{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:WCAFJ7Q274YYUGGRSF3TL2ZNBP","short_pith_number":"pith:WCAFJ7Q2","canonical_record":{"source":{"id":"1705.07283","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-05-20T09:20:06Z","cross_cats_sorted":[],"title_canon_sha256":"93ec9560da586b38f2c41486fa526611345415e7a65fe85af4cc7e62316bebf4","abstract_canon_sha256":"a962fb61b40b99fa7d6e0790b2646dcd085f0a01a422c3726c57247e8c803f9c"},"schema_version":"1.0"},"canonical_sha256":"b08054fe1aff318a18d1917735eb2d0bd76c95714b45b375a338796b0be5bda4","source":{"kind":"arxiv","id":"1705.07283","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1705.07283","created_at":"2026-05-18T00:31:19Z"},{"alias_kind":"arxiv_version","alias_value":"1705.07283v2","created_at":"2026-05-18T00:31:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.07283","created_at":"2026-05-18T00:31:19Z"},{"alias_kind":"pith_short_12","alias_value":"WCAFJ7Q274YY","created_at":"2026-05-18T12:31:53Z"},{"alias_kind":"pith_short_16","alias_value":"WCAFJ7Q274YYUGGR","created_at":"2026-05-18T12:31:53Z"},{"alias_kind":"pith_short_8","alias_value":"WCAFJ7Q2","created_at":"2026-05-18T12:31:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:WCAFJ7Q274YYUGGRSF3TL2ZNBP","target":"record","payload":{"canonical_record":{"source":{"id":"1705.07283","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-05-20T09:20:06Z","cross_cats_sorted":[],"title_canon_sha256":"93ec9560da586b38f2c41486fa526611345415e7a65fe85af4cc7e62316bebf4","abstract_canon_sha256":"a962fb61b40b99fa7d6e0790b2646dcd085f0a01a422c3726c57247e8c803f9c"},"schema_version":"1.0"},"canonical_sha256":"b08054fe1aff318a18d1917735eb2d0bd76c95714b45b375a338796b0be5bda4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:31:19.485575Z","signature_b64":"PHJKzhwYAik7rqPkgU/hluXGrsT0c7rIvmd7evq5jSX45GdkhPYUgXyjI4uJscADWE3jVqu0WKVbZyW1GjPTCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b08054fe1aff318a18d1917735eb2d0bd76c95714b45b375a338796b0be5bda4","last_reissued_at":"2026-05-18T00:31:19.484915Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:31:19.484915Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1705.07283","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":"2026-05-18T00:31:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZglIttqmu4CofyD6y9k+1uxHujeES2FoI+pcLcA/OVhKMUVdYwaTVZmE2fDKw63I24y1sZtufcqUzIuav3j7BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T04:05:10.555239Z"},"content_sha256":"717303381240e8b5d85bbeda3c4e9cb1bc2724a2d3f02ba445cc171a66eab697","schema_version":"1.0","event_id":"sha256:717303381240e8b5d85bbeda3c4e9cb1bc2724a2d3f02ba445cc171a66eab697"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:WCAFJ7Q274YYUGGRSF3TL2ZNBP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Structured Bayesian Pruning via Log-Normal Multiplicative Noise","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"stat.ML","authors_text":"Arsenii Ashukha, Dmitry Molchanov, Dmitry Vetrov, Kirill Neklyudov","submitted_at":"2017-05-20T09:20:06Z","abstract_excerpt":"Dropout-based regularization methods can be regarded as injecting random noise with pre-defined magnitude to different parts of the neural network during training. It was recently shown that Bayesian dropout procedure not only improves generalization but also leads to extremely sparse neural architectures by automatically setting the individual noise magnitude per weight. However, this sparsity can hardly be used for acceleration since it is unstructured. In the paper, we propose a new Bayesian model that takes into account the computational structure of neural networks and provides structured"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.07283","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":"2026-05-18T00:31:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Yli9BWkgMj5jQDkrzFBcsdzo6TYQbGBpMaLSnzWItrla4mfSVNDR9GR+wwXekXglp0cRGx/HU3UQPPXV4AJmBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T04:05:10.556518Z"},"content_sha256":"6264b081a2496de988bfa2d43377ee3ae701f0de22a760cf4041ccf859bb1cce","schema_version":"1.0","event_id":"sha256:6264b081a2496de988bfa2d43377ee3ae701f0de22a760cf4041ccf859bb1cce"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WCAFJ7Q274YYUGGRSF3TL2ZNBP/bundle.json","state_url":"https