{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:DZZFWDJ27NTWYDNJFAL2VZEQJU","short_pith_number":"pith:DZZFWDJ2","canonical_record":{"source":{"id":"2405.11530","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-19T11:55:48Z","cross_cats_sorted":[],"title_canon_sha256":"172f1f9d7c9e8a8a1758beaf23d0db7c500ffe79e710b4e6b484c25756001b8d","abstract_canon_sha256":"9d1a2ebc64aaceeb3a8421b5f4f147acd20ee25e45a2a0019e30a232b13dee69"},"schema_version":"1.0"},"canonical_sha256":"1e725b0d3afb676c0da92817aae4904d09f4145854f79535858d03f2c169a600","source":{"kind":"arxiv","id":"2405.11530","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.11530","created_at":"2026-07-05T08:20:41Z"},{"alias_kind":"arxiv_version","alias_value":"2405.11530v1","created_at":"2026-07-05T08:20:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.11530","created_at":"2026-07-05T08:20:41Z"},{"alias_kind":"pith_short_12","alias_value":"DZZFWDJ27NTW","created_at":"2026-07-05T08:20:41Z"},{"alias_kind":"pith_short_16","alias_value":"DZZFWDJ27NTWYDNJ","created_at":"2026-07-05T08:20:41Z"},{"alias_kind":"pith_short_8","alias_value":"DZZFWDJ2","created_at":"2026-07-05T08:20:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:DZZFWDJ27NTWYDNJFAL2VZEQJU","target":"record","payload":{"canonical_record":{"source":{"id":"2405.11530","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-19T11:55:48Z","cross_cats_sorted":[],"title_canon_sha256":"172f1f9d7c9e8a8a1758beaf23d0db7c500ffe79e710b4e6b484c25756001b8d","abstract_canon_sha256":"9d1a2ebc64aaceeb3a8421b5f4f147acd20ee25e45a2a0019e30a232b13dee69"},"schema_version":"1.0"},"canonical_sha256":"1e725b0d3afb676c0da92817aae4904d09f4145854f79535858d03f2c169a600","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:20:41.110153Z","signature_b64":"sTXJAdTQuf/pRiW2RnEc8KmI4Jxb1vq9Mb1PcvlcYQeBifFcYHmjXxX3n0l6WKTZKV4O/8ylnoTJA1fJ2AOZBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1e725b0d3afb676c0da92817aae4904d09f4145854f79535858d03f2c169a600","last_reissued_at":"2026-07-05T08:20:41.109639Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:20:41.109639Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2405.11530","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":"2026-07-05T08:20:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZqvoRyZ4QSfVH3FX8S0RkuGuC/62xt4QiHvggBUN4USifa/ZlKQy5GVQmNTE1nF76qmalORoR7QDapVjMkFKDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T17:39:47.720376Z"},"content_sha256":"45c7d9cc38dd25b04bd134ef70de9b6f2e3fa0b5c95a9305c5ec724c8d435e20","schema_version":"1.0","event_id":"sha256:45c7d9cc38dd25b04bd134ef70de9b6f2e3fa0b5c95a9305c5ec724c8d435e20"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:DZZFWDJ27NTWYDNJFAL2VZEQJU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning More Generalized Experts by Merging Experts in Mixture-of-Experts","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Sejik Park","submitted_at":"2024-05-19T11:55:48Z","abstract_excerpt":"We observe that incorporating a shared layer in a mixture-of-experts can lead to performance degradation. This leads us to hypothesize that learning shared features poses challenges in deep learning, potentially caused by the same feature being learned as various different features. To address this issue, we track each expert's usage frequency and merge the two most frequently selected experts. We then update the least frequently selected expert using the combination of experts. This approach, combined with the subsequent learning of the router's expert selection, allows the model to determine"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.11530","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/2405.11530/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":"2026-07-05T08:20:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TOW1bz183e/E3wKL3nnPX47md7xL9UfprecHCP6rmDGDleTARbzg2svf0+kXb97aJDJ9RznxQxRL6yGcsWPjBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T17:39:47.720779Z"},"content_sha256":"366a0174a76e66187bc90ab32c2235877c8e38b43a8a167586c0dfaeea2777ef","schema_version":"1.0","event_id":"sha256:366a0174a76e66187bc90ab32c2235877c8e38b43a8a167586c0dfaeea2777ef"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DZZFWDJ27NTWYDNJFAL2VZEQJU/bundle.json","state_url":"https://pith.science