{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:YTYKOEBLA5ZI5STYVP2GUGB4JI","short_pith_number":"pith:YTYKOEBL","canonical_record":{"source":{"id":"1803.00184","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-03-01T03:03:53Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"199db76a45627472411f25e6d8629281e91f3771c9c7e618448c7fc8e052d712","abstract_canon_sha256":"977efea5b15f508fd985e2ab7688e46abed358f0b7430e6e658a50acd9cf0092"},"schema_version":"1.0"},"canonical_sha256":"c4f0a7102b07728eca78abf46a183c4a21e03952ecfbf10ae23b51215da03731","source":{"kind":"arxiv","id":"1803.00184","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1803.00184","created_at":"2026-05-18T00:15:09Z"},{"alias_kind":"arxiv_version","alias_value":"1803.00184v3","created_at":"2026-05-18T00:15:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.00184","created_at":"2026-05-18T00:15:09Z"},{"alias_kind":"pith_short_12","alias_value":"YTYKOEBLA5ZI","created_at":"2026-05-18T12:33:04Z"},{"alias_kind":"pith_short_16","alias_value":"YTYKOEBLA5ZI5STY","created_at":"2026-05-18T12:33:04Z"},{"alias_kind":"pith_short_8","alias_value":"YTYKOEBL","created_at":"2026-05-18T12:33:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:YTYKOEBLA5ZI5STYVP2GUGB4JI","target":"record","payload":{"canonical_record":{"source":{"id":"1803.00184","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-03-01T03:03:53Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"199db76a45627472411f25e6d8629281e91f3771c9c7e618448c7fc8e052d712","abstract_canon_sha256":"977efea5b15f508fd985e2ab7688e46abed358f0b7430e6e658a50acd9cf0092"},"schema_version":"1.0"},"canonical_sha256":"c4f0a7102b07728eca78abf46a183c4a21e03952ecfbf10ae23b51215da03731","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:15:09.670283Z","signature_b64":"4BeUDxc/0cHnTkvGRcMb1TDBOAwO8KAwp37tqAZnTUiX1QvrU0PTndeVHc2hzFRhPpuFQ19Me4L9PYPFkajqBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c4f0a7102b07728eca78abf46a183c4a21e03952ecfbf10ae23b51215da03731","last_reissued_at":"2026-05-18T00:15:09.669501Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:15:09.669501Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1803.00184","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":"2026-05-18T00:15:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qgU3Y+b/t5yNT2swikWprx8AKDe7R1XQXbD4j6TAwS40XfQVtpBpjL/BDqr6/5quv5EgmDr+dmL8JCa9RvXoCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T00:47:17.888258Z"},"content_sha256":"e949078eed6da39c74e36132fcd51687dd46ce5bcdfbb76ebd4ef076f860d286","schema_version":"1.0","event_id":"sha256:e949078eed6da39c74e36132fcd51687dd46ce5bcdfbb76ebd4ef076f860d286"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:YTYKOEBLA5ZI5STYVP2GUGB4JI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning Sparse Structured Ensembles with SG-MCMC and Network Pruning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Yichi Zhang, Zhijian Ou","submitted_at":"2018-03-01T03:03:53Z","abstract_excerpt":"An ensemble of neural networks is known to be more robust and accurate than an individual network, however usually with linearly-increased cost in both training and testing. In this work, we propose a two-stage method to learn Sparse Structured Ensembles (SSEs) for neural networks. In the first stage, we run SG-MCMC with group sparse priors to draw an ensemble of samples from the posterior distribution of network parameters. In the second stage, we apply weight-pruning to each sampled network and then perform retraining over the remained connections. In this way of learning SSEs with SG-MCMC a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.00184","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":"2026-05-18T00:15:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"i6VqR6DGetHuuuJmq3R1E8NjgT6ZDrcvQIIFsMOWwxyRK8r9maCtg59mqkeTe0mqcLIzuJ+DPudpc98034b3AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T00:47:17.888931Z"},"content_sha256":"ef9e73cc4d6ed112c0ea2024ee8157594d982da69936d87a8bccfb6324906bd5","schema_version":"1.0","event_id":"sha256:ef9e73cc4d6ed112c0ea2024ee8157594d982da69936d87a8bccfb6324906bd5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YTYKOEBLA5ZI5STYVP2GUGB4JI/bundle.json","state_url":"https://pith.science