{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:JVLUKMPDODHDEKYD7JVQS66HXA","short_pith_number":"pith:JVLUKMPD","canonical_record":{"source":{"id":"2111.02399","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-11-01T02:27:44Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"54ca24b624991bf143f788b73576ec8f53d1517d214aff2cf2395fbf9a6ef283","abstract_canon_sha256":"ff849a90d8ab276661b0476a5dc24d13594a9ae40c7bae49ae66eac1ccb9a2b3"},"schema_version":"1.0"},"canonical_sha256":"4d574531e370ce322b03fa6b097bc7b825efb9386e407f1b9a8d7841edc56b24","source":{"kind":"arxiv","id":"2111.02399","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2111.02399","created_at":"2026-07-05T04:30:05Z"},{"alias_kind":"arxiv_version","alias_value":"2111.02399v2","created_at":"2026-07-05T04:30:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.02399","created_at":"2026-07-05T04:30:05Z"},{"alias_kind":"pith_short_12","alias_value":"JVLUKMPDODHD","created_at":"2026-07-05T04:30:05Z"},{"alias_kind":"pith_short_16","alias_value":"JVLUKMPDODHDEKYD","created_at":"2026-07-05T04:30:05Z"},{"alias_kind":"pith_short_8","alias_value":"JVLUKMPD","created_at":"2026-07-05T04:30:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:JVLUKMPDODHDEKYD7JVQS66HXA","target":"record","payload":{"canonical_record":{"source":{"id":"2111.02399","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-11-01T02:27:44Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"54ca24b624991bf143f788b73576ec8f53d1517d214aff2cf2395fbf9a6ef283","abstract_canon_sha256":"ff849a90d8ab276661b0476a5dc24d13594a9ae40c7bae49ae66eac1ccb9a2b3"},"schema_version":"1.0"},"canonical_sha256":"4d574531e370ce322b03fa6b097bc7b825efb9386e407f1b9a8d7841edc56b24","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:30:05.426042Z","signature_b64":"ObW3jmCzGX2jfOBviFpX51BWGO6lMbh5OIVOCjpCtxm1ZMcOu6YQwAUhxv9pDam/qc57AWPma/lqcHKYK+MhCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4d574531e370ce322b03fa6b097bc7b825efb9386e407f1b9a8d7841edc56b24","last_reissued_at":"2026-07-05T04:30:05.425536Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:30:05.425536Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2111.02399","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":"2026-07-05T04:30:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gqwdlBzw7vyAtT5a9yseBuwEThoNX0doMwd1VeSJBN6kIa6hg1Hb7PErkURPqadDw9IXEjgq+QBXUcEEM0KyBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T21:38:05.738984Z"},"content_sha256":"0392c2f37a658450cd8ac576834b12bb98a087dea52dffe5b7df194763066374","schema_version":"1.0","event_id":"sha256:0392c2f37a658450cd8ac576834b12bb98a087dea52dffe5b7df194763066374"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:JVLUKMPDODHDEKYD7JVQS66HXA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning Pruned Structure and Weights Simultaneously from Scratch: an Attention based Approach","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Ming Dong, Qisheng He, Weisong Shi","submitted_at":"2021-11-01T02:27:44Z","abstract_excerpt":"As a deep learning model typically contains millions of trainable weights, there has been a growing demand for a more efficient network structure with reduced storage space and improved run-time efficiency. Pruning is one of the most popular network compression techniques. In this paper, we propose a novel unstructured pruning pipeline, Attention-based Simultaneous sparse structure and Weight Learning (ASWL). Unlike traditional channel-wise or weight-wise attention mechanism, ASWL proposed an efficient algorithm to calculate the pruning ratio through layer-wise attention for each layer, and bo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.02399","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2111.02399/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2026-07-05T04:30:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GG3ni0S5Ees7na7oBtrU6GeHbahLjaGInu9nyWDEcolpRYWYskI19Q4tNxGxmYiqvhCF401lfznvAIcGAHlcBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T21:38:05.739504Z"},"content_sha256":"56eb6b4ebb041ba0f2c82e62a35b0fe2d8bc0a97886cb45ccf10963f50ad47c6","schema_version":"1.0","event_id":"sha256:56eb6b4ebb041ba0f2c82e62a35b0fe2d8bc0a97886cb45ccf10963f50ad47c6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JVLUKMPDODHDEKYD7JVQS66HXA/bundle.json","state_url":"https://pith.science/pith/JVLUKMPDODHDEKYD7JVQS66HXA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JVLUKMPDODHDEKYD7JVQS66HXA/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":"2026-08-18T21:38:05Z","links":{"resolver":"https://pith.science/pith/JVLUKMPDODHDEKYD7JVQS66HXA","bundle":"https://pith.science/pith/JVLUKMPDODHDEKYD7JVQS66HXA/bundle.json","state":"https://pith.science/pith/JVLUKMPDODHDEKYD7JVQS66HXA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JVLUKMPDODHDEKYD7JVQS66HXA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:JVLUKMPDODHDEKYD7JVQS66HXA","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":"ff849a90d8ab276661b0476a5dc24d13594a9ae40c7bae49ae66eac1ccb9a2b3","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-11-01T02:27:44Z","title_canon_sha256":"54ca24b624991bf143f788b73576ec8f53d1517d214aff2cf2395fbf9a6ef283"},"schema_version":"1.0","source":{"id":"2111.02399","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2111.02399","created_at":"2026-07-05T04:30:05Z"},{"alias_kind":"arxiv_version","alias_value":"2111.02399v2","created_at":"2026-07-05T04:30:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.02399","created_at":"2026-07-05T04:30:05Z"},{"alias_kind":"pith_short_12","alias_value":"JVLUKMPDODHD","created_at":"2026-07-05T04:30:05Z"},{"alias_kind":"pith_short_16","alias_value":"JVLUKMPDODHDEKYD","created_at":"2026-07-05T04:30:05Z"},{"alias_kind":"pith_short_8","alias_value":"JVLUKMPD","created_at":"2026-07-05T04:30:05Z"}],"graph_snapshots":[{"event_id":"sha256:56eb6b4ebb041ba0f2c82e62a35b0fe2d8bc0a97886cb45ccf10963f50ad47c6","target":"graph","created_at":"2026-07-05T04:30:05Z","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/2111.02399/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"As a deep learning model typically contains millions of trainable weights, there has been a growing demand for a more efficient network structure with reduced storage space and improved run-time efficiency. Pruning is one of the most popular network compression techniques. In this paper, we propose a novel unstructured pruning pipeline, Attention-based Simultaneous sparse structure and Weight Learning (ASWL). Unlike traditional channel-wise or weight-wise attention mechanism, ASWL proposed an efficient algorithm to calculate the pruning ratio through layer-wise attention for each layer, and bo","authors_text":"Ming Dong, Qisheng He, Weisong Shi","cross_cats":["cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-11-01T02:27:44Z","title":"Learning Pruned Structure and Weights Simultaneously from Scratch: an Attention based Approach"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.02399","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":"sha256:0392c2f37a658450cd8ac576834b12bb98a087dea52dffe5b7df194763066374","target":"record","created_at":"2026-07-05T04:30:05Z","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":"ff849a90d8ab276661b0476a5dc24d13594a9ae40c7bae49ae66eac1ccb9a2b3","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-11-01T02:27:44Z","title_canon_sha256":"54ca24b624991bf143f788b73576ec8f53d1517d214aff2cf2395fbf9a6ef283"},"schema_version":"1.0","source":{"id":"2111.02399","kind":"arxiv","version":2}},"canonical_sha256":"4d574531e370ce322b03fa6b097bc7b825efb9386e407f1b9a8d7841edc56b24","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4d574531e370ce322b03fa6b097bc7b825efb9386e407f1b9a8d7841edc56b24","first_computed_at":"2026-07-05T04:30:05.425536Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:30:05.425536Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ObW3jmCzGX2jfOBviFpX51BWGO6lMbh5OIVOCjpCtxm1ZMcOu6YQwAUhxv9pDam/qc57AWPma/lqcHKYK+MhCw==","signature_status":"signed_v1","signed_at":"2026-07-05T04:30:05.426042Z","signed_message":"canonical_sha256_bytes"},"source_id":"2111.02399","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0392c2f37a658450cd8ac576834b12bb98a087dea52dffe5b7df194763066374","sha256:56eb6b4ebb041ba0f2c82e62a35b0fe2d8bc0a97886cb45ccf10963f50ad47c6"],"state_sha256":"d6e6afa6da2f1cfc936668d6f5723207f67460632b2c3eb609c13376ffc48b06"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4Hk+vKClwi+3nda6LUt+7maKnEOvGDcS3e1nICOTO2WlGM2PfiKh6nm0T9JgrS0WlL+LuLFq8fbTtruXTj56DQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T21:38:05.744288Z","bundle_sha256":"b2399eee51fb7c26250f377f5b5b88b9f0b2acee55335ad3ee287586fa0c5947"}}