{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:IAHIUQBQWRPSE62U3HLXCKPHGF","short_pith_number":"pith:IAHIUQBQ","canonical_record":{"source":{"id":"1705.08665","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-05-24T09:07:01Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"3fc6309ba2cd3562480b0d3093a84dcfe2c43744d1e8e3abe9cf628ca4ba6a69","abstract_canon_sha256":"2756aa33cdc2ba8dd510400e8a2f93c7d2df4ebf83f573690b5908515e9fdbe6"},"schema_version":"1.0"},"canonical_sha256":"400e8a4030b45f227b54d9d77129e73142eaaf5c3b7f393c7df56c7356b7729e","source":{"kind":"arxiv","id":"1705.08665","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1705.08665","created_at":"2026-05-18T00:31:19Z"},{"alias_kind":"arxiv_version","alias_value":"1705.08665v4","created_at":"2026-05-18T00:31:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.08665","created_at":"2026-05-18T00:31:19Z"},{"alias_kind":"pith_short_12","alias_value":"IAHIUQBQWRPS","created_at":"2026-05-18T12:31:21Z"},{"alias_kind":"pith_short_16","alias_value":"IAHIUQBQWRPSE62U","created_at":"2026-05-18T12:31:21Z"},{"alias_kind":"pith_short_8","alias_value":"IAHIUQBQ","created_at":"2026-05-18T12:31:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:IAHIUQBQWRPSE62U3HLXCKPHGF","target":"record","payload":{"canonical_record":{"source":{"id":"1705.08665","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-05-24T09:07:01Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"3fc6309ba2cd3562480b0d3093a84dcfe2c43744d1e8e3abe9cf628ca4ba6a69","abstract_canon_sha256":"2756aa33cdc2ba8dd510400e8a2f93c7d2df4ebf83f573690b5908515e9fdbe6"},"schema_version":"1.0"},"canonical_sha256":"400e8a4030b45f227b54d9d77129e73142eaaf5c3b7f393c7df56c7356b7729e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:31:19.408674Z","signature_b64":"0RijrW6LSh4IpOdTSpr7ZZa1udzHvPKdWdZWio7s38MkREM6b2hY94T/Hhci5mkBJLy86LzSY1X5ZoFr7aHaAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"400e8a4030b45f227b54d9d77129e73142eaaf5c3b7f393c7df56c7356b7729e","last_reissued_at":"2026-05-18T00:31:19.407923Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:31:19.407923Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1705.08665","source_version":4,"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":"QzoJVC7p/Ojat7UsD9TYdrSl2WpXze+7jFYlW/5msjglZCS6W/RBS3Fx+8Ft6+7Tg6du5C3rWsXplGSO1BYxCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T14:05:33.982007Z"},"content_sha256":"42831d2a00f45e6e753f81f53fcf80b0556d79a597213e71e9926bd3c10d3415","schema_version":"1.0","event_id":"sha256:42831d2a00f45e6e753f81f53fcf80b0556d79a597213e71e9926bd3c10d3415"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:IAHIUQBQWRPSE62U3HLXCKPHGF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Bayesian Compression for Deep Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Christos Louizos, Karen Ullrich, Max Welling","submitted_at":"2017-05-24T09:07:01Z","abstract_excerpt":"Compression and computational efficiency in deep learning have become a problem of great significance. In this work, we argue that the most principled and effective way to attack this problem is by adopting a Bayesian point of view, where through sparsity inducing priors we prune large parts of the network. We introduce two novelties in this paper: 1) we use hierarchical priors to prune nodes instead of individual weights, and 2) we use the posterior uncertainties to determine the optimal fixed point precision to encode the weights. Both factors significantly contribute to achieving the state "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.08665","kind":"arxiv","version":4},"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":"OtLFp3L3bRndwgVacC9+4uQX0+pU/lqTJ5z9BIwn7/RrmYO8luoT9OVDHZRCw4c+9uNviy9FPg5UAYIh7ozACQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T14:05:33.982378Z"},"content_sha256":"086d96a651a6690e055fbe39d1b2a01d698e06b34ba998dc6c5d444becdc480b","schema_version":"1.0","event_id":"sha256:086d96a651a6690e055fbe39d1b2a01d698e06b34ba998dc6c5d444becdc480b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IAHIUQBQWRPSE62U3HLXCKPHGF/bundle.json","state_url":"https://pith.science/pith