{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2014:5VNVCFMGQR4IVNRUFNQTGVX564","short_pith_number":"pith:5VNVCFMG","canonical_record":{"source":{"id":"1411.4229","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2014-11-16T08:37:25Z","cross_cats_sorted":[],"title_canon_sha256":"183169acb00e9f980937dce55baa49560d963b2184b8358b2c8cd1f27afcf30c","abstract_canon_sha256":"325d30214f5b8af5987656b2e0ca33b1477ae84a13ad4e6d81ed2ad1a01ba68b"},"schema_version":"1.0"},"canonical_sha256":"ed5b51158684788ab6342b613356fdf711d738d24c455b9459043cf1353fbc9a","source":{"kind":"arxiv","id":"1411.4229","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1411.4229","created_at":"2026-05-18T02:35:46Z"},{"alias_kind":"arxiv_version","alias_value":"1411.4229v1","created_at":"2026-05-18T02:35:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1411.4229","created_at":"2026-05-18T02:35:46Z"},{"alias_kind":"pith_short_12","alias_value":"5VNVCFMGQR4I","created_at":"2026-05-18T12:28:16Z"},{"alias_kind":"pith_short_16","alias_value":"5VNVCFMGQR4IVNRU","created_at":"2026-05-18T12:28:16Z"},{"alias_kind":"pith_short_8","alias_value":"5VNVCFMG","created_at":"2026-05-18T12:28:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2014:5VNVCFMGQR4IVNRUFNQTGVX564","target":"record","payload":{"canonical_record":{"source":{"id":"1411.4229","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2014-11-16T08:37:25Z","cross_cats_sorted":[],"title_canon_sha256":"183169acb00e9f980937dce55baa49560d963b2184b8358b2c8cd1f27afcf30c","abstract_canon_sha256":"325d30214f5b8af5987656b2e0ca33b1477ae84a13ad4e6d81ed2ad1a01ba68b"},"schema_version":"1.0"},"canonical_sha256":"ed5b51158684788ab6342b613356fdf711d738d24c455b9459043cf1353fbc9a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:35:46.163858Z","signature_b64":"M982HXEdxS/ql7yRezMk/w6jwviKKkCV2B0kIUPKFiPq9INBljInCjJbacAbX9MssnwiqPnqM8RT4DmsOW7PBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ed5b51158684788ab6342b613356fdf711d738d24c455b9459043cf1353fbc9a","last_reissued_at":"2026-05-18T02:35:46.163246Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:35:46.163246Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1411.4229","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":"2026-05-18T02:35:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iEDOMzypME1yA2x3/hI2Mlk+gxtlxzaB43ZnxGUwgHb+9g02fxI+icYm8VMn9lvLzOOQ08VTuXCSpLss0l4SBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T12:43:12.476701Z"},"content_sha256":"fc3cc5311033b9a3f5409259f9c5bcbf0d5b1a704075fe15938ef1fd119c9a52","schema_version":"1.0","event_id":"sha256:fc3cc5311033b9a3f5409259f9c5bcbf0d5b1a704075fe15938ef1fd119c9a52"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2014:5VNVCFMGQR4IVNRUFNQTGVX564","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Efficient and Accurate Approximations of Nonlinear Convolutional Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jianhua Zou, Jian Sun, Kaiming He, Xiang Ming, Xiangyu Zhang","submitted_at":"2014-11-16T08:37:25Z","abstract_excerpt":"This paper aims to accelerate the test-time computation of deep convolutional neural networks (CNNs). Unlike existing methods that are designed for approximating linear filters or linear responses, our method takes the nonlinear units into account. We minimize the reconstruction error of the nonlinear responses, subject to a low-rank constraint which helps to reduce the complexity of filters. We develop an effective solution to this constrained nonlinear optimization problem. An algorithm is also presented for reducing the accumulated error when multiple layers are approximated. A whole-model "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1411.4229","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":"2026-05-18T02:35:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4eleOsh/Rep1yxugQ9ITen/F7CqCTugMfM5PYQkFZVJj1NYeM55FfFKVkEBUUisDc7PW7aKa4oQwSHMv6bLCBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T12:43:12.477047Z"},"content_sha256":"076f57903ab444f24544852d442b87bc42d614659dabb9f537a0e13c2c057302","schema_version":"1.0","event_id":"sha256:076f57903ab444f24544852d442b87bc42d614659dabb9f537a0e13c2c057302"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5VNVCFMGQR4IVNRUFNQTGVX564/bundle.json","state_url":"https://pith.science