{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:AM47LHN3GZWEIIDV6XKPJVPXPN","short_pith_number":"pith:AM47LHN3","canonical_record":{"source":{"id":"1810.08083","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-10-18T14:35:23Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"d5c8ce86cc0a578d2615c7e36e5a4efe8c3d9ae38506458d0db1a6e06c488aed","abstract_canon_sha256":"6a3a632d78b26cb18420d5df0aeb6d66bace66cc641282c4ac701d7e0f3172f2"},"schema_version":"1.0"},"canonical_sha256":"0339f59dbb366c442075f5d4f4d5f77b57c355a2cc6af39c0daba71a30358bed","source":{"kind":"arxiv","id":"1810.08083","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.08083","created_at":"2026-05-17T23:55:34Z"},{"alias_kind":"arxiv_version","alias_value":"1810.08083v2","created_at":"2026-05-17T23:55:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.08083","created_at":"2026-05-17T23:55:34Z"},{"alias_kind":"pith_short_12","alias_value":"AM47LHN3GZWE","created_at":"2026-05-18T12:32:13Z"},{"alias_kind":"pith_short_16","alias_value":"AM47LHN3GZWEIIDV","created_at":"2026-05-18T12:32:13Z"},{"alias_kind":"pith_short_8","alias_value":"AM47LHN3","created_at":"2026-05-18T12:32:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:AM47LHN3GZWEIIDV6XKPJVPXPN","target":"record","payload":{"canonical_record":{"source":{"id":"1810.08083","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-10-18T14:35:23Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"d5c8ce86cc0a578d2615c7e36e5a4efe8c3d9ae38506458d0db1a6e06c488aed","abstract_canon_sha256":"6a3a632d78b26cb18420d5df0aeb6d66bace66cc641282c4ac701d7e0f3172f2"},"schema_version":"1.0"},"canonical_sha256":"0339f59dbb366c442075f5d4f4d5f77b57c355a2cc6af39c0daba71a30358bed","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:55:34.007501Z","signature_b64":"3gM/LbbWiyMlaMyLRIGNhkTg31hd7DBy/xX86qJ43Ujc/YnJJaQsk8bmUVzaMIBNdW7MpGv82nAoM6eIlRWPDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0339f59dbb366c442075f5d4f4d5f77b57c355a2cc6af39c0daba71a30358bed","last_reissued_at":"2026-05-17T23:55:34.007018Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:55:34.007018Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1810.08083","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":"2026-05-17T23:55:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QsL6g7nAJ4rLo7PVSUBwvKVLLAaCLEmF4/JIelPxk4Rki4z3TRGHdXBfM16KE+ysybaFhrlAtBvSZ2ajHTU1Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T01:48:28.433544Z"},"content_sha256":"443603c1a00fbe477e674bc0aff550c3cfcc2f913b97fa897a3878e313a12acf","schema_version":"1.0","event_id":"sha256:443603c1a00fbe477e674bc0aff550c3cfcc2f913b97fa897a3878e313a12acf"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:AM47LHN3GZWEIIDV6XKPJVPXPN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Good Initializations of Variational Bayes for Deep Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Maurizio Filippone, Pietro Michiardi, Simone Rossi","submitted_at":"2018-10-18T14:35:23Z","abstract_excerpt":"Stochastic variational inference is an established way to carry out approximate Bayesian inference for deep models. While there have been effective proposals for good initializations for loss minimization in deep learning, far less attention has been devoted to the issue of initialization of stochastic variational inference. We address this by proposing a novel layer-wise initialization strategy based on Bayesian linear models. The proposed method is extensively validated on regression and classification tasks, including Bayesian DeepNets and ConvNets, showing faster and better convergence com"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.08083","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":"2026-05-17T23:55:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SjZabUTgqPDuG6Otk2wY0oZYhFJ+s2n1HZdye6Ug0iiHMKm3xbqrB7vI0jM4CYekNJQqDBpWX8/Kzes79YA6BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T01:48:28.434398Z"},"content_sha256":"adeb828b1e6b8e09047568c4a390b02e5b06048e9693091022badf47b168765a","schema_version":"1.0","event_id":"sha256:adeb828b1e6b8e09047568c4a390b02e5b06048e9693091022badf47b168765a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AM47LHN3GZWEIIDV6XKPJVPXPN/bundle.json","state_url":"https://pith.science