{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:R3FCDIIURJZSJ43BUPJK2WRPTZ","short_pith_number":"pith:R3FCDIIU","canonical_record":{"source":{"id":"2412.14711","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-19T10:21:20Z","cross_cats_sorted":[],"title_canon_sha256":"e56ef04c268b02d3941283b14c687280d99f78b920afca19fb97e95330a25095","abstract_canon_sha256":"05558398e474381c498883fa72923fa2d4dbc2a92b2885eaf76094a94d52f7c8"},"schema_version":"1.0"},"canonical_sha256":"8eca21a1148a7324f361a3d2ad5a2f9e572e600cc24f501c90b452ea09e8678d","source":{"kind":"arxiv","id":"2412.14711","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.14711","created_at":"2026-07-05T10:21:06Z"},{"alias_kind":"arxiv_version","alias_value":"2412.14711v2","created_at":"2026-07-05T10:21:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.14711","created_at":"2026-07-05T10:21:06Z"},{"alias_kind":"pith_short_12","alias_value":"R3FCDIIURJZS","created_at":"2026-07-05T10:21:06Z"},{"alias_kind":"pith_short_16","alias_value":"R3FCDIIURJZSJ43B","created_at":"2026-07-05T10:21:06Z"},{"alias_kind":"pith_short_8","alias_value":"R3FCDIIU","created_at":"2026-07-05T10:21:06Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:R3FCDIIURJZSJ43BUPJK2WRPTZ","target":"record","payload":{"canonical_record":{"source":{"id":"2412.14711","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-19T10:21:20Z","cross_cats_sorted":[],"title_canon_sha256":"e56ef04c268b02d3941283b14c687280d99f78b920afca19fb97e95330a25095","abstract_canon_sha256":"05558398e474381c498883fa72923fa2d4dbc2a92b2885eaf76094a94d52f7c8"},"schema_version":"1.0"},"canonical_sha256":"8eca21a1148a7324f361a3d2ad5a2f9e572e600cc24f501c90b452ea09e8678d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:21:06.153881Z","signature_b64":"AfYtiFY+S+6oi3soZfu8nGSJMT4GIS88U/JWWuJITgvm9PHcv4hStdZWtnUrSbJOOMMSxZk1T23jZbR2J+BjDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8eca21a1148a7324f361a3d2ad5a2f9e572e600cc24f501c90b452ea09e8678d","last_reissued_at":"2026-07-05T10:21:06.153408Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:21:06.153408Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.14711","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":"2026-07-05T10:21:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aAZgxmqfrkKC8PA8A5e2icGs8mzpIF4elkkdPifCIPbxySkkAmeRFgebjHJ1CZ3mT7L7Lzlwkzw/kqWwh8jjBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T04:46:24.482918Z"},"content_sha256":"7f0a616fdb42e7204a0196a2302d64ea32e8f71ede42d4708f51a40b38539fa4","schema_version":"1.0","event_id":"sha256:7f0a616fdb42e7204a0196a2302d64ea32e8f71ede42d4708f51a40b38539fa4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:R3FCDIIURJZSJ43BUPJK2WRPTZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ReMoE: Fully Differentiable Mixture-of-Experts with ReLU Routing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jianfei Chen, Jun Zhu, Ziteng Wang","submitted_at":"2024-12-19T10:21:20Z","abstract_excerpt":"Sparsely activated Mixture-of-Experts (MoE) models are widely adopted to scale up model capacity without increasing the computation budget. However, vanilla TopK routers are trained in a discontinuous, non-differentiable way, limiting their performance and scalability. To address this issue, we propose ReMoE, a fully differentiable MoE architecture that offers a simple yet effective drop-in replacement for the conventional TopK+Softmax routing, utilizing ReLU as the router instead. We further propose methods to regulate the router's sparsity while balancing the load among experts. ReMoE's cont"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.14711","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/2412.14711/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":"2026-07-05T10:21:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vm6PqR+wgdSkv0L9D9KU4/oc5QSpFctGzzjy1HUVwlhdBthIZR4XO6PRrrrFBa5aElUntgkSC+ly5bXvCrm0DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T04:46:24.483785Z"},"content_sha256":"fc396781640cb889838ab469e94f7706e9c291c1e88ef791686092f3ad0544ef","schema_version":"1.0","event_id":"sha256:fc396781640cb889838ab469e94f7706e9c291c1e88ef791686092f3ad0544ef"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/R3FCDIIURJZSJ43BUPJK2WRPTZ/bundle.json","state_url":"https://pith.