{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:ZNDHJWPSZJCX5VUGRGCONYI355","short_pith_number":"pith:ZNDHJWPS","canonical_record":{"source":{"id":"1906.10771","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-25T22:20:16Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"b855b640123dc0d4cb08143074e1c043f0273945fefefe9a56653b4577fcbd10","abstract_canon_sha256":"bf2b7b1ba9deaba099daea8c38f10b0f9f1d2aa7264aa7889e90d98c2c73b91f"},"schema_version":"1.0"},"canonical_sha256":"cb4674d9f2ca457ed6868984e6e11bef7ff348748a77ff267e1f8c86d43a9fc2","source":{"kind":"arxiv","id":"1906.10771","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.10771","created_at":"2026-05-17T23:42:14Z"},{"alias_kind":"arxiv_version","alias_value":"1906.10771v1","created_at":"2026-05-17T23:42:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.10771","created_at":"2026-05-17T23:42:14Z"},{"alias_kind":"pith_short_12","alias_value":"ZNDHJWPSZJCX","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_16","alias_value":"ZNDHJWPSZJCX5VUG","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_8","alias_value":"ZNDHJWPS","created_at":"2026-05-18T12:33:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:ZNDHJWPSZJCX5VUGRGCONYI355","target":"record","payload":{"canonical_record":{"source":{"id":"1906.10771","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-25T22:20:16Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"b855b640123dc0d4cb08143074e1c043f0273945fefefe9a56653b4577fcbd10","abstract_canon_sha256":"bf2b7b1ba9deaba099daea8c38f10b0f9f1d2aa7264aa7889e90d98c2c73b91f"},"schema_version":"1.0"},"canonical_sha256":"cb4674d9f2ca457ed6868984e6e11bef7ff348748a77ff267e1f8c86d43a9fc2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:42:14.826386Z","signature_b64":"uv8QqdU+7wK/YTutEDUTpKanud++JXJT3LnLaK/HxB7goDKWmwhaJCpernk2L2iuIILIYc2U3UmyrnkNa1HlCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cb4674d9f2ca457ed6868984e6e11bef7ff348748a77ff267e1f8c86d43a9fc2","last_reissued_at":"2026-05-17T23:42:14.825509Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:42:14.825509Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1906.10771","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":"2026-05-17T23:42:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"icBpl4PzBD7KejgwNoR/trsqMLA2MqpJ8DM79wkpVOSrcqmVl4lLgVf/HG9thVYTEhtAQ9w6tl4jblXDwwHoBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T13:50:16.742008Z"},"content_sha256":"237c61fc7545f0fd374758d3eefba4bff088b9c0ce4ae03be909d552e6eeb2d7","schema_version":"1.0","event_id":"sha256:237c61fc7545f0fd374758d3eefba4bff088b9c0ce4ae03be909d552e6eeb2d7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:ZNDHJWPSZJCX5VUGRGCONYI355","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Importance Estimation for Neural Network Pruning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Arun Mallya, Iuri Frosio, Jan Kautz, Pavlo Molchanov, Stephen Tyree","submitted_at":"2019-06-25T22:20:16Z","abstract_excerpt":"Structural pruning of neural network parameters reduces computation, energy, and memory transfer costs during inference. We propose a novel method that estimates the contribution of a neuron (filter) to the final loss and iteratively removes those with smaller scores. We describe two variations of our method using the first and second-order Taylor expansions to approximate a filter's contribution. Both methods scale consistently across any network layer without requiring per-layer sensitivity analysis and can be applied to any kind of layer, including skip connections. For modern networks trai"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.10771","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":"2026-05-17T23:42:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IiX80OlFfCoFjWkFgEnUCp+Gnh9jWMzg8WCKCFR7yykn0ip6Qkr4hwcH3lowqKuijYaGCFbY5Ui7QGg0Nr58DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T13:50:16.742714Z"},"content_sha256":"eb0a56db17e542aad82e562b6905624c00855c7d5e208d841a060720c2da3cec","schema_version":"1.0","event_id":"sha256:eb0a56db17e542aad82e562b6905624c00855c7d5e208d841a060720c2da3cec"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZNDHJWPSZJCX5VUGRGCONYI355/bundle.json","state_url":"https://pith.science/pith/ZNDHJWPSZJCX5VUGRGCONYI355/