{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:CCMVNNYKTKWMLHOIA2DLO7B3CA","short_pith_number":"pith:CCMVNNYK","canonical_record":{"source":{"id":"2102.01732","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-02T20:06:47Z","cross_cats_sorted":["cs.NE"],"title_canon_sha256":"c2b5e78a2b359c65654ba2382aa26ea257821ab65b7ffaaa13dabb799b041066","abstract_canon_sha256":"80e3aff43537be83d427d5dcf8908da8bee462f4f7e28503dfe3bdbefa572359"},"schema_version":"1.0"},"canonical_sha256":"109956b70a9aacc59dc80686b77c3b102b308ea0e359c2c172b2b945812dcb04","source":{"kind":"arxiv","id":"2102.01732","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2102.01732","created_at":"2026-07-05T04:39:16Z"},{"alias_kind":"arxiv_version","alias_value":"2102.01732v2","created_at":"2026-07-05T04:39:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.01732","created_at":"2026-07-05T04:39:16Z"},{"alias_kind":"pith_short_12","alias_value":"CCMVNNYKTKWM","created_at":"2026-07-05T04:39:16Z"},{"alias_kind":"pith_short_16","alias_value":"CCMVNNYKTKWMLHOI","created_at":"2026-07-05T04:39:16Z"},{"alias_kind":"pith_short_8","alias_value":"CCMVNNYK","created_at":"2026-07-05T04:39:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:CCMVNNYKTKWMLHOIA2DLO7B3CA","target":"record","payload":{"canonical_record":{"source":{"id":"2102.01732","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-02T20:06:47Z","cross_cats_sorted":["cs.NE"],"title_canon_sha256":"c2b5e78a2b359c65654ba2382aa26ea257821ab65b7ffaaa13dabb799b041066","abstract_canon_sha256":"80e3aff43537be83d427d5dcf8908da8bee462f4f7e28503dfe3bdbefa572359"},"schema_version":"1.0"},"canonical_sha256":"109956b70a9aacc59dc80686b77c3b102b308ea0e359c2c172b2b945812dcb04","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:39:16.125958Z","signature_b64":"kJwSz4WF1UwVxmzEDzQsSVvLOSfPQqBqzm4eXqnhMaFhCBXOq1vTBnmiOotp0LDlohdJEOz1HpXjGLv6mukvCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"109956b70a9aacc59dc80686b77c3b102b308ea0e359c2c172b2b945812dcb04","last_reissued_at":"2026-07-05T04:39:16.125490Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:39:16.125490Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2102.01732","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":"2026-07-05T04:39:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"R4bVaxE2nJDHTzPR8jSuHoxNt4fhr6mo5lEAodTDOlLJfpBevUL7L0LStwSEz/VIDVeqQ1iZmKC5vtXTs7QpAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T10:18:09.663818Z"},"content_sha256":"f0dbd51e0c26a83fb2a7193f21929649c9afb94cfeb137f86eb236331aca9841","schema_version":"1.0","event_id":"sha256:f0dbd51e0c26a83fb2a7193f21929649c9afb94cfeb137f86eb236331aca9841"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:CCMVNNYKTKWMLHOIA2DLO7B3CA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Truly Sparse Neural Networks at Scale","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE"],"primary_cat":"cs.LG","authors_text":"Decebal Constantin Mocanu, Mykola Pechenizkiyi, Selima Curci","submitted_at":"2021-02-02T20:06:47Z","abstract_excerpt":"Recently, sparse training methods have started to be established as a de facto approach for training and inference efficiency in artificial neural networks. Yet, this efficiency is just in theory. In practice, everyone uses a binary mask to simulate sparsity since the typical deep learning software and hardware are optimized for dense matrix operations. In this paper, we take an orthogonal approach, and we show that we can train truly sparse neural networks to harvest their full potential. To achieve this goal, we introduce three novel contributions, specially designed for sparse neural networ"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.01732","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2102.01732/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2026-07-05T04:39:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iDG6tLNIVYn1nySDGdK5XZApAp9J8DMDoqLVtH5IUrw+TOzrJttYQACD5a4uuhryJLdZdcZJ8QxUpyR28GsJCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T10:18:09.664436Z"},"content_sha256":"a6f32d10b9e974b4f8ff80ff9baeaf90bd682de36b96685d4acc42975335f820","schema_version":"1.0","event_id":"sha256:a6f32d10b9e974b4f8ff80ff9baeaf90bd682de36b96685d4acc42975335f820"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CCMVNNYKTKWMLHOIA2DLO7B3CA/bundle.json","state_url":"https://pith.science