{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:JGJCN27PMNDRV74VTLO2LHHVZZ","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":"b65dc290e17b6f6160533e7f0a94c8b29faafacfd60b8d3ca52fdc4e11743601","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-04-20T01:40:19Z","title_canon_sha256":"1a7b42cb04ba72572f7cf0e315a49e0588fe67185402f1b084ab1b6eca0b2a43"},"schema_version":"1.0","source":{"id":"2204.09179","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2204.09179","created_at":"2026-07-05T05:05:46Z"},{"alias_kind":"arxiv_version","alias_value":"2204.09179v3","created_at":"2026-07-05T05:05:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.09179","created_at":"2026-07-05T05:05:46Z"},{"alias_kind":"pith_short_12","alias_value":"JGJCN27PMNDR","created_at":"2026-07-05T05:05:46Z"},{"alias_kind":"pith_short_16","alias_value":"JGJCN27PMNDRV74V","created_at":"2026-07-05T05:05:46Z"},{"alias_kind":"pith_short_8","alias_value":"JGJCN27P","created_at":"2026-07-05T05:05:46Z"}],"graph_snapshots":[{"event_id":"sha256:58fb279ea36b480c0020a35092de23812d9c6ed75079e2ea9c21d819928f0bf4","target":"graph","created_at":"2026-07-05T05:05:46Z","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/2204.09179/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Sparse mixture of experts provides larger model capacity while requiring a constant computational overhead. It employs the routing mechanism to distribute input tokens to the best-matched experts according to their hidden representations. However, learning such a routing mechanism encourages token clustering around expert centroids, implying a trend toward representation collapse. In this work, we propose to estimate the routing scores between tokens and experts on a low-dimensional hypersphere. We conduct extensive experiments on cross-lingual language model pre-training and fine-tuning on do","authors_text":"Barun Patra, Damai Dai, Furu Wei, Heyan Huang, Li Dong, Payal Bajaj, Saksham Singhal, Shaohan Huang, Shuming Ma, Xian-Ling Mao, Xia Song, Zewen Chi","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-04-20T01:40:19Z","title":"On the Representation Collapse of Sparse Mixture of Experts"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.09179","kind":"arxiv","version":3},"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":"sha256:176272a5e87fa5f7e17a64194c8535afad3ab98323095696320c578c61f200eb","target":"record","created_at":"2026-07-05T05:05:46Z","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":"b65dc290e17b6f6160533e7f0a94c8b29faafacfd60b8d3ca52fdc4e11743601","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-04-20T01:40:19Z","title_canon_sha256":"1a7b42cb04ba72572f7cf0e315a49e0588fe67185402f1b084ab1b6eca0b2a43"},"schema_version":"1.0","source":{"id":"2204.09179","kind":"arxiv","version":3}},"canonical_sha256":"499226ebef63471aff959adda59cf5ce58ab4090da69114215f70c44f2ace0c0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"499226ebef63471aff959adda59cf5ce58ab4090da69114215f70c44f2ace0c0","first_computed_at":"2026-07-05T05:05:46.668565Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:05:46.668565Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Y050R1FOs6oH6KvWZTd7YkgXNxj6oID/6I7Env8hYJ+HWGPzx06//g+IobiVkJw8TrCJg9RxK+hZyiUX6b0oCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:05:46.669046Z","signed_message":"canonical_sha256_bytes"},"source_id":"2204.09179","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:176272a5e87fa5f7e17a64194c8535afad3ab98323095696320c578c61f200eb","sha256:58fb279ea36b480c0020a35092de23812d9c6ed75079e2ea9c21d819928f0bf4"],"state_sha256":"54991af198f969f016de289b944a9b758a788a259479ffa05898d7c0e619a10f"}