{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2015:QJYJ5WWDE2BHFWFASTJJDSROCL","short_pith_number":"pith:QJYJ5WWD","canonical_record":{"source":{"id":"1506.04416","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-06-14T16:22:16Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"2a4fb98255b073b77f26cc162b138dd9d1c95fae08495c2e0b3fedd62536fad2","abstract_canon_sha256":"cdbc7df5fc424e6523e186dd36865e8427cd8819b4ee2896a91406e7e0c3c262"},"schema_version":"1.0"},"canonical_sha256":"82709edac3268272d8a094d291ca2e12d3c5237d3439dba1451eff80a199cd1d","source":{"kind":"arxiv","id":"1506.04416","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1506.04416","created_at":"2026-05-18T01:27:31Z"},{"alias_kind":"arxiv_version","alias_value":"1506.04416v3","created_at":"2026-05-18T01:27:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1506.04416","created_at":"2026-05-18T01:27:31Z"},{"alias_kind":"pith_short_12","alias_value":"QJYJ5WWDE2BH","created_at":"2026-05-18T12:29:37Z"},{"alias_kind":"pith_short_16","alias_value":"QJYJ5WWDE2BHFWFA","created_at":"2026-05-18T12:29:37Z"},{"alias_kind":"pith_short_8","alias_value":"QJYJ5WWD","created_at":"2026-05-18T12:29:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2015:QJYJ5WWDE2BHFWFASTJJDSROCL","target":"record","payload":{"canonical_record":{"source":{"id":"1506.04416","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-06-14T16:22:16Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"2a4fb98255b073b77f26cc162b138dd9d1c95fae08495c2e0b3fedd62536fad2","abstract_canon_sha256":"cdbc7df5fc424e6523e186dd36865e8427cd8819b4ee2896a91406e7e0c3c262"},"schema_version":"1.0"},"canonical_sha256":"82709edac3268272d8a094d291ca2e12d3c5237d3439dba1451eff80a199cd1d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:27:31.532610Z","signature_b64":"cOSwvdSondTnY8BjzQFlVOJFT1SzFm9/xiKXYjkqkOjV0gHrARIfHlJG266YjLbuFT4kPT/cyHc+zpy4HfOfAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"82709edac3268272d8a094d291ca2e12d3c5237d3439dba1451eff80a199cd1d","last_reissued_at":"2026-05-18T01:27:31.531964Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:27:31.531964Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1506.04416","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":"2026-05-18T01:27:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cSmlhGGT/roCHgai2FzTm9JA18NcSyoX2vgXp3a9EFQx5qdjBcGQDHEzMnTIfZP4R2RrZi2joC1Rz28qSoOIBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-20T04:35:47.951528Z"},"content_sha256":"d35ee760db2b7f5cdd5004192bacc059307d8276b415354880cb07d817330c36","schema_version":"1.0","event_id":"sha256:d35ee760db2b7f5cdd5004192bacc059307d8276b415354880cb07d817330c36"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2015:QJYJ5WWDE2BHFWFASTJJDSROCL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Bayesian Dark Knowledge","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Anoop Korattikara, Kevin Murphy, Max Welling, Vivek Rathod","submitted_at":"2015-06-14T16:22:16Z","abstract_excerpt":"We consider the problem of Bayesian parameter estimation for deep neural networks, which is important in problem settings where we may have little data, and/ or where we need accurate posterior predictive densities, e.g., for applications involving bandits or active learning. One simple approach to this is to use online Monte Carlo methods, such as SGLD (stochastic gradient Langevin dynamics). Unfortunately, such a method needs to store many copies of the parameters (which wastes memory), and needs to make predictions using many versions of the model (which wastes time).\n  We describe a method"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1506.04416","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":"2026-05-18T01:27:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EJeciZh+YI4uP6Huijmk5KnhHnGGPDyAHC2QPSjL6+t44Cj6POd6njknaeeRwSkSRa0xHJ3orbozHtmpXbENCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-20T04:35:47.952259Z"},"content_sha256":"085ea574c8303eaedfba0bddfa49c3b19735fff4f7118a7880186cfbf117b310","schema_version":"1.0","event_id":"sha256:085ea574c8303eaedfba0bddfa49c3b19735fff4f7118a7880186cfbf117b310"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QJYJ5WWDE2BHFWFASTJJDSROCL/bundle.json","state_url":"https