{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:QBIPDRS7TY3AXHRRWOAAYCMJJS","short_pith_number":"pith:QBIPDRS7","canonical_record":{"source":{"id":"1906.00399","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2019-06-02T13:17:37Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"9b34ad6fa09b2327e3ae03e71a2d20eb2fccb73194cf7f388be9b4d198bea364","abstract_canon_sha256":"8a97336aff6891f13e29b50684b46c0c7a38977cd50c95fc09d4b6fcf002ebb4"},"schema_version":"1.0"},"canonical_sha256":"8050f1c65f9e360b9e31b3800c09894c98c8024895d54bab4675d08c3df60b6f","source":{"kind":"arxiv","id":"1906.00399","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.00399","created_at":"2026-05-17T23:41:30Z"},{"alias_kind":"arxiv_version","alias_value":"1906.00399v2","created_at":"2026-05-17T23:41:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.00399","created_at":"2026-05-17T23:41:30Z"},{"alias_kind":"pith_short_12","alias_value":"QBIPDRS7TY3A","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_16","alias_value":"QBIPDRS7TY3AXHRR","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_8","alias_value":"QBIPDRS7","created_at":"2026-05-18T12:33:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:QBIPDRS7TY3AXHRRWOAAYCMJJS","target":"record","payload":{"canonical_record":{"source":{"id":"1906.00399","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2019-06-02T13:17:37Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"9b34ad6fa09b2327e3ae03e71a2d20eb2fccb73194cf7f388be9b4d198bea364","abstract_canon_sha256":"8a97336aff6891f13e29b50684b46c0c7a38977cd50c95fc09d4b6fcf002ebb4"},"schema_version":"1.0"},"canonical_sha256":"8050f1c65f9e360b9e31b3800c09894c98c8024895d54bab4675d08c3df60b6f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:41:30.266923Z","signature_b64":"6/y67rv1vNEpSzzpTxOljFIsLW9oi462wwphJ38+gJkwVMLXxLIVSsHy3FXDsSW5slLHQvAST9C33qX4RAqVBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8050f1c65f9e360b9e31b3800c09894c98c8024895d54bab4675d08c3df60b6f","last_reissued_at":"2026-05-17T23:41:30.266031Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:41:30.266031Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1906.00399","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":"2026-05-17T23:41:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"M03KdOkts6riVBzfE0kTJ5+eAz4JOXje+ZxW/ALHOMDqZ3rlKtirDZqq2FdK2fhILvx5AH1AzBZKdWDpk/WNBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T20:23:52.650584Z"},"content_sha256":"55843a1bae289a0cfed36711a822bb106525c80ce87bed95f5ff3f3902e56303","schema_version":"1.0","event_id":"sha256:55843a1bae289a0cfed36711a822bb106525c80ce87bed95f5ff3f3902e56303"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:QBIPDRS7TY3AXHRRWOAAYCMJJS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Multi-Objective Pruning for CNNs Using Genetic Algorithm","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.NE","authors_text":"Boyu Diao, Chao Li, Chuanguang Yang, Yongjun Xu, Zhulin An","submitted_at":"2019-06-02T13:17:37Z","abstract_excerpt":"In this work, we propose a heuristic genetic algorithm (GA) for pruning convolutional neural networks (CNNs) according to the multi-objective trade-off among error, computation and sparsity. In our experiments, we apply our approach to prune pre-trained LeNet across the MNIST dataset, which reduces 95.42% parameter size and achieves 16$\\times$ speedups of convolutional layer computation with tiny accuracy loss by laying emphasis on sparsity and computation, respectively. Our empirical study suggests that GA is an alternative pruning approach for obtaining a competitive compression performance."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.00399","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":"2026-05-17T23:41:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"exhR5+9GIcWnadXdXj7EA3KvhdwqNWulVrBs1xeukQ5/J13qMZMKKAFexCYkKst8+h7zsR4vghNxmw9QgzW5Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T20:23:52.650945Z"},"content_sha256":"e8aff82e619a146c19c3fd78b669a5ef3a13d5d08080079a50507a1d8f66f4de","schema_version":"1.0","event_id":"sha256:e8aff82e619a146c19c3fd78b669a5ef3a13d5d08080079a50507a1d8f66f4de"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QBIPDRS7TY3AXHRRWOAAYCMJJS/bundle.json","state_url":"https://