{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:MJV2DV5K6U4UAJO3QYCWPCCZPS","short_pith_number":"pith:MJV2DV5K","canonical_record":{"source":{"id":"2003.13593","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2020-03-30T16:20:46Z","cross_cats_sorted":["cs.CV","eess.IV","stat.ML"],"title_canon_sha256":"e5386d4348f647384326c0c713a8a15ebdb572d8a1cec56cf7fdf18f384f8dc8","abstract_canon_sha256":"5489d0bf4a922e97d9b50c94137fcfd40b1b107aee1be9275f1719909b0ee3d4"},"schema_version":"1.0"},"canonical_sha256":"626ba1d7aaf5394025db86056788597caa105a9ac892b09926bc374072c48d5d","source":{"kind":"arxiv","id":"2003.13593","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2003.13593","created_at":"2026-07-05T00:54:04Z"},{"alias_kind":"arxiv_version","alias_value":"2003.13593v2","created_at":"2026-07-05T00:54:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.13593","created_at":"2026-07-05T00:54:04Z"},{"alias_kind":"pith_short_12","alias_value":"MJV2DV5K6U4U","created_at":"2026-07-05T00:54:04Z"},{"alias_kind":"pith_short_16","alias_value":"MJV2DV5K6U4UAJO3","created_at":"2026-07-05T00:54:04Z"},{"alias_kind":"pith_short_8","alias_value":"MJV2DV5K","created_at":"2026-07-05T00:54:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:MJV2DV5K6U4UAJO3QYCWPCCZPS","target":"record","payload":{"canonical_record":{"source":{"id":"2003.13593","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2020-03-30T16:20:46Z","cross_cats_sorted":["cs.CV","eess.IV","stat.ML"],"title_canon_sha256":"e5386d4348f647384326c0c713a8a15ebdb572d8a1cec56cf7fdf18f384f8dc8","abstract_canon_sha256":"5489d0bf4a922e97d9b50c94137fcfd40b1b107aee1be9275f1719909b0ee3d4"},"schema_version":"1.0"},"canonical_sha256":"626ba1d7aaf5394025db86056788597caa105a9ac892b09926bc374072c48d5d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:54:04.786895Z","signature_b64":"u/Ocfao/xj+bZsfRK+St3p7GjPpK82xJ1nRBLlnFsApQFXxvd3Z1b9d6SFz4vcAKEnSbC3m0t5LeRV1BhnYBCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"626ba1d7aaf5394025db86056788597caa105a9ac892b09926bc374072c48d5d","last_reissued_at":"2026-07-05T00:54:04.786404Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:54:04.786404Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2003.13593","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":"2026-07-05T00:54:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"geHSJRSrE01MkgFQvwXGySbobHtspH5QJQ56O8GRCct4M+7ERJqshP1vqyyjprLF4HrFtm+5RO42lbmrq4f2Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T19:06:48.761785Z"},"content_sha256":"b6faf8e62375752c926d139adc6a84f8f2033223c9c047f7227f4cdf7cd6a8e3","schema_version":"1.0","event_id":"sha256:b6faf8e62375752c926d139adc6a84f8f2033223c9c047f7227f4cdf7cd6a8e3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:MJV2DV5K6U4UAJO3QYCWPCCZPS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"How Not to Give a FLOP: Combining Regularization and Pruning for Efficient Inference","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","eess.IV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Emily Wen, Roy Nehoran, Tai Vu","submitted_at":"2020-03-30T16:20:46Z","abstract_excerpt":"The challenge of speeding up deep learning models during the deployment phase has been a large, expensive bottleneck in the modern tech industry. In this paper, we examine the use of both regularization and pruning for reduced computational complexity and more efficient inference in Deep Neural Networks (DNNs). In particular, we apply mixup and cutout regularizations and soft filter pruning to the ResNet architecture, focusing on minimizing floating-point operations (FLOPs). Furthermore, by using regularization in conjunction with network pruning, we show that such a combination makes a substa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.13593","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/2003.13593/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":"2026-07-05T00:54:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZBRPqHuXieTz3ixmF2lgwe6UAoKNP6P7Ua/AB7KWtLP5NBZUTCSb7GLGpi/dJUj45ddgXS1VyuOS9ljg7tJtBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T19:06:48.762299Z"},"content_sha256":"c65700fc780d1ddea2bf490eeb5e276c67d1b3781f3756215a81bc7e4b520daa","schema_version":"1.0","event_id":"sha256:c65700fc780d1ddea2bf490eeb5e276c67d1b3781f3756215a81bc7e4b520daa"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MJV2DV5K6U4UAJO3QYCWPCCZPS/bundle.json","state_url":"https://pith.science