{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:RHB4QHGBKXJT5XGSWN7W25XVIR","short_pith_number":"pith:RHB4QHGB","canonical_record":{"source":{"id":"1608.01409","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-08-04T01:16:39Z","cross_cats_sorted":[],"title_canon_sha256":"e4051827dc06a2b055fa8e7b522a973870d92c206abb2e93f43588c1ca1dbc2e","abstract_canon_sha256":"0555cf686f069d492eb55886e4c11e0695ff174e5aa98132f5d41032ac9565fb"},"schema_version":"1.0"},"canonical_sha256":"89c3c81cc155d33edcd2b37f6d76f54442f54a754ba9ecbe9cb2c0630edb9678","source":{"kind":"arxiv","id":"1608.01409","version":5},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1608.01409","created_at":"2026-05-18T00:39:13Z"},{"alias_kind":"arxiv_version","alias_value":"1608.01409v5","created_at":"2026-05-18T00:39:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1608.01409","created_at":"2026-05-18T00:39:13Z"},{"alias_kind":"pith_short_12","alias_value":"RHB4QHGBKXJT","created_at":"2026-05-18T12:30:41Z"},{"alias_kind":"pith_short_16","alias_value":"RHB4QHGBKXJT5XGS","created_at":"2026-05-18T12:30:41Z"},{"alias_kind":"pith_short_8","alias_value":"RHB4QHGB","created_at":"2026-05-18T12:30:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:RHB4QHGBKXJT5XGSWN7W25XVIR","target":"record","payload":{"canonical_record":{"source":{"id":"1608.01409","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-08-04T01:16:39Z","cross_cats_sorted":[],"title_canon_sha256":"e4051827dc06a2b055fa8e7b522a973870d92c206abb2e93f43588c1ca1dbc2e","abstract_canon_sha256":"0555cf686f069d492eb55886e4c11e0695ff174e5aa98132f5d41032ac9565fb"},"schema_version":"1.0"},"canonical_sha256":"89c3c81cc155d33edcd2b37f6d76f54442f54a754ba9ecbe9cb2c0630edb9678","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:39:13.312531Z","signature_b64":"1dRQCL6EzdwyS6OC8pwoRWyOL93jjrZcqNyYWinZko7h9b8Uy+8K3J/AEQom0z661Uwy4RsuSv0RUqn+hSW3Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"89c3c81cc155d33edcd2b37f6d76f54442f54a754ba9ecbe9cb2c0630edb9678","last_reissued_at":"2026-05-18T00:39:13.311860Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:39:13.311860Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1608.01409","source_version":5,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:39:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fNbXqskKeDpJUjYu4fEZTGbN1xNA3y0jAIKysrftuiEw63jYKjI9Po7+rzfnmbpQMYkOErBjYTzg3E8c0zShCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-22T05:16:55.906190Z"},"content_sha256":"5cb8ee298fb7f099492fe21393dabce582768140084f8dc50cc5596a8f773a52","schema_version":"1.0","event_id":"sha256:5cb8ee298fb7f099492fe21393dabce582768140084f8dc50cc5596a8f773a52"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:RHB4QHGBKXJT5XGSWN7W25XVIR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Faster CNNs with Direct Sparse Convolutions and Guided Pruning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hai Li, Jongsoo Park, Ping Tak Peter Tang, Pradeep Dubey, Sheng Li, Wei Wen, Yiran Chen","submitted_at":"2016-08-04T01:16:39Z","abstract_excerpt":"Phenomenally successful in practical inference problems, convolutional neural networks (CNN) are widely deployed in mobile devices, data centers, and even supercomputers. The number of parameters needed in CNNs, however, are often large and undesirable. Consequently, various methods have been developed to prune a CNN once it is trained. Nevertheless, the resulting CNNs offer limited benefits. While pruning the fully connected layers reduces a CNN's size considerably, it does not improve inference speed noticeably as the compute heavy parts lie in convolutions. Pruning CNNs in a way that increa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1608.01409","kind":"arxiv","version":5},"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":"2026-05-18T00:39:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4EKQXUAAQeMmDmL5sSTOTOoraR9V7wiv5JRYRlc12M4hh2eQ9RTW7O55xoXmO3/92ZqzoeamufieLFEPjHbYCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-22T05:16:55.906755Z"},"content_sha256":"e06f0bce60ae54f1a2dc791764f169c64f0b7acbe3770d1116cb9348efba4f3a","schema_version":"1.0","event_id":"sha256:e06f0bce60ae54f1a2dc791764f169c64f0b7acbe3770d1116cb9348efba4f3a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RHB4QHGBKXJT5XGSWN7W25XVIR/bundle.json","state_url":"https://pith.science