{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:ZHQ43C4MCYOPB6GZ4D37O2LRFI","short_pith_number":"pith:ZHQ43C4M","canonical_record":{"source":{"id":"1901.02757","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-09T14:18:47Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"9b35c110b7179decce96b9030aa450ffe41dfd23ede077fcee2f373541369ef9","abstract_canon_sha256":"eda7314d80531d8c906bc5acc631b0a877c86aa9ac9020e03b57af2aa3978091"},"schema_version":"1.0"},"canonical_sha256":"c9e1cd8b8c161cf0f8d9e0f7f769712a1e1a87b43a234a0e988e795d24bc61f1","source":{"kind":"arxiv","id":"1901.02757","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1901.02757","created_at":"2026-05-17T23:56:39Z"},{"alias_kind":"arxiv_version","alias_value":"1901.02757v1","created_at":"2026-05-17T23:56:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.02757","created_at":"2026-05-17T23:56:39Z"},{"alias_kind":"pith_short_12","alias_value":"ZHQ43C4MCYOP","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_16","alias_value":"ZHQ43C4MCYOPB6GZ","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_8","alias_value":"ZHQ43C4M","created_at":"2026-05-18T12:33:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:ZHQ43C4MCYOPB6GZ4D37O2LRFI","target":"record","payload":{"canonical_record":{"source":{"id":"1901.02757","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-09T14:18:47Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"9b35c110b7179decce96b9030aa450ffe41dfd23ede077fcee2f373541369ef9","abstract_canon_sha256":"eda7314d80531d8c906bc5acc631b0a877c86aa9ac9020e03b57af2aa3978091"},"schema_version":"1.0"},"canonical_sha256":"c9e1cd8b8c161cf0f8d9e0f7f769712a1e1a87b43a234a0e988e795d24bc61f1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:56:39.520667Z","signature_b64":"mQrumpdoO8fXMwAVIJr3Fp8Vzl2JrY4OBUuEvz4gb40sdnZClr2UhOAsdNNDsl8Sl/HOg8zHLWmgVWAMGNsADw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c9e1cd8b8c161cf0f8d9e0f7f769712a1e1a87b43a234a0e988e795d24bc61f1","last_reissued_at":"2026-05-17T23:56:39.520131Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:56:39.520131Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1901.02757","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":"2026-05-17T23:56:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Lr4eWwL/zhjY6YWuD/vfGtGgOj0bI8ir+cAI89eGLR4+hhYhPedRW7T3iIPHwp3YQNd4oU3Rgquwu0HyY4B6Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-29T20:56:40.750801Z"},"content_sha256":"4d014fa9547556c0ff81ef3d4d88d6203234708c9f0bbab0faf17c75a079a450","schema_version":"1.0","event_id":"sha256:4d014fa9547556c0ff81ef3d4d88d6203234708c9f0bbab0faf17c75a079a450"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:ZHQ43C4MCYOPB6GZ4D37O2LRFI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"How Compact?: Assessing Compactness of Representations through Layer-Wise Pruning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Hyun-Joo Jung, Jaedeok Kim, Yoonsuck Choe","submitted_at":"2019-01-09T14:18:47Z","abstract_excerpt":"Various forms of representations may arise in the many layers embedded in deep neural networks (DNNs). Of these, where can we find the most compact representation? We propose to use a pruning framework to answer this question: How compact can each layer be compressed, without losing performance? Most of the existing DNN compression methods do not consider the relative compressibility of the individual layers. They uniformly apply a single target sparsity to all layers or adapt layer sparsity using heuristics and additional training. We propose a principled method that automatically determines "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.02757","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":"2026-05-17T23:56:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ogO3gc/C7iqNATe9Rvl/vbAadnJgSLoynrDrGpUb26rIfHXm10JH8hvDYhwWf11OIIBRVAuB8/bMRUGhNeqECA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-29T20:56:40.751144Z"},"content_sha256":"d3d5d7889baefa355a150579306e4ec432ce1d8dc5490cb228c5208b055e701c","schema_version":"1.0","event_id":"sha256:d3d5d7889baefa355a150579306e4ec432ce1d8dc5490cb228c5208b055e701c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZHQ43C4MCYOPB6GZ4D37O2LRFI/bundle.json","state_url":"https://pith