{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:QTCVSXC747GLXHDUEQPFAAOIHU","short_pith_number":"pith:QTCVSXC7","canonical_record":{"source":{"id":"2503.23100","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-29T14:35:34Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"6b273728644a8444edd46df253580876669593ceab6dbd48312be1d5dee59711","abstract_canon_sha256":"6988b68231bd1478a50362eef9b27acb686a6bc1c2840ea0daea88cef15a374a"},"schema_version":"1.0"},"canonical_sha256":"84c5595c5fe7ccbb9c74241e5001c83d3fd52553f3ff88c03ec16343c01c18d1","source":{"kind":"arxiv","id":"2503.23100","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.23100","created_at":"2026-07-05T11:09:10Z"},{"alias_kind":"arxiv_version","alias_value":"2503.23100v2","created_at":"2026-07-05T11:09:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.23100","created_at":"2026-07-05T11:09:10Z"},{"alias_kind":"pith_short_12","alias_value":"QTCVSXC747GL","created_at":"2026-07-05T11:09:10Z"},{"alias_kind":"pith_short_16","alias_value":"QTCVSXC747GLXHDU","created_at":"2026-07-05T11:09:10Z"},{"alias_kind":"pith_short_8","alias_value":"QTCVSXC7","created_at":"2026-07-05T11:09:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:QTCVSXC747GLXHDUEQPFAAOIHU","target":"record","payload":{"canonical_record":{"source":{"id":"2503.23100","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-29T14:35:34Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"6b273728644a8444edd46df253580876669593ceab6dbd48312be1d5dee59711","abstract_canon_sha256":"6988b68231bd1478a50362eef9b27acb686a6bc1c2840ea0daea88cef15a374a"},"schema_version":"1.0"},"canonical_sha256":"84c5595c5fe7ccbb9c74241e5001c83d3fd52553f3ff88c03ec16343c01c18d1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:09:10.531628Z","signature_b64":"tgQZ5shDmv+vPlwHV5DKNZBXCsDRSv8lteg1KMhYJaou91I6YjkTay/QPYYFEa7xVKLeFw6xeqLjMbXPiAzWDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"84c5595c5fe7ccbb9c74241e5001c83d3fd52553f3ff88c03ec16343c01c18d1","last_reissued_at":"2026-07-05T11:09:10.531129Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:09:10.531129Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2503.23100","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:09:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mxmYkaGErmgUAwUzVCkLFFcTKalMhAluCWV4YBfBo1WcIUCI/um4jvR0flOk82EZgzqyrOaTQ/q8kAe1dbM9Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-31T21:22:51.146628Z"},"content_sha256":"aa5281062183fab9bc5e58f06f23d60cfd62ce97304f1cc48cfb603df20eedb0","schema_version":"1.0","event_id":"sha256:aa5281062183fab9bc5e58f06f23d60cfd62ce97304f1cc48cfb603df20eedb0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:QTCVSXC747GLXHDUEQPFAAOIHU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MoLAE: Mixture of Latent Experts for Parameter-Efficient Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Han Wu, Mingxuan Yuan, Ruifeng She, Tao Zhong, Xiaojin Fu, Xiongwei Han, Zehua Liu","submitted_at":"2025-03-29T14:35:34Z","abstract_excerpt":"Mixture of Experts (MoE) has become a key architectural paradigm for efficiently scaling Large Language Models (LLMs) by selectively activating a subset of parameters for each input token. However, standard MoE architectures face significant challenges, including high memory consumption and communication overhead during distributed training. In this paper, we introduce Mixture of Latent Experts (MoLAE), a novel parameterization that addresses these limitations by reformulating expert operations through a shared projection into a lower-dimensional latent space, followed by expert-specific trans"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.23100","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/2503.23100/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":"2026-07-05T11:09:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CfDLpHC+SbNNLWwfHhlJ4bwVIu1EKkGW/gkJTD3nhfipoRP3GqutG/vTn8Jh+WLoP3G/9OxdCzsHNSQJypCrDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-31T21:22:51.147358Z"},"content_sha256":"6e6dd61db7ec1859bdf28d1ea6d8c9244c355c6ba0d4e1f5b91c9b93d53da51d","schema_version":"1.0","event_id":"sha256:6e6dd61db7ec1859bdf28d1ea6d8c9244c355c6ba0d4e1f5b91c9b93d53da51d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QTCVSXC747GLXHDUEQPFAAOIHU/bundle.json","state_url":"https://pith.science/pith