/pith/AM47LHN3GZWEIIDV6XKPJVPXPN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AM47LHN3GZWEIIDV6XKPJVPXPN/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":"2026-06-10T01:48:28Z","links":{"resolver":"https://pith.science/pith/AM47LHN3GZWEIIDV6XKPJVPXPN","bundle":"https://pith.science/pith/AM47LHN3GZWEIIDV6XKPJVPXPN/bundle.json","state":"https://pith.science/pith/AM47LHN3GZWEIIDV6XKPJVPXPN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AM47LHN3GZWEIIDV6XKPJVPXPN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:AM47LHN3GZWEIIDV6XKPJVPXPN","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":"6a3a632d78b26cb18420d5df0aeb6d66bace66cc641282c4ac701d7e0f3172f2","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-10-18T14:35:23Z","title_canon_sha256":"d5c8ce86cc0a578d2615c7e36e5a4efe8c3d9ae38506458d0db1a6e06c488aed"},"schema_version":"1.0","source":{"id":"1810.08083","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.08083","created_at":"2026-05-17T23:55:34Z"},{"alias_kind":"arxiv_version","alias_value":"1810.08083v2","created_at":"2026-05-17T23:55:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.08083","created_at":"2026-05-17T23:55:34Z"},{"alias_kind":"pith_short_12","alias_value":"AM47LHN3GZWE","created_at":"2026-05-18T12:32:13Z"},{"alias_kind":"pith_short_16","alias_value":"AM47LHN3GZWEIIDV","created_at":"2026-05-18T12:32:13Z"},{"alias_kind":"pith_short_8","alias_value":"AM47LHN3","created_at":"2026-05-18T12:32:13Z"}],"graph_snapshots":[{"event_id":"sha256:adeb828b1e6b8e09047568c4a390b02e5b06048e9693091022badf47b168765a","target":"graph","created_at":"2026-05-17T23:55:34Z","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":"Stochastic variational inference is an established way to carry out approximate Bayesian inference for deep models. While there have been effective proposals for good initializations for loss minimization in deep learning, far less attention has been devoted to the issue of initialization of stochastic variational inference. We address this by proposing a novel layer-wise initialization strategy based on Bayesian linear models. The proposed method is extensively validated on regression and classification tasks, including Bayesian DeepNets and ConvNets, showing faster and better convergence com","authors_text":"Maurizio Filippone, Pietro Michiardi, Simone Rossi","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-10-18T14:35:23Z","title":"Good Initializations of Variational Bayes for Deep Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.08083","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":"sha256:443603c1a00fbe477e674bc0aff550c3cfcc2f913b97fa897a3878e313a12acf","target":"record","created_at":"2026-05-17T23:55:34Z","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":"6a3a632d78b26cb18420d5df0aeb6d66bace66cc641282c4ac701d7e0f3172f2","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-10-18T14:35:23Z","title_canon_sha256":"d5c8ce86cc0a578d2615c7e36e5a4efe8c3d9ae38506458d0db1a6e06c488aed"},"schema_version":"1.0","source":{"id":"1810.08083","kind":"arxiv","version":2}},"canonical_sha256":"0339f59dbb366c442075f5d4f4d5f77b57c355a2cc6af39c0daba71a30358bed","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0339f59dbb366c442075f5d4f4d5f77b57c355a2cc6af39c0daba71a30358bed","first_computed_at":"2026-05-17T23:55:34.007018Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:55:34.007018Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3gM/LbbWiyMlaMyLRIGNhkTg31hd7DBy/xX86qJ43Ujc/YnJJaQsk8bmUVzaMIBNdW7MpGv82nAoM6eIlRWPDA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:55:34.007501Z","signed_message":"canonical_sha256_bytes"},"source_id":"1810.08083","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:443603c1a00fbe477e674bc0aff550c3cfcc2f913b97fa897a3878e313a12acf","sha256:adeb828b1e6b8e09047568c4a390b02e5b06048e9693091022badf47b168765a"],"state_sha256":"3acd1ea61ad464973cd2a674e4d4feeeb8f1731d8ca41ed8c03ca8f72dfe99e3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TU3GI+SDKEiXdY4f2k3yKQEwUL9KiwaY0wuwar4w3Yb1QJF/GghYyjx+cJAP26zjkJvl+/wAw4yL0OAGiscyDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-10T01:48:28.438738Z","bundle_sha256":"9fc340e9af6750be4b36f36c3ae3409132416fd80517b3e21a825ac5652c68d4"}}