{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:Q5DHJJKJA3XBYQG6OWGNBC3N5S","short_pith_number":"pith:Q5DHJJKJ","canonical_record":{"source":{"id":"2605.29716","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-28T10:13:50Z","cross_cats_sorted":[],"title_canon_sha256":"3718718f7b1df0b039bc18d698e1fbae5b46caa09b118598c8881e43002b4ff3","abstract_canon_sha256":"8ab874f72f58aaf8d926146933c02e34ac377fc5d701c545f789c9b0e4f0604b"},"schema_version":"1.0"},"canonical_sha256":"874674a54906ee1c40de758cd08b6decac5a01f13ae923e0e2294c4906c28079","source":{"kind":"arxiv","id":"2605.29716","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.29716","created_at":"2026-05-29T01:05:56Z"},{"alias_kind":"arxiv_version","alias_value":"2605.29716v1","created_at":"2026-05-29T01:05:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.29716","created_at":"2026-05-29T01:05:56Z"},{"alias_kind":"pith_short_12","alias_value":"Q5DHJJKJA3XB","created_at":"2026-05-29T01:05:56Z"},{"alias_kind":"pith_short_16","alias_value":"Q5DHJJKJA3XBYQG6","created_at":"2026-05-29T01:05:56Z"},{"alias_kind":"pith_short_8","alias_value":"Q5DHJJKJ","created_at":"2026-05-29T01:05:56Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:Q5DHJJKJA3XBYQG6OWGNBC3N5S","target":"record","payload":{"canonical_record":{"source":{"id":"2605.29716","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-28T10:13:50Z","cross_cats_sorted":[],"title_canon_sha256":"3718718f7b1df0b039bc18d698e1fbae5b46caa09b118598c8881e43002b4ff3","abstract_canon_sha256":"8ab874f72f58aaf8d926146933c02e34ac377fc5d701c545f789c9b0e4f0604b"},"schema_version":"1.0"},"canonical_sha256":"874674a54906ee1c40de758cd08b6decac5a01f13ae923e0e2294c4906c28079","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-29T01:05:56.763727Z","signature_b64":"jVUKZ2E6c6bdZglWX6wO9nNAgGKLKLVLBexHgu8c5MVX4T2zRiaE52w4EC/t8SaM3Snsbs22MSELkZfCturKBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"874674a54906ee1c40de758cd08b6decac5a01f13ae923e0e2294c4906c28079","last_reissued_at":"2026-05-29T01:05:56.762794Z","signature_status":"signed_v1","first_computed_at":"2026-05-29T01:05:56.762794Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.29716","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":"2026-05-29T01:05:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NPxVWu6ifBDsPPGkknel1DvPQvQzgb3BF05lBrDo+TwZQJo1YjyNcG3UnHP2uBeAOJABxSi67XBq9RF7gMQhCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-08T15:10:22.192447Z"},"content_sha256":"ff69aafbbb33dae04dc1920eb484b2f14ebdbb3ff9eaee09446c055a8f1deb7e","schema_version":"1.0","event_id":"sha256:ff69aafbbb33dae04dc1920eb484b2f14ebdbb3ff9eaee09446c055a8f1deb7e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:Q5DHJJKJA3XBYQG6OWGNBC3N5S","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"NaRA: Noise-Aware LoRA for Parameter-Efficient Fine-Tuning of Diffusion LLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Ruping Huang, Shuaidi Wang, Yu Zhang, Zhan Zhuang","submitted_at":"2026-05-28T10:13:50Z","abstract_excerpt":"Diffusion Large Language Models (dLLMs) have emerged as a promising non-autoregressive generative paradigm. Given the prohibitive computational cost of full fine-tuning, Parameter-Efficient Fine-Tuning (PEFT) has become the standard approach. However, existing PEFT methods (e.g., LoRA), originally tailored for autoregressive models, rely on static parameters that are agnostic to the noise level. Consequently, they ignore the intrinsic dynamics of the diffusion process, where input distributions and generation difficulty shift significantly along the denoising trajectory, rendering them subopti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.29716","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/2605.29716/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":"2026-05-29T01:05:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"A+cWo1cOe3dFDD/u5BklOW8/fBjCiFazDEqu6wkF0mt2vFEN0ewERzGgGVSEW5b6MOG52643tjWV9k2+JTwDCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-08T15:10:22.193127Z"},"content_sha256":"542de9cccf5953b0eedd60ff27dbeab6b951fa564b408bf4fd8ba2f288e9bcd3","schema_version":"1.0","event_id":"sha256:542de9cccf5953b0eedd60ff27dbeab6b951fa564b408bf4fd8ba2f288e9bcd3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Q5DHJJKJA3XBYQG6OWGNBC3N5S/bundle.json","state_url":