/pith/DZZFWDJ27NTWYDNJFAL2VZEQJU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DZZFWDJ27NTWYDNJFAL2VZEQJU/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":"2026-08-05T17:39:47Z","links":{"resolver":"https://pith.science/pith/DZZFWDJ27NTWYDNJFAL2VZEQJU","bundle":"https://pith.science/pith/DZZFWDJ27NTWYDNJFAL2VZEQJU/bundle.json","state":"https://pith.science/pith/DZZFWDJ27NTWYDNJFAL2VZEQJU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DZZFWDJ27NTWYDNJFAL2VZEQJU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:DZZFWDJ27NTWYDNJFAL2VZEQJU","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":"9d1a2ebc64aaceeb3a8421b5f4f147acd20ee25e45a2a0019e30a232b13dee69","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-19T11:55:48Z","title_canon_sha256":"172f1f9d7c9e8a8a1758beaf23d0db7c500ffe79e710b4e6b484c25756001b8d"},"schema_version":"1.0","source":{"id":"2405.11530","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.11530","created_at":"2026-07-05T08:20:41Z"},{"alias_kind":"arxiv_version","alias_value":"2405.11530v1","created_at":"2026-07-05T08:20:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.11530","created_at":"2026-07-05T08:20:41Z"},{"alias_kind":"pith_short_12","alias_value":"DZZFWDJ27NTW","created_at":"2026-07-05T08:20:41Z"},{"alias_kind":"pith_short_16","alias_value":"DZZFWDJ27NTWYDNJ","created_at":"2026-07-05T08:20:41Z"},{"alias_kind":"pith_short_8","alias_value":"DZZFWDJ2","created_at":"2026-07-05T08:20:41Z"}],"graph_snapshots":[{"event_id":"sha256:366a0174a76e66187bc90ab32c2235877c8e38b43a8a167586c0dfaeea2777ef","target":"graph","created_at":"2026-07-05T08:20:41Z","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/2405.11530/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We observe that incorporating a shared layer in a mixture-of-experts can lead to performance degradation. This leads us to hypothesize that learning shared features poses challenges in deep learning, potentially caused by the same feature being learned as various different features. To address this issue, we track each expert's usage frequency and merge the two most frequently selected experts. We then update the least frequently selected expert using the combination of experts. This approach, combined with the subsequent learning of the router's expert selection, allows the model to determine","authors_text":"Sejik Park","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-19T11:55:48Z","title":"Learning More Generalized Experts by Merging Experts in Mixture-of-Experts"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.11530","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":"sha256:45c7d9cc38dd25b04bd134ef70de9b6f2e3fa0b5c95a9305c5ec724c8d435e20","target":"record","created_at":"2026-07-05T08:20:41Z","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":"9d1a2ebc64aaceeb3a8421b5f4f147acd20ee25e45a2a0019e30a232b13dee69","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-19T11:55:48Z","title_canon_sha256":"172f1f9d7c9e8a8a1758beaf23d0db7c500ffe79e710b4e6b484c25756001b8d"},"schema_version":"1.0","source":{"id":"2405.11530","kind":"arxiv","version":1}},"canonical_sha256":"1e725b0d3afb676c0da92817aae4904d09f4145854f79535858d03f2c169a600","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1e725b0d3afb676c0da92817aae4904d09f4145854f79535858d03f2c169a600","first_computed_at":"2026-07-05T08:20:41.109639Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:20:41.109639Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"sTXJAdTQuf/pRiW2RnEc8KmI4Jxb1vq9Mb1PcvlcYQeBifFcYHmjXxX3n0l6WKTZKV4O/8ylnoTJA1fJ2AOZBA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:20:41.110153Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.11530","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:45c7d9cc38dd25b04bd134ef70de9b6f2e3fa0b5c95a9305c5ec724c8d435e20","sha256:366a0174a76e66187bc90ab32c2235877c8e38b43a8a167586c0dfaeea2777ef"],"state_sha256":"4dcb8ae5e9a26fa2c14d1a65e3c6adfc8c06e2aa4cc05e3d397d939b4b297aa7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fYpnEZC1K0KUizGyuJ0ITmyxmbBm46GDfypACv80OM7eJkm9c5D5vCnlPZgnurdyIMe/H7nSNzI7LakDRO68CQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T17:39:47.724938Z","bundle_sha256":"09f936f110938cb6a9872322c80f986e7588cfe5bd39a309359913658ebe879c"}}