{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:YE26JPZL2QGM2EZ2CQFGWGRX2M","short_pith_number":"pith:YE26JPZL","canonical_record":{"source":{"id":"2505.14350","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-20T13:34:06Z","cross_cats_sorted":[],"title_canon_sha256":"9331c1704b4faae9214c33870909203e5341479aab432fa1814e409c9ed396e8","abstract_canon_sha256":"487756d437af3d7e7722444e44189be7489fb75a2aa298d9995eabdd1a4eb701"},"schema_version":"1.0"},"canonical_sha256":"c135e4bf2bd40ccd133a140a6b1a37d32edc3e1657dc6723844b04e70639542f","source":{"kind":"arxiv","id":"2505.14350","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.14350","created_at":"2026-07-05T11:06:33Z"},{"alias_kind":"arxiv_version","alias_value":"2505.14350v2","created_at":"2026-07-05T11:06:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.14350","created_at":"2026-07-05T11:06:33Z"},{"alias_kind":"pith_short_12","alias_value":"YE26JPZL2QGM","created_at":"2026-07-05T11:06:33Z"},{"alias_kind":"pith_short_16","alias_value":"YE26JPZL2QGM2EZ2","created_at":"2026-07-05T11:06:33Z"},{"alias_kind":"pith_short_8","alias_value":"YE26JPZL","created_at":"2026-07-05T11:06:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:YE26JPZL2QGM2EZ2CQFGWGRX2M","target":"record","payload":{"canonical_record":{"source":{"id":"2505.14350","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-20T13:34:06Z","cross_cats_sorted":[],"title_canon_sha256":"9331c1704b4faae9214c33870909203e5341479aab432fa1814e409c9ed396e8","abstract_canon_sha256":"487756d437af3d7e7722444e44189be7489fb75a2aa298d9995eabdd1a4eb701"},"schema_version":"1.0"},"canonical_sha256":"c135e4bf2bd40ccd133a140a6b1a37d32edc3e1657dc6723844b04e70639542f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:06:33.374724Z","signature_b64":"qAUbHyJdfkSmCrX6gQORlX6QEIgUzbnp5qadiFDwhwdDGBfXz/gkbu2BRZbgaRRfpHrjWq0ANer3twSvYUYVCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c135e4bf2bd40ccd133a140a6b1a37d32edc3e1657dc6723844b04e70639542f","last_reissued_at":"2026-07-05T11:06:33.374343Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:06:33.374343Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.14350","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":"2026-07-05T11:06:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"j/f6P2cr0Rj0fZPe5LVuEy4mg76qaiGBCUYSBmZzd/sesFh6AtDmqUGaV/dx89ZOfiOglhYpr9CK9KgG525NDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T14:34:23.878239Z"},"content_sha256":"6cde901111e5f1936c20243ff1534001789d40986575c81e8583e3501db070ec","schema_version":"1.0","event_id":"sha256:6cde901111e5f1936c20243ff1534001789d40986575c81e8583e3501db070ec"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:YE26JPZL2QGM2EZ2CQFGWGRX2M","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"OSoRA: Output-Dimension and Singular-Value Initialized Low-Rank Adaptation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jialong Han, Ke Zhang, Si Zhang","submitted_at":"2025-05-20T13:34:06Z","abstract_excerpt":"Fine-tuning Large Language Models (LLMs) has become increasingly challenging due to their massive scale and associated computational costs. Parameter-Efficient Fine-Tuning (PEFT) methodologies have been proposed as computational alternatives; however, their implementations still require significant resources. In this paper, we present OSoRA (Output-Dimension and Singular-Value Initialized Low-Rank Adaptation), a novel PEFT method for LLMs. OSoRA extends Low-Rank Adaptation (LoRA) by integrating Singular Value Decomposition (SVD) with learnable scaling vectors in a unified framework. It first p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.14350","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/2505.14350/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":"2026-07-05T11:06:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jrXobTGJEPOcJIu+vcHvhySOU9s5/hoFmZZdkCQx9SGCXRWqIzX71rPBitWzW1Vq9Ap7pofhkLqE+HQrDpvEAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T14:34:23.878976Z"},"content_sha256":"39c25f7d7ad0486e1741cb53f74d2a1e403769cc787c8373146f4e793bc21278","schema_version":"1.0","event_id":"sha256:39c25f7d7ad0486e1741cb53f74d2a1e403769cc787c8373146f4e793bc21278"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YE26JPZL2QGM2EZ2CQFGWGRX2M/bundle.json","state_url":"https://pith