163cc286e24e331cac98d7135a9f086412375","source":{"kind":"arxiv","id":"1811.03575","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1811.03575","created_at":"2026-05-17T23:53:04Z"},{"alias_kind":"arxiv_version","alias_value":"1811.03575v3","created_at":"2026-05-17T23:53:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.03575","created_at":"2026-05-17T23:53:04Z"},{"alias_kind":"pith_short_12","alias_value":"5EQDZZXXA7HX","created_at":"2026-05-18T12:32:08Z"},{"alias_kind":"pith_short_16","alias_value":"5EQDZZXXA7HXLLIR","created_at":"2026-05-18T12:32:08Z"},{"alias_kind":"pith_short_8","alias_value":"5EQDZZXX","created_at":"2026-05-18T12:32:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:5EQDZZXXA7HXLLIRVQWSJULDZQ","target":"record","payload":{"canonical_record":{"source":{"id":"1811.03575","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-11-08T17:56:43Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"2abc9af106b69e3d2cde01f2dc313a2f14d0f8f6dc93489b6c53992872c4b8f4","abstract_canon_sha256":"4d9a1e3384f0e1e28083c51fc9dc969c644b07e98101106e7c55a206854f2a60"},"schema_version":"1.0"},"canonical_sha256":"e9203ce6f707cf75ad11ac2d24d163cc286e24e331cac98d7135a9f086412375","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:53:04.344348Z","signature_b64":"CIl0hmvCmBBUQZmOdZBgZQl+cA4kv+z7fSLfDCxg/LZ9NRUEEbp3p3nrglo7NHpLo/2YPF4K0rixlmFvzEbcBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e9203ce6f707cf75ad11ac2d24d163cc286e24e331cac98d7135a9f086412375","last_reissued_at":"2026-05-17T23:53:04.343892Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:53:04.343892Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1811.03575","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:53:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TJDjcUQPXaSJ7jplLyZxD7FkEXDMXi1j9cidgfgRL6HcqoWp1M3z4o0Ga802CkpKHtcF1I/Y87gW8XwhJMRuBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T21:22:15.630276Z"},"content_sha256":"01dca8eff1475af791f3797ccc87d9d109137b9a951ccc4957022b1935809e4e","schema_version":"1.0","event_id":"sha256:01dca8eff1475af791f3797ccc87d9d109137b9a951ccc4957022b1935809e4e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:5EQDZZXXA7HXLLIRVQWSJULDZQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Large-Scale Visual Active Learning with Deep Probabilistic Ensembles","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CV","authors_text":"Adam Lesnikowski, Jose M. Alvarez, Kashyap Chitta","submitted_at":"2018-11-08T17:56:43Z","abstract_excerpt":"Annotating the right data for training deep neural networks is an important challenge. Active learning using uncertainty estimates from Bayesian Neural Networks (BNNs) could provide an effective solution to this. Despite being theoretically principled, BNNs require approximations to be applied to large-scale problems, where both performance and uncertainty estimation are crucial. In this paper, we introduce Deep Probabilistic Ensembles (DPEs), a scalable technique that uses a regularized ensemble to approximate a deep BNN. We conduct a series of large-scale visual active learning experiments t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.03575","kind":"arxiv","version":3},"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":"2026-05-17T23:53:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"l0f4pwtOM6SfYWaIm8zYqweYqMu9OkCd0x7yO3PrN5lRymPoNoc4Dm40gyxyZg2jp4mWfpPktMKi4eyJiuR5Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T21:22:15.630998Z"},"content_sha256":"3f1b5f04ae56ad57fdd78796668476351365dcab00814f312f3f52baa2fc4b52","schema_version":"1.0","event_id":"sha256:3f1b5f04ae56ad57fdd78796668476351365dcab00814f312f3f52baa2fc4b52"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5EQDZZXXA7HXLLIRVQWSJULDZQ/bundle.json","state_url":"https://pith.science/pith/5EQDZZXXA7HXLLIRVQWSJULDZQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5EQDZZXXA7HXLLIRVQWSJULDZQ/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":"2026-06-06T21:22:15Z","links":{"resolver":"https://pith.science/pith/5EQDZZXXA7HXLLIRVQWSJULDZQ","