{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:34EWLCNOG6XGDQCH44KUM2E7YA","short_pith_number":"pith:34EWLCNO","canonical_record":{"source":{"id":"2605.18795","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-11T06:43:14Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"911aeb2b49ba4b07e61a4684d843ec95809a106ebe8f49cf010a5e051331f386","abstract_canon_sha256":"46106e97312f102580af34a0d2a3eee1aad85ffff811775eebe19f7057db4362"},"schema_version":"1.0"},"canonical_sha256":"df096589ae37ae61c047e71546689fc036e74e941d7af41e94f3408af1d1c0c4","source":{"kind":"arxiv","id":"2605.18795","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.18795","created_at":"2026-05-20T00:06:22Z"},{"alias_kind":"arxiv_version","alias_value":"2605.18795v1","created_at":"2026-05-20T00:06:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.18795","created_at":"2026-05-20T00:06:22Z"},{"alias_kind":"pith_short_12","alias_value":"34EWLCNOG6XG","created_at":"2026-05-20T00:06:22Z"},{"alias_kind":"pith_short_16","alias_value":"34EWLCNOG6XGDQCH","created_at":"2026-05-20T00:06:22Z"},{"alias_kind":"pith_short_8","alias_value":"34EWLCNO","created_at":"2026-05-20T00:06:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:34EWLCNOG6XGDQCH44KUM2E7YA","target":"record","payload":{"canonical_record":{"source":{"id":"2605.18795","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-11T06:43:14Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"911aeb2b49ba4b07e61a4684d843ec95809a106ebe8f49cf010a5e051331f386","abstract_canon_sha256":"46106e97312f102580af34a0d2a3eee1aad85ffff811775eebe19f7057db4362"},"schema_version":"1.0"},"canonical_sha256":"df096589ae37ae61c047e71546689fc036e74e941d7af41e94f3408af1d1c0c4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:06:22.816747Z","signature_b64":"gxCcKnGydZyE6qXgd5W6fbFjw5gxos/V5LurC4df7sRNvK+uiyNklBF+65rie2ppoQJ3biRPrxkm5HW4w5ODCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"df096589ae37ae61c047e71546689fc036e74e941d7af41e94f3408af1d1c0c4","last_reissued_at":"2026-05-20T00:06:22.815746Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:06:22.815746Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.18795","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":"2026-05-20T00:06:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fosRTV2bMg/SWvyyzaSwnV9vawjzl69zbjhAjUZyLbi+KfsPiOetGGDAmgO8GFp7jwCeXuVFrdRTe7KsfekaAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T16:08:12.776231Z"},"content_sha256":"7fd4189bb930eff02c0f6ffed8de368cfd68ada5aac6490d066687ec937ef5a8","schema_version":"1.0","event_id":"sha256:7fd4189bb930eff02c0f6ffed8de368cfd68ada5aac6490d066687ec937ef5a8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:34EWLCNOG6XGDQCH44KUM2E7YA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"HELLoRA: Hot Experts Layer-Level Low-Rank Adaptation for Mixture-of-Experts Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Jia Wei, Longxiang Wang, Ping Chen, Qianyang li, Shaoxun Wang, Yancheng Pan, Zhonghao Zhang, Ziyi Qiu","submitted_at":"2026-05-11T06:43:14Z","abstract_excerpt":"Low-Rank Adaptation (LoRA) dominates parameter-efficient fine-tuning of large language models, yet most variants target dense architectures. Mixture-of-Experts (MoE) models scale parameters at near-constant per-token compute, and their sparse activation patterns create untapped opportunities for more efficient adaptation. We propose Hot-Experts Layer-level Low-Rank Adaptation (HELLoRA), which attaches LoRA modules only to the most frequently activated experts at each layer. This simple mechanism reduces trainable parameters and adapter-induced FLOPs while improving downstream performance, an e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.18795","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/2605.18795/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":"2026-05-20T00:06:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jac3Xx+43t6PsLW2r6EE9nFD87aEsrAKQdP8Tw5BNC68WrNDevrgP7R3DgYS/xjUZOVK8yAjScOAJS0xHZFXCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T16:08:12.776988Z"},"content_sha256":"722c5fd565d2a2cf0c6d37ab261e559f85f131661a20af8ba48f2eee75333c6c","schema_version":"1.0","event_id":"sha256:722c5fd565d2a2cf0c6d37ab261e559f85f131661a20af8ba48f2eee75333c6c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/34EWLCNOG6XGDQCH44KUM2E7YA/bundle.json","state_url":"https://pith.science