{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:GLLWBBEQIPRNTQHEMHK7VXNRGV","short_pith_number":"pith:GLLWBBEQ","canonical_record":{"source":{"id":"2310.01334","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-02T16:51:32Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"f211e477a7538d4acdd825a577141151f7e4e8c993283c5a2133325ff61ef138","abstract_canon_sha256":"11f34890772a8f9146b9cd4f9df9231b682fd0bcb26f55b1304980d8898b6d49"},"schema_version":"1.0"},"canonical_sha256":"32d760849043e2d9c0e461d5faddb1354cb45192f449abeed97c0dc75f4e064d","source":{"kind":"arxiv","id":"2310.01334","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.01334","created_at":"2026-07-05T07:55:59Z"},{"alias_kind":"arxiv_version","alias_value":"2310.01334v2","created_at":"2026-07-05T07:55:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.01334","created_at":"2026-07-05T07:55:59Z"},{"alias_kind":"pith_short_12","alias_value":"GLLWBBEQIPRN","created_at":"2026-07-05T07:55:59Z"},{"alias_kind":"pith_short_16","alias_value":"GLLWBBEQIPRNTQHE","created_at":"2026-07-05T07:55:59Z"},{"alias_kind":"pith_short_8","alias_value":"GLLWBBEQ","created_at":"2026-07-05T07:55:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:GLLWBBEQIPRNTQHEMHK7VXNRGV","target":"record","payload":{"canonical_record":{"source":{"id":"2310.01334","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-02T16:51:32Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"f211e477a7538d4acdd825a577141151f7e4e8c993283c5a2133325ff61ef138","abstract_canon_sha256":"11f34890772a8f9146b9cd4f9df9231b682fd0bcb26f55b1304980d8898b6d49"},"schema_version":"1.0"},"canonical_sha256":"32d760849043e2d9c0e461d5faddb1354cb45192f449abeed97c0dc75f4e064d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:55:59.843981Z","signature_b64":"yGqsSbLbYHukQGFncDPfs4euxsHvNjN7JyD79+UjR+ROppV3Swgxb4aWk5BzCbWtAHph3ucYpFLlwehT/yBXBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"32d760849043e2d9c0e461d5faddb1354cb45192f449abeed97c0dc75f4e064d","last_reissued_at":"2026-07-05T07:55:59.843474Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:55:59.843474Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.01334","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":"2026-07-05T07:55:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KC9zTqXaIB4zN6l4jpNvcoOKrHkD3UZGXh/eBo9m5lhTLB479nDoX/leTSb7BCSbz3vaz2sE6xUDdVSop9NjAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T05:40:50.677211Z"},"content_sha256":"582e98b7e47946bce44f1d00b6876f764c37a0bb8a717afb6da7af28e56a2da5","schema_version":"1.0","event_id":"sha256:582e98b7e47946bce44f1d00b6876f764c37a0bb8a717afb6da7af28e56a2da5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:GLLWBBEQIPRNTQHEMHK7VXNRGV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Merge, Then Compress: Demystify Efficient SMoE with Hints from Its Routing Policy","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Mohit Bansal, Pingzhi Li, Prateek Yadav, Tianlong Chen, Yi-Lin Sung, Yu Cheng, Zhenyu Zhang","submitted_at":"2023-10-02T16:51:32Z","abstract_excerpt":"Sparsely activated Mixture-of-Experts (SMoE) has shown promise to scale up the learning capacity of neural networks, however, they have issues like (a) High Memory Usage, due to duplication of the network layers into multiple copies as experts; and (b) Redundancy in Experts, as common learning-based routing policies suffer from representational collapse. Therefore, vanilla SMoE models are memory inefficient and non-scalable, especially for resource-constrained downstream scenarios. In this paper, we ask: Can we craft a compact SMoE model by consolidating expert information? What is the best re"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.01334","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/2310.01334/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":"2026-07-05T07:55:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bmPvc3UtjYVv1XLOG6ObUfy12vDUlkQ5uYahjU0DHMNJc5k3okz1sb6vFXwb1Yz3P5zm9s7VAQ00BzgbgBmxCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T05:40:50.678398Z"},"content_sha256":"26cbd2008e20daa9f0bab9f0e43b87425c5f9b3843f7873e17771c1562df9a49","schema_version":"1.0","event_id":"sha256:26cbd2008e20daa9f0bab9f0e43b87425c5f9b3843f7873e17771c1562df9a49"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GLLWBBEQIPRNTQHEMHK7VXNRGV/bundle.json","state_url":"https://