{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:4OKEBKDU46AKAHJVTRAPHZGYKQ","short_pith_number":"pith:4OKEBKDU","canonical_record":{"source":{"id":"1810.00518","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-10-01T03:41:25Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"b9afc9696c798b03178e67f3124a5bb77a6b6696ed1f427e60e79a6987e2b7ad","abstract_canon_sha256":"58402aaad74b9d50e080229331afc5a88918d1bd54a4b33fb4c95e299cea65d9"},"schema_version":"1.0"},"canonical_sha256":"e39440a874e780a01d359c40f3e4d8541484bbd504ec74d7a3e888f6501e9e62","source":{"kind":"arxiv","id":"1810.00518","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.00518","created_at":"2026-05-18T00:02:54Z"},{"alias_kind":"arxiv_version","alias_value":"1810.00518v2","created_at":"2026-05-18T00:02:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.00518","created_at":"2026-05-18T00:02:54Z"},{"alias_kind":"pith_short_12","alias_value":"4OKEBKDU46AK","created_at":"2026-05-18T12:32:05Z"},{"alias_kind":"pith_short_16","alias_value":"4OKEBKDU46AKAHJV","created_at":"2026-05-18T12:32:05Z"},{"alias_kind":"pith_short_8","alias_value":"4OKEBKDU","created_at":"2026-05-18T12:32:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:4OKEBKDU46AKAHJVTRAPHZGYKQ","target":"record","payload":{"canonical_record":{"source":{"id":"1810.00518","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-10-01T03:41:25Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"b9afc9696c798b03178e67f3124a5bb77a6b6696ed1f427e60e79a6987e2b7ad","abstract_canon_sha256":"58402aaad74b9d50e080229331afc5a88918d1bd54a4b33fb4c95e299cea65d9"},"schema_version":"1.0"},"canonical_sha256":"e39440a874e780a01d359c40f3e4d8541484bbd504ec74d7a3e888f6501e9e62","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:02:54.583534Z","signature_b64":"EPQDM65Vck7xSi2QiakjAe7R47CCWs6l3gfIT6GQk1fMGE3v2o4/qmt+NgLtTztFLXctQrbGAlW2esq4yQgaCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e39440a874e780a01d359c40f3e4d8541484bbd504ec74d7a3e888f6501e9e62","last_reissued_at":"2026-05-18T00:02:54.582846Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:02:54.582846Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1810.00518","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":"2026-05-18T00:02:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3+APLnTJR/v/ePaOeEneohkyJZ17395Qzprd7yjXaz8DkW+vAKOMt8v6YrJGDSHg1JVXgVlvsTRRlR843nylBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T18:40:00.294842Z"},"content_sha256":"7581a1065f70218335bb18ff73b576271257acc63631eb0ed9542117d202c1ab","schema_version":"1.0","event_id":"sha256:7581a1065f70218335bb18ff73b576271257acc63631eb0ed9542117d202c1ab"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:4OKEBKDU46AKAHJVTRAPHZGYKQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Layer-compensated Pruning for Resource-constrained Convolutional Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Cha Zhang, Diana Marculescu, Ting-Wu Chin","submitted_at":"2018-10-01T03:41:25Z","abstract_excerpt":"Resource-efficient convolution neural networks enable not only the intelligence on edge devices but also opportunities in system-level optimization such as scheduling. In this work, we aim to improve the performance of resource-constrained filter pruning by merging two sub-problems commonly considered, i.e., (i) how many filters to prune for each layer and (ii) which filters to prune given a per-layer pruning budget, into a global filter ranking problem. Our framework entails a novel algorithm, dubbed layer-compensated pruning, where meta-learning is involved to determine better solutions. We "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.00518","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":"2026-05-18T00:02:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"82hW+jLRSFF7DcfQ36Z8F9aG2xufsIFl/JFyEsxJbV/XhUuJ7p6hvpqt3Si76RYxQISvIvHOFuG+Xu+pgl/FCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T18:40:00.295556Z"},"content_sha256":"e4f3f901fbc2f3e9eaec053ac2780850fab08c8322dd2cfdf84fb65f782e4462","schema_version":"1.0","event_id":"sha256:e4f3f901fbc2f3e9eaec053ac2780850fab08c8322dd2cfdf84fb65f782e4462"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4OKEBKDU46AKAHJVTRAPHZGYKQ/bundle.json","state_url":"https://pith.science