/IAHIUQBQWRPSE62U3HLXCKPHGF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IAHIUQBQWRPSE62U3HLXCKPHGF/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":"2026-06-02T14:05:33Z","links":{"resolver":"https://pith.science/pith/IAHIUQBQWRPSE62U3HLXCKPHGF","bundle":"https://pith.science/pith/IAHIUQBQWRPSE62U3HLXCKPHGF/bundle.json","state":"https://pith.science/pith/IAHIUQBQWRPSE62U3HLXCKPHGF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IAHIUQBQWRPSE62U3HLXCKPHGF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:IAHIUQBQWRPSE62U3HLXCKPHGF","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":"2756aa33cdc2ba8dd510400e8a2f93c7d2df4ebf83f573690b5908515e9fdbe6","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-05-24T09:07:01Z","title_canon_sha256":"3fc6309ba2cd3562480b0d3093a84dcfe2c43744d1e8e3abe9cf628ca4ba6a69"},"schema_version":"1.0","source":{"id":"1705.08665","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1705.08665","created_at":"2026-05-18T00:31:19Z"},{"alias_kind":"arxiv_version","alias_value":"1705.08665v4","created_at":"2026-05-18T00:31:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.08665","created_at":"2026-05-18T00:31:19Z"},{"alias_kind":"pith_short_12","alias_value":"IAHIUQBQWRPS","created_at":"2026-05-18T12:31:21Z"},{"alias_kind":"pith_short_16","alias_value":"IAHIUQBQWRPSE62U","created_at":"2026-05-18T12:31:21Z"},{"alias_kind":"pith_short_8","alias_value":"IAHIUQBQ","created_at":"2026-05-18T12:31:21Z"}],"graph_snapshots":[{"event_id":"sha256:086d96a651a6690e055fbe39d1b2a01d698e06b34ba998dc6c5d444becdc480b","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":"Compression and computational efficiency in deep learning have become a problem of great significance. In this work, we argue that the most principled and effective way to attack this problem is by adopting a Bayesian point of view, where through sparsity inducing priors we prune large parts of the network. We introduce two novelties in this paper: 1) we use hierarchical priors to prune nodes instead of individual weights, and 2) we use the posterior uncertainties to determine the optimal fixed point precision to encode the weights. Both factors significantly contribute to achieving the state ","authors_text":"Christos Louizos, Karen Ullrich, Max Welling","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-05-24T09:07:01Z","title":"Bayesian Compression for Deep Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.08665","kind":"arxiv","version":4},"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":"sha256:42831d2a00f45e6e753f81f53fcf80b0556d79a597213e71e9926bd3c10d3415","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":"2756aa33cdc2ba8dd510400e8a2f93c7d2df4ebf83f573690b5908515e9fdbe6","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-05-24T09:07:01Z","title_canon_sha256":"3fc6309ba2cd3562480b0d3093a84dcfe2c43744d1e8e3abe9cf628ca4ba6a69"},"schema_version":"1.0","source":{"id":"1705.08665","kind":"arxiv","version":4}},"canonical_sha256":"400e8a4030b45f227b54d9d77129e73142eaaf5c3b7f393c7df56c7356b7729e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"400e8a4030b45f227b54d9d77129e73142eaaf5c3b7f393c7df56c7356b7729e","first_computed_at":"2026-05-18T00:31:19.407923Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:31:19.407923Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0RijrW6LSh4IpOdTSpr7ZZa1udzHvPKdWdZWio7s38MkREM6b2hY94T/Hhci5mkBJLy86LzSY1X5ZoFr7aHaAw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:31:19.408674Z","signed_message":"canonical_sha256_bytes"},"source_id":"1705.08665","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:42831d2a00f45e6e753f81f53fcf80b0556d79a597213e71e9926bd3c10d3415","sha256:086d96a651a6690e055fbe39d1b2a01d698e06b34ba998dc6c5d444becdc480b"],"state_sha256":"8e87e9a42d957b37949867b37bbcb547841147de18bab3dfb37a27a4d980558d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tY4zbFkdTKey9oQMESYdcXJaWsgK3AQJJvy760G3MBXFEDB+5GeVmqhLGjk8j3oUz4lAazWnd9wMuAK+1FEqCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-02T14:05:33.984444Z","bundle_sha256":"67065b253fa4dc7449df9504833f2a10584a2c32f8737ccbb787f9e9fe3a8480"}}