{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:75OBVREO6GB4S6V34ENU6VQAGC","short_pith_number":"pith:75OBVREO","canonical_record":{"source":{"id":"2304.05511","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-04-11T21:37:13Z","cross_cats_sorted":[],"title_canon_sha256":"5c19bdf74949a4373b2cec30d18f654c2b8c35086e792d66e8c3391e2aabb182","abstract_canon_sha256":"c3e60a98df4e3a06a217b8f8ecdd40685a33769742e97fec77c9522f9ac09965"},"schema_version":"1.0"},"canonical_sha256":"ff5c1ac48ef183c97abbe11b4f560030a88781ce597f8d57a6364fdc0d58f15b","source":{"kind":"arxiv","id":"2304.05511","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.05511","created_at":"2026-07-05T06:00:19Z"},{"alias_kind":"arxiv_version","alias_value":"2304.05511v1","created_at":"2026-07-05T06:00:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.05511","created_at":"2026-07-05T06:00:19Z"},{"alias_kind":"pith_short_12","alias_value":"75OBVREO6GB4","created_at":"2026-07-05T06:00:19Z"},{"alias_kind":"pith_short_16","alias_value":"75OBVREO6GB4S6V3","created_at":"2026-07-05T06:00:19Z"},{"alias_kind":"pith_short_8","alias_value":"75OBVREO","created_at":"2026-07-05T06:00:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:75OBVREO6GB4S6V34ENU6VQAGC","target":"record","payload":{"canonical_record":{"source":{"id":"2304.05511","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-04-11T21:37:13Z","cross_cats_sorted":[],"title_canon_sha256":"5c19bdf74949a4373b2cec30d18f654c2b8c35086e792d66e8c3391e2aabb182","abstract_canon_sha256":"c3e60a98df4e3a06a217b8f8ecdd40685a33769742e97fec77c9522f9ac09965"},"schema_version":"1.0"},"canonical_sha256":"ff5c1ac48ef183c97abbe11b4f560030a88781ce597f8d57a6364fdc0d58f15b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:00:19.600543Z","signature_b64":"y/U7Z1jQtuQ++Wp1WSepQ/+JhKhk94AtJNDTI2KgoP2WZt8UTFk45/Azk2ELwzfbC9XOl8jy4/IyJ7+uC1RTCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ff5c1ac48ef183c97abbe11b4f560030a88781ce597f8d57a6364fdc0d58f15b","last_reissued_at":"2026-07-05T06:00:19.599943Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:00:19.599943Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2304.05511","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":"2026-07-05T06:00:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MVQAV9YVS4PRMKzpUrlnDyMNWIXboNEmnRCVFE71GJByur83fNBXm1Dnzi+mMuY80SNVeVIiGAlVh8viDpyLBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T06:01:04.967059Z"},"content_sha256":"d389976cd74aacd6c4313de9140d1b37500a499caa03d95ef273e07be9bdd47b","schema_version":"1.0","event_id":"sha256:d389976cd74aacd6c4313de9140d1b37500a499caa03d95ef273e07be9bdd47b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:75OBVREO6GB4S6V34ENU6VQAGC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Training Large Language Models Efficiently with Sparsity and Dataflow","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Darshan Gandhi, Raghu Prabhakar, Urmish Thakker, Venkat Srinivasan","submitted_at":"2023-04-11T21:37:13Z","abstract_excerpt":"Large foundation language models have shown their versatility in being able to be adapted to perform a wide variety of downstream tasks, such as text generation, sentiment analysis, semantic search etc. However, training such large foundational models is a non-trivial exercise that requires a significant amount of compute power and expertise from machine learning and systems experts. As models get larger, these demands are only increasing. Sparsity is a promising technique to relieve the compute requirements for training. However, sparsity introduces new challenges in training the sparse model"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.05511","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2304.05511/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":"2026-07-05T06:00:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yXWnQtAy6xqZT6NVAYBol1QdidAQQUU9BI1psNJR0WYdCHg4k74bFl3k6Zx+cUWtFv3/YSKzILGVj+5G8ZxjAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T06:01:04.967670Z"},"content_sha256":"4c76818b563322af27e548e66978ab18aa38c173118d28252bdb77fb184a3391","schema_version":"1.0","event_id":"sha256:4c76818b563322af27e548e66978ab18aa38c173118d28252bdb77fb184a3391"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/75OBVREO6GB4S6V34ENU6VQAGC/bundle.json","state_url":"https://pith.science