{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:U75GO3OMA5ZJJ56FZFAM5P6E2T","short_pith_number":"pith:U75GO3OM","canonical_record":{"source":{"id":"1905.07855","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-20T03:12:32Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"a88f08d2a726a609e74ee7cd8713940033be4402cf92ad9da876ed162f9a9735","abstract_canon_sha256":"cca1902e400b8400d2b9183191bac66092d79a9ba6f7888d107c9a3a20b4c56d"},"schema_version":"1.0"},"canonical_sha256":"a7fa676dcc077294f7c5c940cebfc4d4e405c89ed073bc0a7d5dd13c5a9821a7","source":{"kind":"arxiv","id":"1905.07855","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.07855","created_at":"2026-05-17T23:45:48Z"},{"alias_kind":"arxiv_version","alias_value":"1905.07855v1","created_at":"2026-05-17T23:45:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.07855","created_at":"2026-05-17T23:45:48Z"},{"alias_kind":"pith_short_12","alias_value":"U75GO3OMA5ZJ","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_16","alias_value":"U75GO3OMA5ZJJ56F","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_8","alias_value":"U75GO3OM","created_at":"2026-05-18T12:33:30Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:U75GO3OMA5ZJJ56FZFAM5P6E2T","target":"record","payload":{"canonical_record":{"source":{"id":"1905.07855","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-20T03:12:32Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"a88f08d2a726a609e74ee7cd8713940033be4402cf92ad9da876ed162f9a9735","abstract_canon_sha256":"cca1902e400b8400d2b9183191bac66092d79a9ba6f7888d107c9a3a20b4c56d"},"schema_version":"1.0"},"canonical_sha256":"a7fa676dcc077294f7c5c940cebfc4d4e405c89ed073bc0a7d5dd13c5a9821a7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:45:48.317290Z","signature_b64":"sWEvh9OM1LJnKlrSxjkmTKhWVFHfe6fssEP4YNb6AoXhgBE48gDVeF8eLRRU8Ibs6kgU9leRdivObGWzaoixCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a7fa676dcc077294f7c5c940cebfc4d4e405c89ed073bc0a7d5dd13c5a9821a7","last_reissued_at":"2026-05-17T23:45:48.316599Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:45:48.316599Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1905.07855","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":"2026-05-17T23:45:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eOBZvBvwr9KhWuneuxrj8qHNoFjMgsl7/j2dD/RzNwWDyANTa+uvHeduwY18SxkmOtaUmUk5pwk9BC0SZPDNAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-30T18:18:41.272683Z"},"content_sha256":"5a84ef77295e3127728d989bef4937039991a7612f7659298e64507955675b0c","schema_version":"1.0","event_id":"sha256:5a84ef77295e3127728d989bef4937039991a7612f7659298e64507955675b0c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:U75GO3OMA5ZJJ56FZFAM5P6E2T","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MaxEntropy Pursuit Variational Inference","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Evgenii Egorov, Evgeny Burnaev, Kirill Neklydov, Ruslan Kostoev","submitted_at":"2019-05-20T03:12:32Z","abstract_excerpt":"One of the core problems in variational inference is a choice of approximate posterior distribution. It is crucial to trade-off between efficient inference with simple families as mean-field models and accuracy of inference. We propose a variant of a greedy approximation of the posterior distribution with tractable base learners. Using Max-Entropy approach, we obtain a well-defined optimization problem. We demonstrate the ability of the method to capture complex multimodal posterior via continual learning setting for neural networks."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.07855","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":"2026-05-17T23:45:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eJ7XtI53SIM6VVy+veQDJrplJyqxZxJbkBpeMY8O8UbHVr/5kXbd8olM6OjosFgAHMaoEOQiRTLCIOTWfbPBBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-30T18:18:41.273021Z"},"content_sha256":"62d000c0a0a7d52839688049ebec4c516cbbea3873803ce73298583f47d9284c","schema_version":"1.0","event_id":"sha256:62d000c0a0a7d52839688049ebec4c516cbbea3873803ce73298583f47d9284c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/U75GO3OMA5ZJJ56FZFAM5P6E2T/bundle.json","state_url":"https://pith.science/