bundle":"https://pith.science/pith/5EQDZZXXA7HXLLIRVQWSJULDZQ/bundle.json","state":"https://pith.science/pith/5EQDZZXXA7HXLLIRVQWSJULDZQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5EQDZZXXA7HXLLIRVQWSJULDZQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:5EQDZZXXA7HXLLIRVQWSJULDZQ","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":"4d9a1e3384f0e1e28083c51fc9dc969c644b07e98101106e7c55a206854f2a60","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-11-08T17:56:43Z","title_canon_sha256":"2abc9af106b69e3d2cde01f2dc313a2f14d0f8f6dc93489b6c53992872c4b8f4"},"schema_version":"1.0","source":{"id":"1811.03575","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1811.03575","created_at":"2026-05-17T23:53:04Z"},{"alias_kind":"arxiv_version","alias_value":"1811.03575v3","created_at":"2026-05-17T23:53:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.03575","created_at":"2026-05-17T23:53:04Z"},{"alias_kind":"pith_short_12","alias_value":"5EQDZZXXA7HX","created_at":"2026-05-18T12:32:08Z"},{"alias_kind":"pith_short_16","alias_value":"5EQDZZXXA7HXLLIR","created_at":"2026-05-18T12:32:08Z"},{"alias_kind":"pith_short_8","alias_value":"5EQDZZXX","created_at":"2026-05-18T12:32:08Z"}],"graph_snapshots":[{"event_id":"sha256:3f1b5f04ae56ad57fdd78796668476351365dcab00814f312f3f52baa2fc4b52","target":"graph","created_at":"2026-05-17T23:53:04Z","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":"Annotating the right data for training deep neural networks is an important challenge. Active learning using uncertainty estimates from Bayesian Neural Networks (BNNs) could provide an effective solution to this. Despite being theoretically principled, BNNs require approximations to be applied to large-scale problems, where both performance and uncertainty estimation are crucial. In this paper, we introduce Deep Probabilistic Ensembles (DPEs), a scalable technique that uses a regularized ensemble to approximate a deep BNN. We conduct a series of large-scale visual active learning experiments t","authors_text":"Adam Lesnikowski, Jose M. Alvarez, Kashyap Chitta","cross_cats":["cs.LG","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-11-08T17:56:43Z","title":"Large-Scale Visual Active Learning with Deep Probabilistic Ensembles"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.03575","kind":"arxiv","version":3},"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":"sha256:01dca8eff1475af791f3797ccc87d9d109137b9a951ccc4957022b1935809e4e","target":"record","created_at":"2026-05-17T23:53:04Z","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":"4d9a1e3384f0e1e28083c51fc9dc969c644b07e98101106e7c55a206854f2a60","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-11-08T17:56:43Z","title_canon_sha256":"2abc9af106b69e3d2cde01f2dc313a2f14d0f8f6dc93489b6c53992872c4b8f4"},"schema_version":"1.0","source":{"id":"1811.03575","kind":"arxiv","version":3}},"canonical_sha256":"e9203ce6f707cf75ad11ac2d24d163cc286e24e331cac98d7135a9f086412375","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e9203ce6f707cf75ad11ac2d24d163cc286e24e331cac98d7135a9f086412375","first_computed_at":"2026-05-17T23:53:04.343892Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:53:04.343892Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CIl0hmvCmBBUQZmOdZBgZQl+cA4kv+z7fSLfDCxg/LZ9NRUEEbp3p3nrglo7NHpLo/2YPF4K0rixlmFvzEbcBw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:53:04.344348Z","signed_message":"canonical_sha256_bytes"},"source_id":"1811.03575","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:01dca8eff1475af791f3797ccc87d9d109137b9a951ccc4957022b1935809e4e","sha256:3f1b5f04ae56ad57fdd78796668476351365dcab00814f312f3f52baa2fc4b52"],"state_sha256":"7428649c79946446dbff6bf939f7a04191541cc512df45561922d9e30ef3c96f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bS5Sfvj3FGBBzKQ05U4qZZw2MOqgy5nMSvUVjD6/6GB7ut7x4vhlgx2cn3PRBLum06fjN+EsXrj9m6HZtE1gBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-06T21:22:15.635435Z","bundle_sha256":"d93511f83554a03c6d7b298ced0325699ff28d550535207ef57f6719548577a4"}}