{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:OXL5LF52BRING2EFKID225S3BH","short_pith_number":"pith:OXL5LF52","schema_version":"1.0","canonical_sha256":"75d7d597ba0c50d368855207ad765b09e6770e9a0951adddad0b949dd863d723","source":{"kind":"arxiv","id":"2607.09757","version":1},"attestation_state":"computed","paper":{"title":"RSLoRA: Training-free Rank Allocation for LoRA via Representational Sensitivity Probing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Guo Yu, Haidong Kang, Jiaqi Liu, Qihui Zhao","submitted_at":"2026-07-05T13:58:38Z","abstract_excerpt":"Low-Rank Adaptation (LoRA) has become a cornerstone of parameter-efficient fine-tuning (PEFT); however, the conventional practice of uniform rank assignment ignores the functional heterogeneity of neural layers. Existing rank allocation methods typically struggle with a trade-off between computational intensity and heuristic simplicity: training-based methods suffer from prohibitive overhead, while pre-allocation methods fail to capture the dynamic task-specific representation manifold. In this paper, we propose RSLoRA (Representational Sensitivity LoRA), a training-free and gradient-free rank"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2607.09757","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-05T13:58:38Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a179c3a29d48891895e10617bb1e8c1f626c7e630388e95d8157529b56991487","abstract_canon_sha256":"b275dfcb16648ef7d513e49267d23a5de82e6c5eaac2fe54c48621d03515f565"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-14T00:18:34.093707Z","signature_b64":"fOIZpDEVa6oG2djBU+oUvaDJOxnUySnq2FywhXIdrZgkclumlzan40dLiJp2KV4SFF47PLA6Wtd4jIOWOgYwCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"75d7d597ba0c50d368855207ad765b09e6770e9a0951adddad0b949dd863d723","last_reissued_at":"2026-07-14T00:18:34.092838Z","signature_status":"signed_v1","first_computed_at":"2026-07-14T00:18:34.092838Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RSLoRA: Training-free Rank Allocation for LoRA via Representational Sensitivity Probing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Guo Yu, Haidong Kang, Jiaqi Liu, Qihui Zhao","submitted_at":"2026-07-05T13:58:38Z","abstract_excerpt":"Low-Rank Adaptation (LoRA) has become a cornerstone of parameter-efficient fine-tuning (PEFT); however, the conventional practice of uniform rank assignment ignores the functional heterogeneity of neural layers. Existing rank allocation methods typically struggle with a trade-off between computational intensity and heuristic simplicity: training-based methods suffer from prohibitive overhead, while pre-allocation methods fail to capture the dynamic task-specific representation manifold. In this paper, we propose RSLoRA (Representational Sensitivity LoRA), a training-free and gradient-free rank"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.09757","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/2607.09757/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2607.09757","created_at":"2026-07-14T00:18:34.093266+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.09757v1","created_at":"2026-07-14T00:18:34.093266+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.09757","created_at":"2026-07-14T00:18:34.093266+00:00"},{"alias_kind":"pith_short_12","alias_value":"OXL5LF52BRIN","created_at":"2026-07-14T00:18:34.093266+00:00"},{"alias_kind":"pith_short_16","alias_value":"OXL5LF52BRING2EF","created_at":"2026-07-14T00:18:34.093266+00:00"},{"alias_kind":"pith_short_8","alias_value":"OXL5LF52","created_at":"2026-07-14T00:18:34.093266+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OXL5LF52BRING2EFKID225S3BH","json":"https://pith.science/pith/OXL5LF52BRING2EFKID225S3BH.json","graph_json":"https://pith.science/api/pith-number/OXL5LF52BRING2EFKID225S3BH/graph.json","events_json":"https://pith.science/api/pith-number/OXL5LF52BRING2EFKID225S3BH/events.json","paper":"https://pith.science/paper/OXL5LF52"},"agent_actions":{"view_html":"https://pith.science/pith/OXL5LF52BRING2EFKID225S3BH","download_json":"https://pith.science/pith/OXL5LF52BRING2EFKID225S3BH.json","view_paper":"https://pith.science/paper/OXL5LF52","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.09757&json=true","fetch_graph":"https://pith.science/api/pith-number/OXL5LF52BRING2EFKID225S3BH/graph.json","fetch_events":"https://pith.science/api/pith-number/OXL5LF52BRING2EFKID225S3BH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OXL5LF52BRING2EFKID225S3BH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OXL5LF52BRING2EFKID225S3BH/action/storage_attestation","attest_author":"https://pith.science/pith/OXL5LF52BRING2EFKID225S3BH/action/author_attestation","sign_citation":"https://pith.science/pith/OXL5LF52BRING2EFKID225S3BH/action/citation_signature","submit_replication":"https://pith.science/pith/OXL5LF52BRING2EFKID225S3BH/action/replication_record"}},"created_at":"2026-07-14T00:18:34.093266+00:00","updated_at":"2026-07-14T00:18:34.093266+00:00"}