{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:ASWBVY7WEMGMLHX2ZCTPTHDPOS","short_pith_number":"pith:ASWBVY7W","canonical_record":{"source":{"id":"2410.10054","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-14T00:43:02Z","cross_cats_sorted":[],"title_canon_sha256":"3f4cf373d3f42e9ff5f75e08584f2f3ccdca21bf7c926d3993227a57018912e8","abstract_canon_sha256":"518d8f2bd1b5c294cf7f92205ee8c518a69f1c05e15ddebfa37f00aec7ff6765"},"schema_version":"1.0"},"canonical_sha256":"04ac1ae3f6230cc59efac8a6f99c6f74ac7d9b83df6c745ef033bc1eaad171b5","source":{"kind":"arxiv","id":"2410.10054","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.10054","created_at":"2026-07-05T09:20:10Z"},{"alias_kind":"arxiv_version","alias_value":"2410.10054v1","created_at":"2026-07-05T09:20:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.10054","created_at":"2026-07-05T09:20:10Z"},{"alias_kind":"pith_short_12","alias_value":"ASWBVY7WEMGM","created_at":"2026-07-05T09:20:10Z"},{"alias_kind":"pith_short_16","alias_value":"ASWBVY7WEMGMLHX2","created_at":"2026-07-05T09:20:10Z"},{"alias_kind":"pith_short_8","alias_value":"ASWBVY7W","created_at":"2026-07-05T09:20:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:ASWBVY7WEMGMLHX2ZCTPTHDPOS","target":"record","payload":{"canonical_record":{"source":{"id":"2410.10054","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-14T00:43:02Z","cross_cats_sorted":[],"title_canon_sha256":"3f4cf373d3f42e9ff5f75e08584f2f3ccdca21bf7c926d3993227a57018912e8","abstract_canon_sha256":"518d8f2bd1b5c294cf7f92205ee8c518a69f1c05e15ddebfa37f00aec7ff6765"},"schema_version":"1.0"},"canonical_sha256":"04ac1ae3f6230cc59efac8a6f99c6f74ac7d9b83df6c745ef033bc1eaad171b5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:20:10.398605Z","signature_b64":"s//thLnQmjn4nyb9ml0vW18CszyykmqN3WR5Nu698gZX+rZ1NPPROWMsbBHuaUWXJMNDuwclrE+8BnN02ZRFAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"04ac1ae3f6230cc59efac8a6f99c6f74ac7d9b83df6c745ef033bc1eaad171b5","last_reissued_at":"2026-07-05T09:20:10.398129Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:20:10.398129Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.10054","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":"2026-07-05T09:20:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HX4LjidWTuix/UoF7RxoAub5qu7UiAY302amiSmX8HXP0MBiOw7+IINJbYPsBqAEVBJMIo2Fvy/C+lPdo8JLCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T11:57:39.608619Z"},"content_sha256":"a31abbbc81b2096520fc9d532998d48be9f3bde1337cb7dc2c4d4138f10aca3e","schema_version":"1.0","event_id":"sha256:a31abbbc81b2096520fc9d532998d48be9f3bde1337cb7dc2c4d4138f10aca3e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:ASWBVY7WEMGMLHX2ZCTPTHDPOS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"AlphaLoRA: Assigning LoRA Experts Based on Layer Training Quality","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chongyang Gao, Peijun Qing, Soroush Vosoughi, Xingjian Diao, Yaoqing Yang, Yefan Zhou","submitted_at":"2024-10-14T00:43:02Z","abstract_excerpt":"Parameter-efficient fine-tuning methods, such as Low-Rank Adaptation (LoRA), are known to enhance training efficiency in Large Language Models (LLMs). Due to the limited parameters of LoRA, recent studies seek to combine LoRA with Mixture-of-Experts (MoE) to boost performance across various tasks. However, inspired by the observed redundancy in traditional MoE structures, previous studies identify similar redundancy among LoRA experts within the MoE architecture, highlighting the necessity for non-uniform allocation of LoRA experts across different layers. In this paper, we leverage Heavy-Tail"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.10054","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/2410.10054/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":"2026-07-05T09:20:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GwUBVqkJPFYy30xNJkxDJmFtLwUryenx2XIFdOGMFrMfc0/AmenrU2/Q61q/pHFyRcQyIQWamKDIYKrN/4nsCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T11:57:39.609138Z"},"content_sha256":"f4e28c89dc8d57a652c2eecdf5bfea0126f343aa16f0e6a8064877ebf2b2f567","schema_version":"1.0","event_id":"sha256:f4e28c89dc8d57a652c2eecdf5bfea0126f343aa16f0e6a8064877ebf2b2f567"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ASWBVY7WEMGMLHX2ZCTPTHDPOS/bundle.json","state_url":"https://pith.science/pith/ASWBVY7WEMGMLHX2ZCTPTHDPOS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ASWBVY7WEMGMLHX2ZCTPTHDPOS/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":"2026-08-08T11:57:39Z","links":{"resolver":"https://pith.science/pith/ASWBVY7WEMGMLHX2ZCTPTHDPOS","bundle":"https://pith.science/pith/ASWBVY7WEMGMLHX2ZCTPTHDPOS/bundle.json","state":"https://pith.science/pith/ASWBVY7WEMGMLHX2ZCTPTHDPOS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ASWBVY7WEMGMLHX2ZCTPTHDPOS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ASWBVY7WEMGMLHX2ZCTPTHDPOS","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":"518d8f2bd1b5c294cf7f92205ee8c518a69f1c05e15ddebfa37f00aec7ff6765","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-14T00:43:02Z","title_canon_sha256":"3f4cf373d3f42e9ff5f75e08584f2f3ccdca21bf7c926d3993227a57018912e8"},"schema_version":"1.0","source":{"id":"2410.10054","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.10054","created_at":"2026-07-05T09:20:10Z"},{"alias_kind":"arxiv_version","alias_value":"2410.10054v1","created_at":"2026-07-05T09:20:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.10054","created_at":"2026-07-05T09:20:10Z"},{"alias_kind":"pith_short_12","alias_value":"ASWBVY7WEMGM","created_at":"2026-07-05T09:20:10Z"},{"alias_kind":"pith_short_16","alias_value":"ASWBVY7WEMGMLHX2","created_at":"2026-07-05T09:20:10Z"},{"alias_kind":"pith_short_8","alias_value":"ASWBVY7W","created_at":"2026-07-05T09:20:10Z"}],"graph_snapshots":[{"event_id":"sha256:f4e28c89dc8d57a652c2eecdf5bfea0126f343aa16f0e6a8064877ebf2b2f567","target":"graph","created_at":"2026-07-05T09:20:10Z","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/2410.10054/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Parameter-efficient fine-tuning methods, such as Low-Rank Adaptation (LoRA), are known to enhance training efficiency in Large Language Models (LLMs). Due to the limited parameters of LoRA, recent studies seek to combine LoRA with Mixture-of-Experts (MoE) to boost performance across various tasks. However, inspired by the observed redundancy in traditional MoE structures, previous studies identify similar redundancy among LoRA experts within the MoE architecture, highlighting the necessity for non-uniform allocation of LoRA experts across different layers. In this paper, we leverage Heavy-Tail","authors_text":"Chongyang Gao, Peijun Qing, Soroush Vosoughi, Xingjian Diao, Yaoqing Yang, Yefan Zhou","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-14T00:43:02Z","title":"AlphaLoRA: Assigning LoRA Experts Based on Layer Training Quality"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.10054","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:a31abbbc81b2096520fc9d532998d48be9f3bde1337cb7dc2c4d4138f10aca3e","target":"record","created_at":"2026-07-05T09:20:10Z","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":"518d8f2bd1b5c294cf7f92205ee8c518a69f1c05e15ddebfa37f00aec7ff6765","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-14T00:43:02Z","title_canon_sha256":"3f4cf373d3f42e9ff5f75e08584f2f3ccdca21bf7c926d3993227a57018912e8"},"schema_version":"1.0","source":{"id":"2410.10054","kind":"arxiv","version":1}},"canonical_sha256":"04ac1ae3f6230cc59efac8a6f99c6f74ac7d9b83df6c745ef033bc1eaad171b5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"04ac1ae3f6230cc59efac8a6f99c6f74ac7d9b83df6c745ef033bc1eaad171b5","first_computed_at":"2026-07-05T09:20:10.398129Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:20:10.398129Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"s//thLnQmjn4nyb9ml0vW18CszyykmqN3WR5Nu698gZX+rZ1NPPROWMsbBHuaUWXJMNDuwclrE+8BnN02ZRFAw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:20:10.398605Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.10054","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a31abbbc81b2096520fc9d532998d48be9f3bde1337cb7dc2c4d4138f10aca3e","sha256:f4e28c89dc8d57a652c2eecdf5bfea0126f343aa16f0e6a8064877ebf2b2f567"],"state_sha256":"4c6ceb190d4f82a9cb7685a1162662a33da2a68f46d4aeeac4828eaf582ab6e1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5h3SZi9ofyY6Qw//QwDAtydfI+Lmi/VbAMJQHJZCsl9RT63r26JhH0OHM+5z/bhaZf3y/wnFpEPdBtX5f91JCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T11:57:39.615521Z","bundle_sha256":"eb227eea8f2ec3145c363614e99673d0f4b3871c99a253a6a58194ce790e38ef"}}