pith.science/pith/GLLWBBEQIPRNTQHEMHK7VXNRGV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GLLWBBEQIPRNTQHEMHK7VXNRGV/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":"2026-08-10T05:40:50Z","links":{"resolver":"https://pith.science/pith/GLLWBBEQIPRNTQHEMHK7VXNRGV","bundle":"https://pith.science/pith/GLLWBBEQIPRNTQHEMHK7VXNRGV/bundle.json","state":"https://pith.science/pith/GLLWBBEQIPRNTQHEMHK7VXNRGV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GLLWBBEQIPRNTQHEMHK7VXNRGV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:GLLWBBEQIPRNTQHEMHK7VXNRGV","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":"11f34890772a8f9146b9cd4f9df9231b682fd0bcb26f55b1304980d8898b6d49","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-02T16:51:32Z","title_canon_sha256":"f211e477a7538d4acdd825a577141151f7e4e8c993283c5a2133325ff61ef138"},"schema_version":"1.0","source":{"id":"2310.01334","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.01334","created_at":"2026-07-05T07:55:59Z"},{"alias_kind":"arxiv_version","alias_value":"2310.01334v2","created_at":"2026-07-05T07:55:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.01334","created_at":"2026-07-05T07:55:59Z"},{"alias_kind":"pith_short_12","alias_value":"GLLWBBEQIPRN","created_at":"2026-07-05T07:55:59Z"},{"alias_kind":"pith_short_16","alias_value":"GLLWBBEQIPRNTQHE","created_at":"2026-07-05T07:55:59Z"},{"alias_kind":"pith_short_8","alias_value":"GLLWBBEQ","created_at":"2026-07-05T07:55:59Z"}],"graph_snapshots":[{"event_id":"sha256:26cbd2008e20daa9f0bab9f0e43b87425c5f9b3843f7873e17771c1562df9a49","target":"graph","created_at":"2026-07-05T07:55:59Z","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/2310.01334/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Sparsely activated Mixture-of-Experts (SMoE) has shown promise to scale up the learning capacity of neural networks, however, they have issues like (a) High Memory Usage, due to duplication of the network layers into multiple copies as experts; and (b) Redundancy in Experts, as common learning-based routing policies suffer from representational collapse. Therefore, vanilla SMoE models are memory inefficient and non-scalable, especially for resource-constrained downstream scenarios. In this paper, we ask: Can we craft a compact SMoE model by consolidating expert information? What is the best re","authors_text":"Mohit Bansal, Pingzhi Li, Prateek Yadav, Tianlong Chen, Yi-Lin Sung, Yu Cheng, Zhenyu Zhang","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-02T16:51:32Z","title":"Merge, Then Compress: Demystify Efficient SMoE with Hints from Its Routing Policy"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.01334","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":"sha256:582e98b7e47946bce44f1d00b6876f764c37a0bb8a717afb6da7af28e56a2da5","target":"record","created_at":"2026-07-05T07:55:59Z","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":"11f34890772a8f9146b9cd4f9df9231b682fd0bcb26f55b1304980d8898b6d49","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-02T16:51:32Z","title_canon_sha256":"f211e477a7538d4acdd825a577141151f7e4e8c993283c5a2133325ff61ef138"},"schema_version":"1.0","source":{"id":"2310.01334","kind":"arxiv","version":2}},"canonical_sha256":"32d760849043e2d9c0e461d5faddb1354cb45192f449abeed97c0dc75f4e064d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"32d760849043e2d9c0e461d5faddb1354cb45192f449abeed97c0dc75f4e064d","first_computed_at":"2026-07-05T07:55:59.843474Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:55:59.843474Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yGqsSbLbYHukQGFncDPfs4euxsHvNjN7JyD79+UjR+ROppV3Swgxb4aWk5BzCbWtAHph3ucYpFLlwehT/yBXBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:55:59.843981Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.01334","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:582e98b7e47946bce44f1d00b6876f764c37a0bb8a717afb6da7af28e56a2da5","sha256:26cbd2008e20daa9f0bab9f0e43b87425c5f9b3843f7873e17771c1562df9a49"],"state_sha256":"2f724858e2ea3bc1956d3355dd10c128c5c6606917470ef9ad23efbc68e69c1d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yPG3wEVWTlRe4js13XIT4UjVrDgbsOcGopklceE8hU3kIvekVbMn20r4sCIsKd7Tg24xwg8qSwCw06URDHVsAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T05:40:50.685327Z","bundle_sha256":"de70691aebac670c8620a0d0a3ef36d98b82ee8133bd433ae030a1df67e753f5"}}