.science/pith/ZHQ43C4MCYOPB6GZ4D37O2LRFI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZHQ43C4MCYOPB6GZ4D37O2LRFI/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":"2026-06-29T20:56:40Z","links":{"resolver":"https://pith.science/pith/ZHQ43C4MCYOPB6GZ4D37O2LRFI","bundle":"https://pith.science/pith/ZHQ43C4MCYOPB6GZ4D37O2LRFI/bundle.json","state":"https://pith.science/pith/ZHQ43C4MCYOPB6GZ4D37O2LRFI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZHQ43C4MCYOPB6GZ4D37O2LRFI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:ZHQ43C4MCYOPB6GZ4D37O2LRFI","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":"eda7314d80531d8c906bc5acc631b0a877c86aa9ac9020e03b57af2aa3978091","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-09T14:18:47Z","title_canon_sha256":"9b35c110b7179decce96b9030aa450ffe41dfd23ede077fcee2f373541369ef9"},"schema_version":"1.0","source":{"id":"1901.02757","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1901.02757","created_at":"2026-05-17T23:56:39Z"},{"alias_kind":"arxiv_version","alias_value":"1901.02757v1","created_at":"2026-05-17T23:56:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.02757","created_at":"2026-05-17T23:56:39Z"},{"alias_kind":"pith_short_12","alias_value":"ZHQ43C4MCYOP","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_16","alias_value":"ZHQ43C4MCYOPB6GZ","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_8","alias_value":"ZHQ43C4M","created_at":"2026-05-18T12:33:33Z"}],"graph_snapshots":[{"event_id":"sha256:d3d5d7889baefa355a150579306e4ec432ce1d8dc5490cb228c5208b055e701c","target":"graph","created_at":"2026-05-17T23:56:39Z","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":"Various forms of representations may arise in the many layers embedded in deep neural networks (DNNs). Of these, where can we find the most compact representation? We propose to use a pruning framework to answer this question: How compact can each layer be compressed, without losing performance? Most of the existing DNN compression methods do not consider the relative compressibility of the individual layers. They uniformly apply a single target sparsity to all layers or adapt layer sparsity using heuristics and additional training. We propose a principled method that automatically determines ","authors_text":"Hyun-Joo Jung, Jaedeok Kim, Yoonsuck Choe","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-09T14:18:47Z","title":"How Compact?: Assessing Compactness of Representations through Layer-Wise Pruning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.02757","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":"sha256:4d014fa9547556c0ff81ef3d4d88d6203234708c9f0bbab0faf17c75a079a450","target":"record","created_at":"2026-05-17T23:56:39Z","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":"eda7314d80531d8c906bc5acc631b0a877c86aa9ac9020e03b57af2aa3978091","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-09T14:18:47Z","title_canon_sha256":"9b35c110b7179decce96b9030aa450ffe41dfd23ede077fcee2f373541369ef9"},"schema_version":"1.0","source":{"id":"1901.02757","kind":"arxiv","version":1}},"canonical_sha256":"c9e1cd8b8c161cf0f8d9e0f7f769712a1e1a87b43a234a0e988e795d24bc61f1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c9e1cd8b8c161cf0f8d9e0f7f769712a1e1a87b43a234a0e988e795d24bc61f1","first_computed_at":"2026-05-17T23:56:39.520131Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:56:39.520131Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mQrumpdoO8fXMwAVIJr3Fp8Vzl2JrY4OBUuEvz4gb40sdnZClr2UhOAsdNNDsl8Sl/HOg8zHLWmgVWAMGNsADw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:56:39.520667Z","signed_message":"canonical_sha256_bytes"},"source_id":"1901.02757","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4d014fa9547556c0ff81ef3d4d88d6203234708c9f0bbab0faf17c75a079a450","sha256:d3d5d7889baefa355a150579306e4ec432ce1d8dc5490cb228c5208b055e701c"],"state_sha256":"3e1e383e6f0bd895eb5d2ad1844148f84491a36d816ef1988906225f8abe0165"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UdysqG9ckv90HKYyRKGZFSXecp3wVjD0UWvP3q+qcKc6kvm8T2q8dCeYoGe2lNuwLVInOuu5lB683YB7Cx9SDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-29T20:56:40.753141Z","bundle_sha256":"d6bc32ce84bdb5e833819a841c3988f648d782afc32be8110922871ef0956858"}}