/pith/75OBVREO6GB4S6V34ENU6VQAGC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/75OBVREO6GB4S6V34ENU6VQAGC/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":"2026-08-17T06:01:04Z","links":{"resolver":"https://pith.science/pith/75OBVREO6GB4S6V34ENU6VQAGC","bundle":"https://pith.science/pith/75OBVREO6GB4S6V34ENU6VQAGC/bundle.json","state":"https://pith.science/pith/75OBVREO6GB4S6V34ENU6VQAGC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/75OBVREO6GB4S6V34ENU6VQAGC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:75OBVREO6GB4S6V34ENU6VQAGC","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":"c3e60a98df4e3a06a217b8f8ecdd40685a33769742e97fec77c9522f9ac09965","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-04-11T21:37:13Z","title_canon_sha256":"5c19bdf74949a4373b2cec30d18f654c2b8c35086e792d66e8c3391e2aabb182"},"schema_version":"1.0","source":{"id":"2304.05511","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.05511","created_at":"2026-07-05T06:00:19Z"},{"alias_kind":"arxiv_version","alias_value":"2304.05511v1","created_at":"2026-07-05T06:00:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.05511","created_at":"2026-07-05T06:00:19Z"},{"alias_kind":"pith_short_12","alias_value":"75OBVREO6GB4","created_at":"2026-07-05T06:00:19Z"},{"alias_kind":"pith_short_16","alias_value":"75OBVREO6GB4S6V3","created_at":"2026-07-05T06:00:19Z"},{"alias_kind":"pith_short_8","alias_value":"75OBVREO","created_at":"2026-07-05T06:00:19Z"}],"graph_snapshots":[{"event_id":"sha256:4c76818b563322af27e548e66978ab18aa38c173118d28252bdb77fb184a3391","target":"graph","created_at":"2026-07-05T06:00:19Z","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/2304.05511/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large foundation language models have shown their versatility in being able to be adapted to perform a wide variety of downstream tasks, such as text generation, sentiment analysis, semantic search etc. However, training such large foundational models is a non-trivial exercise that requires a significant amount of compute power and expertise from machine learning and systems experts. As models get larger, these demands are only increasing. Sparsity is a promising technique to relieve the compute requirements for training. However, sparsity introduces new challenges in training the sparse model","authors_text":"Darshan Gandhi, Raghu Prabhakar, Urmish Thakker, Venkat Srinivasan","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-04-11T21:37:13Z","title":"Training Large Language Models Efficiently with Sparsity and Dataflow"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.05511","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:d389976cd74aacd6c4313de9140d1b37500a499caa03d95ef273e07be9bdd47b","target":"record","created_at":"2026-07-05T06:00:19Z","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":"c3e60a98df4e3a06a217b8f8ecdd40685a33769742e97fec77c9522f9ac09965","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-04-11T21:37:13Z","title_canon_sha256":"5c19bdf74949a4373b2cec30d18f654c2b8c35086e792d66e8c3391e2aabb182"},"schema_version":"1.0","source":{"id":"2304.05511","kind":"arxiv","version":1}},"canonical_sha256":"ff5c1ac48ef183c97abbe11b4f560030a88781ce597f8d57a6364fdc0d58f15b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ff5c1ac48ef183c97abbe11b4f560030a88781ce597f8d57a6364fdc0d58f15b","first_computed_at":"2026-07-05T06:00:19.599943Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:00:19.599943Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"y/U7Z1jQtuQ++Wp1WSepQ/+JhKhk94AtJNDTI2KgoP2WZt8UTFk45/Azk2ELwzfbC9XOl8jy4/IyJ7+uC1RTCw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:00:19.600543Z","signed_message":"canonical_sha256_bytes"},"source_id":"2304.05511","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d389976cd74aacd6c4313de9140d1b37500a499caa03d95ef273e07be9bdd47b","sha256:4c76818b563322af27e548e66978ab18aa38c173118d28252bdb77fb184a3391"],"state_sha256":"3df5dd864e7e90fe44496cb38cf1c80253a6492e478d2622345a0c8794f8707b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UkQtTbe1lxq2vPsjQA2W62JGXOflLNYg473WRUJaNYUgm8YI+qKt2EDgbEdYw6us0Hs0X3WCbb2cFfHv0DPoDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T06:01:04.971576Z","bundle_sha256":"aff7a3538d40de864faae8ce47967659ee831f25cc30ad5e5c62d5a5820bd0c8"}}