{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:VULR45EB3ROZR5B4DDQJIV625S","short_pith_number":"pith:VULR45EB","canonical_record":{"source":{"id":"1802.03885","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-12T04:16:21Z","cross_cats_sorted":["cs.AR"],"title_canon_sha256":"d98d5476cc5e06131c6822c7d400460cf3b47d8eb5ec617c987dbc1817bbac11","abstract_canon_sha256":"f362856485fc5f1a89998e41eea4428a0cd0560518148cb3655b219d61bd9559"},"schema_version":"1.0"},"canonical_sha256":"ad171e7481dc5d98f43c18e09457daec8d77be756118b2d27a72e3fb51035ab0","source":{"kind":"arxiv","id":"1802.03885","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.03885","created_at":"2026-05-18T00:23:50Z"},{"alias_kind":"arxiv_version","alias_value":"1802.03885v1","created_at":"2026-05-18T00:23:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.03885","created_at":"2026-05-18T00:23:50Z"},{"alias_kind":"pith_short_12","alias_value":"VULR45EB3ROZ","created_at":"2026-05-18T12:32:59Z"},{"alias_kind":"pith_short_16","alias_value":"VULR45EB3ROZR5B4","created_at":"2026-05-18T12:32:59Z"},{"alias_kind":"pith_short_8","alias_value":"VULR45EB","created_at":"2026-05-18T12:32:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:VULR45EB3ROZR5B4DDQJIV625S","target":"record","payload":{"canonical_record":{"source":{"id":"1802.03885","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-12T04:16:21Z","cross_cats_sorted":["cs.AR"],"title_canon_sha256":"d98d5476cc5e06131c6822c7d400460cf3b47d8eb5ec617c987dbc1817bbac11","abstract_canon_sha256":"f362856485fc5f1a89998e41eea4428a0cd0560518148cb3655b219d61bd9559"},"schema_version":"1.0"},"canonical_sha256":"ad171e7481dc5d98f43c18e09457daec8d77be756118b2d27a72e3fb51035ab0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:23:50.126985Z","signature_b64":"AduB/d3TNPiuSW58y0XUGUnY/zz3xdrEZi9cVozfjjkddDcu9jh+cT48BjQGye+NQoSUzvNTYyL+3NIr8x3ZCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ad171e7481dc5d98f43c18e09457daec8d77be756118b2d27a72e3fb51035ab0","last_reissued_at":"2026-05-18T00:23:50.126366Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:23:50.126366Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1802.03885","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":"2026-05-18T00:23:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ca7UqmfIH6OIGkUgJ0LUhjsISqu3eAd5fA+gXIKU5aXa+zMVyYqqthUk6kX7nGF/5T8ELcEhGHuDX1ipIcUiCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-07T14:06:08.315225Z"},"content_sha256":"007d643353e4d15ac7818d565afb20923f3610cdc9e5d1ddf3b4ecf4b481901b","schema_version":"1.0","event_id":"sha256:007d643353e4d15ac7818d565afb20923f3610cdc9e5d1ddf3b4ecf4b481901b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:VULR45EB3ROZR5B4DDQJIV625S","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ClosNets: a Priori Sparse Topologies for Faster DNN Training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AR"],"primary_cat":"cs.LG","authors_text":"Michel A. Kinsy, Mihailo Isakov","submitted_at":"2018-02-12T04:16:21Z","abstract_excerpt":"Fully-connected layers in deep neural networks (DNN) are often the throughput and power bottleneck during training. This is due to their large size and low data reuse. Pruning dense layers can significantly reduce the size of these networks, but this approach can only be applied after training. In this work we propose a novel fully-connected layer that reduces the memory requirements of DNNs without sacrificing accuracy. We replace a dense matrix with products of sparse matrices whose topologies we pick in advance. This allows us to: (1) train significantly smaller networks without a loss in a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.03885","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":"2026-05-18T00:23:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"B93xUc/fQdlEIsll1Lm1DsRcpRBK/57fAoTAgnrdFRtnoj49dq6YTB13splUIhq8lpCi/SF7YqIRv9SpRHmqDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-07T14:06:08.315835Z"},"content_sha256":"ca0692262a25dd5f35555896b54a89da2f9208f656741506192aa6c447b2402a","schema_version":"1.0","event_id":"sha256:ca0692262a25dd5f35555896b54a89da2f9208f656741506192aa6c447b2402a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VULR45EB3ROZR5B4DDQJIV625S/bundle.json","state_url":"https://pith.science/pith/VULR45EB3ROZR5B4DDQJIV625S/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VULR45EB3ROZR5B4DDQJIV625S/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":"2026-06-07T14:06:08Z","links":{"resolver":"https://pith.science/pith/VULR45EB3ROZR5B4DDQJIV625S","bundle":"https://pith.science/pith/VULR45EB3ROZR5B4DDQJIV625S/bundle.json","state":"https://pith.science/pith/VULR45EB3ROZR5B4DDQJIV625S/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VULR45EB3ROZR5B4DDQJIV625S/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:VULR45EB3ROZR5B4DDQJIV625S","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":"f362856485fc5f1a89998e41eea4428a0cd0560518148cb3655b219d61bd9559","cross_cats_sorted":["cs.AR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-12T04:16:21Z","title_canon_sha256":"d98d5476cc5e06131c6822c7d400460cf3b47d8eb5ec617c987dbc1817bbac11"},"schema_version":"1.0","source":{"id":"1802.03885","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.03885","created_at":"2026-05-18T00:23:50Z"},{"alias_kind":"arxiv_version","alias_value":"1802.03885v1","created_at":"2026-05-18T00:23:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.03885","created_at":"2026-05-18T00:23:50Z"},{"alias_kind":"pith_short_12","alias_value":"VULR45EB3ROZ","created_at":"2026-05-18T12:32:59Z"},{"alias_kind":"pith_short_16","alias_value":"VULR45EB3ROZR5B4","created_at":"2026-05-18T12:32:59Z"},{"alias_kind":"pith_short_8","alias_value":"VULR45EB","created_at":"2026-05-18T12:32:59Z"}],"graph_snapshots":[{"event_id":"sha256:ca0692262a25dd5f35555896b54a89da2f9208f656741506192aa6c447b2402a","target":"graph","created_at":"2026-05-18T00:23:50Z","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":"Fully-connected layers in deep neural networks (DNN) are often the throughput and power bottleneck during training. This is due to their large size and low data reuse. Pruning dense layers can significantly reduce the size of these networks, but this approach can only be applied after training. In this work we propose a novel fully-connected layer that reduces the memory requirements of DNNs without sacrificing accuracy. We replace a dense matrix with products of sparse matrices whose topologies we pick in advance. This allows us to: (1) train significantly smaller networks without a loss in a","authors_text":"Michel A. Kinsy, Mihailo Isakov","cross_cats":["cs.AR"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-12T04:16:21Z","title":"ClosNets: a Priori Sparse Topologies for Faster DNN Training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.03885","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":"sha256:007d643353e4d15ac7818d565afb20923f3610cdc9e5d1ddf3b4ecf4b481901b","target":"record","created_at":"2026-05-18T00:23:50Z","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":"f362856485fc5f1a89998e41eea4428a0cd0560518148cb3655b219d61bd9559","cross_cats_sorted":["cs.AR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-12T04:16:21Z","title_canon_sha256":"d98d5476cc5e06131c6822c7d400460cf3b47d8eb5ec617c987dbc1817bbac11"},"schema_version":"1.0","source":{"id":"1802.03885","kind":"arxiv","version":1}},"canonical_sha256":"ad171e7481dc5d98f43c18e09457daec8d77be756118b2d27a72e3fb51035ab0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ad171e7481dc5d98f43c18e09457daec8d77be756118b2d27a72e3fb51035ab0","first_computed_at":"2026-05-18T00:23:50.126366Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:23:50.126366Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AduB/d3TNPiuSW58y0XUGUnY/zz3xdrEZi9cVozfjjkddDcu9jh+cT48BjQGye+NQoSUzvNTYyL+3NIr8x3ZCw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:23:50.126985Z","signed_message":"canonical_sha256_bytes"},"source_id":"1802.03885","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:007d643353e4d15ac7818d565afb20923f3610cdc9e5d1ddf3b4ecf4b481901b","sha256:ca0692262a25dd5f35555896b54a89da2f9208f656741506192aa6c447b2402a"],"state_sha256":"4b2465dda742066d7271e9d9eeecb3039e1f99e97ef5172ce80b09cede41ab23"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+b5r/E7wpcKywefu/+cCxaYaL/hbm7vYHX/tYH7JkeEf3OHEpv+TAfYJRCiSZfo5pQKHSzewqAFTviFFkskLBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-07T14:06:08.319679Z","bundle_sha256":"45903ee5850309979b5e5bc97f76d3e9836627e600ad567f5082198d66f7791b"}}