{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:FDP3QX5HOMF67EBER56HXSEVGH","short_pith_number":"pith:FDP3QX5H","canonical_record":{"source":{"id":"2408.15901","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-28T16:12:55Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"3e16b2be2bdf5bbe2536c5b5a6273ba2161a876505fa45d49213a0c3c878aed7","abstract_canon_sha256":"fedec2d93c6dee1b800df4c3cd09760078694185fa6b50e031ad8964e108bd22"},"schema_version":"1.0"},"canonical_sha256":"28dfb85fa7730bef90248f7c7bc89531e1982c547bad80cdd164929998bf2122","source":{"kind":"arxiv","id":"2408.15901","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.15901","created_at":"2026-07-05T09:00:19Z"},{"alias_kind":"arxiv_version","alias_value":"2408.15901v1","created_at":"2026-07-05T09:00:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.15901","created_at":"2026-07-05T09:00:19Z"},{"alias_kind":"pith_short_12","alias_value":"FDP3QX5HOMF6","created_at":"2026-07-05T09:00:19Z"},{"alias_kind":"pith_short_16","alias_value":"FDP3QX5HOMF67EBE","created_at":"2026-07-05T09:00:19Z"},{"alias_kind":"pith_short_8","alias_value":"FDP3QX5H","created_at":"2026-07-05T09:00:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:FDP3QX5HOMF67EBER56HXSEVGH","target":"record","payload":{"canonical_record":{"source":{"id":"2408.15901","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-28T16:12:55Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"3e16b2be2bdf5bbe2536c5b5a6273ba2161a876505fa45d49213a0c3c878aed7","abstract_canon_sha256":"fedec2d93c6dee1b800df4c3cd09760078694185fa6b50e031ad8964e108bd22"},"schema_version":"1.0"},"canonical_sha256":"28dfb85fa7730bef90248f7c7bc89531e1982c547bad80cdd164929998bf2122","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:00:19.151579Z","signature_b64":"UrdEN7+RSMDU0ByPxyrXMLG6c//WX7d9eeXbMndD0Y1KgP2WMgAy2L8z+Zh9ObzdxeWiZ6arWQzOM2Z+xZZzCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"28dfb85fa7730bef90248f7c7bc89531e1982c547bad80cdd164929998bf2122","last_reissued_at":"2026-07-05T09:00:19.151129Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:00:19.151129Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2408.15901","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":"2026-07-05T09:00:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FF3/9E5kDDtbzOiBW8wJKoyautbPp47BPq1yis+u34o1RzTob7AAiLiZRpVBxSuVqvLYmLzpT8GVacTo+VtWDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T11:49:56.095243Z"},"content_sha256":"3f7c9dbe25458c9cf26f818308c5dc550f3fa2c1cd81aa55682ed905685466f5","schema_version":"1.0","event_id":"sha256:3f7c9dbe25458c9cf26f818308c5dc550f3fa2c1cd81aa55682ed905685466f5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:FDP3QX5HOMF67EBER56HXSEVGH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Nexus: Specialization meets Adaptability for Efficiently Training Mixture of Experts","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Acyr Locatelli, Ahmet \\\"Ust\\\"un, Nikolas Gritsch, Qizhen Zhang, Sara Hooker","submitted_at":"2024-08-28T16:12:55Z","abstract_excerpt":"Efficiency, specialization, and adaptability to new data distributions are qualities that are hard to combine in current Large Language Models. The Mixture of Experts (MoE) architecture has been the focus of significant research because its inherent conditional computation enables such desirable properties. In this work, we focus on \"upcycling\" dense expert models into an MoE, aiming to improve specialization while also adding the ability to adapt to new tasks easily. We introduce Nexus, an enhanced MoE architecture with adaptive routing where the model learns to project expert embeddings from"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.15901","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/2408.15901/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":"2026-07-05T09:00:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"B2P4LOH6INxQ1S/Yyab0a2NXkx+TZPofnz/fOMfdcUzNjFjK4Q1/XWG2jTqp/Ez4012kZvOTGLsQaDoxqLBcBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T11:49:56.095726Z"},"content_sha256":"0c88afa41f9a3b55d9451b894cedd3296d5383b7693db9497d6fd4d8d5a58c87","schema_version":"1.0","event_id":"sha256:0c88afa41f9a3b55d9451b894cedd3296d5383b7693db9497d6fd4d8d5a58c87"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FDP3QX5HOMF67EBER56HXSEVGH/bundle.json","state_url":"https://