/pith/YTYKOEBLA5ZI5STYVP2GUGB4JI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YTYKOEBLA5ZI5STYVP2GUGB4JI/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":"2026-05-31T00:47:17Z","links":{"resolver":"https://pith.science/pith/YTYKOEBLA5ZI5STYVP2GUGB4JI","bundle":"https://pith.science/pith/YTYKOEBLA5ZI5STYVP2GUGB4JI/bundle.json","state":"https://pith.science/pith/YTYKOEBLA5ZI5STYVP2GUGB4JI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YTYKOEBLA5ZI5STYVP2GUGB4JI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:YTYKOEBLA5ZI5STYVP2GUGB4JI","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":"977efea5b15f508fd985e2ab7688e46abed358f0b7430e6e658a50acd9cf0092","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-03-01T03:03:53Z","title_canon_sha256":"199db76a45627472411f25e6d8629281e91f3771c9c7e618448c7fc8e052d712"},"schema_version":"1.0","source":{"id":"1803.00184","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1803.00184","created_at":"2026-05-18T00:15:09Z"},{"alias_kind":"arxiv_version","alias_value":"1803.00184v3","created_at":"2026-05-18T00:15:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.00184","created_at":"2026-05-18T00:15:09Z"},{"alias_kind":"pith_short_12","alias_value":"YTYKOEBLA5ZI","created_at":"2026-05-18T12:33:04Z"},{"alias_kind":"pith_short_16","alias_value":"YTYKOEBLA5ZI5STY","created_at":"2026-05-18T12:33:04Z"},{"alias_kind":"pith_short_8","alias_value":"YTYKOEBL","created_at":"2026-05-18T12:33:04Z"}],"graph_snapshots":[{"event_id":"sha256:ef9e73cc4d6ed112c0ea2024ee8157594d982da69936d87a8bccfb6324906bd5","target":"graph","created_at":"2026-05-18T00:15:09Z","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":"An ensemble of neural networks is known to be more robust and accurate than an individual network, however usually with linearly-increased cost in both training and testing. In this work, we propose a two-stage method to learn Sparse Structured Ensembles (SSEs) for neural networks. In the first stage, we run SG-MCMC with group sparse priors to draw an ensemble of samples from the posterior distribution of network parameters. In the second stage, we apply weight-pruning to each sampled network and then perform retraining over the remained connections. In this way of learning SSEs with SG-MCMC a","authors_text":"Yichi Zhang, Zhijian Ou","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-03-01T03:03:53Z","title":"Learning Sparse Structured Ensembles with SG-MCMC and Network Pruning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.00184","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:e949078eed6da39c74e36132fcd51687dd46ce5bcdfbb76ebd4ef076f860d286","target":"record","created_at":"2026-05-18T00:15:09Z","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":"977efea5b15f508fd985e2ab7688e46abed358f0b7430e6e658a50acd9cf0092","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-03-01T03:03:53Z","title_canon_sha256":"199db76a45627472411f25e6d8629281e91f3771c9c7e618448c7fc8e052d712"},"schema_version":"1.0","source":{"id":"1803.00184","kind":"arxiv","version":3}},"canonical_sha256":"c4f0a7102b07728eca78abf46a183c4a21e03952ecfbf10ae23b51215da03731","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c4f0a7102b07728eca78abf46a183c4a21e03952ecfbf10ae23b51215da03731","first_computed_at":"2026-05-18T00:15:09.669501Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:15:09.669501Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4BeUDxc/0cHnTkvGRcMb1TDBOAwO8KAwp37tqAZnTUiX1QvrU0PTndeVHc2hzFRhPpuFQ19Me4L9PYPFkajqBg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:15:09.670283Z","signed_message":"canonical_sha256_bytes"},"source_id":"1803.00184","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e949078eed6da39c74e36132fcd51687dd46ce5bcdfbb76ebd4ef076f860d286","sha256:ef9e73cc4d6ed112c0ea2024ee8157594d982da69936d87a8bccfb6324906bd5"],"state_sha256":"798fdf12697548db354bd32d6219863ee36fe50a648f398689273106bbe5705b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"D+brjoHxzISmNMbemKBINTqK/hyEbgiKTh3VmBk905+KAN5KoVyWLDJj0i2UjxXm1WyGlAtx0CikVbKWpVClDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-31T00:47:17.892462Z","bundle_sha256":"6de2bde1ab73b0f0edaff003e0e6ac2d4fee249cc96ce8c9da1ad17e2f9a6482"}}