{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:I2SOXMXRDDLLHCTP3Z3LDOX3RY","short_pith_number":"pith:I2SOXMXR","canonical_record":{"source":{"id":"1901.02132","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-01-08T02:17:44Z","cross_cats_sorted":["cs.LG","cs.NE"],"title_canon_sha256":"7cf04d09b5a6dd7cecae3f0caf57af5350d4d909b28d27803e59de497549604a","abstract_canon_sha256":"f9f1f43338bc3709f818c351966359398c616cdfde279bc59425c6cb8dd05be9"},"schema_version":"1.0"},"canonical_sha256":"46a4ebb2f118d6b38a6fde76b1bafb8e14bdd46359efa62261ce4316c1914ce4","source":{"kind":"arxiv","id":"1901.02132","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1901.02132","created_at":"2026-05-17T23:56:43Z"},{"alias_kind":"arxiv_version","alias_value":"1901.02132v1","created_at":"2026-05-17T23:56:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.02132","created_at":"2026-05-17T23:56:43Z"},{"alias_kind":"pith_short_12","alias_value":"I2SOXMXRDDLL","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_16","alias_value":"I2SOXMXRDDLLHCTP","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_8","alias_value":"I2SOXMXR","created_at":"2026-05-18T12:33:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:I2SOXMXRDDLLHCTP3Z3LDOX3RY","target":"record","payload":{"canonical_record":{"source":{"id":"1901.02132","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-01-08T02:17:44Z","cross_cats_sorted":["cs.LG","cs.NE"],"title_canon_sha256":"7cf04d09b5a6dd7cecae3f0caf57af5350d4d909b28d27803e59de497549604a","abstract_canon_sha256":"f9f1f43338bc3709f818c351966359398c616cdfde279bc59425c6cb8dd05be9"},"schema_version":"1.0"},"canonical_sha256":"46a4ebb2f118d6b38a6fde76b1bafb8e14bdd46359efa62261ce4316c1914ce4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:56:43.941239Z","signature_b64":"qc0wMVrzSMXdnwOwlLrP2w6RAW2ULcHW8pLgCkZ6JO4AspbFz/YaFjwRvDps8edQvwQrJXxuLqg1M5+OUSbqCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"46a4ebb2f118d6b38a6fde76b1bafb8e14bdd46359efa62261ce4316c1914ce4","last_reissued_at":"2026-05-17T23:56:43.940650Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:56:43.940650Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1901.02132","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:56:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XYVkQ5PmA/iK6QVOkhnD2s9nxmeuVgO4gaA6nkUDgBGGM3mX+N02UARNYFBJInxM2oWS3Eer7+fcyEYtZu6YDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T08:28:37.896570Z"},"content_sha256":"d80117e80058ee4321d70020ecc846f1d926f53b6ae0b36fa09261a09ef339ed","schema_version":"1.0","event_id":"sha256:d80117e80058ee4321d70020ecc846f1d926f53b6ae0b36fa09261a09ef339ed"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:I2SOXMXRDDLLHCTP3Z3LDOX3RY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Spatial-Winograd Pruning Enabling Sparse Winograd Convolution","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NE"],"primary_cat":"cs.CV","authors_text":"Jiecao Yu, Jongsoo Park, Maxim Naumov","submitted_at":"2019-01-08T02:17:44Z","abstract_excerpt":"Deep convolutional neural networks (CNNs) are deployed in various applications but demand immense computational requirements. Pruning techniques and Winograd convolution are two typical methods to reduce the CNN computation. However, they cannot be directly combined because Winograd transformation fills in the sparsity resulting from pruning. Li et al. (2017) propose sparse Winograd convolution in which weights are directly pruned in the Winograd domain, but this technique is not very practical because Winograd-domain retraining requires low learning rates and hence significantly longer traini"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.02132","kind":"arxiv","version":1},"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":"2026-05-17T23:56:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KYY6ofkleuNrk1WyzCjjf9m2j8bJWQhuN8rc6IKsc2nheFGoSeObe4y1k972ADmBvFc/ukTRL8du486cAZ2yAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T08:28:37.897227Z"},"content_sha256":"51c95d070096d8d67e60a3d0a8a0a530e07e95ccc38979c1d4c01901f6e2fbd8","schema_version":"1.0","event_id":"sha256:51c95d070096d8d67e60a3d0a8a0a530e07e95ccc38979c1d4c01901f6e2fbd8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/I2SOXMXRDDLLHCTP3Z3LDOX3RY/bundle.json","state_url":"https://pith.science