{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:GHFTGZBVXD7QM5CJMVSWJTI4FE","short_pith_number":"pith:GHFTGZBV","canonical_record":{"source":{"id":"2601.16991","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-01-08T20:34:12Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b75e5cc69182fe2d4ee6520e0a6f066027f2bc039de96afc306835b4ba1dcca0","abstract_canon_sha256":"e4326b0e1298ce0bcca108b9ce22e9c23421d8333d8518adcadd9338a80210a8"},"schema_version":"1.0"},"canonical_sha256":"31cb336435b8ff067449656564cd1c29144a8e53d469525705f6322d55307ecb","source":{"kind":"arxiv","id":"2601.16991","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2601.16991","created_at":"2026-07-21T01:21:42Z"},{"alias_kind":"arxiv_version","alias_value":"2601.16991v3","created_at":"2026-07-21T01:21:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.16991","created_at":"2026-07-21T01:21:42Z"},{"alias_kind":"pith_short_12","alias_value":"GHFTGZBVXD7Q","created_at":"2026-07-21T01:21:42Z"},{"alias_kind":"pith_short_16","alias_value":"GHFTGZBVXD7QM5CJ","created_at":"2026-07-21T01:21:42Z"},{"alias_kind":"pith_short_8","alias_value":"GHFTGZBV","created_at":"2026-07-21T01:21:42Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:GHFTGZBVXD7QM5CJMVSWJTI4FE","target":"record","payload":{"canonical_record":{"source":{"id":"2601.16991","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-01-08T20:34:12Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b75e5cc69182fe2d4ee6520e0a6f066027f2bc039de96afc306835b4ba1dcca0","abstract_canon_sha256":"e4326b0e1298ce0bcca108b9ce22e9c23421d8333d8518adcadd9338a80210a8"},"schema_version":"1.0"},"canonical_sha256":"31cb336435b8ff067449656564cd1c29144a8e53d469525705f6322d55307ecb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-21T01:21:42.517643Z","signature_b64":"qiVmpi3X4mN1qDty2lHHFD3YUNVWeEj9cOoQOm56WmqweX5lbFPR7Fg8WyT4FbeslAU4LQqdZXBppphjLEbpCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"31cb336435b8ff067449656564cd1c29144a8e53d469525705f6322d55307ecb","last_reissued_at":"2026-07-21T01:21:42.516703Z","signature_status":"signed_v1","first_computed_at":"2026-07-21T01:21:42.516703Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2601.16991","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-21T01:21:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wH/vGrfMT4CnJ5oSqtASU4FnXrUbrZznov5ZTkWyAOTAcmY1nbnh5LfE83R4bACFcC2XsqLq6wQAf4NXJ+/rDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T10:46:12.171456Z"},"content_sha256":"8dc288222fb7724e0de5ddd5d4be5fa1f205bf0e06f583c1fbeb62f14296ce55","schema_version":"1.0","event_id":"sha256:8dc288222fb7724e0de5ddd5d4be5fa1f205bf0e06f583c1fbeb62f14296ce55"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:GHFTGZBVXD7QM5CJMVSWJTI4FE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Sparsity-Aware Low-Rank Representation for Efficient Fine-Tuning of Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Danning Ke, Longteng Zhang, Qiang Wang, Qihong Lin, Sen Wu, Shaohuai Shi, Shuai Hou, Xiaowen Chu, Zhengyu Qing, Zhuo Zheng","submitted_at":"2026-01-08T20:34:12Z","abstract_excerpt":"Adapting large pre-trained language models to downstream tasks often entails fine-tuning millions of parameters or deploying costly dense weight updates, which hinders their use in resource-constrained environments. Low-rank Adaptation (LoRA) reduces trainable parameters by factorizing weight updates, yet the underlying dense weights still impose high storage and computation costs. Magnitude-based pruning can yield sparse models but typically degrades LoRA's performance when applied naively. In this paper, we introduce SALR (Sparsity-Aware Low-Rank Representation), a novel fine-tuning paradigm"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.16991","kind":"arxiv","version":3},"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/2601.16991/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":"2026-07-21T01:21:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"i2yx+EnOdv/xzKHdetSVtoPqYFZ1NIMgV9ekNslVZyHKzqMzIcPnr1prTXHIZybnwI2sr59AelP5ikYZTe4/BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T10:46:12.172070Z"},"content_sha256":"3583a8f7c362472340bdff9f0e88354816bd2113b37754a84deea2f520f26719","schema_version":"1.0","event_id":"sha256:3583a8f7c362472340bdff9f0e88354816bd2113b37754a84deea2f520f26719"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GHFTGZBVXD7QM5CJMVSWJTI4FE/bundle.json","state_url":"https://pith.science/pith/GHFTGZBVXD7QM5CJMVSWJTI4FE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GHFTGZBVXD7QM5CJMVSWJTI4FE/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":"2026-08-04T10:46:12Z","links":{"resolver":"https://pith.science/pith/GHFTGZBVXD7QM5CJMVSWJTI4FE","bundle":"https://pith.science/pith/GHFTGZBVXD7QM5CJMVSWJTI4FE/bundle.json","state":"https://pith.science/pith/GHFTGZBVXD7QM5CJMVSWJTI4FE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GHFTGZBVXD7QM5CJMVSWJTI4FE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:GHFTGZBVXD7QM5CJMVSWJTI4FE","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":"e4326b0e1298ce0bcca108b9ce22e9c23421d8333d8518adcadd9338a80210a8","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-01-08T20:34:12Z","title_canon_sha256":"b75e5cc69182fe2d4ee6520e0a6f066027f2bc039de96afc306835b4ba1dcca0"},"schema_version":"1.0","source":{"id":"2601.16991","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2601.16991","created_at":"2026-07-21T01:21:42Z"},{"alias_kind":"arxiv_version","alias_value":"2601.16991v3","created_at":"2026-07-21T01:21:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.16991","created_at":"2026-07-21T01:21:42Z"},{"alias_kind":"pith_short_12","alias_value":"GHFTGZBVXD7Q","created_at":"2026-07-21T01:21:42Z"},{"alias_kind":"pith_short_16","alias_value":"GHFTGZBVXD7QM5CJ","created_at":"2026-07-21T01:21:42Z"},{"alias_kind":"pith_short_8","alias_value":"GHFTGZBV","created_at":"2026-07-21T01:21:42Z"}],"graph_snapshots":[{"event_id":"sha256:3583a8f7c362472340bdff9f0e88354816bd2113b37754a84deea2f520f26719","target":"graph","created_at":"2026-07-21T01:21:42Z","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/2601.16991/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Adapting large pre-trained language models to downstream tasks often entails fine-tuning millions of parameters or deploying costly dense weight updates, which hinders their use in resource-constrained environments. Low-rank Adaptation (LoRA) reduces trainable parameters by factorizing weight updates, yet the underlying dense weights still impose high storage and computation costs. Magnitude-based pruning can yield sparse models but typically degrades LoRA's performance when applied naively. In this paper, we introduce SALR (Sparsity-Aware Low-Rank Representation), a novel fine-tuning paradigm","authors_text":"Danning Ke, Longteng Zhang, Qiang Wang, Qihong Lin, Sen Wu, Shaohuai Shi, Shuai Hou, Xiaowen Chu, Zhengyu Qing, Zhuo Zheng","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-01-08T20:34:12Z","title":"Sparsity-Aware Low-Rank Representation for Efficient Fine-Tuning of Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.16991","kind":"arxiv","version":3},"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":"sha256:8dc288222fb7724e0de5ddd5d4be5fa1f205bf0e06f583c1fbeb62f14296ce55","target":"record","created_at":"2026-07-21T01:21:42Z","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":"e4326b0e1298ce0bcca108b9ce22e9c23421d8333d8518adcadd9338a80210a8","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-01-08T20:34:12Z","title_canon_sha256":"b75e5cc69182fe2d4ee6520e0a6f066027f2bc039de96afc306835b4ba1dcca0"},"schema_version":"1.0","source":{"id":"2601.16991","kind":"arxiv","version":3}},"canonical_sha256":"31cb336435b8ff067449656564cd1c29144a8e53d469525705f6322d55307ecb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"31cb336435b8ff067449656564cd1c29144a8e53d469525705f6322d55307ecb","first_computed_at":"2026-07-21T01:21:42.516703Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-21T01:21:42.516703Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qiVmpi3X4mN1qDty2lHHFD3YUNVWeEj9cOoQOm56WmqweX5lbFPR7Fg8WyT4FbeslAU4LQqdZXBppphjLEbpCQ==","signature_status":"signed_v1","signed_at":"2026-07-21T01:21:42.517643Z","signed_message":"canonical_sha256_bytes"},"source_id":"2601.16991","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8dc288222fb7724e0de5ddd5d4be5fa1f205bf0e06f583c1fbeb62f14296ce55","sha256:3583a8f7c362472340bdff9f0e88354816bd2113b37754a84deea2f520f26719"],"state_sha256":"7328dead655a17128c24282648a0bab41c3e8dbcfc6fe9d9cf1a4f0d5282f69e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3HMJ0fdtxc+usq4kcgEUIDPU7f8fhHnTAgxreGneUa8mRKh6rj6fh0gy7KBKgAqXvT+KKaD9woVeqoOln69WDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T10:46:12.176762Z","bundle_sha256":"760fac233f3c17433923a67cd197815fa820d208072dcbce547094eda38b8457"}}