{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:SCS7FGJJSSZRP5TIFNBHUSE5TA","short_pith_number":"pith:SCS7FGJJ","canonical_record":{"source":{"id":"1906.05180","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-12T14:46:01Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"888a2942399f962b7a41c09e8d2a155b349bad64a4a60a17c23617a4ca23c77e","abstract_canon_sha256":"10462f6b547d9ecd810591950f8b072c239b082e3c24a90ab4b89baf80de811c"},"schema_version":"1.0"},"canonical_sha256":"90a5f2992994b317f6682b427a489d982b830ce4d21d7ee31d6c9ef38c27dc5f","source":{"kind":"arxiv","id":"1906.05180","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.05180","created_at":"2026-05-17T23:43:29Z"},{"alias_kind":"arxiv_version","alias_value":"1906.05180v1","created_at":"2026-05-17T23:43:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.05180","created_at":"2026-05-17T23:43:29Z"},{"alias_kind":"pith_short_12","alias_value":"SCS7FGJJSSZR","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_16","alias_value":"SCS7FGJJSSZRP5TI","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_8","alias_value":"SCS7FGJJ","created_at":"2026-05-18T12:33:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:SCS7FGJJSSZRP5TIFNBHUSE5TA","target":"record","payload":{"canonical_record":{"source":{"id":"1906.05180","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-12T14:46:01Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"888a2942399f962b7a41c09e8d2a155b349bad64a4a60a17c23617a4ca23c77e","abstract_canon_sha256":"10462f6b547d9ecd810591950f8b072c239b082e3c24a90ab4b89baf80de811c"},"schema_version":"1.0"},"canonical_sha256":"90a5f2992994b317f6682b427a489d982b830ce4d21d7ee31d6c9ef38c27dc5f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:43:29.272540Z","signature_b64":"HDcHbSvJnDXRz8QHxqfAuW2wc30MxEv/vzYrFnl/aLvvHsv4i4JllmK8nYR+OyVvnEyoUPmYbon3RfZtKWh+BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"90a5f2992994b317f6682b427a489d982b830ce4d21d7ee31d6c9ef38c27dc5f","last_reissued_at":"2026-05-17T23:43:29.272069Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:43:29.272069Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1906.05180","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":"2026-05-17T23:43:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Zc8XEnaCA+cxWegkMhwjBLYBW0/Q4cdAghjA8YIyXTlOHKTF3EhwAV3RDP3Z0A9HrU2kBMVF1PZPTxjCZNgyCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T13:19:45.454887Z"},"content_sha256":"a22171d022da4a33b3fdce3bdc766122799b2ba0d21434ffccd529e78d9bddc7","schema_version":"1.0","event_id":"sha256:a22171d022da4a33b3fdce3bdc766122799b2ba0d21434ffccd529e78d9bddc7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:SCS7FGJJSSZRP5TIFNBHUSE5TA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Parameterized Structured Pruning for Deep Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Franz Pernkopf, Guenther Schindler, Holger Froening, Wolfgang Roth","submitted_at":"2019-06-12T14:46:01Z","abstract_excerpt":"As a result of the growing size of Deep Neural Networks (DNNs), the gap to hardware capabilities in terms of memory and compute increases. To effectively compress DNNs, quantization and connection pruning are usually considered. However, unconstrained pruning usually leads to unstructured parallelism, which maps poorly to massively parallel processors, and substantially reduces the efficiency of general-purpose processors. Similar applies to quantization, which often requires dedicated hardware. We propose Parameterized Structured Pruning (PSP), a novel method to dynamically learn the shape of"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.05180","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":"2026-05-17T23:43:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/KR9N99/mlP/RDsJkfx3PGd3LJje/jiERBhyAyntYz+K15CkzuvSf5IKHuewlRX4ymx2Psp6KLPUJdiEgQXnCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T13:19:45.455226Z"},"content_sha256":"86c2b19f3c1634074f0110d409aad3815a02b4f2e539afbf92b2c1921b772f37","schema_version":"1.0","event_id":"sha256:86c2b19f3c1634074f0110d409aad3815a02b4f2e539afbf92b2c1921b772f37"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SCS7FGJJSSZRP5TIFNBHUSE5TA/bundle.json","state_url":"https://pith.science/pith/SCS7FGJJSSZRP5TIFNBHUSE5TA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SCS7FGJJSSZRP5TIFNBHUSE5TA/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":"2026-05-30T13:19:45Z","links":{"resolver":"https://pith.science/pith/SCS7FGJJSSZRP5TIFNBHUSE5TA","bundle":"https://pith.science/pith/SCS7FGJJSSZRP5TIFNBHUSE5TA/bundle.json","state":"https://pith.science/pith/SCS7FGJJSSZRP5TIFNBHUSE5TA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SCS7FGJJSSZRP5TIFNBHUSE5TA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:SCS7FGJJSSZRP5TIFNBHUSE5TA","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":"10462f6b547d9ecd810591950f8b072c239b082e3c24a90ab4b89baf80de811c","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-12T14:46:01Z","title_canon_sha256":"888a2942399f962b7a41c09e8d2a155b349bad64a4a60a17c23617a4ca23c77e"},"schema_version":"1.0","source":{"id":"1906.05180","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.05180","created_at":"2026-05-17T23:43:29Z"},{"alias_kind":"arxiv_version","alias_value":"1906.05180v1","created_at":"2026-05-17T23:43:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.05180","created_at":"2026-05-17T23:43:29Z"},{"alias_kind":"pith_short_12","alias_value":"SCS7FGJJSSZR","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_16","alias_value":"SCS7FGJJSSZRP5TI","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_8","alias_value":"SCS7FGJJ","created_at":"2026-05-18T12:33:27Z"}],"graph_snapshots":[{"event_id":"sha256:86c2b19f3c1634074f0110d409aad3815a02b4f2e539afbf92b2c1921b772f37","target":"graph","created_at":"2026-05-17T23:43:29Z","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":"As a result of the growing size of Deep Neural Networks (DNNs), the gap to hardware capabilities in terms of memory and compute increases. To effectively compress DNNs, quantization and connection pruning are usually considered. However, unconstrained pruning usually leads to unstructured parallelism, which maps poorly to massively parallel processors, and substantially reduces the efficiency of general-purpose processors. Similar applies to quantization, which often requires dedicated hardware. We propose Parameterized Structured Pruning (PSP), a novel method to dynamically learn the shape of","authors_text":"Franz Pernkopf, Guenther Schindler, Holger Froening, Wolfgang Roth","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-12T14:46:01Z","title":"Parameterized Structured Pruning for Deep Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.05180","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:a22171d022da4a33b3fdce3bdc766122799b2ba0d21434ffccd529e78d9bddc7","target":"record","created_at":"2026-05-17T23:43:29Z","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":"10462f6b547d9ecd810591950f8b072c239b082e3c24a90ab4b89baf80de811c","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-12T14:46:01Z","title_canon_sha256":"888a2942399f962b7a41c09e8d2a155b349bad64a4a60a17c23617a4ca23c77e"},"schema_version":"1.0","source":{"id":"1906.05180","kind":"arxiv","version":1}},"canonical_sha256":"90a5f2992994b317f6682b427a489d982b830ce4d21d7ee31d6c9ef38c27dc5f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"90a5f2992994b317f6682b427a489d982b830ce4d21d7ee31d6c9ef38c27dc5f","first_computed_at":"2026-05-17T23:43:29.272069Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:43:29.272069Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HDcHbSvJnDXRz8QHxqfAuW2wc30MxEv/vzYrFnl/aLvvHsv4i4JllmK8nYR+OyVvnEyoUPmYbon3RfZtKWh+BQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:43:29.272540Z","signed_message":"canonical_sha256_bytes"},"source_id":"1906.05180","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a22171d022da4a33b3fdce3bdc766122799b2ba0d21434ffccd529e78d9bddc7","sha256:86c2b19f3c1634074f0110d409aad3815a02b4f2e539afbf92b2c1921b772f37"],"state_sha256":"fe38b70324e3bde81097578451c5d5e69e055e0e499f2938e4b103aa8f5ac6a5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HiS8f84jqaxqXrXjf1Tc5z+dBzrmrrD6FQiQjZGa2H4QxrscZpHwpsYh4AMmuifI5AYUo5mIOr9cVgQpCV2gBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T13:19:45.457196Z","bundle_sha256":"4d676ff5a2966f857f40f06e78a97db4036a7be2a8e5503946ec564aee32309d"}}