{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:7ZN3ETNNQVMC2SPL3GOXJ7YQNB","short_pith_number":"pith:7ZN3ETNN","canonical_record":{"source":{"id":"1711.02857","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-11-08T07:54:41Z","cross_cats_sorted":["cs.AI","cs.CV","math.NA","stat.ML"],"title_canon_sha256":"34b697f1786e539f5cea2cab2713d936f0958f7be0670ed12eed69bdfd2ddd9f","abstract_canon_sha256":"662f5ef3cecdfbdd5214ebd701d97260cf228d35fd30cf4346f4a2f6f6c653bf"},"schema_version":"1.0"},"canonical_sha256":"fe5bb24dad85582d49ebd99d74ff106858fa3f0fd016c257f41a0d9ed5f656b3","source":{"kind":"arxiv","id":"1711.02857","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1711.02857","created_at":"2026-05-18T00:31:01Z"},{"alias_kind":"arxiv_version","alias_value":"1711.02857v1","created_at":"2026-05-18T00:31:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.02857","created_at":"2026-05-18T00:31:01Z"},{"alias_kind":"pith_short_12","alias_value":"7ZN3ETNNQVMC","created_at":"2026-05-18T12:31:05Z"},{"alias_kind":"pith_short_16","alias_value":"7ZN3ETNNQVMC2SPL","created_at":"2026-05-18T12:31:05Z"},{"alias_kind":"pith_short_8","alias_value":"7ZN3ETNN","created_at":"2026-05-18T12:31:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:7ZN3ETNNQVMC2SPL3GOXJ7YQNB","target":"record","payload":{"canonical_record":{"source":{"id":"1711.02857","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-11-08T07:54:41Z","cross_cats_sorted":["cs.AI","cs.CV","math.NA","stat.ML"],"title_canon_sha256":"34b697f1786e539f5cea2cab2713d936f0958f7be0670ed12eed69bdfd2ddd9f","abstract_canon_sha256":"662f5ef3cecdfbdd5214ebd701d97260cf228d35fd30cf4346f4a2f6f6c653bf"},"schema_version":"1.0"},"canonical_sha256":"fe5bb24dad85582d49ebd99d74ff106858fa3f0fd016c257f41a0d9ed5f656b3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:31:01.508840Z","signature_b64":"cJ4FIaQCIFNrXAFvGSe708QR2SHb3qrwNknvDzE3zumwDTWDLpBdcI5PeqCdxzsGFy687A6R55kb/XcPYoAEAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fe5bb24dad85582d49ebd99d74ff106858fa3f0fd016c257f41a0d9ed5f656b3","last_reissued_at":"2026-05-18T00:31:01.508127Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:31:01.508127Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1711.02857","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":"2026-05-18T00:31:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ltJWI4vYApwupOFIdBOQQO4j8YL4MLTEboMfO2iJBXGBXeXZ92z/1bTQL5T9FgybiwhvyjYYMSM+H+2xxuyTCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T20:49:38.994082Z"},"content_sha256":"5ab866d9eb8ae3799657f56024120b27e93397fc59adbb45c7d20cddfaf03a5b","schema_version":"1.0","event_id":"sha256:5ab866d9eb8ae3799657f56024120b27e93397fc59adbb45c7d20cddfaf03a5b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:7ZN3ETNNQVMC2SPL3GOXJ7YQNB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning Sparse Visual Representations with Leaky Capped Norm Regularizers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","math.NA","stat.ML"],"primary_cat":"cs.LG","authors_text":"Dahua Lin, Jianqiao Wangni","submitted_at":"2017-11-08T07:54:41Z","abstract_excerpt":"Sparsity inducing regularization is an important part for learning over-complete visual representations. Despite the popularity of $\\ell_1$ regularization, in this paper, we investigate the usage of non-convex regularizations in this problem. Our contribution consists of three parts. First, we propose the leaky capped norm regularization (LCNR), which allows model weights below a certain threshold to be regularized more strongly as opposed to those above, therefore imposes strong sparsity and only introduces controllable estimation bias. We propose a majorization-minimization algorithm to opti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.02857","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":"2026-05-18T00:31:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"puKo7sezIIC7lnXKmCe54l/IfPsALr9GCT1/ljX41pyP3V5YuWmriAGaDPWq0/vc6vwFG8vhyY4xcPpdYWDEDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T20:49:38.994734Z"},"content_sha256":"7ccc20d97433d7806c8f8bc344a2356807c21061836b0f7b50c8f3df42401b39","schema_version":"1.0","event_id":"sha256:7ccc20d97433d7806c8f8bc344a2356807c21061836b0f7b50c8f3df42401b39"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7ZN3ETNNQVMC2SPL3GOXJ7YQNB/bundle.json","state_url":"https://pith.science/pith/7