science/pith/R3FCDIIURJZSJ43BUPJK2WRPTZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/R3FCDIIURJZSJ43BUPJK2WRPTZ/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":"2026-08-08T04:46:24Z","links":{"resolver":"https://pith.science/pith/R3FCDIIURJZSJ43BUPJK2WRPTZ","bundle":"https://pith.science/pith/R3FCDIIURJZSJ43BUPJK2WRPTZ/bundle.json","state":"https://pith.science/pith/R3FCDIIURJZSJ43BUPJK2WRPTZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/R3FCDIIURJZSJ43BUPJK2WRPTZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:R3FCDIIURJZSJ43BUPJK2WRPTZ","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":"05558398e474381c498883fa72923fa2d4dbc2a92b2885eaf76094a94d52f7c8","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-19T10:21:20Z","title_canon_sha256":"e56ef04c268b02d3941283b14c687280d99f78b920afca19fb97e95330a25095"},"schema_version":"1.0","source":{"id":"2412.14711","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.14711","created_at":"2026-07-05T10:21:06Z"},{"alias_kind":"arxiv_version","alias_value":"2412.14711v2","created_at":"2026-07-05T10:21:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.14711","created_at":"2026-07-05T10:21:06Z"},{"alias_kind":"pith_short_12","alias_value":"R3FCDIIURJZS","created_at":"2026-07-05T10:21:06Z"},{"alias_kind":"pith_short_16","alias_value":"R3FCDIIURJZSJ43B","created_at":"2026-07-05T10:21:06Z"},{"alias_kind":"pith_short_8","alias_value":"R3FCDIIU","created_at":"2026-07-05T10:21:06Z"}],"graph_snapshots":[{"event_id":"sha256:fc396781640cb889838ab469e94f7706e9c291c1e88ef791686092f3ad0544ef","target":"graph","created_at":"2026-07-05T10:21:06Z","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/2412.14711/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Sparsely activated Mixture-of-Experts (MoE) models are widely adopted to scale up model capacity without increasing the computation budget. However, vanilla TopK routers are trained in a discontinuous, non-differentiable way, limiting their performance and scalability. To address this issue, we propose ReMoE, a fully differentiable MoE architecture that offers a simple yet effective drop-in replacement for the conventional TopK+Softmax routing, utilizing ReLU as the router instead. We further propose methods to regulate the router's sparsity while balancing the load among experts. ReMoE's cont","authors_text":"Jianfei Chen, Jun Zhu, Ziteng Wang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-19T10:21:20Z","title":"ReMoE: Fully Differentiable Mixture-of-Experts with ReLU Routing"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.14711","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":"sha256:7f0a616fdb42e7204a0196a2302d64ea32e8f71ede42d4708f51a40b38539fa4","target":"record","created_at":"2026-07-05T10:21:06Z","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":"05558398e474381c498883fa72923fa2d4dbc2a92b2885eaf76094a94d52f7c8","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-19T10:21:20Z","title_canon_sha256":"e56ef04c268b02d3941283b14c687280d99f78b920afca19fb97e95330a25095"},"schema_version":"1.0","source":{"id":"2412.14711","kind":"arxiv","version":2}},"canonical_sha256":"8eca21a1148a7324f361a3d2ad5a2f9e572e600cc24f501c90b452ea09e8678d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8eca21a1148a7324f361a3d2ad5a2f9e572e600cc24f501c90b452ea09e8678d","first_computed_at":"2026-07-05T10:21:06.153408Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:21:06.153408Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AfYtiFY+S+6oi3soZfu8nGSJMT4GIS88U/JWWuJITgvm9PHcv4hStdZWtnUrSbJOOMMSxZk1T23jZbR2J+BjDA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:21:06.153881Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.14711","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7f0a616fdb42e7204a0196a2302d64ea32e8f71ede42d4708f51a40b38539fa4","sha256:fc396781640cb889838ab469e94f7706e9c291c1e88ef791686092f3ad0544ef"],"state_sha256":"73bf691fc608a640311e698a873557fa9c88317ed5916ab1f667fed0ce3bc2a5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3TizlqQTupqNqQbO1SggnhHy1Ob4KW5xyd/i1QIXiNlrUS3ztgO+xQFo++4ym09TupJhk0bqoPSSznjrzozhBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T04:46:24.491159Z","bundle_sha256":"97328268bf4d7f2c0672b59b36d433c6731657ab04e5191aa0c2c9bf0dc3baf4"}}