{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:F3ML6QYCVSPPDMCJV4JL2RBY26","short_pith_number":"pith:F3ML6QYC","canonical_record":{"source":{"id":"1905.11533","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-05-27T22:54:59Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"4174259e4157ed6467509e8b8a6ca9bbf5425052a3e488aa25359358e75d6406","abstract_canon_sha256":"225d2a3bfdc6a93e4c1f60e619d216ba062b595c09db48045d610c0adc5a45a7"},"schema_version":"1.0"},"canonical_sha256":"2ed8bf4302ac9ef1b049af12bd4438d79dd8d859e665eb9a533b2855b8637100","source":{"kind":"arxiv","id":"1905.11533","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.11533","created_at":"2026-05-17T23:44:47Z"},{"alias_kind":"arxiv_version","alias_value":"1905.11533v2","created_at":"2026-05-17T23:44:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.11533","created_at":"2026-05-17T23:44:47Z"},{"alias_kind":"pith_short_12","alias_value":"F3ML6QYCVSPP","created_at":"2026-05-18T12:33:15Z"},{"alias_kind":"pith_short_16","alias_value":"F3ML6QYCVSPPDMCJ","created_at":"2026-05-18T12:33:15Z"},{"alias_kind":"pith_short_8","alias_value":"F3ML6QYC","created_at":"2026-05-18T12:33:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:F3ML6QYCVSPPDMCJV4JL2RBY26","target":"record","payload":{"canonical_record":{"source":{"id":"1905.11533","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-05-27T22:54:59Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"4174259e4157ed6467509e8b8a6ca9bbf5425052a3e488aa25359358e75d6406","abstract_canon_sha256":"225d2a3bfdc6a93e4c1f60e619d216ba062b595c09db48045d610c0adc5a45a7"},"schema_version":"1.0"},"canonical_sha256":"2ed8bf4302ac9ef1b049af12bd4438d79dd8d859e665eb9a533b2855b8637100","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:44:47.094934Z","signature_b64":"Z9ktT0hGMkCtGeL5EFweB5n0bo5ygMO/knBCx0IyYE2pYMhiKKY0IT8F1WsTBKINZKHnrbZaz1ZLEdAtPrHsCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2ed8bf4302ac9ef1b049af12bd4438d79dd8d859e665eb9a533b2855b8637100","last_reissued_at":"2026-05-17T23:44:47.094079Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:44:47.094079Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1905.11533","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":"2026-05-17T23:44:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SXzg6cl6+6N95df2OSGyXWT9lZXKUOI0wm5/SPUbo8+YmeqnqcME0oh2/N6zXDTJAUgOieNpxlLb1V61vXgQAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T19:48:30.349400Z"},"content_sha256":"7619dedbb13d9ac5ac74c0908a199c4e4cf358277a17261665cf31bf8cc511a6","schema_version":"1.0","event_id":"sha256:7619dedbb13d9ac5ac74c0908a199c4e4cf358277a17261665cf31bf8cc511a6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:F3ML6QYCVSPPDMCJV4JL2RBY26","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"CGaP: Continuous Growth and Pruning for Efficient Deep Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Xiaocong Du, Yu Cao, Zheng Li","submitted_at":"2019-05-27T22:54:59Z","abstract_excerpt":"Today a canonical approach to reduce the computation cost of Deep Neural Networks (DNNs) is to pre-define an over-parameterized model before training to guarantee the learning capacity, and then prune unimportant learning units (filters and neurons) during training to improve model compactness. We argue it is unnecessary to introduce redundancy at the beginning of the training but then reduce redundancy for the ultimate inference model. In this paper, we propose a Continuous Growth and Pruning (CGaP) scheme to minimize the redundancy from the beginning. CGaP starts the training from a small ne"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.11533","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":"2026-05-17T23:44:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"itWRMfVrIyV8RnJwNLrgGXmFjVieKDwri7rbrMT7PpxxPskjnBtYPgGn7fskzffk5MdLwRMF/iyi7yFfiHX6Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T19:48:30.349732Z"},"content_sha256":"4162ed4255d817fa0b53797cf1e17a65957884e731a6317d4b9a39abfcc74ddf","schema_version":"1.0","event_id":"sha256:4162ed4255d817fa0b53797cf1e17a65957884e731a6317d4b9a39abfcc74ddf"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/F3ML6QYCVSPPDMCJV4JL2RBY26/bundle.json","state_url":"https://pith.science/pith/