{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:ND2WWIX3P24QGFT7KGNG5SP7UX","short_pith_number":"pith:ND2WWIX3","canonical_record":{"source":{"id":"2309.05444","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-09-11T13:31:00Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"e68171099625f2d28d883458472182858c17233a63a56044aa1bb1d49734300f","abstract_canon_sha256":"958496c0763840523c1e33319c2564e4bade7e0a404e8c5ff5e5a413317c7b9f"},"schema_version":"1.0"},"canonical_sha256":"68f56b22fb7eb903167f519a6ec9ffa5f6a9920a9965dfe00fd31c3c6dea2a6f","source":{"kind":"arxiv","id":"2309.05444","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.05444","created_at":"2026-07-05T06:49:35Z"},{"alias_kind":"arxiv_version","alias_value":"2309.05444v1","created_at":"2026-07-05T06:49:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.05444","created_at":"2026-07-05T06:49:35Z"},{"alias_kind":"pith_short_12","alias_value":"ND2WWIX3P24Q","created_at":"2026-07-05T06:49:35Z"},{"alias_kind":"pith_short_16","alias_value":"ND2WWIX3P24QGFT7","created_at":"2026-07-05T06:49:35Z"},{"alias_kind":"pith_short_8","alias_value":"ND2WWIX3","created_at":"2026-07-05T06:49:35Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:ND2WWIX3P24QGFT7KGNG5SP7UX","target":"record","payload":{"canonical_record":{"source":{"id":"2309.05444","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-09-11T13:31:00Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"e68171099625f2d28d883458472182858c17233a63a56044aa1bb1d49734300f","abstract_canon_sha256":"958496c0763840523c1e33319c2564e4bade7e0a404e8c5ff5e5a413317c7b9f"},"schema_version":"1.0"},"canonical_sha256":"68f56b22fb7eb903167f519a6ec9ffa5f6a9920a9965dfe00fd31c3c6dea2a6f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:49:35.358145Z","signature_b64":"l+ZY0rUhGpl75kQ32l13HhSjSqsGL1g2vFTk+4VLnFSU1M+N+aNYw4bIL0Ll65Eq9XCdt3zjzxB1wP1L/taZCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"68f56b22fb7eb903167f519a6ec9ffa5f6a9920a9965dfe00fd31c3c6dea2a6f","last_reissued_at":"2026-07-05T06:49:35.357524Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:49:35.357524Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2309.05444","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":"2026-07-05T06:49:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2EGRBK2vOZZH+sWAjgj0JSwzDKoOSk9oX//wM6rcdqQdZfCE9UhptCFp4pVE/Rn/VNTuxDO+BXS/y3s1FLHxBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T05:41:16.696603Z"},"content_sha256":"fca52beee6160621d3813848adb1749bac573ae9a8829f3fba1ed0959ee5c05e","schema_version":"1.0","event_id":"sha256:fca52beee6160621d3813848adb1749bac573ae9a8829f3fba1ed0959ee5c05e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:ND2WWIX3P24QGFT7KGNG5SP7UX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Pushing Mixture of Experts to the Limit: Extremely Parameter Efficient MoE for Instruction Tuning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Acyr Locatelli, Ahmet \\\"Ust\\\"un, Arash Ahmadian, Beyza Ermi\\c{s}, Sara Hooker, Ted Zadouri","submitted_at":"2023-09-11T13:31:00Z","abstract_excerpt":"The Mixture of Experts (MoE) is a widely known neural architecture where an ensemble of specialized sub-models optimizes overall performance with a constant computational cost. However, conventional MoEs pose challenges at scale due to the need to store all experts in memory. In this paper, we push MoE to the limit. We propose extremely parameter-efficient MoE by uniquely combining MoE architecture with lightweight experts.Our MoE architecture outperforms standard parameter-efficient fine-tuning (PEFT) methods and is on par with full fine-tuning by only updating the lightweight experts -- less"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.05444","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/2309.05444/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":"2026-07-05T06:49:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5pR8ggRdBDFxDNDJv4DamGhaVmQh18WKrrhD1Evq5RF1/XbsJpPQfrm4qgfZucYMwXyx4pB/ah2Va312S7lWCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T05:41:16.696980Z"},"content_sha256":"a482e8c2cd0db4740b306e9308524212088631cb5a16e5b457f5be36a9f37ef1","schema_version":"1.0","event_id":"sha256:a482e8c2cd0db4740b306e9308524212088631cb5a16e5b457f5be36a9f37ef1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ND2WWIX3P24QGFT7KGNG5SP7UX/bundle.json","state_url":"https://