{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:VOKL55CGGEGTJT7ECQTBAXGCK5","short_pith_number":"pith:VOKL55CG","canonical_record":{"source":{"id":"1905.10145","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-24T10:56:02Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"ca5b20183a15ed84824cd2fb2c496cc145fd9988bb5e9c7bd6095373392dcc39","abstract_canon_sha256":"2a1e5b47de2c0d3df4da45ef0fa96c6caf98c3109302f67d734661f6f1339e08"},"schema_version":"1.0"},"canonical_sha256":"ab94bef446310d34cfe41426105cc2575f68a2bacc43fbe7e221a8ad4f6a77c8","source":{"kind":"arxiv","id":"1905.10145","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.10145","created_at":"2026-05-17T23:45:11Z"},{"alias_kind":"arxiv_version","alias_value":"1905.10145v1","created_at":"2026-05-17T23:45:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.10145","created_at":"2026-05-17T23:45:11Z"},{"alias_kind":"pith_short_12","alias_value":"VOKL55CGGEGT","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_16","alias_value":"VOKL55CGGEGTJT7E","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_8","alias_value":"VOKL55CG","created_at":"2026-05-18T12:33:30Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:VOKL55CGGEGTJT7ECQTBAXGCK5","target":"record","payload":{"canonical_record":{"source":{"id":"1905.10145","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-24T10:56:02Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"ca5b20183a15ed84824cd2fb2c496cc145fd9988bb5e9c7bd6095373392dcc39","abstract_canon_sha256":"2a1e5b47de2c0d3df4da45ef0fa96c6caf98c3109302f67d734661f6f1339e08"},"schema_version":"1.0"},"canonical_sha256":"ab94bef446310d34cfe41426105cc2575f68a2bacc43fbe7e221a8ad4f6a77c8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:45:11.231778Z","signature_b64":"IWMrrG2NZigbBOyJpPM0fN0+8EeuejFlJp6STU6IymxNT8YMG9SIUCsTQvtcubV0YvmtoylSwQizzkFYLbJvCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ab94bef446310d34cfe41426105cc2575f68a2bacc43fbe7e221a8ad4f6a77c8","last_reissued_at":"2026-05-17T23:45:11.231251Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:45:11.231251Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1905.10145","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":"2026-05-17T23:45:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WePy+E2II6Ou+iCkpogEo3bbWwnx5pNbjhR5P659Exbj0fDaWcv/Lc7EhdzJjxZYeYpn2sRYt5/ClDBUQX/GCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T19:34:42.232237Z"},"content_sha256":"7afe50075747e0f9d18429ebe397fa278220ade054a66c5522779cd5d3c575f3","schema_version":"1.0","event_id":"sha256:7afe50075747e0f9d18429ebe397fa278220ade054a66c5522779cd5d3c575f3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:VOKL55CGGEGTJT7ECQTBAXGCK5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning Low-Rank Approximation for CNNs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Byeongwook Kim, Dongsoo Lee, Gu-Yeon Wei, Se Jung Kwon","submitted_at":"2019-05-24T10:56:02Z","abstract_excerpt":"Low-rank approximation is an effective model compression technique to not only reduce parameter storage requirements, but to also reduce computations. For convolutional neural networks (CNNs), however, well-known low-rank approximation methods, such as Tucker or CP decomposition, result in degraded model accuracy because decomposed layers hinder training convergence. In this paper, we propose a new training technique that finds a flat minimum in the view of low-rank approximation without a decomposed structure during training. By preserving the original model structure, 2-dimensional low-rank "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.10145","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":"2026-05-17T23:45:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eIhiRx2HN8PB/ogcHvFvZXRW6uWpkQK3BPC5+stwcAM7vq8g5EXcYJjNBDmjWSGx62wjUE9kM3pEDt22abRHAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T19:34:42.232581Z"},"content_sha256":"370a73df3fd10ab9aa4608c85eba442f1ebe07c70f70e8ae24351a26c0f4894b","schema_version":"1.0","event_id":"sha256:370a73df3fd10ab9aa4608c85eba442f1ebe07c70f70e8ae24351a26c0f4894b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VOKL55CGGEGTJT7ECQTBAXGCK5/bundle.json","state_url":"https://pith.science