{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:MGYT5QUUODZLY6AQZ3TTONVLF6","short_pith_number":"pith:MGYT5QUU","canonical_record":{"source":{"id":"1702.06257","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-02-21T04:10:31Z","cross_cats_sorted":[],"title_canon_sha256":"4b880d9039792c7ed7c20d55cd63b9d839ff71ce3e5799c586e16ee09b91753f","abstract_canon_sha256":"8932a1e8ee2c243075c851319f96f144e2c70a67e207ff6c39e73127a71b0fd3"},"schema_version":"1.0"},"canonical_sha256":"61b13ec29470f2bc7810cee73736ab2f8f201463917c187ca15ab3325fdc5637","source":{"kind":"arxiv","id":"1702.06257","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1702.06257","created_at":"2026-05-18T00:50:14Z"},{"alias_kind":"arxiv_version","alias_value":"1702.06257v1","created_at":"2026-05-18T00:50:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1702.06257","created_at":"2026-05-18T00:50:14Z"},{"alias_kind":"pith_short_12","alias_value":"MGYT5QUUODZL","created_at":"2026-05-18T12:31:31Z"},{"alias_kind":"pith_short_16","alias_value":"MGYT5QUUODZLY6AQ","created_at":"2026-05-18T12:31:31Z"},{"alias_kind":"pith_short_8","alias_value":"MGYT5QUU","created_at":"2026-05-18T12:31:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:MGYT5QUUODZLY6AQZ3TTONVLF6","target":"record","payload":{"canonical_record":{"source":{"id":"1702.06257","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-02-21T04:10:31Z","cross_cats_sorted":[],"title_canon_sha256":"4b880d9039792c7ed7c20d55cd63b9d839ff71ce3e5799c586e16ee09b91753f","abstract_canon_sha256":"8932a1e8ee2c243075c851319f96f144e2c70a67e207ff6c39e73127a71b0fd3"},"schema_version":"1.0"},"canonical_sha256":"61b13ec29470f2bc7810cee73736ab2f8f201463917c187ca15ab3325fdc5637","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:50:14.583677Z","signature_b64":"F8a+/S/vYT028tCAGFVMBAqMWaqu0T8OgxEMEpuFXdCZ+BbtLpfokEGc6WJBo7iQRaDuKMikdL4nTl8x1yKgCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"61b13ec29470f2bc7810cee73736ab2f8f201463917c187ca15ab3325fdc5637","last_reissued_at":"2026-05-18T00:50:14.583081Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:50:14.583081Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1702.06257","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":"2026-05-18T00:50:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0MOOiXu6HqltslLiDIpcvrSdUrZYGQ5HpSDLaeVLMzwN5mew4G+exL2pPEXudz/Wf6TTw0AsLf/DkK67AqSUCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T19:44:24.564919Z"},"content_sha256":"95345e6a93adc60769ab34ae4a795e82970d547047df8608e800ecfb20b3352c","schema_version":"1.0","event_id":"sha256:95345e6a93adc60769ab34ae4a795e82970d547047df8608e800ecfb20b3352c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:MGYT5QUUODZLY6AQZ3TTONVLF6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"The Power of Sparsity in Convolutional Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andrey Zhmoginov, Mark Sandler, Soravit Changpinyo","submitted_at":"2017-02-21T04:10:31Z","abstract_excerpt":"Deep convolutional networks are well-known for their high computational and memory demands. Given limited resources, how does one design a network that balances its size, training time, and prediction accuracy? A surprisingly effective approach to trade accuracy for size and speed is to simply reduce the number of channels in each convolutional layer by a fixed fraction and retrain the network. In many cases this leads to significantly smaller networks with only minimal changes to accuracy. In this paper, we take a step further by empirically examining a strategy for deactivating connections b"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1702.06257","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":"2026-05-18T00:50:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ekjs1VwPBly3MDRp/F3rxyGDQFhyWBZr3jxSZTSWIuL+jqScGZL9yMuGu3W7CVE/jvpgcSslW60dZJhLAU23Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T19:44:24.565278Z"},"content_sha256":"c5969943380d926a9a6617f71c92c3a350f418b1238dbf1091d75f2519f3bb00","schema_version":"1.0","event_id":"sha256:c5969943380d926a9a6617f71c92c3a350f418b1238dbf1091d75f2519f3bb00"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MGYT5QUUODZLY6AQZ3TTONVLF6/bundle.json","state_url":"https://pith.science/pith