ZN3ETNNQVMC2SPL3GOXJ7YQNB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7ZN3ETNNQVMC2SPL3GOXJ7YQNB/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":"2026-06-04T20:49:38Z","links":{"resolver":"https://pith.science/pith/7ZN3ETNNQVMC2SPL3GOXJ7YQNB","bundle":"https://pith.science/pith/7ZN3ETNNQVMC2SPL3GOXJ7YQNB/bundle.json","state":"https://pith.science/pith/7ZN3ETNNQVMC2SPL3GOXJ7YQNB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7ZN3ETNNQVMC2SPL3GOXJ7YQNB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:7ZN3ETNNQVMC2SPL3GOXJ7YQNB","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":"662f5ef3cecdfbdd5214ebd701d97260cf228d35fd30cf4346f4a2f6f6c653bf","cross_cats_sorted":["cs.AI","cs.CV","math.NA","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-11-08T07:54:41Z","title_canon_sha256":"34b697f1786e539f5cea2cab2713d936f0958f7be0670ed12eed69bdfd2ddd9f"},"schema_version":"1.0","source":{"id":"1711.02857","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1711.02857","created_at":"2026-05-18T00:31:01Z"},{"alias_kind":"arxiv_version","alias_value":"1711.02857v1","created_at":"2026-05-18T00:31:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.02857","created_at":"2026-05-18T00:31:01Z"},{"alias_kind":"pith_short_12","alias_value":"7ZN3ETNNQVMC","created_at":"2026-05-18T12:31:05Z"},{"alias_kind":"pith_short_16","alias_value":"7ZN3ETNNQVMC2SPL","created_at":"2026-05-18T12:31:05Z"},{"alias_kind":"pith_short_8","alias_value":"7ZN3ETNN","created_at":"2026-05-18T12:31:05Z"}],"graph_snapshots":[{"event_id":"sha256:7ccc20d97433d7806c8f8bc344a2356807c21061836b0f7b50c8f3df42401b39","target":"graph","created_at":"2026-05-18T00:31:01Z","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":"Sparsity inducing regularization is an important part for learning over-complete visual representations. Despite the popularity of $\\ell_1$ regularization, in this paper, we investigate the usage of non-convex regularizations in this problem. Our contribution consists of three parts. First, we propose the leaky capped norm regularization (LCNR), which allows model weights below a certain threshold to be regularized more strongly as opposed to those above, therefore imposes strong sparsity and only introduces controllable estimation bias. We propose a majorization-minimization algorithm to opti","authors_text":"Dahua Lin, Jianqiao Wangni","cross_cats":["cs.AI","cs.CV","math.NA","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-11-08T07:54:41Z","title":"Learning Sparse Visual Representations with Leaky Capped Norm Regularizers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.02857","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":"sha256:5ab866d9eb8ae3799657f56024120b27e93397fc59adbb45c7d20cddfaf03a5b","target":"record","created_at":"2026-05-18T00:31:01Z","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":"662f5ef3cecdfbdd5214ebd701d97260cf228d35fd30cf4346f4a2f6f6c653bf","cross_cats_sorted":["cs.AI","cs.CV","math.NA","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-11-08T07:54:41Z","title_canon_sha256":"34b697f1786e539f5cea2cab2713d936f0958f7be0670ed12eed69bdfd2ddd9f"},"schema_version":"1.0","source":{"id":"1711.02857","kind":"arxiv","version":1}},"canonical_sha256":"fe5bb24dad85582d49ebd99d74ff106858fa3f0fd016c257f41a0d9ed5f656b3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fe5bb24dad85582d49ebd99d74ff106858fa3f0fd016c257f41a0d9ed5f656b3","first_computed_at":"2026-05-18T00:31:01.508127Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:31:01.508127Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"cJ4FIaQCIFNrXAFvGSe708QR2SHb3qrwNknvDzE3zumwDTWDLpBdcI5PeqCdxzsGFy687A6R55kb/XcPYoAEAA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:31:01.508840Z","signed_message":"canonical_sha256_bytes"},"source_id":"1711.02857","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5ab866d9eb8ae3799657f56024120b27e93397fc59adbb45c7d20cddfaf03a5b","sha256:7ccc20d97433d7806c8f8bc344a2356807c21061836b0f7b50c8f3df42401b39"],"state_sha256":"75fc70cde0c70595609ef05876a17ff9d8ff2c2c052be906f48295facb6b76e6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cP0LLfbiGclwDC5mZtyMAfR9A1xMzaKln0rnM6ca6JwSeM02BO89lcFZ+GsyPUcr4oNGQOC0fvJ3HPzv7nW5DQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-04T20:49:38.998741Z","bundle_sha256":"0aec97c4f446d7c28bcfe96dec50bc8dcdee76dcd71cb4a95b543dca3c765ad5"}}