/pith/I2SOXMXRDDLLHCTP3Z3LDOX3RY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/I2SOXMXRDDLLHCTP3Z3LDOX3RY/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":"2026-05-26T08:28:37Z","links":{"resolver":"https://pith.science/pith/I2SOXMXRDDLLHCTP3Z3LDOX3RY","bundle":"https://pith.science/pith/I2SOXMXRDDLLHCTP3Z3LDOX3RY/bundle.json","state":"https://pith.science/pith/I2SOXMXRDDLLHCTP3Z3LDOX3RY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/I2SOXMXRDDLLHCTP3Z3LDOX3RY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:I2SOXMXRDDLLHCTP3Z3LDOX3RY","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":"f9f1f43338bc3709f818c351966359398c616cdfde279bc59425c6cb8dd05be9","cross_cats_sorted":["cs.LG","cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-01-08T02:17:44Z","title_canon_sha256":"7cf04d09b5a6dd7cecae3f0caf57af5350d4d909b28d27803e59de497549604a"},"schema_version":"1.0","source":{"id":"1901.02132","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1901.02132","created_at":"2026-05-17T23:56:43Z"},{"alias_kind":"arxiv_version","alias_value":"1901.02132v1","created_at":"2026-05-17T23:56:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.02132","created_at":"2026-05-17T23:56:43Z"},{"alias_kind":"pith_short_12","alias_value":"I2SOXMXRDDLL","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_16","alias_value":"I2SOXMXRDDLLHCTP","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_8","alias_value":"I2SOXMXR","created_at":"2026-05-18T12:33:18Z"}],"graph_snapshots":[{"event_id":"sha256:51c95d070096d8d67e60a3d0a8a0a530e07e95ccc38979c1d4c01901f6e2fbd8","target":"graph","created_at":"2026-05-17T23:56:43Z","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":"Deep convolutional neural networks (CNNs) are deployed in various applications but demand immense computational requirements. Pruning techniques and Winograd convolution are two typical methods to reduce the CNN computation. However, they cannot be directly combined because Winograd transformation fills in the sparsity resulting from pruning. Li et al. (2017) propose sparse Winograd convolution in which weights are directly pruned in the Winograd domain, but this technique is not very practical because Winograd-domain retraining requires low learning rates and hence significantly longer traini","authors_text":"Jiecao Yu, Jongsoo Park, Maxim Naumov","cross_cats":["cs.LG","cs.NE"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-01-08T02:17:44Z","title":"Spatial-Winograd Pruning Enabling Sparse Winograd Convolution"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.02132","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:d80117e80058ee4321d70020ecc846f1d926f53b6ae0b36fa09261a09ef339ed","target":"record","created_at":"2026-05-17T23:56:43Z","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":"f9f1f43338bc3709f818c351966359398c616cdfde279bc59425c6cb8dd05be9","cross_cats_sorted":["cs.LG","cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-01-08T02:17:44Z","title_canon_sha256":"7cf04d09b5a6dd7cecae3f0caf57af5350d4d909b28d27803e59de497549604a"},"schema_version":"1.0","source":{"id":"1901.02132","kind":"arxiv","version":1}},"canonical_sha256":"46a4ebb2f118d6b38a6fde76b1bafb8e14bdd46359efa62261ce4316c1914ce4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"46a4ebb2f118d6b38a6fde76b1bafb8e14bdd46359efa62261ce4316c1914ce4","first_computed_at":"2026-05-17T23:56:43.940650Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:56:43.940650Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qc0wMVrzSMXdnwOwlLrP2w6RAW2ULcHW8pLgCkZ6JO4AspbFz/YaFjwRvDps8edQvwQrJXxuLqg1M5+OUSbqCw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:56:43.941239Z","signed_message":"canonical_sha256_bytes"},"source_id":"1901.02132","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d80117e80058ee4321d70020ecc846f1d926f53b6ae0b36fa09261a09ef339ed","sha256:51c95d070096d8d67e60a3d0a8a0a530e07e95ccc38979c1d4c01901f6e2fbd8"],"state_sha256":"321e21cb43a9261deedd07f153e2b9646d9c86a6866d16897f7c0478c39bb915"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tmm3fg5+JweldWqe7hU2qX3EShCAXifnAmzxjin73cmu3a1r+NacIxxQEbAvv6k5FDRh3H0B4mXC+MDe2BaLDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T08:28:37.901076Z","bundle_sha256":"a6b55e96eb251f10f467b83d8fe1e6e0c7c39287541d3bcb96c91b5b4a213d7d"}}