/MGYT5QUUODZLY6AQZ3TTONVLF6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MGYT5QUUODZLY6AQZ3TTONVLF6/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":"2026-06-10T19:44:24Z","links":{"resolver":"https://pith.science/pith/MGYT5QUUODZLY6AQZ3TTONVLF6","bundle":"https://pith.science/pith/MGYT5QUUODZLY6AQZ3TTONVLF6/bundle.json","state":"https://pith.science/pith/MGYT5QUUODZLY6AQZ3TTONVLF6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MGYT5QUUODZLY6AQZ3TTONVLF6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:MGYT5QUUODZLY6AQZ3TTONVLF6","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":"8932a1e8ee2c243075c851319f96f144e2c70a67e207ff6c39e73127a71b0fd3","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-02-21T04:10:31Z","title_canon_sha256":"4b880d9039792c7ed7c20d55cd63b9d839ff71ce3e5799c586e16ee09b91753f"},"schema_version":"1.0","source":{"id":"1702.06257","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1702.06257","created_at":"2026-05-18T00:50:14Z"},{"alias_kind":"arxiv_version","alias_value":"1702.06257v1","created_at":"2026-05-18T00:50:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1702.06257","created_at":"2026-05-18T00:50:14Z"},{"alias_kind":"pith_short_12","alias_value":"MGYT5QUUODZL","created_at":"2026-05-18T12:31:31Z"},{"alias_kind":"pith_short_16","alias_value":"MGYT5QUUODZLY6AQ","created_at":"2026-05-18T12:31:31Z"},{"alias_kind":"pith_short_8","alias_value":"MGYT5QUU","created_at":"2026-05-18T12:31:31Z"}],"graph_snapshots":[{"event_id":"sha256:c5969943380d926a9a6617f71c92c3a350f418b1238dbf1091d75f2519f3bb00","target":"graph","created_at":"2026-05-18T00:50:14Z","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":"Deep convolutional networks are well-known for their high computational and memory demands. Given limited resources, how does one design a network that balances its size, training time, and prediction accuracy? A surprisingly effective approach to trade accuracy for size and speed is to simply reduce the number of channels in each convolutional layer by a fixed fraction and retrain the network. In many cases this leads to significantly smaller networks with only minimal changes to accuracy. In this paper, we take a step further by empirically examining a strategy for deactivating connections b","authors_text":"Andrey Zhmoginov, Mark Sandler, Soravit Changpinyo","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-02-21T04:10:31Z","title":"The Power of Sparsity in Convolutional Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1702.06257","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":"sha256:95345e6a93adc60769ab34ae4a795e82970d547047df8608e800ecfb20b3352c","target":"record","created_at":"2026-05-18T00:50:14Z","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":"8932a1e8ee2c243075c851319f96f144e2c70a67e207ff6c39e73127a71b0fd3","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-02-21T04:10:31Z","title_canon_sha256":"4b880d9039792c7ed7c20d55cd63b9d839ff71ce3e5799c586e16ee09b91753f"},"schema_version":"1.0","source":{"id":"1702.06257","kind":"arxiv","version":1}},"canonical_sha256":"61b13ec29470f2bc7810cee73736ab2f8f201463917c187ca15ab3325fdc5637","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"61b13ec29470f2bc7810cee73736ab2f8f201463917c187ca15ab3325fdc5637","first_computed_at":"2026-05-18T00:50:14.583081Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:50:14.583081Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"F8a+/S/vYT028tCAGFVMBAqMWaqu0T8OgxEMEpuFXdCZ+BbtLpfokEGc6WJBo7iQRaDuKMikdL4nTl8x1yKgCA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:50:14.583677Z","signed_message":"canonical_sha256_bytes"},"source_id":"1702.06257","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:95345e6a93adc60769ab34ae4a795e82970d547047df8608e800ecfb20b3352c","sha256:c5969943380d926a9a6617f71c92c3a350f418b1238dbf1091d75f2519f3bb00"],"state_sha256":"0e3e4db08656f9d21633f518b12951f76786daaeca72519532e93447ecaeb0e2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VizrGzB506vaEq5kS+q/l7bAGY6Hs4FZF+XPhPdjvb0hJTSy3pIcTToWZg3+60iMJ1gtQRwC3oVZl96tzGErDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-10T19:44:24.567270Z","bundle_sha256":"1b7dc495da041c1fdaed0897e0632ac691fbd794864a59d3f425018f6705d03f"}}