F3ML6QYCVSPPDMCJV4JL2RBY26/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/F3ML6QYCVSPPDMCJV4JL2RBY26/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":"2026-06-01T19:48:30Z","links":{"resolver":"https://pith.science/pith/F3ML6QYCVSPPDMCJV4JL2RBY26","bundle":"https://pith.science/pith/F3ML6QYCVSPPDMCJV4JL2RBY26/bundle.json","state":"https://pith.science/pith/F3ML6QYCVSPPDMCJV4JL2RBY26/state.json","well_known_bundle":"https://pith.science/.well-known/pith/F3ML6QYCVSPPDMCJV4JL2RBY26/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:F3ML6QYCVSPPDMCJV4JL2RBY26","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":"225d2a3bfdc6a93e4c1f60e619d216ba062b595c09db48045d610c0adc5a45a7","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-05-27T22:54:59Z","title_canon_sha256":"4174259e4157ed6467509e8b8a6ca9bbf5425052a3e488aa25359358e75d6406"},"schema_version":"1.0","source":{"id":"1905.11533","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.11533","created_at":"2026-05-17T23:44:47Z"},{"alias_kind":"arxiv_version","alias_value":"1905.11533v2","created_at":"2026-05-17T23:44:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.11533","created_at":"2026-05-17T23:44:47Z"},{"alias_kind":"pith_short_12","alias_value":"F3ML6QYCVSPP","created_at":"2026-05-18T12:33:15Z"},{"alias_kind":"pith_short_16","alias_value":"F3ML6QYCVSPPDMCJ","created_at":"2026-05-18T12:33:15Z"},{"alias_kind":"pith_short_8","alias_value":"F3ML6QYC","created_at":"2026-05-18T12:33:15Z"}],"graph_snapshots":[{"event_id":"sha256:4162ed4255d817fa0b53797cf1e17a65957884e731a6317d4b9a39abfcc74ddf","target":"graph","created_at":"2026-05-17T23:44:47Z","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":"Today a canonical approach to reduce the computation cost of Deep Neural Networks (DNNs) is to pre-define an over-parameterized model before training to guarantee the learning capacity, and then prune unimportant learning units (filters and neurons) during training to improve model compactness. We argue it is unnecessary to introduce redundancy at the beginning of the training but then reduce redundancy for the ultimate inference model. In this paper, we propose a Continuous Growth and Pruning (CGaP) scheme to minimize the redundancy from the beginning. CGaP starts the training from a small ne","authors_text":"Xiaocong Du, Yu Cao, Zheng Li","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-05-27T22:54:59Z","title":"CGaP: Continuous Growth and Pruning for Efficient Deep Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.11533","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":"sha256:7619dedbb13d9ac5ac74c0908a199c4e4cf358277a17261665cf31bf8cc511a6","target":"record","created_at":"2026-05-17T23:44:47Z","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":"225d2a3bfdc6a93e4c1f60e619d216ba062b595c09db48045d610c0adc5a45a7","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-05-27T22:54:59Z","title_canon_sha256":"4174259e4157ed6467509e8b8a6ca9bbf5425052a3e488aa25359358e75d6406"},"schema_version":"1.0","source":{"id":"1905.11533","kind":"arxiv","version":2}},"canonical_sha256":"2ed8bf4302ac9ef1b049af12bd4438d79dd8d859e665eb9a533b2855b8637100","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2ed8bf4302ac9ef1b049af12bd4438d79dd8d859e665eb9a533b2855b8637100","first_computed_at":"2026-05-17T23:44:47.094079Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:44:47.094079Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Z9ktT0hGMkCtGeL5EFweB5n0bo5ygMO/knBCx0IyYE2pYMhiKKY0IT8F1WsTBKINZKHnrbZaz1ZLEdAtPrHsCg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:44:47.094934Z","signed_message":"canonical_sha256_bytes"},"source_id":"1905.11533","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7619dedbb13d9ac5ac74c0908a199c4e4cf358277a17261665cf31bf8cc511a6","sha256:4162ed4255d817fa0b53797cf1e17a65957884e731a6317d4b9a39abfcc74ddf"],"state_sha256":"404334d4e9397ca0bfc0cef1fc341b4be10f825ab1710bf41a7d577582e79150"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hJEpBf8lbsD+2ksEDysRoogQhvTAQczitmESReWJ1rykvn5BOJQ+tq0qLORtqqUCa+W70J79V6b3FyV8naAACQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-01T19:48:30.351979Z","bundle_sha256":"07e996bb5817009f63aaa548444ab474b591564bc23e3e69b16d7f0dd43e7806"}}