.science/pith/YE26JPZL2QGM2EZ2CQFGWGRX2M/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YE26JPZL2QGM2EZ2CQFGWGRX2M/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":"2026-08-11T14:34:23Z","links":{"resolver":"https://pith.science/pith/YE26JPZL2QGM2EZ2CQFGWGRX2M","bundle":"https://pith.science/pith/YE26JPZL2QGM2EZ2CQFGWGRX2M/bundle.json","state":"https://pith.science/pith/YE26JPZL2QGM2EZ2CQFGWGRX2M/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YE26JPZL2QGM2EZ2CQFGWGRX2M/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:YE26JPZL2QGM2EZ2CQFGWGRX2M","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":"487756d437af3d7e7722444e44189be7489fb75a2aa298d9995eabdd1a4eb701","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-20T13:34:06Z","title_canon_sha256":"9331c1704b4faae9214c33870909203e5341479aab432fa1814e409c9ed396e8"},"schema_version":"1.0","source":{"id":"2505.14350","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.14350","created_at":"2026-07-05T11:06:33Z"},{"alias_kind":"arxiv_version","alias_value":"2505.14350v2","created_at":"2026-07-05T11:06:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.14350","created_at":"2026-07-05T11:06:33Z"},{"alias_kind":"pith_short_12","alias_value":"YE26JPZL2QGM","created_at":"2026-07-05T11:06:33Z"},{"alias_kind":"pith_short_16","alias_value":"YE26JPZL2QGM2EZ2","created_at":"2026-07-05T11:06:33Z"},{"alias_kind":"pith_short_8","alias_value":"YE26JPZL","created_at":"2026-07-05T11:06:33Z"}],"graph_snapshots":[{"event_id":"sha256:39c25f7d7ad0486e1741cb53f74d2a1e403769cc787c8373146f4e793bc21278","target":"graph","created_at":"2026-07-05T11:06:33Z","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/2505.14350/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Fine-tuning Large Language Models (LLMs) has become increasingly challenging due to their massive scale and associated computational costs. Parameter-Efficient Fine-Tuning (PEFT) methodologies have been proposed as computational alternatives; however, their implementations still require significant resources. In this paper, we present OSoRA (Output-Dimension and Singular-Value Initialized Low-Rank Adaptation), a novel PEFT method for LLMs. OSoRA extends Low-Rank Adaptation (LoRA) by integrating Singular Value Decomposition (SVD) with learnable scaling vectors in a unified framework. It first p","authors_text":"Jialong Han, Ke Zhang, Si Zhang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-20T13:34:06Z","title":"OSoRA: Output-Dimension and Singular-Value Initialized Low-Rank Adaptation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.14350","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":"sha256:6cde901111e5f1936c20243ff1534001789d40986575c81e8583e3501db070ec","target":"record","created_at":"2026-07-05T11:06:33Z","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":"487756d437af3d7e7722444e44189be7489fb75a2aa298d9995eabdd1a4eb701","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-20T13:34:06Z","title_canon_sha256":"9331c1704b4faae9214c33870909203e5341479aab432fa1814e409c9ed396e8"},"schema_version":"1.0","source":{"id":"2505.14350","kind":"arxiv","version":2}},"canonical_sha256":"c135e4bf2bd40ccd133a140a6b1a37d32edc3e1657dc6723844b04e70639542f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c135e4bf2bd40ccd133a140a6b1a37d32edc3e1657dc6723844b04e70639542f","first_computed_at":"2026-07-05T11:06:33.374343Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:06:33.374343Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qAUbHyJdfkSmCrX6gQORlX6QEIgUzbnp5qadiFDwhwdDGBfXz/gkbu2BRZbgaRRfpHrjWq0ANer3twSvYUYVCg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:06:33.374724Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.14350","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6cde901111e5f1936c20243ff1534001789d40986575c81e8583e3501db070ec","sha256:39c25f7d7ad0486e1741cb53f74d2a1e403769cc787c8373146f4e793bc21278"],"state_sha256":"b41205cf7ff68f958226d2abacb3fd9dfed0b2870f6e8f6b976cf41e20e2a74a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tl+j0lQay+5kSIts2Xo7h4+ArgxrQZfXGzUZUGWO8nS9AXpJA+8ijyGBBp3gPf/c0RiD0XlMX6RI2M1pYBbMAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T14:34:23.884474Z","bundle_sha256":"8e86a9c2971457abc6dccffe2fcb3fd4e784a1d335f63f068191e7750b96d040"}}