/pith/CCMVNNYKTKWMLHOIA2DLO7B3CA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CCMVNNYKTKWMLHOIA2DLO7B3CA/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":"2026-08-08T10:18:09Z","links":{"resolver":"https://pith.science/pith/CCMVNNYKTKWMLHOIA2DLO7B3CA","bundle":"https://pith.science/pith/CCMVNNYKTKWMLHOIA2DLO7B3CA/bundle.json","state":"https://pith.science/pith/CCMVNNYKTKWMLHOIA2DLO7B3CA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CCMVNNYKTKWMLHOIA2DLO7B3CA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:CCMVNNYKTKWMLHOIA2DLO7B3CA","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":"80e3aff43537be83d427d5dcf8908da8bee462f4f7e28503dfe3bdbefa572359","cross_cats_sorted":["cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-02T20:06:47Z","title_canon_sha256":"c2b5e78a2b359c65654ba2382aa26ea257821ab65b7ffaaa13dabb799b041066"},"schema_version":"1.0","source":{"id":"2102.01732","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2102.01732","created_at":"2026-07-05T04:39:16Z"},{"alias_kind":"arxiv_version","alias_value":"2102.01732v2","created_at":"2026-07-05T04:39:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.01732","created_at":"2026-07-05T04:39:16Z"},{"alias_kind":"pith_short_12","alias_value":"CCMVNNYKTKWM","created_at":"2026-07-05T04:39:16Z"},{"alias_kind":"pith_short_16","alias_value":"CCMVNNYKTKWMLHOI","created_at":"2026-07-05T04:39:16Z"},{"alias_kind":"pith_short_8","alias_value":"CCMVNNYK","created_at":"2026-07-05T04:39:16Z"}],"graph_snapshots":[{"event_id":"sha256:a6f32d10b9e974b4f8ff80ff9baeaf90bd682de36b96685d4acc42975335f820","target":"graph","created_at":"2026-07-05T04:39:16Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2102.01732/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recently, sparse training methods have started to be established as a de facto approach for training and inference efficiency in artificial neural networks. Yet, this efficiency is just in theory. In practice, everyone uses a binary mask to simulate sparsity since the typical deep learning software and hardware are optimized for dense matrix operations. In this paper, we take an orthogonal approach, and we show that we can train truly sparse neural networks to harvest their full potential. To achieve this goal, we introduce three novel contributions, specially designed for sparse neural networ","authors_text":"Decebal Constantin Mocanu, Mykola Pechenizkiyi, Selima Curci","cross_cats":["cs.NE"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-02T20:06:47Z","title":"Truly Sparse Neural Networks at Scale"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.01732","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:f0dbd51e0c26a83fb2a7193f21929649c9afb94cfeb137f86eb236331aca9841","target":"record","created_at":"2026-07-05T04:39:16Z","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":"80e3aff43537be83d427d5dcf8908da8bee462f4f7e28503dfe3bdbefa572359","cross_cats_sorted":["cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-02T20:06:47Z","title_canon_sha256":"c2b5e78a2b359c65654ba2382aa26ea257821ab65b7ffaaa13dabb799b041066"},"schema_version":"1.0","source":{"id":"2102.01732","kind":"arxiv","version":2}},"canonical_sha256":"109956b70a9aacc59dc80686b77c3b102b308ea0e359c2c172b2b945812dcb04","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"109956b70a9aacc59dc80686b77c3b102b308ea0e359c2c172b2b945812dcb04","first_computed_at":"2026-07-05T04:39:16.125490Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:39:16.125490Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kJwSz4WF1UwVxmzEDzQsSVvLOSfPQqBqzm4eXqnhMaFhCBXOq1vTBnmiOotp0LDlohdJEOz1HpXjGLv6mukvCA==","signature_status":"signed_v1","signed_at":"2026-07-05T04:39:16.125958Z","signed_message":"canonical_sha256_bytes"},"source_id":"2102.01732","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f0dbd51e0c26a83fb2a7193f21929649c9afb94cfeb137f86eb236331aca9841","sha256:a6f32d10b9e974b4f8ff80ff9baeaf90bd682de36b96685d4acc42975335f820"],"state_sha256":"cfc4452c6c543b7d137fea389ebdb72e8b955bb6aeb30530853f58ffb4dd2b90"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nB0zSvAhcqWilo1bZSGH6C5jAVVLYsgNuk3hbA/Lo04mZjw9NuENr8d0IwO2XvsRrcVaMX83zhmSXPSqkRz+CA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T10:18:09.670054Z","bundle_sha256":"6ba6aa58bd0427f6d0e1000398766e4b81610464899bf8f8054b24b781225cf9"}}