{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:EDVVLK2BT67RMFMH2HFDZ4BPYI","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":"1a4ec69c956eee316308a7d5aac91af865f2dd6a927d25c894035c123cbad0b9","cross_cats_sorted":["cs.DC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-13T17:29:47Z","title_canon_sha256":"41336821c81ff05ac6c8d1465e457e4e473e7de017d0b07bae8e1f48991b0145"},"schema_version":"1.0","source":{"id":"2002.05645","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2002.05645","created_at":"2026-07-05T01:08:11Z"},{"alias_kind":"arxiv_version","alias_value":"2002.05645v5","created_at":"2026-07-05T01:08:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.05645","created_at":"2026-07-05T01:08:11Z"},{"alias_kind":"pith_short_12","alias_value":"EDVVLK2BT67R","created_at":"2026-07-05T01:08:11Z"},{"alias_kind":"pith_short_16","alias_value":"EDVVLK2BT67RMFMH","created_at":"2026-07-05T01:08:11Z"},{"alias_kind":"pith_short_8","alias_value":"EDVVLK2B","created_at":"2026-07-05T01:08:11Z"}],"graph_snapshots":[{"event_id":"sha256:44c9f31838af7cd3a52372622c0ecfa1939e9f541d60c5c35d764877da0780b3","target":"graph","created_at":"2026-07-05T01:08:11Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2002.05645/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Widely popular transformer-based NLP models such as BERT and Turing-NLG have enormous capacity trending to billions of parameters. Current execution methods demand brute-force resources such as HBM devices and high speed interconnectivity for data parallelism. In this paper, we introduce a new relay-style execution technique called L2L (layer-to-layer) where at any given moment, the device memory is primarily populated only with the executing layer(s)'s footprint. The model resides in the DRAM memory attached to either a CPU or an FPGA as an entity we call eager param-server (EPS). To overcome","authors_text":"Bharadwaj Pudipeddi, Jinwen Xi, Maral Mesmakhosroshahi, Sujeeth Bharadwaj","cross_cats":["cs.DC","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-13T17:29:47Z","title":"Training Large Neural Networks with Constant Memory using a New Execution Algorithm"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.05645","kind":"arxiv","version":5},"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":"sha256:3b1040e474fa1f23a509af13eaf3d883160f0b4fdf074b5f82fc088aad4f7b53","target":"record","created_at":"2026-07-05T01:08:11Z","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":"1a4ec69c956eee316308a7d5aac91af865f2dd6a927d25c894035c123cbad0b9","cross_cats_sorted":["cs.DC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-13T17:29:47Z","title_canon_sha256":"41336821c81ff05ac6c8d1465e457e4e473e7de017d0b07bae8e1f48991b0145"},"schema_version":"1.0","source":{"id":"2002.05645","kind":"arxiv","version":5}},"canonical_sha256":"20eb55ab419fbf161587d1ca3cf02fc22c974f30123a843131286f9ce647a017","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"20eb55ab419fbf161587d1ca3cf02fc22c974f30123a843131286f9ce647a017","first_computed_at":"2026-07-05T01:08:11.691476Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:08:11.691476Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ToJZrPH22KVCzJt7TqAJpRyZDuUIkOQnTQhIU+NIRXWy9BGR9Jt7pMhR8c2R/ilTHEYIPWewHO343qzfB++bBA==","signature_status":"signed_v1","signed_at":"2026-07-05T01:08:11.691955Z","signed_message":"canonical_sha256_bytes"},"source_id":"2002.05645","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3b1040e474fa1f23a509af13eaf3d883160f0b4fdf074b5f82fc088aad4f7b53","sha256:44c9f31838af7cd3a52372622c0ecfa1939e9f541d60c5c35d764877da0780b3"],"state_sha256":"2234e0f6fd89fe7dd393477c012ce4f43b49d72ef898de5026543000759c4d6e"}