{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:77LEJOW5N2NDB632ZS4VWKM7IU","short_pith_number":"pith:77LEJOW5","canonical_record":{"source":{"id":"1810.00859","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-01T17:55:43Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"22271591fe6f2dfac2952b947e0567b22b2d16b0e2871ca21998e2399999a0ae","abstract_canon_sha256":"6ef86d8e453dc58ed7af41e79ddc2e1f484bb33adaeb73d95dd47dd6a0a1c377"},"schema_version":"1.0"},"canonical_sha256":"ffd644badd6e9a30fb7accb95b299f450af2a34d4d23958f2174997ca2e4604d","source":{"kind":"arxiv","id":"1810.00859","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.00859","created_at":"2026-05-17T23:46:55Z"},{"alias_kind":"arxiv_version","alias_value":"1810.00859v2","created_at":"2026-05-17T23:46:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.00859","created_at":"2026-05-17T23:46:55Z"},{"alias_kind":"pith_short_12","alias_value":"77LEJOW5N2ND","created_at":"2026-05-18T12:32:11Z"},{"alias_kind":"pith_short_16","alias_value":"77LEJOW5N2NDB632","created_at":"2026-05-18T12:32:11Z"},{"alias_kind":"pith_short_8","alias_value":"77LEJOW5","created_at":"2026-05-18T12:32:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:77LEJOW5N2NDB632ZS4VWKM7IU","target":"record","payload":{"canonical_record":{"source":{"id":"1810.00859","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-01T17:55:43Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"22271591fe6f2dfac2952b947e0567b22b2d16b0e2871ca21998e2399999a0ae","abstract_canon_sha256":"6ef86d8e453dc58ed7af41e79ddc2e1f484bb33adaeb73d95dd47dd6a0a1c377"},"schema_version":"1.0"},"canonical_sha256":"ffd644badd6e9a30fb7accb95b299f450af2a34d4d23958f2174997ca2e4604d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:46:55.102387Z","signature_b64":"EkqdoGGeV/CiCkk/3U5DtOvSuMC1p40x0a7KBqxlM8ebT+s3JZPahP/iJcuGCqFhLz13N0WyZ85GlFYur4bbAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ffd644badd6e9a30fb7accb95b299f450af2a34d4d23958f2174997ca2e4604d","last_reissued_at":"2026-05-17T23:46:55.101845Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:46:55.101845Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1810.00859","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":"2026-05-17T23:46:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"e6EUlPPFZXvRKDNJ/5zthmTZatKwD2Re+TGWYoij1HtQIUcfb5KXCF1kleIrPyLJlSh0LZcXpL8ku2ZJq7fgBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T19:57:33.886818Z"},"content_sha256":"b0db191a49ae2f5d958624991f49424a15fb7192f3ee11726ef6d88578796485","schema_version":"1.0","event_id":"sha256:b0db191a49ae2f5d958624991f49424a15fb7192f3ee11726ef6d88578796485"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:77LEJOW5N2NDB632ZS4VWKM7IU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Dynamic Sparse Graph for Efficient Deep Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Guoqi Li, Lei Deng, Liu Liu, Maohua Zhu, Xing Hu, Yuan Xie, Yufei Ding","submitted_at":"2018-10-01T17:55:43Z","abstract_excerpt":"We propose to execute deep neural networks (DNNs) with dynamic and sparse graph (DSG) structure for compressive memory and accelerative execution during both training and inference. The great success of DNNs motivates the pursuing of lightweight models for the deployment onto embedded devices. However, most of the previous studies optimize for inference while neglect training or even complicate it. Training is far more intractable, since (i) the neurons dominate the memory cost rather than the weights in inference; (ii) the dynamic activation makes previous sparse acceleration via one-off opti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.00859","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":""},"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":"2026-05-17T23:46:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ox10RTSzrKCOLFYlO8BS18+9BqGO+fHWGDAP1TP4FSpW87rJMsi8uPSR8uwnghd84F5WGX6OI7jtkL5NO4ouBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T19:57:33.887488Z"},"content_sha256":"9e87f9d490a48c565a007de21de9a20e699f3f35d7a5189840877db25a05d00b","schema_version":"1.0","event_id":"sha256:9e87f9d490a48c565a007de21de9a20e699f3f35d7a5189840877db25a05d00b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/77LEJOW5N2NDB632ZS4VWKM7IU/bundle.