{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:6KPQZL3CD4X3RKI5EDWTY2WZJL","short_pith_number":"pith:6KPQZL3C","canonical_record":{"source":{"id":"1901.01021","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-01-04T08:46:16Z","cross_cats_sorted":[],"title_canon_sha256":"0b61f3e33b37ad0042e567ff3a9b4c139cf2821b4c18797b7beff34a277522b3","abstract_canon_sha256":"bd66510c2cdda0d9b89a953419cebed09470874361d50f66bce30ff44f72801e"},"schema_version":"1.0"},"canonical_sha256":"f29f0caf621f2fb8a91d20ed3c6ad94aef92abdf1d4cdb19eaf2682bfc7e01e9","source":{"kind":"arxiv","id":"1901.01021","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1901.01021","created_at":"2026-05-17T23:56:57Z"},{"alias_kind":"arxiv_version","alias_value":"1901.01021v1","created_at":"2026-05-17T23:56:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.01021","created_at":"2026-05-17T23:56:57Z"},{"alias_kind":"pith_short_12","alias_value":"6KPQZL3CD4X3","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_16","alias_value":"6KPQZL3CD4X3RKI5","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_8","alias_value":"6KPQZL3C","created_at":"2026-05-18T12:33:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:6KPQZL3CD4X3RKI5EDWTY2WZJL","target":"record","payload":{"canonical_record":{"source":{"id":"1901.01021","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-01-04T08:46:16Z","cross_cats_sorted":[],"title_canon_sha256":"0b61f3e33b37ad0042e567ff3a9b4c139cf2821b4c18797b7beff34a277522b3","abstract_canon_sha256":"bd66510c2cdda0d9b89a953419cebed09470874361d50f66bce30ff44f72801e"},"schema_version":"1.0"},"canonical_sha256":"f29f0caf621f2fb8a91d20ed3c6ad94aef92abdf1d4cdb19eaf2682bfc7e01e9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:56:57.372833Z","signature_b64":"e27WEg4t0W9rw3PdviFYWZLGt6y8ZS3l4DEtUN0OwhfK2PtgzU/W8QEHaT2aJbcx5ld+IPL0+ZWwQJrLFYYzCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f29f0caf621f2fb8a91d20ed3c6ad94aef92abdf1d4cdb19eaf2682bfc7e01e9","last_reissued_at":"2026-05-17T23:56:57.372074Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:56:57.372074Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1901.01021","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":"2026-05-17T23:56:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gCL9rWnV76RZTuSS6bFYqzbvyxK75tKnrmWfRqFfuREVJWBAX+2nsRbq0RVSS+RsNDDbYevf4IwscHiQ9BMcAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T12:30:50.654951Z"},"content_sha256":"c29aeb86179d3d00cdb4e73c05e5bba4dab8293a40e3444331c243646d469382","schema_version":"1.0","event_id":"sha256:c29aeb86179d3d00cdb4e73c05e5bba4dab8293a40e3444331c243646d469382"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:6KPQZL3CD4X3RKI5EDWTY2WZJL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Transformed $\\ell_1$ Regularization for Learning Sparse Deep Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jianyu Miao, Lingfeng Niu, Peng Zhang, Rongrong Ma","submitted_at":"2019-01-04T08:46:16Z","abstract_excerpt":"Deep neural networks (DNNs) have achieved extraordinary success in numerous areas. However, to attain this success, DNNs often carry a large number of weight parameters, leading to heavy costs of memory and computation resources. Overfitting is also likely to happen in such network when the training data are insufficient. These shortcomings severely hinder the application of DNNs in resource-constrained platforms. In fact, many network weights are known to be redundant and can be removed from the network without much loss of performance. To this end, we introduce a new non-convex integrated tr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.01021","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":"2026-05-17T23:56:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VDIY5XWoQ3pB5p3RI6i/8GvMgd2I3cXVKiyHGF04Pmtpxktstt6Jh8w374HZyF+3Kb63mIVnZUSjiS8i8PX6DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T12:30:50.655309Z"},"content_sha256":"db5f709caf384d537110acfcdd421691ce2aeb56e611b324913f6bd9d409ebc7","schema_version":"1.0","event_id":"sha256:db5f709caf384d537110acfcdd421691ce2aeb56e611b324913f6bd9d409ebc7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6KPQZL3CD4X3RKI5EDWTY2WZJL/bundle.json","state_url":"https://pith.science