/pith/4OKEBKDU46AKAHJVTRAPHZGYKQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4OKEBKDU46AKAHJVTRAPHZGYKQ/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":"2026-06-06T18:40:00Z","links":{"resolver":"https://pith.science/pith/4OKEBKDU46AKAHJVTRAPHZGYKQ","bundle":"https://pith.science/pith/4OKEBKDU46AKAHJVTRAPHZGYKQ/bundle.json","state":"https://pith.science/pith/4OKEBKDU46AKAHJVTRAPHZGYKQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4OKEBKDU46AKAHJVTRAPHZGYKQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:4OKEBKDU46AKAHJVTRAPHZGYKQ","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":"58402aaad74b9d50e080229331afc5a88918d1bd54a4b33fb4c95e299cea65d9","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-10-01T03:41:25Z","title_canon_sha256":"b9afc9696c798b03178e67f3124a5bb77a6b6696ed1f427e60e79a6987e2b7ad"},"schema_version":"1.0","source":{"id":"1810.00518","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.00518","created_at":"2026-05-18T00:02:54Z"},{"alias_kind":"arxiv_version","alias_value":"1810.00518v2","created_at":"2026-05-18T00:02:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.00518","created_at":"2026-05-18T00:02:54Z"},{"alias_kind":"pith_short_12","alias_value":"4OKEBKDU46AK","created_at":"2026-05-18T12:32:05Z"},{"alias_kind":"pith_short_16","alias_value":"4OKEBKDU46AKAHJV","created_at":"2026-05-18T12:32:05Z"},{"alias_kind":"pith_short_8","alias_value":"4OKEBKDU","created_at":"2026-05-18T12:32:05Z"}],"graph_snapshots":[{"event_id":"sha256:e4f3f901fbc2f3e9eaec053ac2780850fab08c8322dd2cfdf84fb65f782e4462","target":"graph","created_at":"2026-05-18T00:02:54Z","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":"Resource-efficient convolution neural networks enable not only the intelligence on edge devices but also opportunities in system-level optimization such as scheduling. In this work, we aim to improve the performance of resource-constrained filter pruning by merging two sub-problems commonly considered, i.e., (i) how many filters to prune for each layer and (ii) which filters to prune given a per-layer pruning budget, into a global filter ranking problem. Our framework entails a novel algorithm, dubbed layer-compensated pruning, where meta-learning is involved to determine better solutions. We ","authors_text":"Cha Zhang, Diana Marculescu, Ting-Wu Chin","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-10-01T03:41:25Z","title":"Layer-compensated Pruning for Resource-constrained Convolutional Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.00518","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":"sha256:7581a1065f70218335bb18ff73b576271257acc63631eb0ed9542117d202c1ab","target":"record","created_at":"2026-05-18T00:02:54Z","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":"58402aaad74b9d50e080229331afc5a88918d1bd54a4b33fb4c95e299cea65d9","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-10-01T03:41:25Z","title_canon_sha256":"b9afc9696c798b03178e67f3124a5bb77a6b6696ed1f427e60e79a6987e2b7ad"},"schema_version":"1.0","source":{"id":"1810.00518","kind":"arxiv","version":2}},"canonical_sha256":"e39440a874e780a01d359c40f3e4d8541484bbd504ec74d7a3e888f6501e9e62","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e39440a874e780a01d359c40f3e4d8541484bbd504ec74d7a3e888f6501e9e62","first_computed_at":"2026-05-18T00:02:54.582846Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:02:54.582846Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"EPQDM65Vck7xSi2QiakjAe7R47CCWs6l3gfIT6GQk1fMGE3v2o4/qmt+NgLtTztFLXctQrbGAlW2esq4yQgaCA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:02:54.583534Z","signed_message":"canonical_sha256_bytes"},"source_id":"1810.00518","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7581a1065f70218335bb18ff73b576271257acc63631eb0ed9542117d202c1ab","sha256:e4f3f901fbc2f3e9eaec053ac2780850fab08c8322dd2cfdf84fb65f782e4462"],"state_sha256":"a4af898236fcfabb0bf1a6f00cea4cdc12186a75fe2e44edebf4fda639b90279"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+E8NEPIk+8S4IRoQQjdpLSYk5gfjUVKiPOO2py8TFvxPV2TjAiazuVUItCz0CpYNixaK8bXuMaVbNinh6uwLDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-06T18:40:00.299173Z","bundle_sha256":"810cef9eff3572e968e281a095210b45924876b02552e5a14a0b9a84129ba4f1"}}