{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:ONRCZJGWJZJA3P5VCNSXODCPFZ","short_pith_number":"pith:ONRCZJGW","schema_version":"1.0","canonical_sha256":"73622ca4d64e520dbfb51365770c4f2e6478029165c52feffb85d7f8cb4a6a0c","source":{"kind":"arxiv","id":"2302.12441","version":2},"attestation_state":"computed","paper":{"title":"MUX-PLMs: Data Multiplexing for High-throughput Language Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Ameet Deshpande, Carlos E. Jimenez, Izhak Shafran, Karthik Narasimhan, Mingqiu Wang, Vishvak Murahari, Yuan Cao","submitted_at":"2023-02-24T04:03:15Z","abstract_excerpt":"The widespread adoption of large language models such as ChatGPT and Bard has led to unprecedented demand for these technologies. The burgeoning cost of inference for ever-increasing model sizes coupled with hardware shortages has limited affordable access and poses a pressing need for efficiency approaches geared towards high throughput and performance. Multi-input multi-output (MIMO) algorithms such as data multiplexing, offer a promising solution with a many-fold increase in throughput by performing inference for multiple inputs at the cost of a single input. Yet these approaches are not cu"},"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":"2302.12441","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2023-02-24T04:03:15Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"fc741f75249be626c35416303ba3b725c797efb1958000d1ada214249a9e2eb9","abstract_canon_sha256":"c41c271bb2535c5c36e6783b9d70737ab3fa57f809c4de60f1c179562e7c41b4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:12:44.941001Z","signature_b64":"jDkiV2IE/x6VHvxQT9SBWx8DESXtdMzWMKHmUJW9+rnsQiNUIPCearMC2LlHuvAnIeIXM8SRfK0GbB3BLEnFBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"73622ca4d64e520dbfb51365770c4f2e6478029165c52feffb85d7f8cb4a6a0c","last_reissued_at":"2026-07-05T06:12:44.940542Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:12:44.940542Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MUX-PLMs: Data Multiplexing for High-throughput Language Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Ameet Deshpande, Carlos E. Jimenez, Izhak Shafran, Karthik Narasimhan, Mingqiu Wang, Vishvak Murahari, Yuan Cao","submitted_at":"2023-02-24T04:03:15Z","abstract_excerpt":"The widespread adoption of large language models such as ChatGPT and Bard has led to unprecedented demand for these technologies. The burgeoning cost of inference for ever-increasing model sizes coupled with hardware shortages has limited affordable access and poses a pressing need for efficiency approaches geared towards high throughput and performance. Multi-input multi-output (MIMO) algorithms such as data multiplexing, offer a promising solution with a many-fold increase in throughput by performing inference for multiple inputs at the cost of a single input. Yet these approaches are not cu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.12441","kind":"arxiv","version":2},"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/2302.12441/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":"2302.12441","created_at":"2026-07-05T06:12:44.940600+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.12441v2","created_at":"2026-07-05T06:12:44.940600+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.12441","created_at":"2026-07-05T06:12:44.940600+00:00"},{"alias_kind":"pith_short_12","alias_value":"ONRCZJGWJZJA","created_at":"2026-07-05T06:12:44.940600+00:00"},{"alias_kind":"pith_short_16","alias_value":"ONRCZJGWJZJA3P5V","created_at":"2026-07-05T06:12:44.940600+00:00"},{"alias_kind":"pith_short_8","alias_value":"ONRCZJGW","created_at":"2026-07-05T06:12:44.940600+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/ONRCZJGWJZJA3P5VCNSXODCPFZ","json":"https://pith.science/pith/ONRCZJGWJZJA3P5VCNSXODCPFZ.json","graph_json":"https://pith.science/api/pith-number/ONRCZJGWJZJA3P5VCNSXODCPFZ/graph.json","events_json":"https://pith.science/api/pith-number/ONRCZJGWJZJA3P5VCNSXODCPFZ/events.json","paper":"https://pith.science/paper/ONRCZJGW"},"agent_actions":{"view_html":"https://pith.science/pith/ONRCZJGWJZJA3P5VCNSXODCPFZ","download_json":"https://pith.science/pith/ONRCZJGWJZJA3P5VCNSXODCPFZ.json","view_paper":"https://pith.science/paper/ONRCZJGW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.12441&json=true","fetch_graph":"https://pith.science/api/pith-number/ONRCZJGWJZJA3P5VCNSXODCPFZ/graph.json","fetch_events":"https://pith.science/api/pith-number/ONRCZJGWJZJA3P5VCNSXODCPFZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ONRCZJGWJZJA3P5VCNSXODCPFZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ONRCZJGWJZJA3P5VCNSXODCPFZ/action/storage_attestation","attest_author":"https://pith.science/pith/ONRCZJGWJZJA3P5VCNSXODCPFZ/action/author_attestation","sign_citation":"https://pith.science/pith/ONRCZJGWJZJA3P5VCNSXODCPFZ/action/citation_signature","submit_replication":"https://pith.science/pith/ONRCZJGWJZJA3P5VCNSXODCPFZ/action/replication_record"}},"created_at":"2026-07-05T06:12:44.940600+00:00","updated_at":"2026-07-05T06:12:44.940600+00:00"}