/pith/34EWLCNOG6XGDQCH44KUM2E7YA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/34EWLCNOG6XGDQCH44KUM2E7YA/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":"2026-05-25T16:08:12Z","links":{"resolver":"https://pith.science/pith/34EWLCNOG6XGDQCH44KUM2E7YA","bundle":"https://pith.science/pith/34EWLCNOG6XGDQCH44KUM2E7YA/bundle.json","state":"https://pith.science/pith/34EWLCNOG6XGDQCH44KUM2E7YA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/34EWLCNOG6XGDQCH44KUM2E7YA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:34EWLCNOG6XGDQCH44KUM2E7YA","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":"46106e97312f102580af34a0d2a3eee1aad85ffff811775eebe19f7057db4362","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-11T06:43:14Z","title_canon_sha256":"911aeb2b49ba4b07e61a4684d843ec95809a106ebe8f49cf010a5e051331f386"},"schema_version":"1.0","source":{"id":"2605.18795","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.18795","created_at":"2026-05-20T00:06:22Z"},{"alias_kind":"arxiv_version","alias_value":"2605.18795v1","created_at":"2026-05-20T00:06:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.18795","created_at":"2026-05-20T00:06:22Z"},{"alias_kind":"pith_short_12","alias_value":"34EWLCNOG6XG","created_at":"2026-05-20T00:06:22Z"},{"alias_kind":"pith_short_16","alias_value":"34EWLCNOG6XGDQCH","created_at":"2026-05-20T00:06:22Z"},{"alias_kind":"pith_short_8","alias_value":"34EWLCNO","created_at":"2026-05-20T00:06:22Z"}],"graph_snapshots":[{"event_id":"sha256:722c5fd565d2a2cf0c6d37ab261e559f85f131661a20af8ba48f2eee75333c6c","target":"graph","created_at":"2026-05-20T00:06:22Z","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/2605.18795/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Low-Rank Adaptation (LoRA) dominates parameter-efficient fine-tuning of large language models, yet most variants target dense architectures. Mixture-of-Experts (MoE) models scale parameters at near-constant per-token compute, and their sparse activation patterns create untapped opportunities for more efficient adaptation. We propose Hot-Experts Layer-level Low-Rank Adaptation (HELLoRA), which attaches LoRA modules only to the most frequently activated experts at each layer. This simple mechanism reduces trainable parameters and adapter-induced FLOPs while improving downstream performance, an e","authors_text":"Jia Wei, Longxiang Wang, Ping Chen, Qianyang li, Shaoxun Wang, Yancheng Pan, Zhonghao Zhang, Ziyi Qiu","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-11T06:43:14Z","title":"HELLoRA: Hot Experts Layer-Level Low-Rank Adaptation for Mixture-of-Experts Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.18795","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":"sha256:7fd4189bb930eff02c0f6ffed8de368cfd68ada5aac6490d066687ec937ef5a8","target":"record","created_at":"2026-05-20T00:06:22Z","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":"46106e97312f102580af34a0d2a3eee1aad85ffff811775eebe19f7057db4362","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-11T06:43:14Z","title_canon_sha256":"911aeb2b49ba4b07e61a4684d843ec95809a106ebe8f49cf010a5e051331f386"},"schema_version":"1.0","source":{"id":"2605.18795","kind":"arxiv","version":1}},"canonical_sha256":"df096589ae37ae61c047e71546689fc036e74e941d7af41e94f3408af1d1c0c4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"df096589ae37ae61c047e71546689fc036e74e941d7af41e94f3408af1d1c0c4","first_computed_at":"2026-05-20T00:06:22.815746Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:06:22.815746Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gxCcKnGydZyE6qXgd5W6fbFjw5gxos/V5LurC4df7sRNvK+uiyNklBF+65rie2ppoQJ3biRPrxkm5HW4w5ODCA==","signature_status":"signed_v1","signed_at":"2026-05-20T00:06:22.816747Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.18795","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7fd4189bb930eff02c0f6ffed8de368cfd68ada5aac6490d066687ec937ef5a8","sha256:722c5fd565d2a2cf0c6d37ab261e559f85f131661a20af8ba48f2eee75333c6c"],"state_sha256":"84edc6662846191ce1ac1bfa9a8c1ea8d6a42d0cec79cc2e270fe4cb4602495d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uZ7hSJQ2XmSgh09Dj653nNHsSZjxwsCcxQjqAz65uV7a0004Qyi/7NA/v5PAyMUObrii+RwdCjAPMeqCsCTsCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T16:08:12.780867Z","bundle_sha256":"38c2a36d30a4b977cb178d16616328ccbb5c2cc4baa84b4ee77b62f70a356b20"}}