{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:WBAGA3UJKA5INZPGYX7MRYYYMA","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":"140dea10ea468d5f767b21f796d91a8895ce0ce92f233c8b2d14b94c854f35b9","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-01-06T18:58:09Z","title_canon_sha256":"64d77cf43963b958c7d42496c9b7b5646f46e79dbf69f9bb14ed952cc7179b85"},"schema_version":"1.0","source":{"id":"2301.02654","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2301.02654","created_at":"2026-07-05T05:31:08Z"},{"alias_kind":"arxiv_version","alias_value":"2301.02654v1","created_at":"2026-07-05T05:31:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.02654","created_at":"2026-07-05T05:31:08Z"},{"alias_kind":"pith_short_12","alias_value":"WBAGA3UJKA5I","created_at":"2026-07-05T05:31:08Z"},{"alias_kind":"pith_short_16","alias_value":"WBAGA3UJKA5INZPG","created_at":"2026-07-05T05:31:08Z"},{"alias_kind":"pith_short_8","alias_value":"WBAGA3UJ","created_at":"2026-07-05T05:31:08Z"}],"graph_snapshots":[{"event_id":"sha256:c30038af5a387ebdc7ed7b2ca887bf6cfe4664dde42577e2e6b097bd214c38fd","target":"graph","created_at":"2026-07-05T05:31:08Z","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/2301.02654/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large-scale Transformer models are known for their exceptional performance in a range of tasks, but training them can be difficult due to the requirement for communication-intensive model parallelism. One way to improve training speed is to compress the message size in communication. Previous approaches have primarily focused on compressing gradients in a data parallelism setting, but compression in a model-parallel setting is an understudied area. We have discovered that model parallelism has fundamentally different characteristics than data parallelism. In this work, we present the first emp","authors_text":"Dacheng Li, Eric P. Xing, Hongyi Wang, Shivaram Venkataraman, Song Bian","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-01-06T18:58:09Z","title":"Does compressing activations help model parallel training?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.02654","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":"sha256:34bc78df30206d032f268b7135e2984aa2bd7fa513469a0ebc29536b82ac759c","target":"record","created_at":"2026-07-05T05:31:08Z","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":"140dea10ea468d5f767b21f796d91a8895ce0ce92f233c8b2d14b94c854f35b9","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-01-06T18:58:09Z","title_canon_sha256":"64d77cf43963b958c7d42496c9b7b5646f46e79dbf69f9bb14ed952cc7179b85"},"schema_version":"1.0","source":{"id":"2301.02654","kind":"arxiv","version":1}},"canonical_sha256":"b040606e89503a86e5e6c5fec8e3186020bfc6a76bd7fe2e69960b916f103417","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b040606e89503a86e5e6c5fec8e3186020bfc6a76bd7fe2e69960b916f103417","first_computed_at":"2026-07-05T05:31:08.994841Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:31:08.994841Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AeS6y8CM4GvYcUN/xK91hjws1F+SrWtoy8alkPxdfOgZ973+sX2nSy5Xbsh4x7Xx+6kauht/9jcJOeHeu1gZAw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:31:08.995290Z","signed_message":"canonical_sha256_bytes"},"source_id":"2301.02654","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:34bc78df30206d032f268b7135e2984aa2bd7fa513469a0ebc29536b82ac759c","sha256:c30038af5a387ebdc7ed7b2ca887bf6cfe4664dde42577e2e6b097bd214c38fd"],"state_sha256":"230136d0f9fe28d644e8f8769d427bf6d712fd15c966087ae8aeae7e333084ca"}