{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:ASYX34ZIFSYHO4E5WLOV3SK2R3","short_pith_number":"pith:ASYX34ZI","canonical_record":{"source":{"id":"1611.06440","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-11-19T22:48:30Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"13eaf976c1917a44eb427dcb873a19dfc1d3d14398d1168bbf43c02efe260624","abstract_canon_sha256":"63021476001690ddc5b75798101927745c786634499d181b132b847edbdf3c7c"},"schema_version":"1.0"},"canonical_sha256":"04b17df3282cb077709db2dd5dc95a8ee98431fa660568cfaa562cc1e927ccd8","source":{"kind":"arxiv","id":"1611.06440","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1611.06440","created_at":"2026-05-18T00:42:44Z"},{"alias_kind":"arxiv_version","alias_value":"1611.06440v2","created_at":"2026-05-18T00:42:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1611.06440","created_at":"2026-05-18T00:42:44Z"},{"alias_kind":"pith_short_12","alias_value":"ASYX34ZIFSYH","created_at":"2026-05-18T12:30:07Z"},{"alias_kind":"pith_short_16","alias_value":"ASYX34ZIFSYHO4E5","created_at":"2026-05-18T12:30:07Z"},{"alias_kind":"pith_short_8","alias_value":"ASYX34ZI","created_at":"2026-05-18T12:30:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:ASYX34ZIFSYHO4E5WLOV3SK2R3","target":"record","payload":{"canonical_record":{"source":{"id":"1611.06440","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-11-19T22:48:30Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"13eaf976c1917a44eb427dcb873a19dfc1d3d14398d1168bbf43c02efe260624","abstract_canon_sha256":"63021476001690ddc5b75798101927745c786634499d181b132b847edbdf3c7c"},"schema_version":"1.0"},"canonical_sha256":"04b17df3282cb077709db2dd5dc95a8ee98431fa660568cfaa562cc1e927ccd8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:42:44.068339Z","signature_b64":"bqdhbBROUctmbUUICIccGC3SkZEh8S4tAT8it1be+8fk7b2Aw4ypamv2KvIRM6i11jHueEgU9UkkqEq/7IYgAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"04b17df3282cb077709db2dd5dc95a8ee98431fa660568cfaa562cc1e927ccd8","last_reissued_at":"2026-05-18T00:42:44.067714Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:42:44.067714Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1611.06440","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":"2026-05-18T00:42:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5fx3XsbErScFOE4OLUtNvNb2znFe9DfZIcgqsNfb6qrMSs3RhFum0OwVs5DxbfydBomzb+qvG0uD69e6UdNGCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-22T00:40:39.275908Z"},"content_sha256":"23c38c41182e6f36d9a50eedbc8b24a7baaf4f6e4366b834a75dc8301076b0e4","schema_version":"1.0","event_id":"sha256:23c38c41182e6f36d9a50eedbc8b24a7baaf4f6e4366b834a75dc8301076b0e4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:ASYX34ZIFSYHO4E5WLOV3SK2R3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Pruning Convolutional Neural Networks for Resource Efficient Inference","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Jan Kautz, Pavlo Molchanov, Stephen Tyree, Tero Karras, Timo Aila","submitted_at":"2016-11-19T22:48:30Z","abstract_excerpt":"We propose a new formulation for pruning convolutional kernels in neural networks to enable efficient inference. We interleave greedy criteria-based pruning with fine-tuning by backpropagation - a computationally efficient procedure that maintains good generalization in the pruned network. We propose a new criterion based on Taylor expansion that approximates the change in the cost function induced by pruning network parameters. We focus on transfer learning, where large pretrained networks are adapted to specialized tasks. The proposed criterion demonstrates superior performance compared to o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1611.06440","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":""},"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":"2026-05-18T00:42:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mVZmnJAb/Q4jbdRJPkgexgcPSFqmq+wn3QgjdEgTFCk/9N7shFWq8ywIn6LgJzQw87KbIS6QdTZCKn83OsuuDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-22T00:40:39.276591Z"},"content_sha256":"11e59f180566742807545ad92fe81fb2fed6ead75f54979f5b2e3ba13b484125","schema_version":"1.0","event_id":"sha256:11e59f180566742807545ad92fe81fb2fed6ead75f54979f5b2e3ba13b484125"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ASYX34ZIFSYHO4E5WLOV3SK2R3/bundle.json