"https://pith.science/pith/Q5DHJJKJA3XBYQG6OWGNBC3N5S/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Q5DHJJKJA3XBYQG6OWGNBC3N5S/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":"2026-06-08T15:10:22Z","links":{"resolver":"https://pith.science/pith/Q5DHJJKJA3XBYQG6OWGNBC3N5S","bundle":"https://pith.science/pith/Q5DHJJKJA3XBYQG6OWGNBC3N5S/bundle.json","state":"https://pith.science/pith/Q5DHJJKJA3XBYQG6OWGNBC3N5S/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Q5DHJJKJA3XBYQG6OWGNBC3N5S/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:Q5DHJJKJA3XBYQG6OWGNBC3N5S","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":"8ab874f72f58aaf8d926146933c02e34ac377fc5d701c545f789c9b0e4f0604b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-28T10:13:50Z","title_canon_sha256":"3718718f7b1df0b039bc18d698e1fbae5b46caa09b118598c8881e43002b4ff3"},"schema_version":"1.0","source":{"id":"2605.29716","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.29716","created_at":"2026-05-29T01:05:56Z"},{"alias_kind":"arxiv_version","alias_value":"2605.29716v1","created_at":"2026-05-29T01:05:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.29716","created_at":"2026-05-29T01:05:56Z"},{"alias_kind":"pith_short_12","alias_value":"Q5DHJJKJA3XB","created_at":"2026-05-29T01:05:56Z"},{"alias_kind":"pith_short_16","alias_value":"Q5DHJJKJA3XBYQG6","created_at":"2026-05-29T01:05:56Z"},{"alias_kind":"pith_short_8","alias_value":"Q5DHJJKJ","created_at":"2026-05-29T01:05:56Z"}],"graph_snapshots":[{"event_id":"sha256:542de9cccf5953b0eedd60ff27dbeab6b951fa564b408bf4fd8ba2f288e9bcd3","target":"graph","created_at":"2026-05-29T01:05:56Z","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/2605.29716/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Diffusion Large Language Models (dLLMs) have emerged as a promising non-autoregressive generative paradigm. Given the prohibitive computational cost of full fine-tuning, Parameter-Efficient Fine-Tuning (PEFT) has become the standard approach. However, existing PEFT methods (e.g., LoRA), originally tailored for autoregressive models, rely on static parameters that are agnostic to the noise level. Consequently, they ignore the intrinsic dynamics of the diffusion process, where input distributions and generation difficulty shift significantly along the denoising trajectory, rendering them subopti","authors_text":"Ruping Huang, Shuaidi Wang, Yu Zhang, Zhan Zhuang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-28T10:13:50Z","title":"NaRA: Noise-Aware LoRA for Parameter-Efficient Fine-Tuning of Diffusion LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.29716","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:ff69aafbbb33dae04dc1920eb484b2f14ebdbb3ff9eaee09446c055a8f1deb7e","target":"record","created_at":"2026-05-29T01:05:56Z","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":"8ab874f72f58aaf8d926146933c02e34ac377fc5d701c545f789c9b0e4f0604b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-28T10:13:50Z","title_canon_sha256":"3718718f7b1df0b039bc18d698e1fbae5b46caa09b118598c8881e43002b4ff3"},"schema_version":"1.0","source":{"id":"2605.29716","kind":"arxiv","version":1}},"canonical_sha256":"874674a54906ee1c40de758cd08b6decac5a01f13ae923e0e2294c4906c28079","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"874674a54906ee1c40de758cd08b6decac5a01f13ae923e0e2294c4906c28079","first_computed_at":"2026-05-29T01:05:56.762794Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-29T01:05:56.762794Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jVUKZ2E6c6bdZglWX6wO9nNAgGKLKLVLBexHgu8c5MVX4T2zRiaE52w4EC/t8SaM3Snsbs22MSELkZfCturKBg==","signature_status":"signed_v1","signed_at":"2026-05-29T01:05:56.763727Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.29716","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ff69aafbbb33dae04dc1920eb484b2f14ebdbb3ff9eaee09446c055a8f1deb7e","sha256:542de9cccf5953b0eedd60ff27dbeab6b951fa564b408bf4fd8ba2f288e9bcd3"],"state_sha256":"eb720ed8056725043a29e86330fdc1abc6d2d907c5af9d8e7d368fb1beef532b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0zC53usHukOqnPxOj4RsoeU287HRPDfOnD0+T3TNtlHJb7xkg5Gm9H7u9l+K+VCq1BdrxWfWvnQMDt6NdGdpBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-08T15:10:22.197071Z","bundle_sha256":"c7469ce2941d9c055834486b89f6d2ea0002d3d0d9b42c41d31145fe9eb95566"}}