/pith/RHB4QHGBKXJT5XGSWN7W25XVIR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RHB4QHGBKXJT5XGSWN7W25XVIR/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":"2026-05-22T05:16:55Z","links":{"resolver":"https://pith.science/pith/RHB4QHGBKXJT5XGSWN7W25XVIR","bundle":"https://pith.science/pith/RHB4QHGBKXJT5XGSWN7W25XVIR/bundle.json","state":"https://pith.science/pith/RHB4QHGBKXJT5XGSWN7W25XVIR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RHB4QHGBKXJT5XGSWN7W25XVIR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:RHB4QHGBKXJT5XGSWN7W25XVIR","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":"0555cf686f069d492eb55886e4c11e0695ff174e5aa98132f5d41032ac9565fb","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-08-04T01:16:39Z","title_canon_sha256":"e4051827dc06a2b055fa8e7b522a973870d92c206abb2e93f43588c1ca1dbc2e"},"schema_version":"1.0","source":{"id":"1608.01409","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1608.01409","created_at":"2026-05-18T00:39:13Z"},{"alias_kind":"arxiv_version","alias_value":"1608.01409v5","created_at":"2026-05-18T00:39:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1608.01409","created_at":"2026-05-18T00:39:13Z"},{"alias_kind":"pith_short_12","alias_value":"RHB4QHGBKXJT","created_at":"2026-05-18T12:30:41Z"},{"alias_kind":"pith_short_16","alias_value":"RHB4QHGBKXJT5XGS","created_at":"2026-05-18T12:30:41Z"},{"alias_kind":"pith_short_8","alias_value":"RHB4QHGB","created_at":"2026-05-18T12:30:41Z"}],"graph_snapshots":[{"event_id":"sha256:e06f0bce60ae54f1a2dc791764f169c64f0b7acbe3770d1116cb9348efba4f3a","target":"graph","created_at":"2026-05-18T00:39:13Z","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":"Phenomenally successful in practical inference problems, convolutional neural networks (CNN) are widely deployed in mobile devices, data centers, and even supercomputers. The number of parameters needed in CNNs, however, are often large and undesirable. Consequently, various methods have been developed to prune a CNN once it is trained. Nevertheless, the resulting CNNs offer limited benefits. While pruning the fully connected layers reduces a CNN's size considerably, it does not improve inference speed noticeably as the compute heavy parts lie in convolutions. Pruning CNNs in a way that increa","authors_text":"Hai Li, Jongsoo Park, Ping Tak Peter Tang, Pradeep Dubey, Sheng Li, Wei Wen, Yiran Chen","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-08-04T01:16:39Z","title":"Faster CNNs with Direct Sparse Convolutions and Guided Pruning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1608.01409","kind":"arxiv","version":5},"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":"sha256:5cb8ee298fb7f099492fe21393dabce582768140084f8dc50cc5596a8f773a52","target":"record","created_at":"2026-05-18T00:39:13Z","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":"0555cf686f069d492eb55886e4c11e0695ff174e5aa98132f5d41032ac9565fb","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-08-04T01:16:39Z","title_canon_sha256":"e4051827dc06a2b055fa8e7b522a973870d92c206abb2e93f43588c1ca1dbc2e"},"schema_version":"1.0","source":{"id":"1608.01409","kind":"arxiv","version":5}},"canonical_sha256":"89c3c81cc155d33edcd2b37f6d76f54442f54a754ba9ecbe9cb2c0630edb9678","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"89c3c81cc155d33edcd2b37f6d76f54442f54a754ba9ecbe9cb2c0630edb9678","first_computed_at":"2026-05-18T00:39:13.311860Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:39:13.311860Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1dRQCL6EzdwyS6OC8pwoRWyOL93jjrZcqNyYWinZko7h9b8Uy+8K3J/AEQom0z661Uwy4RsuSv0RUqn+hSW3Aw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:39:13.312531Z","signed_message":"canonical_sha256_bytes"},"source_id":"1608.01409","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5cb8ee298fb7f099492fe21393dabce582768140084f8dc50cc5596a8f773a52","sha256:e06f0bce60ae54f1a2dc791764f169c64f0b7acbe3770d1116cb9348efba4f3a"],"state_sha256":"d1240e099dba8822032136c5bce780404589d832cf3d54c35b3709671a87374a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nbjZQ3vG25dk6tFWghVIa1DlGp+t+Es8zbMDnIY38hB6YXwIDYlkfx975Ijkr5tyO5/9k3zzEwvSXvF/NNxqCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-22T05:16:55.909517Z","bundle_sha256":"3a255787068bf3617810f021cd2e6339c42827abcc9f3e4b9ad808c8c99b0eaf"}}