://pith.science/pith/WCAFJ7Q274YYUGGRSF3TL2ZNBP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WCAFJ7Q274YYUGGRSF3TL2ZNBP/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":"2026-08-17T04:05:10Z","links":{"resolver":"https://pith.science/pith/WCAFJ7Q274YYUGGRSF3TL2ZNBP","bundle":"https://pith.science/pith/WCAFJ7Q274YYUGGRSF3TL2ZNBP/bundle.json","state":"https://pith.science/pith/WCAFJ7Q274YYUGGRSF3TL2ZNBP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WCAFJ7Q274YYUGGRSF3TL2ZNBP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:WCAFJ7Q274YYUGGRSF3TL2ZNBP","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":"a962fb61b40b99fa7d6e0790b2646dcd085f0a01a422c3726c57247e8c803f9c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-05-20T09:20:06Z","title_canon_sha256":"93ec9560da586b38f2c41486fa526611345415e7a65fe85af4cc7e62316bebf4"},"schema_version":"1.0","source":{"id":"1705.07283","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1705.07283","created_at":"2026-05-18T00:31:19Z"},{"alias_kind":"arxiv_version","alias_value":"1705.07283v2","created_at":"2026-05-18T00:31:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.07283","created_at":"2026-05-18T00:31:19Z"},{"alias_kind":"pith_short_12","alias_value":"WCAFJ7Q274YY","created_at":"2026-05-18T12:31:53Z"},{"alias_kind":"pith_short_16","alias_value":"WCAFJ7Q274YYUGGR","created_at":"2026-05-18T12:31:53Z"},{"alias_kind":"pith_short_8","alias_value":"WCAFJ7Q2","created_at":"2026-05-18T12:31:53Z"}],"graph_snapshots":[{"event_id":"sha256:6264b081a2496de988bfa2d43377ee3ae701f0de22a760cf4041ccf859bb1cce","target":"graph","created_at":"2026-05-18T00:31:19Z","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":"Dropout-based regularization methods can be regarded as injecting random noise with pre-defined magnitude to different parts of the neural network during training. It was recently shown that Bayesian dropout procedure not only improves generalization but also leads to extremely sparse neural architectures by automatically setting the individual noise magnitude per weight. However, this sparsity can hardly be used for acceleration since it is unstructured. In the paper, we propose a new Bayesian model that takes into account the computational structure of neural networks and provides structured","authors_text":"Arsenii Ashukha, Dmitry Molchanov, Dmitry Vetrov, Kirill Neklyudov","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-05-20T09:20:06Z","title":"Structured Bayesian Pruning via Log-Normal Multiplicative Noise"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.07283","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":"sha256:717303381240e8b5d85bbeda3c4e9cb1bc2724a2d3f02ba445cc171a66eab697","target":"record","created_at":"2026-05-18T00:31:19Z","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":"a962fb61b40b99fa7d6e0790b2646dcd085f0a01a422c3726c57247e8c803f9c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-05-20T09:20:06Z","title_canon_sha256":"93ec9560da586b38f2c41486fa526611345415e7a65fe85af4cc7e62316bebf4"},"schema_version":"1.0","source":{"id":"1705.07283","kind":"arxiv","version":2}},"canonical_sha256":"b08054fe1aff318a18d1917735eb2d0bd76c95714b45b375a338796b0be5bda4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b08054fe1aff318a18d1917735eb2d0bd76c95714b45b375a338796b0be5bda4","first_computed_at":"2026-05-18T00:31:19.484915Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:31:19.484915Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PHJKzhwYAik7rqPkgU/hluXGrsT0c7rIvmd7evq5jSX45GdkhPYUgXyjI4uJscADWE3jVqu0WKVbZyW1GjPTCQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:31:19.485575Z","signed_message":"canonical_sha256_bytes"},"source_id":"1705.07283","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:717303381240e8b5d85bbeda3c4e9cb1bc2724a2d3f02ba445cc171a66eab697","sha256:6264b081a2496de988bfa2d43377ee3ae701f0de22a760cf4041ccf859bb1cce"],"state_sha256":"ce16eb94980cc3fceade6d75ce6b5c9534fd1f18e8509fa3894908986d0d1f63"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MQaDg+DoNULGVpcEh4B8KNaq8vnxmcZHZPTDK/8NNOS2OUBSMJK1k/jY+TrL7aJ1DM9w+GxL4CiCu2FfyFn2DA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T04:05:10.566074Z","bundle_sha256":"702537c29a25f3ccd80c1af284fe64e4f728c88cdf40b1acea9222e9f680d6b5"}}