json","state_url":"https://pith.science/pith/77LEJOW5N2NDB632ZS4VWKM7IU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/77LEJOW5N2NDB632ZS4VWKM7IU/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":"2026-05-25T19:57:33Z","links":{"resolver":"https://pith.science/pith/77LEJOW5N2NDB632ZS4VWKM7IU","bundle":"https://pith.science/pith/77LEJOW5N2NDB632ZS4VWKM7IU/bundle.json","state":"https://pith.science/pith/77LEJOW5N2NDB632ZS4VWKM7IU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/77LEJOW5N2NDB632ZS4VWKM7IU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:77LEJOW5N2NDB632ZS4VWKM7IU","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":"6ef86d8e453dc58ed7af41e79ddc2e1f484bb33adaeb73d95dd47dd6a0a1c377","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-01T17:55:43Z","title_canon_sha256":"22271591fe6f2dfac2952b947e0567b22b2d16b0e2871ca21998e2399999a0ae"},"schema_version":"1.0","source":{"id":"1810.00859","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.00859","created_at":"2026-05-17T23:46:55Z"},{"alias_kind":"arxiv_version","alias_value":"1810.00859v2","created_at":"2026-05-17T23:46:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.00859","created_at":"2026-05-17T23:46:55Z"},{"alias_kind":"pith_short_12","alias_value":"77LEJOW5N2ND","created_at":"2026-05-18T12:32:11Z"},{"alias_kind":"pith_short_16","alias_value":"77LEJOW5N2NDB632","created_at":"2026-05-18T12:32:11Z"},{"alias_kind":"pith_short_8","alias_value":"77LEJOW5","created_at":"2026-05-18T12:32:11Z"}],"graph_snapshots":[{"event_id":"sha256:9e87f9d490a48c565a007de21de9a20e699f3f35d7a5189840877db25a05d00b","target":"graph","created_at":"2026-05-17T23:46:55Z","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":"We propose to execute deep neural networks (DNNs) with dynamic and sparse graph (DSG) structure for compressive memory and accelerative execution during both training and inference. The great success of DNNs motivates the pursuing of lightweight models for the deployment onto embedded devices. However, most of the previous studies optimize for inference while neglect training or even complicate it. Training is far more intractable, since (i) the neurons dominate the memory cost rather than the weights in inference; (ii) the dynamic activation makes previous sparse acceleration via one-off opti","authors_text":"Guoqi Li, Lei Deng, Liu Liu, Maohua Zhu, Xing Hu, Yuan Xie, Yufei Ding","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-01T17:55:43Z","title":"Dynamic Sparse Graph for Efficient Deep Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.00859","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:b0db191a49ae2f5d958624991f49424a15fb7192f3ee11726ef6d88578796485","target":"record","created_at":"2026-05-17T23:46:55Z","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":"6ef86d8e453dc58ed7af41e79ddc2e1f484bb33adaeb73d95dd47dd6a0a1c377","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-01T17:55:43Z","title_canon_sha256":"22271591fe6f2dfac2952b947e0567b22b2d16b0e2871ca21998e2399999a0ae"},"schema_version":"1.0","source":{"id":"1810.00859","kind":"arxiv","version":2}},"canonical_sha256":"ffd644badd6e9a30fb7accb95b299f450af2a34d4d23958f2174997ca2e4604d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ffd644badd6e9a30fb7accb95b299f450af2a34d4d23958f2174997ca2e4604d","first_computed_at":"2026-05-17T23:46:55.101845Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:46:55.101845Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"EkqdoGGeV/CiCkk/3U5DtOvSuMC1p40x0a7KBqxlM8ebT+s3JZPahP/iJcuGCqFhLz13N0WyZ85GlFYur4bbAw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:46:55.102387Z","signed_message":"canonical_sha256_bytes"},"source_id":"1810.00859","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b0db191a49ae2f5d958624991f49424a15fb7192f3ee11726ef6d88578796485","sha256:9e87f9d490a48c565a007de21de9a20e699f3f35d7a5189840877db25a05d00b"],"state_sha256":"8fa2a0067f746f3ab7eaa9effeae485244d9f0e9464fa90df0d762bfc1cae7fc"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"e18LUUREe9xoY84CjS+Y5N0wQhld6z7IT1qNSoKcDcXEg7VtSlp7zdFm1smXmu0xaNc0BJtWesvNabfzfDS3DA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T19:57:33.891490Z","bundle_sha256":"e962e1ce911301ebeb2b72731cf9ca8fa09c2493da635b2fbe78f6297330649c"}}