","state_url":"https://pith.science/pith/ASYX34ZIFSYHO4E5WLOV3SK2R3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ASYX34ZIFSYHO4E5WLOV3SK2R3/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":"2026-05-22T00:40:39Z","links":{"resolver":"https://pith.science/pith/ASYX34ZIFSYHO4E5WLOV3SK2R3","bundle":"https://pith.science/pith/ASYX34ZIFSYHO4E5WLOV3SK2R3/bundle.json","state":"https://pith.science/pith/ASYX34ZIFSYHO4E5WLOV3SK2R3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ASYX34ZIFSYHO4E5WLOV3SK2R3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:ASYX34ZIFSYHO4E5WLOV3SK2R3","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":"63021476001690ddc5b75798101927745c786634499d181b132b847edbdf3c7c","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-11-19T22:48:30Z","title_canon_sha256":"13eaf976c1917a44eb427dcb873a19dfc1d3d14398d1168bbf43c02efe260624"},"schema_version":"1.0","source":{"id":"1611.06440","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1611.06440","created_at":"2026-05-18T00:42:44Z"},{"alias_kind":"arxiv_version","alias_value":"1611.06440v2","created_at":"2026-05-18T00:42:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1611.06440","created_at":"2026-05-18T00:42:44Z"},{"alias_kind":"pith_short_12","alias_value":"ASYX34ZIFSYH","created_at":"2026-05-18T12:30:07Z"},{"alias_kind":"pith_short_16","alias_value":"ASYX34ZIFSYHO4E5","created_at":"2026-05-18T12:30:07Z"},{"alias_kind":"pith_short_8","alias_value":"ASYX34ZI","created_at":"2026-05-18T12:30:07Z"}],"graph_snapshots":[{"event_id":"sha256:11e59f180566742807545ad92fe81fb2fed6ead75f54979f5b2e3ba13b484125","target":"graph","created_at":"2026-05-18T00:42:44Z","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":"We propose a new formulation for pruning convolutional kernels in neural networks to enable efficient inference. We interleave greedy criteria-based pruning with fine-tuning by backpropagation - a computationally efficient procedure that maintains good generalization in the pruned network. We propose a new criterion based on Taylor expansion that approximates the change in the cost function induced by pruning network parameters. We focus on transfer learning, where large pretrained networks are adapted to specialized tasks. The proposed criterion demonstrates superior performance compared to o","authors_text":"Jan Kautz, Pavlo Molchanov, Stephen Tyree, Tero Karras, Timo Aila","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-11-19T22:48:30Z","title":"Pruning Convolutional Neural Networks for Resource Efficient Inference"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1611.06440","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":"sha256:23c38c41182e6f36d9a50eedbc8b24a7baaf4f6e4366b834a75dc8301076b0e4","target":"record","created_at":"2026-05-18T00:42:44Z","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":"63021476001690ddc5b75798101927745c786634499d181b132b847edbdf3c7c","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-11-19T22:48:30Z","title_canon_sha256":"13eaf976c1917a44eb427dcb873a19dfc1d3d14398d1168bbf43c02efe260624"},"schema_version":"1.0","source":{"id":"1611.06440","kind":"arxiv","version":2}},"canonical_sha256":"04b17df3282cb077709db2dd5dc95a8ee98431fa660568cfaa562cc1e927ccd8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"04b17df3282cb077709db2dd5dc95a8ee98431fa660568cfaa562cc1e927ccd8","first_computed_at":"2026-05-18T00:42:44.067714Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:42:44.067714Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bqdhbBROUctmbUUICIccGC3SkZEh8S4tAT8it1be+8fk7b2Aw4ypamv2KvIRM6i11jHueEgU9UkkqEq/7IYgAQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:42:44.068339Z","signed_message":"canonical_sha256_bytes"},"source_id":"1611.06440","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:23c38c41182e6f36d9a50eedbc8b24a7baaf4f6e4366b834a75dc8301076b0e4","sha256:11e59f180566742807545ad92fe81fb2fed6ead75f54979f5b2e3ba13b484125"],"state_sha256":"56455df61013404382ad73bf0197642367ed9d380f0f40254b98116a43333546"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vmYTQEG6Wp34XKAE2batmRwLmMuAnC0ImGbqQbz53ddkQ2hQoxRhW4yNaeTbq0ym187WLkuHAPq5BQ5VKp/WAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-22T00:40:39.280261Z","bundle_sha256":"8d1be0c11a4163508b76f0b4112d81884d73fff582386d17f4fce5353eab5e53"}}