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZNDHJWPSZJCX5VUGRGCONYI355/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":"2026-06-06T13:50:16Z","links":{"resolver":"https://pith.science/pith/ZNDHJWPSZJCX5VUGRGCONYI355","bundle":"https://pith.science/pith/ZNDHJWPSZJCX5VUGRGCONYI355/bundle.json","state":"https://pith.science/pith/ZNDHJWPSZJCX5VUGRGCONYI355/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZNDHJWPSZJCX5VUGRGCONYI355/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:ZNDHJWPSZJCX5VUGRGCONYI355","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":"bf2b7b1ba9deaba099daea8c38f10b0f9f1d2aa7264aa7889e90d98c2c73b91f","cross_cats_sorted":["cs.CV","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-25T22:20:16Z","title_canon_sha256":"b855b640123dc0d4cb08143074e1c043f0273945fefefe9a56653b4577fcbd10"},"schema_version":"1.0","source":{"id":"1906.10771","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.10771","created_at":"2026-05-17T23:42:14Z"},{"alias_kind":"arxiv_version","alias_value":"1906.10771v1","created_at":"2026-05-17T23:42:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.10771","created_at":"2026-05-17T23:42:14Z"},{"alias_kind":"pith_short_12","alias_value":"ZNDHJWPSZJCX","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_16","alias_value":"ZNDHJWPSZJCX5VUG","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_8","alias_value":"ZNDHJWPS","created_at":"2026-05-18T12:33:33Z"}],"graph_snapshots":[{"event_id":"sha256:eb0a56db17e542aad82e562b6905624c00855c7d5e208d841a060720c2da3cec","target":"graph","created_at":"2026-05-17T23:42:14Z","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":"Structural pruning of neural network parameters reduces computation, energy, and memory transfer costs during inference. We propose a novel method that estimates the contribution of a neuron (filter) to the final loss and iteratively removes those with smaller scores. We describe two variations of our method using the first and second-order Taylor expansions to approximate a filter's contribution. Both methods scale consistently across any network layer without requiring per-layer sensitivity analysis and can be applied to any kind of layer, including skip connections. For modern networks trai","authors_text":"Arun Mallya, Iuri Frosio, Jan Kautz, Pavlo Molchanov, Stephen Tyree","cross_cats":["cs.CV","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-25T22:20:16Z","title":"Importance Estimation for Neural Network Pruning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.10771","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":"sha256:237c61fc7545f0fd374758d3eefba4bff088b9c0ce4ae03be909d552e6eeb2d7","target":"record","created_at":"2026-05-17T23:42:14Z","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":"bf2b7b1ba9deaba099daea8c38f10b0f9f1d2aa7264aa7889e90d98c2c73b91f","cross_cats_sorted":["cs.CV","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-25T22:20:16Z","title_canon_sha256":"b855b640123dc0d4cb08143074e1c043f0273945fefefe9a56653b4577fcbd10"},"schema_version":"1.0","source":{"id":"1906.10771","kind":"arxiv","version":1}},"canonical_sha256":"cb4674d9f2ca457ed6868984e6e11bef7ff348748a77ff267e1f8c86d43a9fc2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cb4674d9f2ca457ed6868984e6e11bef7ff348748a77ff267e1f8c86d43a9fc2","first_computed_at":"2026-05-17T23:42:14.825509Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:42:14.825509Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uv8QqdU+7wK/YTutEDUTpKanud++JXJT3LnLaK/HxB7goDKWmwhaJCpernk2L2iuIILIYc2U3UmyrnkNa1HlCg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:42:14.826386Z","signed_message":"canonical_sha256_bytes"},"source_id":"1906.10771","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:237c61fc7545f0fd374758d3eefba4bff088b9c0ce4ae03be909d552e6eeb2d7","sha256:eb0a56db17e542aad82e562b6905624c00855c7d5e208d841a060720c2da3cec"],"state_sha256":"7c740d5d7b6b8c5181e847b42cc9e3249842137959ff7a806371b2389155cea4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ogFiozinOkhj6srGLm5i4VvA8b/FsqQLPVmGnXOfiBopisunfkbHek6BRiG1Mx7XI8ajsQWScTBK/g912OAUCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-06T13:50:16.747206Z","bundle_sha256":"ed721f28c31d1a173f691f68b384d03f9381b12f928a37f83dffbf1cc021b736"}}