{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:EKIBJMN45LNHXLTGR5HKHCNEP6","short_pith_number":"pith:EKIBJMN4","canonical_record":{"source":{"id":"2502.08905","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-13T02:41:34Z","cross_cats_sorted":[],"title_canon_sha256":"ff379064fa8abef1bc3e8edf38e434f8c29fe743e06471ca73ab262a6723054a","abstract_canon_sha256":"87269acb75da8845aa12932e53a71fcb8580d9193bbe3261375bfa2559711107"},"schema_version":"1.0"},"canonical_sha256":"229014b1bceada7bae668f4ea389a47fb02d26055b8dc15c202497243b5a5674","source":{"kind":"arxiv","id":"2502.08905","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.08905","created_at":"2026-07-05T11:15:42Z"},{"alias_kind":"arxiv_version","alias_value":"2502.08905v2","created_at":"2026-07-05T11:15:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.08905","created_at":"2026-07-05T11:15:42Z"},{"alias_kind":"pith_short_12","alias_value":"EKIBJMN45LNH","created_at":"2026-07-05T11:15:42Z"},{"alias_kind":"pith_short_16","alias_value":"EKIBJMN45LNHXLTG","created_at":"2026-07-05T11:15:42Z"},{"alias_kind":"pith_short_8","alias_value":"EKIBJMN4","created_at":"2026-07-05T11:15:42Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:EKIBJMN45LNHXLTGR5HKHCNEP6","target":"record","payload":{"canonical_record":{"source":{"id":"2502.08905","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-13T02:41:34Z","cross_cats_sorted":[],"title_canon_sha256":"ff379064fa8abef1bc3e8edf38e434f8c29fe743e06471ca73ab262a6723054a","abstract_canon_sha256":"87269acb75da8845aa12932e53a71fcb8580d9193bbe3261375bfa2559711107"},"schema_version":"1.0"},"canonical_sha256":"229014b1bceada7bae668f4ea389a47fb02d26055b8dc15c202497243b5a5674","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:15:42.676515Z","signature_b64":"dd/kdmAx4u6x242K3eBPc7B65FmtOTNA2huRBiAOX21cRnjuHSxuQBhwaxu07QZwoREsSdh8zUuiuGOjaDmtBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"229014b1bceada7bae668f4ea389a47fb02d26055b8dc15c202497243b5a5674","last_reissued_at":"2026-07-05T11:15:42.675849Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:15:42.675849Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.08905","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:15:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"N0zon+rKSJ23oQZyq0kZ3l+Xjy9V+SmqH8b4mOwxP6vb/Aoej8pmiQ6dfa9YbaQIY2Xi7IWCkn9lT7BTpQKkCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T22:45:48.605273Z"},"content_sha256":"a2ed491b8bdf6c403de3fe0d5c0500b1d1d8d1b71b99360eacf720d5a35df115","schema_version":"1.0","event_id":"sha256:a2ed491b8bdf6c403de3fe0d5c0500b1d1d8d1b71b99360eacf720d5a35df115"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:EKIBJMN45LNHXLTGR5HKHCNEP6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"DiffoRA: Enabling Parameter-Efficient Fine-Tuning via Differential Module Selection","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chun Yuan, Haodi Wang, Tangyu Jiang","submitted_at":"2025-02-13T02:41:34Z","abstract_excerpt":"The Parameter-Efficient Fine-Tuning (PEFT) methods have been extensively researched for large language models in downstream tasks. Among all the existing approaches, the Low-Rank Adaptation (LoRA) has gained popularity for its streamlined design by incorporating low-rank matrices into existing pre-trained models. Though effective, LoRA, as well as its adaptive optimizations, either allocate the same matrix to all the modules or adjust the interior rank of the components based on importance scoring indicators. In this paper, we argue that not all the modules in LLMs are suitable and necessary t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.08905","kind":"arxiv","version":2},"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/2502.08905/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":"2026-07-05T11:15:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Uxa6DxDsFuQtgP3zVWjyCtCBcl4zEkawt2paWAeHN5rVpPvpQiubRIqoU2CoJHfrNLmSryJFbPJxZvDHHxOfDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T22:45:48.606391Z"},"content_sha256":"320a8aa9ffff5484b5caf27fbd20ce915c2a445537779ba85b3a8baca24bc31b","schema_version":"1.0","event_id":"sha256:320a8aa9ffff5484b5caf27fbd20ce915c2a445537779ba85b3a8baca24bc31b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EKIBJMN45LNHXLTGR5HKHCNEP6/bundle.json","state_url":"https://pith.science