{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:75OBVREO6GB4S6V34ENU6VQAGC","short_pith_number":"pith:75OBVREO","schema_version":"1.0","canonical_sha256":"ff5c1ac48ef183c97abbe11b4f560030a88781ce597f8d57a6364fdc0d58f15b","source":{"kind":"arxiv","id":"2304.05511","version":1},"attestation_state":"computed","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"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"},"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"},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2304.05511","created_at":"2026-07-05T06:00:19.600015+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.05511v1","created_at":"2026-07-05T06:00:19.600015+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.05511","created_at":"2026-07-05T06:00:19.600015+00:00"},{"alias_kind":"pith_short_12","alias_value":"75OBVREO6GB4","created_at":"2026-07-05T06:00:19.600015+00:00"},{"alias_kind":"pith_short_16","alias_value":"75OBVREO6GB4S6V3","created_at":"2026-07-05T06:00:19.600015+00:00"},{"alias_kind":"pith_short_8","alias_value":"75OBVREO","created_at":"2026-07-05T06:00:19.600015+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/75OBVREO6GB4S6V34ENU6VQAGC","json":"https://pith.science/pith/75OBVREO6GB4S6V34ENU6VQAGC.json","graph_json":"https://pith.science/api/pith-number/75OBVREO6GB4S6V34ENU6VQAGC/graph.json","events_json":"https://pith.science/api/pith-number/75OBVREO6GB4S6V34ENU6VQAGC/events.json","paper":"https://pith.science/paper/75OBVREO"},"agent_actions":{"view_html":"https://pith.science/pith/75OBVREO6GB4S6V34ENU6VQAGC","download_json":"https://pith.science/pith/75OBVREO6GB4S6V34ENU6VQAGC.json","view_paper":"https://pith.science/paper/75OBVREO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.05511&json=true","fetch_graph":"https://pith.science/api/pith-number/75OBVREO6GB4S6V34ENU6VQAGC/graph.json","fetch_events":"https://pith.science/api/pith-number/75OBVREO6GB4S6V34ENU6VQAGC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/75OBVREO6GB4S6V34ENU6VQAGC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/75OBVREO6GB4S6V34ENU6VQAGC/action/storage_attestation","attest_author":"https://pith.science/pith/75OBVREO6GB4S6V34ENU6VQAGC/action/author_attestation","sign_citation":"https://pith.science/pith/75OBVREO6GB4S6V34ENU6VQAGC/action/citation_signature","submit_replication":"https://pith.science/pith/75OBVREO6GB4S6V34ENU6VQAGC/action/replication_record"}},"created_at":"2026-07-05T06:00:19.600015+00:00","updated_at":"2026-07-05T06:00:19.600015+00:00"}