://pith.science/pith/QJYJ5WWDE2BHFWFASTJJDSROCL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QJYJ5WWDE2BHFWFASTJJDSROCL/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":"2026-05-20T04:35:47Z","links":{"resolver":"https://pith.science/pith/QJYJ5WWDE2BHFWFASTJJDSROCL","bundle":"https://pith.science/pith/QJYJ5WWDE2BHFWFASTJJDSROCL/bundle.json","state":"https://pith.science/pith/QJYJ5WWDE2BHFWFASTJJDSROCL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QJYJ5WWDE2BHFWFASTJJDSROCL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:QJYJ5WWDE2BHFWFASTJJDSROCL","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":"cdbc7df5fc424e6523e186dd36865e8427cd8819b4ee2896a91406e7e0c3c262","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-06-14T16:22:16Z","title_canon_sha256":"2a4fb98255b073b77f26cc162b138dd9d1c95fae08495c2e0b3fedd62536fad2"},"schema_version":"1.0","source":{"id":"1506.04416","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1506.04416","created_at":"2026-05-18T01:27:31Z"},{"alias_kind":"arxiv_version","alias_value":"1506.04416v3","created_at":"2026-05-18T01:27:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1506.04416","created_at":"2026-05-18T01:27:31Z"},{"alias_kind":"pith_short_12","alias_value":"QJYJ5WWDE2BH","created_at":"2026-05-18T12:29:37Z"},{"alias_kind":"pith_short_16","alias_value":"QJYJ5WWDE2BHFWFA","created_at":"2026-05-18T12:29:37Z"},{"alias_kind":"pith_short_8","alias_value":"QJYJ5WWD","created_at":"2026-05-18T12:29:37Z"}],"graph_snapshots":[{"event_id":"sha256:085ea574c8303eaedfba0bddfa49c3b19735fff4f7118a7880186cfbf117b310","target":"graph","created_at":"2026-05-18T01:27:31Z","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 consider the problem of Bayesian parameter estimation for deep neural networks, which is important in problem settings where we may have little data, and/ or where we need accurate posterior predictive densities, e.g., for applications involving bandits or active learning. One simple approach to this is to use online Monte Carlo methods, such as SGLD (stochastic gradient Langevin dynamics). Unfortunately, such a method needs to store many copies of the parameters (which wastes memory), and needs to make predictions using many versions of the model (which wastes time).\n  We describe a method","authors_text":"Anoop Korattikara, Kevin Murphy, Max Welling, Vivek Rathod","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-06-14T16:22:16Z","title":"Bayesian Dark Knowledge"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1506.04416","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:d35ee760db2b7f5cdd5004192bacc059307d8276b415354880cb07d817330c36","target":"record","created_at":"2026-05-18T01:27:31Z","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":"cdbc7df5fc424e6523e186dd36865e8427cd8819b4ee2896a91406e7e0c3c262","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-06-14T16:22:16Z","title_canon_sha256":"2a4fb98255b073b77f26cc162b138dd9d1c95fae08495c2e0b3fedd62536fad2"},"schema_version":"1.0","source":{"id":"1506.04416","kind":"arxiv","version":3}},"canonical_sha256":"82709edac3268272d8a094d291ca2e12d3c5237d3439dba1451eff80a199cd1d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"82709edac3268272d8a094d291ca2e12d3c5237d3439dba1451eff80a199cd1d","first_computed_at":"2026-05-18T01:27:31.531964Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:27:31.531964Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"cOSwvdSondTnY8BjzQFlVOJFT1SzFm9/xiKXYjkqkOjV0gHrARIfHlJG266YjLbuFT4kPT/cyHc+zpy4HfOfAw==","signature_status":"signed_v1","signed_at":"2026-05-18T01:27:31.532610Z","signed_message":"canonical_sha256_bytes"},"source_id":"1506.04416","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d35ee760db2b7f5cdd5004192bacc059307d8276b415354880cb07d817330c36","sha256:085ea574c8303eaedfba0bddfa49c3b19735fff4f7118a7880186cfbf117b310"],"state_sha256":"a86b346683bc90d10cf504a354dc323dfcb371b94ce24700962ce87b0b68d5a1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"efM1PuyufgQjszxOM62D0V+HCRoaz41Z6VZvo+lhihdnp8F2Gq/r8NZi+sEwxzFO7c0vYNkuqpxGfWA4uElCAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-20T04:35:47.956225Z","bundle_sha256":"89635b1b30cbf5d804dfe83e93c6bb8bf0173aaf741dca5ef2b47133e4ec395d"}}