{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:YAXDHWKQGAX66KUI4BD3VHSTEA","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":"3459109ccae67d9b54683a0da7a309ab7739470fd8f15a72bbb1072af23b8423","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-05-14T11:05:21Z","title_canon_sha256":"04a91982761ffde7a2af0fc66c2774d156bc3d176613f2dc27e635f4e172c43a"},"schema_version":"1.0","source":{"id":"2005.06870","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2005.06870","created_at":"2026-07-05T01:02:51Z"},{"alias_kind":"arxiv_version","alias_value":"2005.06870v1","created_at":"2026-07-05T01:02:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.06870","created_at":"2026-07-05T01:02:51Z"},{"alias_kind":"pith_short_12","alias_value":"YAXDHWKQGAX6","created_at":"2026-07-05T01:02:51Z"},{"alias_kind":"pith_short_16","alias_value":"YAXDHWKQGAX66KUI","created_at":"2026-07-05T01:02:51Z"},{"alias_kind":"pith_short_8","alias_value":"YAXDHWKQ","created_at":"2026-07-05T01:02:51Z"}],"graph_snapshots":[{"event_id":"sha256:28316eac173e7e61b7291001257ace5d4e8b37cdf2449016e47fd8cda9773eff","target":"graph","created_at":"2026-07-05T01:02:51Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2005.06870/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present a novel network pruning algorithm called Dynamic Sparse Training that can jointly find the optimal network parameters and sparse network structure in a unified optimization process with trainable pruning thresholds. These thresholds can have fine-grained layer-wise adjustments dynamically via backpropagation. We demonstrate that our dynamic sparse training algorithm can easily train very sparse neural network models with little performance loss using the same number of training epochs as dense models. Dynamic Sparse Training achieves the state of the art performance compared with ot","authors_text":"Hayden K.H. So, Junjie Liu, Ray C. C. Cheung, Runbin Shi, Zhe Xu","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-05-14T11:05:21Z","title":"Dynamic Sparse Training: Find Efficient Sparse Network From Scratch With Trainable Masked Layers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.06870","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":"sha256:6381bd59096e454a914c769ed77cac7f91041bd9ea90a4d68125546c72caf848","target":"record","created_at":"2026-07-05T01:02:51Z","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":"3459109ccae67d9b54683a0da7a309ab7739470fd8f15a72bbb1072af23b8423","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-05-14T11:05:21Z","title_canon_sha256":"04a91982761ffde7a2af0fc66c2774d156bc3d176613f2dc27e635f4e172c43a"},"schema_version":"1.0","source":{"id":"2005.06870","kind":"arxiv","version":1}},"canonical_sha256":"c02e33d950302fef2a88e047ba9e532010710dcb9ebcd7d0d5026405e7ac8bd8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c02e33d950302fef2a88e047ba9e532010710dcb9ebcd7d0d5026405e7ac8bd8","first_computed_at":"2026-07-05T01:02:51.483308Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:02:51.483308Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"sdtW06SfuRHlzLrIu438MttQYihE4qiYzlheu0JOBPaGjKkINSg0FUFrnQQvxKGBZJm9jGj14lsECuneRysZDg==","signature_status":"signed_v1","signed_at":"2026-07-05T01:02:51.483731Z","signed_message":"canonical_sha256_bytes"},"source_id":"2005.06870","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6381bd59096e454a914c769ed77cac7f91041bd9ea90a4d68125546c72caf848","sha256:28316eac173e7e61b7291001257ace5d4e8b37cdf2449016e47fd8cda9773eff"],"state_sha256":"e88525bab73d7423f4022069284a3c4e3614e6481c839c60c5ea5b753c7c1c50"}