pith/U75GO3OMA5ZJJ56FZFAM5P6E2T/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/U75GO3OMA5ZJJ56FZFAM5P6E2T/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":"2026-06-30T18:18:41Z","links":{"resolver":"https://pith.science/pith/U75GO3OMA5ZJJ56FZFAM5P6E2T","bundle":"https://pith.science/pith/U75GO3OMA5ZJJ56FZFAM5P6E2T/bundle.json","state":"https://pith.science/pith/U75GO3OMA5ZJJ56FZFAM5P6E2T/state.json","well_known_bundle":"https://pith.science/.well-known/pith/U75GO3OMA5ZJJ56FZFAM5P6E2T/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:U75GO3OMA5ZJJ56FZFAM5P6E2T","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":"cca1902e400b8400d2b9183191bac66092d79a9ba6f7888d107c9a3a20b4c56d","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-20T03:12:32Z","title_canon_sha256":"a88f08d2a726a609e74ee7cd8713940033be4402cf92ad9da876ed162f9a9735"},"schema_version":"1.0","source":{"id":"1905.07855","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.07855","created_at":"2026-05-17T23:45:48Z"},{"alias_kind":"arxiv_version","alias_value":"1905.07855v1","created_at":"2026-05-17T23:45:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.07855","created_at":"2026-05-17T23:45:48Z"},{"alias_kind":"pith_short_12","alias_value":"U75GO3OMA5ZJ","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_16","alias_value":"U75GO3OMA5ZJJ56F","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_8","alias_value":"U75GO3OM","created_at":"2026-05-18T12:33:30Z"}],"graph_snapshots":[{"event_id":"sha256:62d000c0a0a7d52839688049ebec4c516cbbea3873803ce73298583f47d9284c","target":"graph","created_at":"2026-05-17T23:45:48Z","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":"One of the core problems in variational inference is a choice of approximate posterior distribution. It is crucial to trade-off between efficient inference with simple families as mean-field models and accuracy of inference. We propose a variant of a greedy approximation of the posterior distribution with tractable base learners. Using Max-Entropy approach, we obtain a well-defined optimization problem. We demonstrate the ability of the method to capture complex multimodal posterior via continual learning setting for neural networks.","authors_text":"Evgenii Egorov, Evgeny Burnaev, Kirill Neklydov, Ruslan Kostoev","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-20T03:12:32Z","title":"MaxEntropy Pursuit Variational Inference"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.07855","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":"sha256:5a84ef77295e3127728d989bef4937039991a7612f7659298e64507955675b0c","target":"record","created_at":"2026-05-17T23:45:48Z","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":"cca1902e400b8400d2b9183191bac66092d79a9ba6f7888d107c9a3a20b4c56d","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-20T03:12:32Z","title_canon_sha256":"a88f08d2a726a609e74ee7cd8713940033be4402cf92ad9da876ed162f9a9735"},"schema_version":"1.0","source":{"id":"1905.07855","kind":"arxiv","version":1}},"canonical_sha256":"a7fa676dcc077294f7c5c940cebfc4d4e405c89ed073bc0a7d5dd13c5a9821a7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a7fa676dcc077294f7c5c940cebfc4d4e405c89ed073bc0a7d5dd13c5a9821a7","first_computed_at":"2026-05-17T23:45:48.316599Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:45:48.316599Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"sWEvh9OM1LJnKlrSxjkmTKhWVFHfe6fssEP4YNb6AoXhgBE48gDVeF8eLRRU8Ibs6kgU9leRdivObGWzaoixCQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:45:48.317290Z","signed_message":"canonical_sha256_bytes"},"source_id":"1905.07855","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5a84ef77295e3127728d989bef4937039991a7612f7659298e64507955675b0c","sha256:62d000c0a0a7d52839688049ebec4c516cbbea3873803ce73298583f47d9284c"],"state_sha256":"8f2f4237775e8da48cd20bf140b8f71fee165d685d8c9a4398754d98ba35ca96"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bLU7JlR90rY5Skv9OC42W/+bD25IsADPw0EhDF3ZIJR8A0/1Zf2Am6OFP4oAheHqPeHz4/TDI91Ox3dxckOCDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-30T18:18:41.275047Z","bundle_sha256":"33d3a7a69963de56e2a71a17a01b51b3d7fc34791e268cf6bcb5319f11232f44"}}