/pith/VOKL55CGGEGTJT7ECQTBAXGCK5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VOKL55CGGEGTJT7ECQTBAXGCK5/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":"2026-07-06T19:34:42Z","links":{"resolver":"https://pith.science/pith/VOKL55CGGEGTJT7ECQTBAXGCK5","bundle":"https://pith.science/pith/VOKL55CGGEGTJT7ECQTBAXGCK5/bundle.json","state":"https://pith.science/pith/VOKL55CGGEGTJT7ECQTBAXGCK5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VOKL55CGGEGTJT7ECQTBAXGCK5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:VOKL55CGGEGTJT7ECQTBAXGCK5","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":"2a1e5b47de2c0d3df4da45ef0fa96c6caf98c3109302f67d734661f6f1339e08","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-24T10:56:02Z","title_canon_sha256":"ca5b20183a15ed84824cd2fb2c496cc145fd9988bb5e9c7bd6095373392dcc39"},"schema_version":"1.0","source":{"id":"1905.10145","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.10145","created_at":"2026-05-17T23:45:11Z"},{"alias_kind":"arxiv_version","alias_value":"1905.10145v1","created_at":"2026-05-17T23:45:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.10145","created_at":"2026-05-17T23:45:11Z"},{"alias_kind":"pith_short_12","alias_value":"VOKL55CGGEGT","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_16","alias_value":"VOKL55CGGEGTJT7E","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_8","alias_value":"VOKL55CG","created_at":"2026-05-18T12:33:30Z"}],"graph_snapshots":[{"event_id":"sha256:370a73df3fd10ab9aa4608c85eba442f1ebe07c70f70e8ae24351a26c0f4894b","target":"graph","created_at":"2026-05-17T23:45:11Z","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":"Low-rank approximation is an effective model compression technique to not only reduce parameter storage requirements, but to also reduce computations. For convolutional neural networks (CNNs), however, well-known low-rank approximation methods, such as Tucker or CP decomposition, result in degraded model accuracy because decomposed layers hinder training convergence. In this paper, we propose a new training technique that finds a flat minimum in the view of low-rank approximation without a decomposed structure during training. By preserving the original model structure, 2-dimensional low-rank ","authors_text":"Byeongwook Kim, Dongsoo Lee, Gu-Yeon Wei, Se Jung Kwon","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-24T10:56:02Z","title":"Learning Low-Rank Approximation for CNNs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.10145","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":"sha256:7afe50075747e0f9d18429ebe397fa278220ade054a66c5522779cd5d3c575f3","target":"record","created_at":"2026-05-17T23:45:11Z","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":"2a1e5b47de2c0d3df4da45ef0fa96c6caf98c3109302f67d734661f6f1339e08","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-24T10:56:02Z","title_canon_sha256":"ca5b20183a15ed84824cd2fb2c496cc145fd9988bb5e9c7bd6095373392dcc39"},"schema_version":"1.0","source":{"id":"1905.10145","kind":"arxiv","version":1}},"canonical_sha256":"ab94bef446310d34cfe41426105cc2575f68a2bacc43fbe7e221a8ad4f6a77c8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ab94bef446310d34cfe41426105cc2575f68a2bacc43fbe7e221a8ad4f6a77c8","first_computed_at":"2026-05-17T23:45:11.231251Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:45:11.231251Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"IWMrrG2NZigbBOyJpPM0fN0+8EeuejFlJp6STU6IymxNT8YMG9SIUCsTQvtcubV0YvmtoylSwQizzkFYLbJvCg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:45:11.231778Z","signed_message":"canonical_sha256_bytes"},"source_id":"1905.10145","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7afe50075747e0f9d18429ebe397fa278220ade054a66c5522779cd5d3c575f3","sha256:370a73df3fd10ab9aa4608c85eba442f1ebe07c70f70e8ae24351a26c0f4894b"],"state_sha256":"c4ea7fb2605a9fe4b68cdc5c828a1fc760f00e33fd28d6593a4f67fff0a4f052"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NF7ZfE8Y4nOTexK+m2n9FZ24A9piBJc6HsJLkGazBZL80RvbyQod1B2m7aXY/MF1s0/YmbofyiaNFihngaW9BQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T19:34:42.234364Z","bundle_sha256":"b81722e38914d4c80d04de417f0142622a0c260e5ef7b1978f53c9eb00412a88"}}