/pith/MJV2DV5K6U4UAJO3QYCWPCCZPS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MJV2DV5K6U4UAJO3QYCWPCCZPS/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":"2026-08-09T19:06:48Z","links":{"resolver":"https://pith.science/pith/MJV2DV5K6U4UAJO3QYCWPCCZPS","bundle":"https://pith.science/pith/MJV2DV5K6U4UAJO3QYCWPCCZPS/bundle.json","state":"https://pith.science/pith/MJV2DV5K6U4UAJO3QYCWPCCZPS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MJV2DV5K6U4UAJO3QYCWPCCZPS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:MJV2DV5K6U4UAJO3QYCWPCCZPS","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":"5489d0bf4a922e97d9b50c94137fcfd40b1b107aee1be9275f1719909b0ee3d4","cross_cats_sorted":["cs.CV","eess.IV","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2020-03-30T16:20:46Z","title_canon_sha256":"e5386d4348f647384326c0c713a8a15ebdb572d8a1cec56cf7fdf18f384f8dc8"},"schema_version":"1.0","source":{"id":"2003.13593","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2003.13593","created_at":"2026-07-05T00:54:04Z"},{"alias_kind":"arxiv_version","alias_value":"2003.13593v2","created_at":"2026-07-05T00:54:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.13593","created_at":"2026-07-05T00:54:04Z"},{"alias_kind":"pith_short_12","alias_value":"MJV2DV5K6U4U","created_at":"2026-07-05T00:54:04Z"},{"alias_kind":"pith_short_16","alias_value":"MJV2DV5K6U4UAJO3","created_at":"2026-07-05T00:54:04Z"},{"alias_kind":"pith_short_8","alias_value":"MJV2DV5K","created_at":"2026-07-05T00:54:04Z"}],"graph_snapshots":[{"event_id":"sha256:c65700fc780d1ddea2bf490eeb5e276c67d1b3781f3756215a81bc7e4b520daa","target":"graph","created_at":"2026-07-05T00:54:04Z","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/2003.13593/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The challenge of speeding up deep learning models during the deployment phase has been a large, expensive bottleneck in the modern tech industry. In this paper, we examine the use of both regularization and pruning for reduced computational complexity and more efficient inference in Deep Neural Networks (DNNs). In particular, we apply mixup and cutout regularizations and soft filter pruning to the ResNet architecture, focusing on minimizing floating-point operations (FLOPs). Furthermore, by using regularization in conjunction with network pruning, we show that such a combination makes a substa","authors_text":"Emily Wen, Roy Nehoran, Tai Vu","cross_cats":["cs.CV","eess.IV","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2020-03-30T16:20:46Z","title":"How Not to Give a FLOP: Combining Regularization and Pruning for Efficient Inference"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.13593","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:b6faf8e62375752c926d139adc6a84f8f2033223c9c047f7227f4cdf7cd6a8e3","target":"record","created_at":"2026-07-05T00:54:04Z","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":"5489d0bf4a922e97d9b50c94137fcfd40b1b107aee1be9275f1719909b0ee3d4","cross_cats_sorted":["cs.CV","eess.IV","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2020-03-30T16:20:46Z","title_canon_sha256":"e5386d4348f647384326c0c713a8a15ebdb572d8a1cec56cf7fdf18f384f8dc8"},"schema_version":"1.0","source":{"id":"2003.13593","kind":"arxiv","version":2}},"canonical_sha256":"626ba1d7aaf5394025db86056788597caa105a9ac892b09926bc374072c48d5d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"626ba1d7aaf5394025db86056788597caa105a9ac892b09926bc374072c48d5d","first_computed_at":"2026-07-05T00:54:04.786404Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:54:04.786404Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"u/Ocfao/xj+bZsfRK+St3p7GjPpK82xJ1nRBLlnFsApQFXxvd3Z1b9d6SFz4vcAKEnSbC3m0t5LeRV1BhnYBCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T00:54:04.786895Z","signed_message":"canonical_sha256_bytes"},"source_id":"2003.13593","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b6faf8e62375752c926d139adc6a84f8f2033223c9c047f7227f4cdf7cd6a8e3","sha256:c65700fc780d1ddea2bf490eeb5e276c67d1b3781f3756215a81bc7e4b520daa"],"state_sha256":"0c02236a5d8e9ba81737bbbab336f09b7b4dbbc1621be7b83aec973966966a76"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iqSZWde/CWydXpLNEQeYPaoqdPtB3NZigGfR9TaGpOQDfYy+izumE+cDoaLSQxixmzQ+Wnhwi+abOhwW6MMfBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T19:06:48.767463Z","bundle_sha256":"ed571ee6158397250029dea78bd84d1c4819a1c2923c2a981c198a81f2ee7705"}}