/pith/6KPQZL3CD4X3RKI5EDWTY2WZJL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6KPQZL3CD4X3RKI5EDWTY2WZJL/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":"2026-05-28T12:30:50Z","links":{"resolver":"https://pith.science/pith/6KPQZL3CD4X3RKI5EDWTY2WZJL","bundle":"https://pith.science/pith/6KPQZL3CD4X3RKI5EDWTY2WZJL/bundle.json","state":"https://pith.science/pith/6KPQZL3CD4X3RKI5EDWTY2WZJL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6KPQZL3CD4X3RKI5EDWTY2WZJL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:6KPQZL3CD4X3RKI5EDWTY2WZJL","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":"bd66510c2cdda0d9b89a953419cebed09470874361d50f66bce30ff44f72801e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-01-04T08:46:16Z","title_canon_sha256":"0b61f3e33b37ad0042e567ff3a9b4c139cf2821b4c18797b7beff34a277522b3"},"schema_version":"1.0","source":{"id":"1901.01021","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1901.01021","created_at":"2026-05-17T23:56:57Z"},{"alias_kind":"arxiv_version","alias_value":"1901.01021v1","created_at":"2026-05-17T23:56:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.01021","created_at":"2026-05-17T23:56:57Z"},{"alias_kind":"pith_short_12","alias_value":"6KPQZL3CD4X3","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_16","alias_value":"6KPQZL3CD4X3RKI5","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_8","alias_value":"6KPQZL3C","created_at":"2026-05-18T12:33:10Z"}],"graph_snapshots":[{"event_id":"sha256:db5f709caf384d537110acfcdd421691ce2aeb56e611b324913f6bd9d409ebc7","target":"graph","created_at":"2026-05-17T23:56:57Z","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":"Deep neural networks (DNNs) have achieved extraordinary success in numerous areas. However, to attain this success, DNNs often carry a large number of weight parameters, leading to heavy costs of memory and computation resources. Overfitting is also likely to happen in such network when the training data are insufficient. These shortcomings severely hinder the application of DNNs in resource-constrained platforms. In fact, many network weights are known to be redundant and can be removed from the network without much loss of performance. To this end, we introduce a new non-convex integrated tr","authors_text":"Jianyu Miao, Lingfeng Niu, Peng Zhang, Rongrong Ma","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-01-04T08:46:16Z","title":"Transformed $\\ell_1$ Regularization for Learning Sparse Deep Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.01021","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:c29aeb86179d3d00cdb4e73c05e5bba4dab8293a40e3444331c243646d469382","target":"record","created_at":"2026-05-17T23:56:57Z","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":"bd66510c2cdda0d9b89a953419cebed09470874361d50f66bce30ff44f72801e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-01-04T08:46:16Z","title_canon_sha256":"0b61f3e33b37ad0042e567ff3a9b4c139cf2821b4c18797b7beff34a277522b3"},"schema_version":"1.0","source":{"id":"1901.01021","kind":"arxiv","version":1}},"canonical_sha256":"f29f0caf621f2fb8a91d20ed3c6ad94aef92abdf1d4cdb19eaf2682bfc7e01e9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f29f0caf621f2fb8a91d20ed3c6ad94aef92abdf1d4cdb19eaf2682bfc7e01e9","first_computed_at":"2026-05-17T23:56:57.372074Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:56:57.372074Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"e27WEg4t0W9rw3PdviFYWZLGt6y8ZS3l4DEtUN0OwhfK2PtgzU/W8QEHaT2aJbcx5ld+IPL0+ZWwQJrLFYYzCg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:56:57.372833Z","signed_message":"canonical_sha256_bytes"},"source_id":"1901.01021","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c29aeb86179d3d00cdb4e73c05e5bba4dab8293a40e3444331c243646d469382","sha256:db5f709caf384d537110acfcdd421691ce2aeb56e611b324913f6bd9d409ebc7"],"state_sha256":"0beba153e94212e2ca5d2b42b0cbe5ae1c2ea33f5f0827dfc65fac1ad9e7fdde"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OwGAmqRKgrH6N6aAL5frv9ezPjzHxP7LsQM/qIsSogY7BDpGDgb5dCr14PfPVUN9n77cTigk9h1NHkg7WcePBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T12:30:50.657277Z","bundle_sha256":"d280abec8dca5f0ebcae0f708fbf3c46dc96b16856a981e8a2d0d4bd4d04cd2f"}}