{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:S3WBVI46ECL4ELVW6R5MSMCCHT","short_pith_number":"pith:S3WBVI46","schema_version":"1.0","canonical_sha256":"96ec1aa39e2097c22eb6f47ac930423cd1e77b5306aaaa548ba1972ee546994b","source":{"kind":"arxiv","id":"2304.03589","version":1},"attestation_state":"computed","paper":{"title":"On Efficient Training of Large-Scale Deep Learning Models: A Literature Review","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.DC"],"primary_cat":"cs.LG","authors_text":"Dacheng Tao, Liang Ding, Li Shen, Xinmei Tian, Yan Sun, Zhiyuan Yu","submitted_at":"2023-04-07T11:13:23Z","abstract_excerpt":"The field of deep learning has witnessed significant progress, particularly in computer vision (CV), natural language processing (NLP), and speech. The use of large-scale models trained on vast amounts of data holds immense promise for practical applications, enhancing industrial productivity and facilitating social development. With the increasing demands on computational capacity, though numerous studies have explored the efficient training, a comprehensive summarization on acceleration techniques of training deep learning models is still much anticipated. In this survey, we present a detail"},"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":"2304.03589","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-04-07T11:13:23Z","cross_cats_sorted":["cs.AI","cs.DC"],"title_canon_sha256":"7bc2ec35f9e157e75ef9a57da0cda25a1696829f0fa5d37d87f15bb493b3db1f","abstract_canon_sha256":"84edaeb6cea359ad79b510e404537d384aab8888891377f2d11781bf29638fe2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:58:57.859971Z","signature_b64":"yNtSDIB/KTGyXOG8oGkykzzOXuSDmHDPY53nutVWadKdEh6iBaYjTX3emLvt9aXDBp3sXuIwBUed0r54NYt2Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"96ec1aa39e2097c22eb6f47ac930423cd1e77b5306aaaa548ba1972ee546994b","last_reissued_at":"2026-07-05T05:58:57.859479Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:58:57.859479Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On Efficient Training of Large-Scale Deep Learning Models: A Literature Review","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.DC"],"primary_cat":"cs.LG","authors_text":"Dacheng Tao, Liang Ding, Li Shen, Xinmei Tian, Yan Sun, Zhiyuan Yu","submitted_at":"2023-04-07T11:13:23Z","abstract_excerpt":"The field of deep learning has witnessed significant progress, particularly in computer vision (CV), natural language processing (NLP), and speech. The use of large-scale models trained on vast amounts of data holds immense promise for practical applications, enhancing industrial productivity and facilitating social development. With the increasing demands on computational capacity, though numerous studies have explored the efficient training, a comprehensive summarization on acceleration techniques of training deep learning models is still much anticipated. In this survey, we present a detail"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.03589","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/2304.03589/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":"2304.03589","created_at":"2026-07-05T05:58:57.859547+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.03589v1","created_at":"2026-07-05T05:58:57.859547+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.03589","created_at":"2026-07-05T05:58:57.859547+00:00"},{"alias_kind":"pith_short_12","alias_value":"S3WBVI46ECL4","created_at":"2026-07-05T05:58:57.859547+00:00"},{"alias_kind":"pith_short_16","alias_value":"S3WBVI46ECL4ELVW","created_at":"2026-07-05T05:58:57.859547+00:00"},{"alias_kind":"pith_short_8","alias_value":"S3WBVI46","created_at":"2026-07-05T05:58:57.859547+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.23656","citing_title":"Recursive Block-Diagonal Coupling for Resource-Efficient Training of Vision Models","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2506.12876","citing_title":"MaskPro: Linear-Space Probabilistic Learning for Strict (N:M)-Sparsity on LLMs","ref_index":20,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/S3WBVI46ECL4ELVW6R5MSMCCHT","json":"https://pith.science/pith/S3WBVI46ECL4ELVW6R5MSMCCHT.json","graph_json":"https://pith.science/api/pith-number/S3WBVI46ECL4ELVW6R5MSMCCHT/graph.json","events_json":"https://pith.science/api/pith-number/S3WBVI46ECL4ELVW6R5MSMCCHT/events.json","paper":"https://pith.science/paper/S3WBVI46"},"agent_actions":{"view_html":"https://pith.science/pith/S3WBVI46ECL4ELVW6R5MSMCCHT","download_json":"https://pith.science/pith/S3WBVI46ECL4ELVW6R5MSMCCHT.json","view_paper":"https://pith.science/paper/S3WBVI46","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.03589&json=true","fetch_graph":"https://pith.science/api/pith-number/S3WBVI46ECL4ELVW6R5MSMCCHT/graph.json","fetch_events":"https://pith.science/api/pith-number/S3WBVI46ECL4ELVW6R5MSMCCHT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/S3WBVI46ECL4ELVW6R5MSMCCHT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/S3WBVI46ECL4ELVW6R5MSMCCHT/action/storage_attestation","attest_author":"https://pith.science/pith/S3WBVI46ECL4ELVW6R5MSMCCHT/action/author_attestation","sign_citation":"https://pith.science/pith/S3WBVI46ECL4ELVW6R5MSMCCHT/action/citation_signature","submit_replication":"https://pith.science/pith/S3WBVI46ECL4ELVW6R5MSMCCHT/action/replication_record"}},"created_at":"2026-07-05T05:58:57.859547+00:00","updated_at":"2026-07-05T05:58:57.859547+00:00"}