{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:54IQTKTQ7VAM74ZRWHS4WGWA7F","short_pith_number":"pith:54IQTKTQ","canonical_record":{"source":{"id":"1712.01721","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-12-05T15:58:44Z","cross_cats_sorted":[],"title_canon_sha256":"1dbf36a10a0b2813a055b10535bab69a31be113c029c26b4182f09ba2a16e191","abstract_canon_sha256":"ba5fbb87d03d0cea0c7256b56c38e7e0f70985b05d6d1013261255b436a16832"},"schema_version":"1.0"},"canonical_sha256":"ef1109aa70fd40cff331b1e5cb1ac0f94d666106b68d842e8057839a11abec21","source":{"kind":"arxiv","id":"1712.01721","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1712.01721","created_at":"2026-05-17T23:56:55Z"},{"alias_kind":"arxiv_version","alias_value":"1712.01721v2","created_at":"2026-05-17T23:56:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1712.01721","created_at":"2026-05-17T23:56:55Z"},{"alias_kind":"pith_short_12","alias_value":"54IQTKTQ7VAM","created_at":"2026-05-18T12:31:00Z"},{"alias_kind":"pith_short_16","alias_value":"54IQTKTQ7VAM74ZR","created_at":"2026-05-18T12:31:00Z"},{"alias_kind":"pith_short_8","alias_value":"54IQTKTQ","created_at":"2026-05-18T12:31:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:54IQTKTQ7VAM74ZRWHS4WGWA7F","target":"record","payload":{"canonical_record":{"source":{"id":"1712.01721","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-12-05T15:58:44Z","cross_cats_sorted":[],"title_canon_sha256":"1dbf36a10a0b2813a055b10535bab69a31be113c029c26b4182f09ba2a16e191","abstract_canon_sha256":"ba5fbb87d03d0cea0c7256b56c38e7e0f70985b05d6d1013261255b436a16832"},"schema_version":"1.0"},"canonical_sha256":"ef1109aa70fd40cff331b1e5cb1ac0f94d666106b68d842e8057839a11abec21","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:56:55.676397Z","signature_b64":"Z/HBPlO46i6s1p2DHT5f7vr+h9n8zhMEYBCtnE/KWzMhwlpYeo31gPjWjdzGpRnRhMH6nFAzJpfmmXEk706oAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ef1109aa70fd40cff331b1e5cb1ac0f94d666106b68d842e8057839a11abec21","last_reissued_at":"2026-05-17T23:56:55.675582Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:56:55.675582Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1712.01721","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":"2026-05-17T23:56:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+K+JDivjzCAAZ5GvR1uZiHoCIyQnAhY0k2OhO2juHT9f/DzVpkLqv4HpYZZDA7rMUWd/lEJxuOPAT17YdOuVDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T03:14:00.655528Z"},"content_sha256":"194a5eba88358beaf91c985a3724f4653b1349bf632aa0f6498463d13ea3246b","schema_version":"1.0","event_id":"sha256:194a5eba88358beaf91c985a3724f4653b1349bf632aa0f6498463d13ea3246b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:54IQTKTQ7VAM74ZRWHS4WGWA7F","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Automated Pruning for Deep Neural Network Compression","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alessandro Rozza, Franco Manessi, Paolo Napoletano, Raimondo Schettini, Simone Bianco","submitted_at":"2017-12-05T15:58:44Z","abstract_excerpt":"In this work we present a method to improve the pruning step of the current state-of-the-art methodology to compress neural networks. The novelty of the proposed pruning technique is in its differentiability, which allows pruning to be performed during the backpropagation phase of the network training. This enables an end-to-end learning and strongly reduces the training time. The technique is based on a family of differentiable pruning functions and a new regularizer specifically designed to enforce pruning. The experimental results show that the joint optimization of both the thresholds and "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1712.01721","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":"2026-05-17T23:56:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HO6x71mZJE9fEiIzuI1uCA7m68rPxRGcmbjFGfhsE4mwbHY/wzwH9LxU6xK5kXpZcPtSCOYqTpspTTGx9pdtCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T03:14:00.656175Z"},"content_sha256":"f2e882eaa43cb1593cffa36d711c10815adae6357069510d64637163775d0acd","schema_version":"1.0","event_id":"sha256:f2e882eaa43cb1593cffa36d711c10815adae6357069510d64637163775d0acd"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/54IQTKTQ7VAM74ZRWHS4WGWA7F/bundle.json","state_url":"https://pith.science/pith/54IQTKTQ7VAM74ZRWHS4WGWA7F/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/54IQTKTQ7VAM74ZRWHS4WGWA7F/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":"2026-05-31T03:14:00Z","links":{"resolver":"https://pith.science/pith/54IQTKTQ7VAM74ZRWHS4WGWA7F","bundle":"https://pith.science/pith/54IQTKTQ7VAM74ZRWHS4WGWA7F/bundle.json","state":"https://pith.science/pith/54IQTKTQ7VAM74ZRWHS4WGWA7F/state.json","well_known_bundle":"https://pith.science/.well-known/pith/54IQTKTQ7VAM74ZRWHS4WGWA7F/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:54IQTKTQ7VAM74ZRWHS4WGWA7F","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":"ba5fbb87d03d0cea0c7256b56c38e7e0f70985b05d6d1013261255b436a16832","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-12-05T15:58:44Z","title_canon_sha256":"1dbf36a10a0b2813a055b10535bab69a31be113c029c26b4182f09ba2a16e191"},"schema_version":"1.0","source":{"id":"1712.01721","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1712.01721","created_at":"2026-05-17T23:56:55Z"},{"alias_kind":"arxiv_version","alias_value":"1712.01721v2","created_at":"2026-05-17T23:56:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1712.01721","created_at":"2026-05-17T23:56:55Z"},{"alias_kind":"pith_short_12","alias_value":"54IQTKTQ7VAM","created_at":"2026-05-18T12:31:00Z"},{"alias_kind":"pith_short_16","alias_value":"54IQTKTQ7VAM74ZR","created_at":"2026-05-18T12:31:00Z"},{"alias_kind":"pith_short_8","alias_value":"54IQTKTQ","created_at":"2026-05-18T12:31:00Z"}],"graph_snapshots":[{"event_id":"sha256:f2e882eaa43cb1593cffa36d711c10815adae6357069510d64637163775d0acd","target":"graph","created_at":"2026-05-17T23:56:55Z","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":"In this work we present a method to improve the pruning step of the current state-of-the-art methodology to compress neural networks. The novelty of the proposed pruning technique is in its differentiability, which allows pruning to be performed during the backpropagation phase of the network training. This enables an end-to-end learning and strongly reduces the training time. The technique is based on a family of differentiable pruning functions and a new regularizer specifically designed to enforce pruning. The experimental results show that the joint optimization of both the thresholds and ","authors_text":"Alessandro Rozza, Franco Manessi, Paolo Napoletano, Raimondo Schettini, Simone Bianco","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-12-05T15:58:44Z","title":"Automated Pruning for Deep Neural Network Compression"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1712.01721","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":"sha256:194a5eba88358beaf91c985a3724f4653b1349bf632aa0f6498463d13ea3246b","target":"record","created_at":"2026-05-17T23:56:55Z","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":"ba5fbb87d03d0cea0c7256b56c38e7e0f70985b05d6d1013261255b436a16832","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-12-05T15:58:44Z","title_canon_sha256":"1dbf36a10a0b2813a055b10535bab69a31be113c029c26b4182f09ba2a16e191"},"schema_version":"1.0","source":{"id":"1712.01721","kind":"arxiv","version":2}},"canonical_sha256":"ef1109aa70fd40cff331b1e5cb1ac0f94d666106b68d842e8057839a11abec21","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ef1109aa70fd40cff331b1e5cb1ac0f94d666106b68d842e8057839a11abec21","first_computed_at":"2026-05-17T23:56:55.675582Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:56:55.675582Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Z/HBPlO46i6s1p2DHT5f7vr+h9n8zhMEYBCtnE/KWzMhwlpYeo31gPjWjdzGpRnRhMH6nFAzJpfmmXEk706oAw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:56:55.676397Z","signed_message":"canonical_sha256_bytes"},"source_id":"1712.01721","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:194a5eba88358beaf91c985a3724f4653b1349bf632aa0f6498463d13ea3246b","sha256:f2e882eaa43cb1593cffa36d711c10815adae6357069510d64637163775d0acd"],"state_sha256":"ac2576cf4d7f15a7b653288f9775d8b4116ee1e0bb1b3543edb51f28cc84d5f9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RXQkVhGX6kLNAXqOzEUVwc9IcNghYXJTfR7ispxQ+M7FzuGZkaZHkYoiaMStUcxWEcB5cvhgc6i8N/ev+NelBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-31T03:14:00.659633Z","bundle_sha256":"266acbe487155afaafa6ef104b5948e0b6e8bab213cc637e3f40ecef0fa0ccce"}}