pith.science/pith/FDP3QX5HOMF67EBER56HXSEVGH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FDP3QX5HOMF67EBER56HXSEVGH/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":"2026-08-08T11:49:56Z","links":{"resolver":"https://pith.science/pith/FDP3QX5HOMF67EBER56HXSEVGH","bundle":"https://pith.science/pith/FDP3QX5HOMF67EBER56HXSEVGH/bundle.json","state":"https://pith.science/pith/FDP3QX5HOMF67EBER56HXSEVGH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FDP3QX5HOMF67EBER56HXSEVGH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:FDP3QX5HOMF67EBER56HXSEVGH","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":"fedec2d93c6dee1b800df4c3cd09760078694185fa6b50e031ad8964e108bd22","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-28T16:12:55Z","title_canon_sha256":"3e16b2be2bdf5bbe2536c5b5a6273ba2161a876505fa45d49213a0c3c878aed7"},"schema_version":"1.0","source":{"id":"2408.15901","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.15901","created_at":"2026-07-05T09:00:19Z"},{"alias_kind":"arxiv_version","alias_value":"2408.15901v1","created_at":"2026-07-05T09:00:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.15901","created_at":"2026-07-05T09:00:19Z"},{"alias_kind":"pith_short_12","alias_value":"FDP3QX5HOMF6","created_at":"2026-07-05T09:00:19Z"},{"alias_kind":"pith_short_16","alias_value":"FDP3QX5HOMF67EBE","created_at":"2026-07-05T09:00:19Z"},{"alias_kind":"pith_short_8","alias_value":"FDP3QX5H","created_at":"2026-07-05T09:00:19Z"}],"graph_snapshots":[{"event_id":"sha256:0c88afa41f9a3b55d9451b894cedd3296d5383b7693db9497d6fd4d8d5a58c87","target":"graph","created_at":"2026-07-05T09:00:19Z","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/2408.15901/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Efficiency, specialization, and adaptability to new data distributions are qualities that are hard to combine in current Large Language Models. The Mixture of Experts (MoE) architecture has been the focus of significant research because its inherent conditional computation enables such desirable properties. In this work, we focus on \"upcycling\" dense expert models into an MoE, aiming to improve specialization while also adding the ability to adapt to new tasks easily. We introduce Nexus, an enhanced MoE architecture with adaptive routing where the model learns to project expert embeddings from","authors_text":"Acyr Locatelli, Ahmet \\\"Ust\\\"un, Nikolas Gritsch, Qizhen Zhang, Sara Hooker","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-28T16:12:55Z","title":"Nexus: Specialization meets Adaptability for Efficiently Training Mixture of Experts"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.15901","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":"sha256:3f7c9dbe25458c9cf26f818308c5dc550f3fa2c1cd81aa55682ed905685466f5","target":"record","created_at":"2026-07-05T09:00:19Z","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":"fedec2d93c6dee1b800df4c3cd09760078694185fa6b50e031ad8964e108bd22","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-28T16:12:55Z","title_canon_sha256":"3e16b2be2bdf5bbe2536c5b5a6273ba2161a876505fa45d49213a0c3c878aed7"},"schema_version":"1.0","source":{"id":"2408.15901","kind":"arxiv","version":1}},"canonical_sha256":"28dfb85fa7730bef90248f7c7bc89531e1982c547bad80cdd164929998bf2122","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"28dfb85fa7730bef90248f7c7bc89531e1982c547bad80cdd164929998bf2122","first_computed_at":"2026-07-05T09:00:19.151129Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:00:19.151129Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UrdEN7+RSMDU0ByPxyrXMLG6c//WX7d9eeXbMndD0Y1KgP2WMgAy2L8z+Zh9ObzdxeWiZ6arWQzOM2Z+xZZzCA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:00:19.151579Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.15901","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3f7c9dbe25458c9cf26f818308c5dc550f3fa2c1cd81aa55682ed905685466f5","sha256:0c88afa41f9a3b55d9451b894cedd3296d5383b7693db9497d6fd4d8d5a58c87"],"state_sha256":"8eb56e92d933d9bc5ce65089d34d2399b1d94aa347b97c842263512584085fef"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fwUi+k42/HywHCYw7IzX1mhqRDrABJMejNca0BaiA472ORzx9s1p9k6laY6+6p3SmY7/ylEB+dy7tZmI7qIzBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T11:49:56.099018Z","bundle_sha256":"c0f55ea968d65a63c05ff1fe7121d187c2ba03402f0d61120d85d3f8bdfce3a8"}}