/pith/EKIBJMN45LNHXLTGR5HKHCNEP6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EKIBJMN45LNHXLTGR5HKHCNEP6/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":"2026-08-08T22:45:48Z","links":{"resolver":"https://pith.science/pith/EKIBJMN45LNHXLTGR5HKHCNEP6","bundle":"https://pith.science/pith/EKIBJMN45LNHXLTGR5HKHCNEP6/bundle.json","state":"https://pith.science/pith/EKIBJMN45LNHXLTGR5HKHCNEP6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EKIBJMN45LNHXLTGR5HKHCNEP6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:EKIBJMN45LNHXLTGR5HKHCNEP6","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":"87269acb75da8845aa12932e53a71fcb8580d9193bbe3261375bfa2559711107","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-13T02:41:34Z","title_canon_sha256":"ff379064fa8abef1bc3e8edf38e434f8c29fe743e06471ca73ab262a6723054a"},"schema_version":"1.0","source":{"id":"2502.08905","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.08905","created_at":"2026-07-05T11:15:42Z"},{"alias_kind":"arxiv_version","alias_value":"2502.08905v2","created_at":"2026-07-05T11:15:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.08905","created_at":"2026-07-05T11:15:42Z"},{"alias_kind":"pith_short_12","alias_value":"EKIBJMN45LNH","created_at":"2026-07-05T11:15:42Z"},{"alias_kind":"pith_short_16","alias_value":"EKIBJMN45LNHXLTG","created_at":"2026-07-05T11:15:42Z"},{"alias_kind":"pith_short_8","alias_value":"EKIBJMN4","created_at":"2026-07-05T11:15:42Z"}],"graph_snapshots":[{"event_id":"sha256:320a8aa9ffff5484b5caf27fbd20ce915c2a445537779ba85b3a8baca24bc31b","target":"graph","created_at":"2026-07-05T11:15:42Z","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/2502.08905/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The Parameter-Efficient Fine-Tuning (PEFT) methods have been extensively researched for large language models in downstream tasks. Among all the existing approaches, the Low-Rank Adaptation (LoRA) has gained popularity for its streamlined design by incorporating low-rank matrices into existing pre-trained models. Though effective, LoRA, as well as its adaptive optimizations, either allocate the same matrix to all the modules or adjust the interior rank of the components based on importance scoring indicators. In this paper, we argue that not all the modules in LLMs are suitable and necessary t","authors_text":"Chun Yuan, Haodi Wang, Tangyu Jiang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-13T02:41:34Z","title":"DiffoRA: Enabling Parameter-Efficient Fine-Tuning via Differential Module Selection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.08905","kind":"arxiv","version":2},"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:a2ed491b8bdf6c403de3fe0d5c0500b1d1d8d1b71b99360eacf720d5a35df115","target":"record","created_at":"2026-07-05T11:15:42Z","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":"87269acb75da8845aa12932e53a71fcb8580d9193bbe3261375bfa2559711107","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-13T02:41:34Z","title_canon_sha256":"ff379064fa8abef1bc3e8edf38e434f8c29fe743e06471ca73ab262a6723054a"},"schema_version":"1.0","source":{"id":"2502.08905","kind":"arxiv","version":2}},"canonical_sha256":"229014b1bceada7bae668f4ea389a47fb02d26055b8dc15c202497243b5a5674","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"229014b1bceada7bae668f4ea389a47fb02d26055b8dc15c202497243b5a5674","first_computed_at":"2026-07-05T11:15:42.675849Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:15:42.675849Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dd/kdmAx4u6x242K3eBPc7B65FmtOTNA2huRBiAOX21cRnjuHSxuQBhwaxu07QZwoREsSdh8zUuiuGOjaDmtBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:15:42.676515Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.08905","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a2ed491b8bdf6c403de3fe0d5c0500b1d1d8d1b71b99360eacf720d5a35df115","sha256:320a8aa9ffff5484b5caf27fbd20ce915c2a445537779ba85b3a8baca24bc31b"],"state_sha256":"16cc9a1742c5b3979d674e4e3e83c5240374c6d4452dda58ed5d593c2daa4b93"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gO9P+BerDlx9zAwymzhBt2ZjykGF1FveKQso/YQ/MfTsWVEFaUuUW2DFKBRB8s2rcbvx9gesBrBIJMNmJ/KMCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T22:45:48.613338Z","bundle_sha256":"0ae82d322b11e851d08e5242a7519cd560c211acb6d4cdd085ceff1a35d2bffe"}}