pith.science/pith/ND2WWIX3P24QGFT7KGNG5SP7UX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ND2WWIX3P24QGFT7KGNG5SP7UX/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":"2026-07-09T05:41:16Z","links":{"resolver":"https://pith.science/pith/ND2WWIX3P24QGFT7KGNG5SP7UX","bundle":"https://pith.science/pith/ND2WWIX3P24QGFT7KGNG5SP7UX/bundle.json","state":"https://pith.science/pith/ND2WWIX3P24QGFT7KGNG5SP7UX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ND2WWIX3P24QGFT7KGNG5SP7UX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:ND2WWIX3P24QGFT7KGNG5SP7UX","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":"958496c0763840523c1e33319c2564e4bade7e0a404e8c5ff5e5a413317c7b9f","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-09-11T13:31:00Z","title_canon_sha256":"e68171099625f2d28d883458472182858c17233a63a56044aa1bb1d49734300f"},"schema_version":"1.0","source":{"id":"2309.05444","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.05444","created_at":"2026-07-05T06:49:35Z"},{"alias_kind":"arxiv_version","alias_value":"2309.05444v1","created_at":"2026-07-05T06:49:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.05444","created_at":"2026-07-05T06:49:35Z"},{"alias_kind":"pith_short_12","alias_value":"ND2WWIX3P24Q","created_at":"2026-07-05T06:49:35Z"},{"alias_kind":"pith_short_16","alias_value":"ND2WWIX3P24QGFT7","created_at":"2026-07-05T06:49:35Z"},{"alias_kind":"pith_short_8","alias_value":"ND2WWIX3","created_at":"2026-07-05T06:49:35Z"}],"graph_snapshots":[{"event_id":"sha256:a482e8c2cd0db4740b306e9308524212088631cb5a16e5b457f5be36a9f37ef1","target":"graph","created_at":"2026-07-05T06:49:35Z","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/2309.05444/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The Mixture of Experts (MoE) is a widely known neural architecture where an ensemble of specialized sub-models optimizes overall performance with a constant computational cost. However, conventional MoEs pose challenges at scale due to the need to store all experts in memory. In this paper, we push MoE to the limit. We propose extremely parameter-efficient MoE by uniquely combining MoE architecture with lightweight experts.Our MoE architecture outperforms standard parameter-efficient fine-tuning (PEFT) methods and is on par with full fine-tuning by only updating the lightweight experts -- less","authors_text":"Acyr Locatelli, Ahmet \\\"Ust\\\"un, Arash Ahmadian, Beyza Ermi\\c{s}, Sara Hooker, Ted Zadouri","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-09-11T13:31:00Z","title":"Pushing Mixture of Experts to the Limit: Extremely Parameter Efficient MoE for Instruction Tuning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.05444","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:fca52beee6160621d3813848adb1749bac573ae9a8829f3fba1ed0959ee5c05e","target":"record","created_at":"2026-07-05T06:49:35Z","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":"958496c0763840523c1e33319c2564e4bade7e0a404e8c5ff5e5a413317c7b9f","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-09-11T13:31:00Z","title_canon_sha256":"e68171099625f2d28d883458472182858c17233a63a56044aa1bb1d49734300f"},"schema_version":"1.0","source":{"id":"2309.05444","kind":"arxiv","version":1}},"canonical_sha256":"68f56b22fb7eb903167f519a6ec9ffa5f6a9920a9965dfe00fd31c3c6dea2a6f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"68f56b22fb7eb903167f519a6ec9ffa5f6a9920a9965dfe00fd31c3c6dea2a6f","first_computed_at":"2026-07-05T06:49:35.357524Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:49:35.357524Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"l+ZY0rUhGpl75kQ32l13HhSjSqsGL1g2vFTk+4VLnFSU1M+N+aNYw4bIL0Ll65Eq9XCdt3zjzxB1wP1L/taZCw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:49:35.358145Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.05444","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fca52beee6160621d3813848adb1749bac573ae9a8829f3fba1ed0959ee5c05e","sha256:a482e8c2cd0db4740b306e9308524212088631cb5a16e5b457f5be36a9f37ef1"],"state_sha256":"927781f09e8e86717981f5ea95dccce46637265e52055890f45afa72b26f3216"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BY06iEtTIp5Y/Yljsw41g3ehXYqIXFJasfoRVn85Vs+m514vXLZOlIpOhMKqfo+pPFVNpshhYfHd/J6Mu7IGBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-09T05:41:16.699198Z","bundle_sha256":"af9bcce418d0aff3e4df66951b8770049b0d5bd4ef4e8afb525b1e73195a2193"}}