{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:F5ZCUHUGEBAZ4BNSJFOMM5F6DT","short_pith_number":"pith:F5ZCUHUG","canonical_record":{"source":{"id":"1710.01878","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-10-05T04:26:49Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"193ad00b99fd0bfaa8952781158e0f014f0281c30a22af487e296a3f4ab4860b","abstract_canon_sha256":"62cac133efe7cee2d48831b3beb526dde3f01dab3c369b9110b8793dbb1c148a"},"schema_version":"1.0"},"canonical_sha256":"2f722a1e8620419e05b2495cc674be1cfee41bf466f98450a2f064b2bbb3b861","source":{"kind":"arxiv","id":"1710.01878","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1710.01878","created_at":"2026-05-18T00:30:40Z"},{"alias_kind":"arxiv_version","alias_value":"1710.01878v2","created_at":"2026-05-18T00:30:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1710.01878","created_at":"2026-05-18T00:30:40Z"},{"alias_kind":"pith_short_12","alias_value":"F5ZCUHUGEBAZ","created_at":"2026-05-18T12:31:15Z"},{"alias_kind":"pith_short_16","alias_value":"F5ZCUHUGEBAZ4BNS","created_at":"2026-05-18T12:31:15Z"},{"alias_kind":"pith_short_8","alias_value":"F5ZCUHUG","created_at":"2026-05-18T12:31:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:F5ZCUHUGEBAZ4BNSJFOMM5F6DT","target":"record","payload":{"canonical_record":{"source":{"id":"1710.01878","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-10-05T04:26:49Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"193ad00b99fd0bfaa8952781158e0f014f0281c30a22af487e296a3f4ab4860b","abstract_canon_sha256":"62cac133efe7cee2d48831b3beb526dde3f01dab3c369b9110b8793dbb1c148a"},"schema_version":"1.0"},"canonical_sha256":"2f722a1e8620419e05b2495cc674be1cfee41bf466f98450a2f064b2bbb3b861","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:30:40.778623Z","signature_b64":"EBwgox/uqa+Ltodf1BYUIjt65eWqvWZpVWp/j73qKPUNuoioGr4SjMDLKgcKrmhsgSaG5bqd1wMuou7/BBxuAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2f722a1e8620419e05b2495cc674be1cfee41bf466f98450a2f064b2bbb3b861","last_reissued_at":"2026-05-18T00:30:40.777965Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:30:40.777965Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1710.01878","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":"2026-05-18T00:30:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1GLnZWsTXr06qm+HL8qJXbpG32fwf7X1NvDhTAcUZ/XVVvWkmkw6+OZkPuu7oifBIs/sLic+IpiB+MBlGfbTDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-23T13:26:14.045236Z"},"content_sha256":"c05d376df67d7a49b07f104ab3159eca530b1fe16cb06bfa27e9747677625b3f","schema_version":"1.0","event_id":"sha256:c05d376df67d7a49b07f104ab3159eca530b1fe16cb06bfa27e9747677625b3f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:F5ZCUHUGEBAZ4BNSJFOMM5F6DT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"To prune, or not to prune: exploring the efficacy of pruning for model compression","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Michael Zhu, Suyog Gupta","submitted_at":"2017-10-05T04:26:49Z","abstract_excerpt":"Model pruning seeks to induce sparsity in a deep neural network's various connection matrices, thereby reducing the number of nonzero-valued parameters in the model. Recent reports (Han et al., 2015; Narang et al., 2017) prune deep networks at the cost of only a marginal loss in accuracy and achieve a sizable reduction in model size. This hints at the possibility that the baseline models in these experiments are perhaps severely over-parameterized at the outset and a viable alternative for model compression might be to simply reduce the number of hidden units while maintaining the model's dens"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1710.01878","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":"2026-05-18T00:30:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"p82qi36NLML3gLQ4mg0OKo4VXutt3wm1U4isvuafjXhKpOA6y0Yj0RBWNXupnbL2/wmlppZ+x/WC9ZmoZDqvDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-23T13:26:14.045996Z"},"content_sha256":"934e2b4c8cc891b24c45eef9d384d6b5270aad3706e47c4a128ca5799038bd93","schema_version":"1.0","event_id":"sha256:934e2b4c8cc891b24c45eef9d384d6b5270aad3706e47c4a128ca5799038bd93"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/F5ZCUHUGEBAZ4BNSJFOMM5F6DT/bundle.json","state_url":"https://pith.science/pith/F5ZCUHUGEBAZ4BNSJFOMM5F6DT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/F5ZCUHUGEBAZ4BNSJFOMM5F6DT/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":"2026-05-23T13:26:14Z","links":{"resolver":"https://pith.science/pith/F5ZCUHUGEBAZ4BNSJFOMM5F6DT","bundle":"https://pith.science/pith/F5ZCUHUGEBAZ4BNSJFOMM5F6DT/bundle.json","state":"https://pith.science/pith/F5ZCUHUGEBAZ4BNSJFOMM5F6DT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/F5ZCUHUGEBAZ4BNSJFOMM5F6DT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:F5ZCUHUGEBAZ4BNSJFOMM5F6DT","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":"62cac133efe7cee2d48831b3beb526dde3f01dab3c369b9110b8793dbb1c148a","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-10-05T04:26:49Z","title_canon_sha256":"193ad00b99fd0bfaa8952781158e0f014f0281c30a22af487e296a3f4ab4860b"},"schema_version":"1.0","source":{"id":"1710.01878","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1710.01878","created_at":"2026-05-18T00:30:40Z"},{"alias_kind":"arxiv_version","alias_value":"1710.01878v2","created_at":"2026-05-18T00:30:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1710.01878","created_at":"2026-05-18T00:30:40Z"},{"alias_kind":"pith_short_12","alias_value":"F5ZCUHUGEBAZ","created_at":"2026-05-18T12:31:15Z"},{"alias_kind":"pith_short_16","alias_value":"F5ZCUHUGEBAZ4BNS","created_at":"2026-05-18T12:31:15Z"},{"alias_kind":"pith_short_8","alias_value":"F5ZCUHUG","created_at":"2026-05-18T12:31:15Z"}],"graph_snapshots":[{"event_id":"sha256:934e2b4c8cc891b24c45eef9d384d6b5270aad3706e47c4a128ca5799038bd93","target":"graph","created_at":"2026-05-18T00:30:40Z","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":"Model pruning seeks to induce sparsity in a deep neural network's various connection matrices, thereby reducing the number of nonzero-valued parameters in the model. Recent reports (Han et al., 2015; Narang et al., 2017) prune deep networks at the cost of only a marginal loss in accuracy and achieve a sizable reduction in model size. This hints at the possibility that the baseline models in these experiments are perhaps severely over-parameterized at the outset and a viable alternative for model compression might be to simply reduce the number of hidden units while maintaining the model's dens","authors_text":"Michael Zhu, Suyog Gupta","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-10-05T04:26:49Z","title":"To prune, or not to prune: exploring the efficacy of pruning for model compression"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1710.01878","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:c05d376df67d7a49b07f104ab3159eca530b1fe16cb06bfa27e9747677625b3f","target":"record","created_at":"2026-05-18T00:30:40Z","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":"62cac133efe7cee2d48831b3beb526dde3f01dab3c369b9110b8793dbb1c148a","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-10-05T04:26:49Z","title_canon_sha256":"193ad00b99fd0bfaa8952781158e0f014f0281c30a22af487e296a3f4ab4860b"},"schema_version":"1.0","source":{"id":"1710.01878","kind":"arxiv","version":2}},"canonical_sha256":"2f722a1e8620419e05b2495cc674be1cfee41bf466f98450a2f064b2bbb3b861","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2f722a1e8620419e05b2495cc674be1cfee41bf466f98450a2f064b2bbb3b861","first_computed_at":"2026-05-18T00:30:40.777965Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:30:40.777965Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"EBwgox/uqa+Ltodf1BYUIjt65eWqvWZpVWp/j73qKPUNuoioGr4SjMDLKgcKrmhsgSaG5bqd1wMuou7/BBxuAQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:30:40.778623Z","signed_message":"canonical_sha256_bytes"},"source_id":"1710.01878","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c05d376df67d7a49b07f104ab3159eca530b1fe16cb06bfa27e9747677625b3f","sha256:934e2b4c8cc891b24c45eef9d384d6b5270aad3706e47c4a128ca5799038bd93"],"state_sha256":"00a446dd286e8d0fea283c7a7d1844e79b3633410cc9b9491b7710769984b107"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"D11drahB5KsDU+1qnvXerPakDOWm62hcarikI0o7BgUXuXnfxLYAJFCDRMkD7d8fhXtq0rL9ayKmTAs5avMzCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-23T13:26:14.049669Z","bundle_sha256":"65f8c881728f26550326277e9d44d78c6c11f69b213b7466e5d67c80fcc95baf"}}