/QTCVSXC747GLXHDUEQPFAAOIHU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QTCVSXC747GLXHDUEQPFAAOIHU/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":"2026-07-31T21:22:51Z","links":{"resolver":"https://pith.science/pith/QTCVSXC747GLXHDUEQPFAAOIHU","bundle":"https://pith.science/pith/QTCVSXC747GLXHDUEQPFAAOIHU/bundle.json","state":"https://pith.science/pith/QTCVSXC747GLXHDUEQPFAAOIHU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QTCVSXC747GLXHDUEQPFAAOIHU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:QTCVSXC747GLXHDUEQPFAAOIHU","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":"6988b68231bd1478a50362eef9b27acb686a6bc1c2840ea0daea88cef15a374a","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-29T14:35:34Z","title_canon_sha256":"6b273728644a8444edd46df253580876669593ceab6dbd48312be1d5dee59711"},"schema_version":"1.0","source":{"id":"2503.23100","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.23100","created_at":"2026-07-05T11:09:10Z"},{"alias_kind":"arxiv_version","alias_value":"2503.23100v2","created_at":"2026-07-05T11:09:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.23100","created_at":"2026-07-05T11:09:10Z"},{"alias_kind":"pith_short_12","alias_value":"QTCVSXC747GL","created_at":"2026-07-05T11:09:10Z"},{"alias_kind":"pith_short_16","alias_value":"QTCVSXC747GLXHDU","created_at":"2026-07-05T11:09:10Z"},{"alias_kind":"pith_short_8","alias_value":"QTCVSXC7","created_at":"2026-07-05T11:09:10Z"}],"graph_snapshots":[{"event_id":"sha256:6e6dd61db7ec1859bdf28d1ea6d8c9244c355c6ba0d4e1f5b91c9b93d53da51d","target":"graph","created_at":"2026-07-05T11:09:10Z","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/2503.23100/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Mixture of Experts (MoE) has become a key architectural paradigm for efficiently scaling Large Language Models (LLMs) by selectively activating a subset of parameters for each input token. However, standard MoE architectures face significant challenges, including high memory consumption and communication overhead during distributed training. In this paper, we introduce Mixture of Latent Experts (MoLAE), a novel parameterization that addresses these limitations by reformulating expert operations through a shared projection into a lower-dimensional latent space, followed by expert-specific trans","authors_text":"Han Wu, Mingxuan Yuan, Ruifeng She, Tao Zhong, Xiaojin Fu, Xiongwei Han, Zehua Liu","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-29T14:35:34Z","title":"MoLAE: Mixture of Latent Experts for Parameter-Efficient Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.23100","kind":"arxiv","version":2},"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:aa5281062183fab9bc5e58f06f23d60cfd62ce97304f1cc48cfb603df20eedb0","target":"record","created_at":"2026-07-05T11:09:10Z","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":"6988b68231bd1478a50362eef9b27acb686a6bc1c2840ea0daea88cef15a374a","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-29T14:35:34Z","title_canon_sha256":"6b273728644a8444edd46df253580876669593ceab6dbd48312be1d5dee59711"},"schema_version":"1.0","source":{"id":"2503.23100","kind":"arxiv","version":2}},"canonical_sha256":"84c5595c5fe7ccbb9c74241e5001c83d3fd52553f3ff88c03ec16343c01c18d1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"84c5595c5fe7ccbb9c74241e5001c83d3fd52553f3ff88c03ec16343c01c18d1","first_computed_at":"2026-07-05T11:09:10.531129Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:09:10.531129Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tgQZ5shDmv+vPlwHV5DKNZBXCsDRSv8lteg1KMhYJaou91I6YjkTay/QPYYFEa7xVKLeFw6xeqLjMbXPiAzWDg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:09:10.531628Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.23100","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:aa5281062183fab9bc5e58f06f23d60cfd62ce97304f1cc48cfb603df20eedb0","sha256:6e6dd61db7ec1859bdf28d1ea6d8c9244c355c6ba0d4e1f5b91c9b93d53da51d"],"state_sha256":"0cf8c70d4457b7f418c5064307b1881c4027e99230f704376acdc3774cad3d2a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TWkXiIlSu6ee+BB/0s+kkrBuBpWjo6LsicD8He0kWgsjzzF9sYk7Mp8GwKNB32/0dK3J9P3uyoKgdKTPR8eRCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-31T21:22:51.151282Z","bundle_sha256":"f04c3d6dfca15068ccd271f4e0d33b17f89e3478192c22cce54112c5969eec94"}}