pith.science/pith/QBIPDRS7TY3AXHRRWOAAYCMJJS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QBIPDRS7TY3AXHRRWOAAYCMJJS/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":"2026-06-02T20:23:52Z","links":{"resolver":"https://pith.science/pith/QBIPDRS7TY3AXHRRWOAAYCMJJS","bundle":"https://pith.science/pith/QBIPDRS7TY3AXHRRWOAAYCMJJS/bundle.json","state":"https://pith.science/pith/QBIPDRS7TY3AXHRRWOAAYCMJJS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QBIPDRS7TY3AXHRRWOAAYCMJJS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:QBIPDRS7TY3AXHRRWOAAYCMJJS","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":"8a97336aff6891f13e29b50684b46c0c7a38977cd50c95fc09d4b6fcf002ebb4","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2019-06-02T13:17:37Z","title_canon_sha256":"9b34ad6fa09b2327e3ae03e71a2d20eb2fccb73194cf7f388be9b4d198bea364"},"schema_version":"1.0","source":{"id":"1906.00399","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.00399","created_at":"2026-05-17T23:41:30Z"},{"alias_kind":"arxiv_version","alias_value":"1906.00399v2","created_at":"2026-05-17T23:41:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.00399","created_at":"2026-05-17T23:41:30Z"},{"alias_kind":"pith_short_12","alias_value":"QBIPDRS7TY3A","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_16","alias_value":"QBIPDRS7TY3AXHRR","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_8","alias_value":"QBIPDRS7","created_at":"2026-05-18T12:33:27Z"}],"graph_snapshots":[{"event_id":"sha256:e8aff82e619a146c19c3fd78b669a5ef3a13d5d08080079a50507a1d8f66f4de","target":"graph","created_at":"2026-05-17T23:41:30Z","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":"In this work, we propose a heuristic genetic algorithm (GA) for pruning convolutional neural networks (CNNs) according to the multi-objective trade-off among error, computation and sparsity. In our experiments, we apply our approach to prune pre-trained LeNet across the MNIST dataset, which reduces 95.42% parameter size and achieves 16$\\times$ speedups of convolutional layer computation with tiny accuracy loss by laying emphasis on sparsity and computation, respectively. Our empirical study suggests that GA is an alternative pruning approach for obtaining a competitive compression performance.","authors_text":"Boyu Diao, Chao Li, Chuanguang Yang, Yongjun Xu, Zhulin An","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2019-06-02T13:17:37Z","title":"Multi-Objective Pruning for CNNs Using Genetic Algorithm"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.00399","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":"sha256:55843a1bae289a0cfed36711a822bb106525c80ce87bed95f5ff3f3902e56303","target":"record","created_at":"2026-05-17T23:41:30Z","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":"8a97336aff6891f13e29b50684b46c0c7a38977cd50c95fc09d4b6fcf002ebb4","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2019-06-02T13:17:37Z","title_canon_sha256":"9b34ad6fa09b2327e3ae03e71a2d20eb2fccb73194cf7f388be9b4d198bea364"},"schema_version":"1.0","source":{"id":"1906.00399","kind":"arxiv","version":2}},"canonical_sha256":"8050f1c65f9e360b9e31b3800c09894c98c8024895d54bab4675d08c3df60b6f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8050f1c65f9e360b9e31b3800c09894c98c8024895d54bab4675d08c3df60b6f","first_computed_at":"2026-05-17T23:41:30.266031Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:41:30.266031Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6/y67rv1vNEpSzzpTxOljFIsLW9oi462wwphJ38+gJkwVMLXxLIVSsHy3FXDsSW5slLHQvAST9C33qX4RAqVBQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:41:30.266923Z","signed_message":"canonical_sha256_bytes"},"source_id":"1906.00399","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:55843a1bae289a0cfed36711a822bb106525c80ce87bed95f5ff3f3902e56303","sha256:e8aff82e619a146c19c3fd78b669a5ef3a13d5d08080079a50507a1d8f66f4de"],"state_sha256":"7bc932c6eba38788fdd17a9c1516061c5dfb6b2d78504679ebf8517b393d2f40"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MO+btQUUW2YePQ5JOK/b5mleJdEWc6WwEes0QKxUqnx6r8tMWYySw5HCcHCjn/oOHeIP1i97K11U8PKy59w1Dw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-02T20:23:52.653027Z","bundle_sha256":"22b00ffdcfcef18a88043aa1ecff68d22bb95b19043fe02c74685431919f6f65"}}