/pith/5VNVCFMGQR4IVNRUFNQTGVX564/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5VNVCFMGQR4IVNRUFNQTGVX564/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":"2026-06-04T12:43:12Z","links":{"resolver":"https://pith.science/pith/5VNVCFMGQR4IVNRUFNQTGVX564","bundle":"https://pith.science/pith/5VNVCFMGQR4IVNRUFNQTGVX564/bundle.json","state":"https://pith.science/pith/5VNVCFMGQR4IVNRUFNQTGVX564/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5VNVCFMGQR4IVNRUFNQTGVX564/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2014:5VNVCFMGQR4IVNRUFNQTGVX564","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":"325d30214f5b8af5987656b2e0ca33b1477ae84a13ad4e6d81ed2ad1a01ba68b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2014-11-16T08:37:25Z","title_canon_sha256":"183169acb00e9f980937dce55baa49560d963b2184b8358b2c8cd1f27afcf30c"},"schema_version":"1.0","source":{"id":"1411.4229","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1411.4229","created_at":"2026-05-18T02:35:46Z"},{"alias_kind":"arxiv_version","alias_value":"1411.4229v1","created_at":"2026-05-18T02:35:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1411.4229","created_at":"2026-05-18T02:35:46Z"},{"alias_kind":"pith_short_12","alias_value":"5VNVCFMGQR4I","created_at":"2026-05-18T12:28:16Z"},{"alias_kind":"pith_short_16","alias_value":"5VNVCFMGQR4IVNRU","created_at":"2026-05-18T12:28:16Z"},{"alias_kind":"pith_short_8","alias_value":"5VNVCFMG","created_at":"2026-05-18T12:28:16Z"}],"graph_snapshots":[{"event_id":"sha256:076f57903ab444f24544852d442b87bc42d614659dabb9f537a0e13c2c057302","target":"graph","created_at":"2026-05-18T02:35:46Z","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":"This paper aims to accelerate the test-time computation of deep convolutional neural networks (CNNs). Unlike existing methods that are designed for approximating linear filters or linear responses, our method takes the nonlinear units into account. We minimize the reconstruction error of the nonlinear responses, subject to a low-rank constraint which helps to reduce the complexity of filters. We develop an effective solution to this constrained nonlinear optimization problem. An algorithm is also presented for reducing the accumulated error when multiple layers are approximated. A whole-model ","authors_text":"Jianhua Zou, Jian Sun, Kaiming He, Xiang Ming, Xiangyu Zhang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2014-11-16T08:37:25Z","title":"Efficient and Accurate Approximations of Nonlinear Convolutional Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1411.4229","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:fc3cc5311033b9a3f5409259f9c5bcbf0d5b1a704075fe15938ef1fd119c9a52","target":"record","created_at":"2026-05-18T02:35:46Z","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":"325d30214f5b8af5987656b2e0ca33b1477ae84a13ad4e6d81ed2ad1a01ba68b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2014-11-16T08:37:25Z","title_canon_sha256":"183169acb00e9f980937dce55baa49560d963b2184b8358b2c8cd1f27afcf30c"},"schema_version":"1.0","source":{"id":"1411.4229","kind":"arxiv","version":1}},"canonical_sha256":"ed5b51158684788ab6342b613356fdf711d738d24c455b9459043cf1353fbc9a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ed5b51158684788ab6342b613356fdf711d738d24c455b9459043cf1353fbc9a","first_computed_at":"2026-05-18T02:35:46.163246Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T02:35:46.163246Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"M982HXEdxS/ql7yRezMk/w6jwviKKkCV2B0kIUPKFiPq9INBljInCjJbacAbX9MssnwiqPnqM8RT4DmsOW7PBg==","signature_status":"signed_v1","signed_at":"2026-05-18T02:35:46.163858Z","signed_message":"canonical_sha256_bytes"},"source_id":"1411.4229","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fc3cc5311033b9a3f5409259f9c5bcbf0d5b1a704075fe15938ef1fd119c9a52","sha256:076f57903ab444f24544852d442b87bc42d614659dabb9f537a0e13c2c057302"],"state_sha256":"ab1f703eeec8e41b788ee0b280f79c0e5b7ffad258e522c39baa6666efdc8eae"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QTpRGXr+dz+9WlxKpcNhnOkzHunVG8orz+9fTb7+lKYbkW6rZ7GsAinWZYT7jRYn3cgPdMzEtgF+FhilbB8+BQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-04T12:43:12.479072Z","bundle_sha256":"26029d196cca54067be635e0ad443b10de096096345b009a432b29a7d6833043"}}